GeoBitLarge Spatial Model

Agriculture

Fields, imagery before and after, yields and soil

Fresno County, California, United Statessynthetic data, real placeMaps, charts and report
The question

Which fields lost vegetation between the April and August imagery (NDVI change), where is soil quality poor, and how do yields compare per field?

A farm manager uploads field boundaries, two satellite scenes (April and August), soil samples, irrigation canals and wells, pest scouting, weather stations, yields by season and an agronomist's notes. It wants to know which fields lost vegetation, where soil is poor and how yields compare.

36.6500, -120.0500data covers about 6 by 5 km
11datasets uploaded
21output layers
22maps made
24charts made
48findings
691 sStart run time

Every map and chart this run made is here. 22 map images, 24 charts and the cited report (PDF, Word, Markdown), as exported on 2026-10-22.

Findings (first few)

  • Evidenced: The timeline counts 1,692 dated events in Soil samples, Pest scouting, Yields by season and 1 more per quarter, from Q1 2021 to Q3 2026 12345.
  • Evidenced: By dataset: Soil samples 600; Pest scouting 520; Yields by season 300; Field operations 272 1.
  • Evidenced: The trend is +12.2 events per quarter; the second half of the quarters has 1,512 against 180 in the first (+740.0%) 1.
  • Evidenced: 14 of the 23 quarters had no events 1.
  • Evidenced: The busiest quarters were Q3 2026 (413), Q4 2025 (392), Q2 2026 (301) 1.

What Start ran

Describe mode, the local model only (no paid model); run status succeeded, 9 analyst agents.

gp_calculate_densitygp_find_point_clustersgp_hot_spotsgp_near_repeatgp_space_time_hot_spotsgp_summarize_withinim_change_date_raster (1 failed)im_compute_change_rasterim_index_changers_zonal_statistics

Maps

Every map image this run exported, with legend, north arrow and scale bar. Select one to view it full size.

Summarize within: Fields
Summarize within: FieldsFig. 2
Summarize within: Fields
Summarize within: FieldsFig. 3
Summarize within: Fields
Summarize within: FieldsFig. 4
Emerging hot spots: Pest scouting
Emerging hot spots: Pest scoutingFig. 5
Emerging hot spots: Soil samples
Emerging hot spots: Soil samplesFig. 6
Repeat and near repeat classification: Pest scouting
Repeat and near repeat classification: Pest scoutingFig. 7
NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15
NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15Fig. 8
NDVI decrease / increase
NDVI decrease / increaseFig. 9
NDVI change polygons
NDVI change polygonsFig. 10
Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15
Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15Fig. 11
Fields by planted_year
Fields by planted_yearFig. 12
Hot spot analysis: Pest scouting
Hot spot analysis: Pest scoutingFig. 13
Hot spot analysis: Wells
Hot spot analysis: WellsFig. 14
Hot spot analysis: Soil samples
Hot spot analysis: Soil samplesFig. 15
Calculate density: Pest scouting
Calculate density: Pest scoutingFig. 16
Calculate density: Wells
Calculate density: WellsFig. 17
Calculate density: Soil samples
Calculate density: Soil samplesFig. 18
Find point clusters: Pest scouting
Find point clusters: Pest scoutingFig. 19
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 20
Find point clusters: Wells
Find point clusters: WellsFig. 21
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 22
Find point clusters: Soil samples
Find point clusters: Soil samplesFig. 23

Charts

Every chart image this run exported.

Fields over time (planted_year)
Fields over time (planted_year)Fig. 24
Field operations over time (date)
Field operations over time (date)Fig. 25
Summarize within: Fields
Summarize within: FieldsFig. 26
Summarize within: Fields
Summarize within: FieldsFig. 27
Summarize within: Fields
Summarize within: FieldsFig. 28
Emerging hot spots: Pest scouting
Emerging hot spots: Pest scoutingFig. 29
Emerging hot spots: Soil samples
Emerging hot spots: Soil samplesFig. 30
Repeat and near repeat classification: Pest scouting
Repeat and near repeat classification: Pest scoutingFig. 31
NDVI change polygons
NDVI change polygonsFig. 32
Hot spot analysis: Pest scouting
Hot spot analysis: Pest scoutingFig. 33
Hot spot analysis: Wells
Hot spot analysis: WellsFig. 34
Hot spot analysis: Soil samples
Hot spot analysis: Soil samplesFig. 35
Calculate density: Pest scouting
Calculate density: Pest scoutingFig. 36
Calculate density: Wells
Calculate density: WellsFig. 37
Calculate density: Soil samples
Calculate density: Soil samplesFig. 38
Find point clusters: Pest scouting
Find point clusters: Pest scoutingFig. 39
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 40
Find point clusters: Wells
Find point clusters: WellsFig. 41
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 42
Find point clusters: Soil samples
Find point clusters: Soil samplesFig. 43
Find point clusters: Soil samples over time
Find point clusters: Soil samples over timeFig. 44
Find point clusters: Pest scouting over time
Find point clusters: Pest scouting over timeFig. 45
Repeat and near repeat classification: Pest scouting over time
Repeat and near repeat classification: Pest scouting over timeFig. 46
Timeline: events per quarter by dataset
Timeline: events per quarter by datasetFig. 1

The cited report

Sample: Agriculture, Fresno County: report

Project: Sample: Agriculture, Fresno County
Goal: Describe the project Sample: Agriculture, Fresno County: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: 7221484b-d66d-48ff-94e1-dbedfe96dc7c (running, 12 agent run(s))
Generated: 2026-10-18T06:07:57Z, version 1
Model cost: USD 0.0000 over 5 model call(s)

Data used

DataKindRowsTime spanSummarySource
Fieldsvector, Polygon6060 polygon (area) features; 'crop' has 5 values (top: tomato 16, almond 16, grape 11); 'irrigation' has 3 values (top: drip 28, micro sprinkler 22, furrow 10); 'area_ha' 43.1 to 43.1 (mean 43.1); 'planted_year' 2,008 to 2,025 (mean 2016); named by 'name' (e.g. Field 001 South, Field 002 South, Field 003 South); total area 25.83 km2; extent -120.0841,36.6269 to -120.0159,36.6731. Areas (Fields) with area_ha to compare and map.100
Satellite scene 2026-04-15raster2026-04-154-band float32 raster (imagery), 300 x 250 cells; resolution 20; band 1 0.014 to 0.113; acquired 2026-04-15; extent -120.0844,36.6267 to -120.0156,36.6733. Imagery for visual and change analysis.101
Satellite scene 2026-08-15raster2026-08-154-band float32 raster (imagery), 300 x 250 cells; resolution 20; band 1 0.015 to 0.145; acquired 2026-08-15; extent -120.0844,36.6267 to -120.0156,36.6733. Imagery for visual and change analysis.102
Soil samplesvector, Point6002025-10-01 to 2026-02-27600 point features; dated by 'sampled_on' from 2025-10-01 to 2026-02-27; 'ph' 6.4 to 9 (mean 7.401); 'organic_matter_pct' 0.11 to 1.99 (mean 1.236); 'nitrate_ppm' 3.6 to 65.5 (mean 17.55); extent -120.0834,36.6274 to -120.0174,36.6729. Dated point events: where and when Soil samples happen.2
Irrigation canalsvector, LineString55 line features; 'type' has 2 values (top: lateral 3, canal 2); 'capacity_cfs' 38 to 232 (mean 143); named by 'name' (e.g. Canal 1, Canal 2, Lateral 1); total length 26.99 km; extent -120.0838,36.6270 to -120.0162,36.6730. Lines (Irrigation canals) such as routes or networks.103
Wellsvector, Point4040 point features; 'depth_ft' 307 to 871 (mean 604.4); 'pump_hp' 75 to 200 (mean 140.6); 'static_level_ft' 120 to 418 (mean 282.7); extent -120.0823,36.6281 to -120.0188,36.6714. Point locations of Wells.104
Pest scoutingvector, Point5202026-04-01 to 2026-09-14520 point features; dated by 'observed_at' from 2026-04-01 to 2026-09-14; 'pest' has 4 values (top: aphid 235, navel orangeworm 110, lygus 92); 'threshold_exceeded' has 2 values (top: False 374, True 146); 'count_per_trap' 0 to 13 (mean 4.477); extent -120.0833,36.6271 to -120.0169,36.6728. Dated point events by pest: where and when Pest scouting happen.3
Weather stationsvector, Point33 point features; 'elevation_m' 57 to 65 (mean 61.67); named by 'name' (e.g. Farm weather station 1, Farm weather station 2, Farm weather station 3); extent -120.0663,36.6367 to -120.0366,36.6639. Point locations of Weather stations.105
Yields by seasontable3002021-01-01 to 2025-01-01Table of 300 rows and 5 columns without geometry; dated by 'season' from 2021-01-01 to 2025-01-01; 'crop' has 5 values (top: tomato 80, almond 80, grape 55); 'yield_t_ha' 1.19 to 120.7 (mean 33.16); 'water_af_per_acre' 2.6 to 4.2 (mean 3.395). A table of Yields by season without locations.4
Field operationstable2722026-02-01 to 2026-09-27Table of 272 rows and 5 columns without geometry; dated by 'date' from 2026-02-01 to 2026-09-27; 'operation' has 4 values (top: cultivate 74, irrigate 68, spray 67); 'product' has 3 values (top: UAN-32 67, sulfur 65, water 64); 'rate' 5.1 to 59.9 (mean 33.66). A table of Field operations without locations.5
Agronomist season notesdocument1-page md document 'Agronomist season notes, August 2026'; language en; mentions 7 place(s): Field 001 South (1), Field 010 South (1), Field 017 South (1), Field 018 South (1), Field (1). A document about Field 001 South, Field 010 South, Field 017 South.106
Sample: Agriculture, Fresno Countyrecord107
Summarize within: Fieldslayer, Polygon60108
Summarize within: Fieldslayer, Polygon60109
Summarize within: Fieldslayer, Polygon60110
Emerging hot spots: Pest scoutinglayer, Polygon48111
Emerging hot spots: Soil sampleslayer, Polygon51112
Repeat and near repeat classification: Pest scoutinglayer, Point520113
NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15layer0114
NDVI decrease / increaselayer0115
NDVI change polygonslayer, Polygon175116
Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15layer0117
Hot spot analysis: Pest scoutinglayer, Polygon134118
Hot spot analysis: Wellslayer, Polygon13119
Hot spot analysis: Soil sampleslayer, Polygon139120
Calculate density: Pest scoutinglayer, Polygon937121
Calculate density: Wellslayer, Polygon75122
Calculate density: Soil sampleslayer, Polygon953123
Find point clusters: Pest scoutinglayer, Point520124
Find point clusters: cluster hullslayer, Polygon4125
Find point clusters: Wellslayer, Point40126
Find point clusters: cluster hullslayer, Polygon5127
Find point clusters: Soil sampleslayer, Point600128

Timeline

Timeline: events per quarter by dataset
Figure 1. Timeline: events per quarter by dataset 1. Per quarter, 2021-01-01 to 2026-07-01. Source: Soil samples, Pest scouting, Yields by season, Field operations (1,692 features). The data is in the appendix.

The timeline counts 1,692 dated events in Soil samples, Pest scouting, Yields by season and 1 more per quarter, from Q1 2021 to Q3 2026 12345. By dataset: Soil samples 600; Pest scouting 520; Yields by season 300; Field operations 272 1. The trend is +12.2 events per quarter; the second half of the quarters has 1,512 against 180 in the first (+740.0%) 1. 14 of the 23 quarters had no events 1.

Busiest quarters

  • Q3 2026: 413 events 1
  • Q4 2025: 392 events 1
  • Q2 2026: 301 events 1

Quietest quarters with events

  • Q1 2021: 60 events 1
  • Q1 2022: 60 events 1
  • Q1 2023: 60 events 1

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 6. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 6.

Why it was run on this data. Count Weather stations inside each feature of Fields; the counts map as a choropleth (natural breaks, sequential colors) 7.

What it found. Summarize within on Weather stations, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 8910. It reported result, count 60; result, elapsed ms 2; billing, cost 0.01128; billing, list price 0.01128; billing, upstream cost 0 8.

ResultValue
result, count60
result, elapsed ms2
billing, cost0.01128
billing, list price0.01128
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Weather stations, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 8910.
  • Evidenced: It reported result, count 60; result, elapsed ms 2; billing, cost 0.01128; billing, list price 0.01128; billing, upstream cost 0 8.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "elevation_m"}], "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Weather stations (7a8242c6)"}, "polygons": {"layer": "Fields (a196eb79)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 6. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 6.

Why it was run on this data. Count Weather stations inside each feature of Fields; the counts map as a choropleth (natural breaks, sequential colors) 7.

What it found. Summarize within on Pest scouting, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 101112. It reported result, count 60; result, elapsed ms 2; billing, cost 0.02162; billing, list price 0.02162; billing, upstream cost 0 11.

ResultValue
result, count60
result, elapsed ms2
billing, cost0.02162
billing, list price0.02162
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Pest scouting, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 101112.
  • Evidenced: It reported result, count 60; result, elapsed ms 2; billing, cost 0.02162; billing, list price 0.02162; billing, upstream cost 0 11.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "count_per_trap"}], "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "group_by": "pest", "polygons": {"layer": "Fields (a196eb79)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 6. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 6.

Why it was run on this data. Count Weather stations inside each feature of Fields; the counts map as a choropleth (natural breaks, sequential colors) 7.

What it found. Summarize within on Wells, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 101314. It reported result, count 60; result, elapsed ms 1; billing, cost 0.01202; billing, list price 0.01202; billing, upstream cost 0 13.

ResultValue
result, count60
result, elapsed ms1
billing, cost0.01202
billing, list price0.01202
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Wells, Fields: Summarize within: 1 layer saved: Summarize within: Fields (60 features) 101314.
  • Evidenced: It reported result, count 60; result, elapsed ms 1; billing, cost 0.01202; billing, list price 0.01202; billing, upstream cost 0 13.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "depth_ft"}], "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Wells (15d08948)"}, "polygons": {"layer": "Fields (a196eb79)"}}

Space time hot spots

What this analysis is. Emerging hot spots: Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time 15. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 15.

Why it was run on this data. Pest scouting carry dates in 'observed_at': emerging hot spot analysis finds new, intensifying and fading hot spots per week 16.

What it found. The process began with the "Pest scouting" input 12. Running the "gp_space_time_hot_spots" tool yielded a result containing 48 features 17. This analysis required using 520 features and completed in 8 milliseconds 17. The computational cost for this operation was 0.126 17.

ResultValue
result, count48
result, elapsed ms8
result, resolution8
result, features used520
result, time neighbors0
billing, cost0.126
billing, list price0.126
billing, upstream cost0

Findings

  • Evidenced: Space time hot spots on Pest scouting: Emerging hot spots: 1 layer saved: Emerging hot spots: Pest scouting (48 features) 1217.
  • Evidenced: It reported result, count 48; result, elapsed ms 8; result, resolution 8; result, features used 520; result, time neighbors 0; billing, cost 0.126 17.

Tool gp_space_time_hot_spots; parameters {"project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "interval": "week", "bin_shape": "h3", "resolution": 8, "time_field": "observed_at"}

Space time hot spots

What this analysis is. Emerging hot spots: Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time 15. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 15.

Why it was run on this data. Soil samples carry dates in 'sampled_on': emerging hot spot analysis finds new, intensifying and fading hot spots per week 18.

What it found. The analysis processed the Soil samples 20 and resulted in 51 emerging

ResultValue
result, count51
result, elapsed ms8
result, resolution8
result, features used600
result, time neighbors0
billing, cost0.13
billing, list price0.13
billing, upstream cost0

Findings

  • Evidenced: Space time hot spots on Soil samples: Emerging hot spots: 1 layer saved: Emerging hot spots: Soil samples (51 features) 1920.
  • Evidenced: It reported result, count 51; result, elapsed ms 8; result, resolution 8; result, features used 600; result, time neighbors 0; billing, cost 0.13 19.

Tool gp_space_time_hot_spots; parameters {"project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Soil samples (caf67b23)"}, "interval": "week", "bin_shape": "h3", "resolution": 8, "time_field": "sampled_on"}

Near repeat

What this analysis is. Repeat and near repeat classification: Classify incidents as originators, repeats (same place) or near repeats within a distance and time window, with a Knox test table 21. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 21.

Why it was run on this data. Near repeat analysis tests whether Pest scouting close in space also follow each other within 17 days 22.

What it found. Near repeat on Pest scouting: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Pest scouting (520 features) 1223. It reported result, days 17; result, count 520; result, chains 48; result, distance m 200; result, elapsed ms 11; result, pairs linked 529 23.

ResultValue
result, days17
result, count520
result, chains48
result, distance m200
result, elapsed ms11
result, pairs linked529
billing, cost0.0656
billing, list price0.0656
billing, upstream cost0

Findings

  • Evidenced: Near repeat on Pest scouting: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Pest scouting (520 features) 1223.
  • Evidenced: It reported result, days 17; result, count 520; result, chains 48; result, distance m 200; result, elapsed ms 11; result, pairs linked 529 23.

Tool gp_near_repeat; parameters {"days": 17, "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "distance_m": 200.0, "time_field": "observed_at"}

Index change

What this analysis is. Spectral index change: Change of a spectral index (NDVI, NDWI, NDBI, NBR …) or a band expression between two images: before, after and difference rasters, decrease / increase classes beyond the threshold with polygons and areas; NBR also gives dNBR with burn severity classes 24.

Why it was run on this data. Index change between Satellite scene 2026-04-15 (2026-04-15) and Satellite scene 2026-08-15 (2026-08-15): the changed area, with the changed places as polygons 25.

What it found. Index change: Spectral index change: created NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m) 26. plus 1 more raster layer(s) 26. and layer NDVI change polygons with 175 feature(s) 26. mean before 0.7068; mean after 0.5038; mean difference -0.203; decrease ha 1,053; increase ha 5.32 26. It reported stats, polygons 175; stats, mean after 0.5038; stats, decrease ha 1,053; stats, increase ha 5.32; stats, mean before 0.7068; stats, masked pixels 0 26.

ResultValue
stats, polygons175
stats, mean after0.5038
stats, decrease ha1,053
stats, increase ha5.32
stats, mean before0.7068
stats, masked pixels0
stats, mean difference-0.203
elapsed ms175

Findings

  • Evidenced: Index change: Spectral index change: created NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m) 26.
  • Evidenced: plus 1 more raster layer(s) 26.
  • Evidenced: and layer NDVI change polygons with 175 feature(s) 26.
  • Evidenced: mean before 0.7068; mean after 0.5038; mean difference -0.203; decrease ha 1,053; increase ha 5.32 26.
  • Evidenced: It reported stats, polygons 175; stats, mean after 0.5038; stats, decrease ha 1,053; stats, increase ha 5.32; stats, mean before 0.7068; stats, masked pixels 0 26.

Tool im_index_change; parameters {"after_id": "Satellite scene 2026-08-15 (34efa462)", "polygons": true, "before_id": "Satellite scene 2026-04-15 (6c1f22ed)"}

Compute change raster

What this analysis is. Compute change raster: Pixel value or spectral change between two co-registered images: difference, relative difference, absolute difference, log ratio (radar, dB), Euclidean spectral distance, spectral angle (radians) or the band with most change 27.

Why it was run on this data. A change raster between Satellite scene 2026-04-15 (2026-04-15) and Satellite scene 2026-08-15 (2026-08-15): where and how much the pixels changed 28.

What it found. Compute change raster: Compute change raster: created Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m) 29. mean 0.02217; std 0.03434; min -0.037; max 0.116; masked pixels 0 29. It reported stats, max 0.116; stats, min -0.037; stats, std 0.03434; stats, mean 0.02217; stats, masked pixels 0; elapsed ms 88 29.

ResultValue
stats, max0.116
stats, min-0.037
stats, std0.03434
stats, mean0.02217
stats, masked pixels0
elapsed ms88

Findings

  • Evidenced: Compute change raster: Compute change raster: created Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m) 29.
  • Evidenced: mean 0.02217; std 0.03434; min -0.037; max 0.116; masked pixels 0 29.
  • Evidenced: It reported stats, max 0.116; stats, min -0.037; stats, std 0.03434; stats, mean 0.02217; stats, masked pixels 0; elapsed ms 88 29.

Tool im_compute_change_raster; parameters {"after_id": "Satellite scene 2026-08-15 (34efa462)", "before_id": "Satellite scene 2026-04-15 (6c1f22ed)"}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 30. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 30.

Why it was run on this data. 520 points: Getis-Ord Gi* tests whether the concentrations in Pest scouting are statistically significant 31.

What it found. Hot spots on Pest scouting: Hot spot analysis: 1 layer saved: Hot spot analysis: Pest scouting (134 features) 1232. It reported result, bins 134; result, count 134; result, elapsed ms 10; result, cell size m 500; result, incidents used 520; result, distance band m 500 32.

ResultValue
result, bins134
result, count134
result, elapsed ms10
result, cell size m500
result, incidents used520
result, distance band m500
billing, cost0.0604
billing, list price0.0604
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Pest scouting: Hot spot analysis: 1 layer saved: Hot spot analysis: Pest scouting (134 features) 1232.
  • Evidenced: It reported result, bins 134; result, count 134; result, elapsed ms 10; result, cell size m 500; result, incidents used 520; result, distance band m 500 32.

A model draft was discarded because a sentence did not cite a source of this section.

Tool gp_hot_spots; parameters {"project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 30. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 30.

Why it was run on this data. 40 points: Getis-Ord Gi* tests whether the concentrations in Wells are statistically significant 33.

What it found. The utilization of the Hot spot analysis tool (gp_hot_spots) processed the Wells data 14. The analysis yielded a saved layer with 13 features 34. Performance metrics showed that the analysis involved 13 bins, counted 13 results, and took 2 elapsed ms 34.

ResultValue
result, bins13
result, count13
result, elapsed ms2
result, cell size m2,000
result, incidents used40
result, distance band m2,000
billing, cost0.0508
billing, list price0.0508
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Wells: Hot spot analysis: 1 layer saved: Hot spot analysis: Wells (13 features) 1434.
  • Evidenced: It reported result, bins 13; result, count 13; result, elapsed ms 2; result, cell size m 2,000; result, incidents used 40; result, distance band m 2,000 34.

Tool gp_hot_spots; parameters {"project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Wells (15d08948)"}, "aggregation": "hexagon", "cell_size_m": 2000.0, "distance_band_m": 2000.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 30. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 30.

Why it was run on this data. 600 points: Getis-Ord Gi* tests whether the concentrations in Soil samples are statistically significant 35.

What it found. Hot spots on Soil samples: Hot spot analysis: 1 layer saved: Hot spot analysis: Soil samples (139 features) 2036. It reported result, bins 139; result, count 139; result, elapsed ms 10; result, cell size m 500; result, incidents used 600; result, distance band m 500 36.

ResultValue
result, bins139
result, count139
result, elapsed ms10
result, cell size m500
result, incidents used600
result, distance band m500
billing, cost0.062
billing, list price0.062
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Soil samples: Hot spot analysis: 1 layer saved: Hot spot analysis: Soil samples (139 features) 2036.
  • Evidenced: It reported result, bins 139; result, count 139; result, elapsed ms 10; result, cell size m 500; result, incidents used 600; result, distance band m 500 36.

Tool gp_hot_spots; parameters {"project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Soil samples (caf67b23)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 37. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 37.

Why it was run on this data. 520 points in Pest scouting: a density surface shows where they concentrate 38.

What it found. Calculate density on Pest scouting: Calculate density: 1 layer saved: Calculate density: Pest scouting (937 features) 1239. It reported result, count 937; result, elapsed ms 41; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 111.6 39.

ResultValue
result, count937
result, elapsed ms41
result, bandwidth m500
result, cell size m200
result, excluded null0
result, max density per km2111.6
billing, cost0.0604
billing, list price0.0604
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Pest scouting: Calculate density: 1 layer saved: Calculate density: Pest scouting (937 features) 1239.
  • Evidenced: It reported result, count 937; result, elapsed ms 41; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 111.6 39.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "bandwidth_m": 500.0, "cell_size_m": 200.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 37. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 37.

Why it was run on this data. 40 points in Wells: a density surface shows where they concentrate 40.

What it found. Calculate density on Wells: Calculate density: 1 layer saved: Calculate density: Wells (75 features) 1441. It reported result, count 75; result, elapsed ms 3; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1.638 41.

ResultValue
result, count75
result, elapsed ms3
result, bandwidth m2,000
result, cell size m1,000
result, excluded null0
result, max density per km21.638
billing, cost0.0508
billing, list price0.0508
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Wells: Calculate density: 1 layer saved: Calculate density: Wells (75 features) 1441.
  • Evidenced: It reported result, count 75; result, elapsed ms 3; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1.638 41.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Wells (15d08948)"}, "bandwidth_m": 2000.0, "cell_size_m": 1000.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 37. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 37.

Why it was run on this data. 600 points in Soil samples: a density surface shows where they concentrate 42.

What it found. Calculate density on Soil samples: Calculate density: 1 layer saved: Calculate density: Soil samples (953 features) 2043. It reported result, count 953; result, elapsed ms 30; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 46.63 43.

ResultValue
result, count953
result, elapsed ms30
result, bandwidth m500
result, cell size m200
result, excluded null0
result, max density per km246.63
billing, cost0.062
billing, list price0.062
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Soil samples: Calculate density: 1 layer saved: Calculate density: Soil samples (953 features) 2043.
  • Evidenced: It reported result, count 953; result, elapsed ms 30; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 46.63 43.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Soil samples (caf67b23)"}, "bandwidth_m": 500.0, "cell_size_m": 200.0}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 44. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 44.

Why it was run on this data. DBSCAN finds dense groups of Pest scouting and separates noise 45.

What it found. Find point clusters on Pest scouting: Find point clusters: 2 layers saved: Find point clusters: Pest scouting (520 features); Find point clusters: cluster hulls (4 features) 1246. It reported result, count 520; result, noise 113; result, distance m 500; result, elapsed ms 13; result, min points 13; billing, cost 0.0604 46.

ResultValue
result, count520
result, noise113
result, distance m500
result, elapsed ms13
result, min points13
billing, cost0.0604
billing, list price0.0604
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Pest scouting: Find point clusters: 2 layers saved: Find point clusters: Pest scouting (520 features); Find point clusters: cluster hulls (4 features) 1246.
  • Evidenced: It reported result, count 520; result, noise 113; result, distance m 500; result, elapsed ms 13; result, min points 13; billing, cost 0.0604 46.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Pest scouting (815c2b2c)"}, "distance_m": 500.0, "min_points": 13}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 44. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 44.

Why it was run on this data. DBSCAN finds dense groups of Wells and separates noise 47.

What it found. Find point clusters on Wells: Find point clusters: 2 layers saved: Find point clusters: Wells (40 features); Find point clusters: cluster hulls (5 features) 1448. It reported result, count 40; result, noise 0; result, distance m 1,000; result, elapsed ms 3; result, min points 3; billing, cost 0.0508 48.

ResultValue
result, count40
result, noise0
result, distance m1,000
result, elapsed ms3
result, min points3
billing, cost0.0508
billing, list price0.0508
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Wells: Find point clusters: 2 layers saved: Find point clusters: Wells (40 features); Find point clusters: cluster hulls (5 features) 1448.
  • Evidenced: It reported result, count 40; result, noise 0; result, distance m 1,000; result, elapsed ms 3; result, min points 3; billing, cost 0.0508 48.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Wells (15d08948)"}, "distance_m": 1000.0, "min_points": 3}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 44. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 44.

Why it was run on this data. DBSCAN finds dense groups of Soil samples and separates noise 49.

What it found. Find point clusters on Soil samples: Find point clusters: 1 layer saved: Find point clusters: Soil samples (600 features) 2050. It reported result, count 600; result, noise 600; result, distance m 200; result, elapsed ms 9; result, min points 15; billing, cost 0.062 50.

ResultValue
result, count600
result, noise600
result, distance m200
result, elapsed ms9
result, min points15
billing, cost0.062
billing, list price0.062
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Soil samples: Find point clusters: 1 layer saved: Find point clusters: Soil samples (600 features) 2050.
  • Evidenced: It reported result, count 600; result, noise 600; result, distance m 200; result, elapsed ms 9; result, min points 15; billing, cost 0.062 50.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "c0ff746c-cbbb-48c5-a026-444453a7b463", "features": {"layer": "Soil samples (caf67b23)"}, "distance_m": 200.0, "min_points": 15}

Zonal statistics

What this analysis is. Zonal statistics: count/min/max/mean/std/sum/median/majority per polygon as a table and as GeoJSON 51. In ArcGIS it is Zonal Statistics as Table (polygons) 51.

Why it was run on this data. Statistics of Satellite scene 2026-04-15 inside each feature of Fields 52.

What it found. The analysis used the Zonal statistics tool, specifically rs_zonal_statistics, at step 0 53. This process resulted in 60 row(s) of data 53. Furthermore, the zonal statistics encompassed a total of 60 zones 53.

Findings

  • Evidenced: Zonal statistics: Zonal statistics: 60 row(s) 53.
  • Evidenced: zones 60 53.

Tool rs_zonal_statistics; parameters {"stats": ["mean", "min", "max", "std"], "zones": "Fields (a196eb79)", "raster_id": "Satellite scene 2026-04-15 (6c1f22ed)"}

Zonal statistics

What this analysis is. Zonal statistics: count/min/max/mean/std/sum/median/majority per polygon as a table and as GeoJSON 51. In ArcGIS it is Zonal Statistics as Table (polygons) 51.

Why it was run on this data. Statistics of Satellite scene 2026-04-15 inside each feature of Fields 52.

What it found. The analysis utilized the Zonal statistics tool, specifically rs_zonal_statistics 54. The results indicate an output containing 60 rows 54. Furthermore, the process calculated statistics across 60 distinct zones 54.

Findings

  • Evidenced: Zonal statistics: Zonal statistics: 60 row(s) 54.
  • Evidenced: zones 60 54.

Tool rs_zonal_statistics; parameters {"stats": ["mean", "min", "max", "std"], "zones": "Fields (a196eb79)", "raster_id": "Satellite scene 2026-08-15 (34efa462)"}

Maps and charts

The run also made 22 map image(s) 55565758596061626364656667686970717273747576 and 23 chart(s) 7778798081828384858687888990919293949596979899.

Summarize within: Fields
Figure 2. Summarize within: Fields 55
Summarize within: Fields
Figure 3. Summarize within: Fields 56
Summarize within: Fields
Figure 4. Summarize within: Fields 57
Emerging hot spots: Pest scouting
Figure 5. Emerging hot spots: Pest scouting 58
Emerging hot spots: Soil samples
Figure 6. Emerging hot spots: Soil samples 59
Repeat and near repeat classification: Pest scouting
Figure 7. Repeat and near repeat classification: Pest scouting 60
NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15
Figure 8. NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15 61
NDVI decrease / increase
Figure 9. NDVI decrease / increase 62
NDVI change polygons
Figure 10. NDVI change polygons 63
Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15
Figure 11. Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15 64
Fields by planted_year
Figure 12. Fields by planted_year 65
Hot spot analysis: Pest scouting
Figure 13. Hot spot analysis: Pest scouting 66
Hot spot analysis: Wells
Figure 14. Hot spot analysis: Wells 67
Hot spot analysis: Soil samples
Figure 15. Hot spot analysis: Soil samples 68
Calculate density: Pest scouting
Figure 16. Calculate density: Pest scouting 69
Calculate density: Wells
Figure 17. Calculate density: Wells 70
Calculate density: Soil samples
Figure 18. Calculate density: Soil samples 71
Find point clusters: Pest scouting
Figure 19. Find point clusters: Pest scouting 72
Find point clusters: cluster hulls
Figure 20. Find point clusters: cluster hulls 73
Find point clusters: Wells
Figure 21. Find point clusters: Wells 74
Find point clusters: cluster hulls
Figure 22. Find point clusters: cluster hulls 75
Find point clusters: Soil samples
Figure 23. Find point clusters: Soil samples 76

What the map shows. This map illustrates the concentration of "Fields" across the area, 57

Inferred: read from the image by gemma4:e4b, not evidence.

Fields over time (planted_year)
Figure 24. Fields over time (planted_year) 77. Source: Fields (60 features). The data is in the appendix.
Field operations over time (date)
Figure 25. Field operations over time (date) 78. Per week, 2026-01-26 to 2026-09-21. Source: Field operations (272 features). The data is in the appendix.
Summarize within: Fields
Figure 26. Summarize within: Fields 79. Source: Summarize within: Fields (60 features). The data is in the appendix.
Summarize within: Fields
Figure 27. Summarize within: Fields 80. Source: Summarize within: Fields (60 features). The data is in the appendix.
Summarize within: Fields
Figure 28. Summarize within: Fields 81. Source: Summarize within: Fields (60 features). The data is in the appendix.
Emerging hot spots: Pest scouting
Figure 29. Emerging hot spots: Pest scouting 82. Source: Emerging hot spots: Pest scouting (48 features). The data is in the appendix.
Emerging hot spots: Soil samples
Figure 30. Emerging hot spots: Soil samples 83. Source: Emerging hot spots: Soil samples (51 features). The data is in the appendix.
Repeat and near repeat classification: Pest scouting
Figure 31. Repeat and near repeat classification: Pest scouting 84. Per week, 2026-03-30 to 2026-09-14. Source: Repeat and near repeat classification: Pest scouting (520 features). The data is in the appendix.
NDVI change polygons
Figure 32. NDVI change polygons 85. Source: NDVI change polygons (175 features). The data is in the appendix.
Hot spot analysis: Pest scouting
Figure 33. Hot spot analysis: Pest scouting 86. Source: Hot spot analysis: Pest scouting (134 features). The data is in the appendix.
Hot spot analysis: Wells
Figure 34. Hot spot analysis: Wells 87. Source: Hot spot analysis: Wells (13 features). The data is in the appendix.
Hot spot analysis: Soil samples
Figure 35. Hot spot analysis: Soil samples 88. Source: Hot spot analysis: Soil samples (139 features). The data is in the appendix.
Calculate density: Pest scouting
Figure 36. Calculate density: Pest scouting 89. Source: Calculate density: Pest scouting (937 features). The data is in the appendix.
Calculate density: Wells
Figure 37. Calculate density: Wells 90. Source: Calculate density: Wells (75 features). The data is in the appendix.
Calculate density: Soil samples
Figure 38. Calculate density: Soil samples 91. Source: Calculate density: Soil samples (953 features). The data is in the appendix.
Find point clusters: Pest scouting
Figure 39. Find point clusters: Pest scouting 92. Period: 2026-04-01 to 2026-09-14 (observed_at). Source: Find point clusters: Pest scouting (520 features). The data is in the appendix.
Find point clusters: cluster hulls
Figure 40. Find point clusters: cluster hulls 93. Source: Find point clusters: cluster hulls (4 features). The data is in the appendix.
Find point clusters: Wells
Figure 41. Find point clusters: Wells 94. Source: Find point clusters: Wells (40 features). The data is in the appendix.
Find point clusters: cluster hulls
Figure 42. Find point clusters: cluster hulls 95. Source: Find point clusters: cluster hulls (5 features). The data is in the appendix.
Find point clusters: Soil samples
Figure 43. Find point clusters: Soil samples 96. Period: 2025-10-01 to 2026-02-27 (sampled_on). Source: Find point clusters: Soil samples (600 features). The data is in the appendix.
Find point clusters: Soil samples over time
Figure 44. Find point clusters: Soil samples over time 97. Per week, 2025-09-29 to 2026-02-23. Source: Find point clusters: Soil samples (600 features). The data is in the appendix.
Find point clusters: Pest scouting over time
Figure 45. Find point clusters: Pest scouting over time 98. Per week, 2026-03-30 to 2026-09-14. Source: Find point clusters: Pest scouting (520 features). The data is in the appendix.
Repeat and near repeat classification: Pest scouting over time
Figure 46. Repeat and near repeat classification: Pest scouting over time 99. Per week, 2026-03-30 to 2026-09-14. Source: Repeat and near repeat classification: Pest scouting (520 features). The data is in the appendix.

Changes since the last run

This is the first report of this project.

Sources

  1. 1Rendering: Chart: Timeline: events per quarter by dataset. 92 rows id 210bf478-e864-4742-9c56-7c7e371b620c
  2. 2Dataset: Soil samples. vector, 600 rows id f4ae2248-8882-412c-b6a9-09b418581a65
  3. 3Dataset: Pest scouting. vector, 520 rows id 63eec720-9e01-4dce-9c81-975e42e92d0b
  4. 4Dataset: Yields by season. table, 300 rows id a530983b-a4cf-4197-96b4-ac4ee482921b
  5. 5Dataset: Field operations. table, 272 rows id a8bf3d14-5f38-4346-878a-d28bc636b06e
  6. 6Catalog: Summarize within (operation catalog, gp_summarize_within). Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons. ArcGIS: Summarize Within, Aggregate Points. QGIS: native:countpointsinpolygon, native:sumlinelengths. id gp_summarize_within
  7. 7Plan: Weather stations per feature of Fields (the Start plan's candidate c_454a5cc5eea8). Count Weather stations inside each feature of Fields; the counts map as a choropleth (natural breaks, sequential colors). id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_454a5cc5eea8
  8. 8Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Fields (60 features). id dccd77e6-8290-42cb-9255-e52125568f63:0
  9. 9Layer: Weather stations. 3 features id 7a8242c6-adef-4d23-9e5b-df9ccaca27ad
  10. 10Layer: Fields. 60 features id a196eb79-1c58-44ab-9608-3f8de23cc587
  11. 11Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Fields (60 features). id dccd77e6-8290-42cb-9255-e52125568f63:1
  12. 12Layer: Pest scouting. 520 features id 815c2b2c-fc4f-4927-8f05-1744f43ca273
  13. 13Tool result: gp_summarize_within, step 2. Summarize within: 1 layer saved: Summarize within: Fields (60 features). id dccd77e6-8290-42cb-9255-e52125568f63:2
  14. 14Layer: Wells. 40 features id 15d08948-7e45-4cf2-ad71-6bb21299a25d
  15. 15Catalog: Emerging hot spots (operation catalog, gp_space_time_hot_spots). Where hot spots are new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating or historical over time. ArcGIS: Emerging Hot Spot Analysis, Create Space Time Cube. id gp_space_time_hot_spots
  16. 16Plan: Space time hot spots of Pest scouting (the Start plan's candidate c_45dd616af1e5). Pest scouting carry dates in 'observed_at': emerging hot spot analysis finds new, intensifying and fading hot spots per week. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_45dd616af1e5
  17. 17Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Pest scouting (48 features). id 4244d4f5-f923-4458-9154-022dacee4c61:0
  18. 18Plan: Space time hot spots of Soil samples (the Start plan's candidate c_850c0bb45f60). Soil samples carry dates in 'sampled_on': emerging hot spot analysis finds new, intensifying and fading hot spots per week. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_850c0bb45f60
  19. 19Tool result: gp_space_time_hot_spots, step 1. Emerging hot spots: 1 layer saved: Emerging hot spots: Soil samples (51 features). id 4244d4f5-f923-4458-9154-022dacee4c61:1
  20. 20Layer: Soil samples. 600 features id caf67b23-0043-4bf5-8531-43267ce2ed9f
  21. 21Catalog: Repeat and near repeat classification (operation catalog, gp_near_repeat). Classify incidents as originators, repeats (same place) or near repeats within a distance and time window, with a Knox test table. ArcGIS: Repeat and Near Repeat Classification, Near Repeat Calculator. id gp_near_repeat
  22. 22Plan: Near repeat of Pest scouting (the Start plan's candidate c_a26d0b1eb35d). Near repeat analysis tests whether Pest scouting close in space also follow each other within 17 days. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_a26d0b1eb35d
  23. 23Tool result: gp_near_repeat, step 2. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Pest scouting (520 features). id 4244d4f5-f923-4458-9154-022dacee4c61:2
  24. 24Catalog: Spectral index change (analysis catalog, im_index_change). Change of a spectral index (NDVI, NDWI, NDBI, NBR ...) or a band expression between two images: before, after and difference rasters, decrease / increase classes beyond the threshold with polygons and areas; NBR also gives dNBR with burn severity classes. id im_index_change
  25. 25Plan: Index change of Satellite scene 2026-04-15 and Satellite scene 2026-08-15 (the Start plan's candidate c_09e02b8174f1). Index change between Satellite scene 2026-04-15 (2026-04-15) and Satellite scene 2026-08-15 (2026-08-15): the changed area, with the changed places as polygons. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_09e02b8174f1
  26. 26Tool result: im_index_change, step 0. Spectral index change: created NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m). plus 1 more raster layer(s). and layer NDVI change polygons with 175 feature(s). mean before 0.7068; mean after 0.5038; mean difference -0.203; decrease ha 1,053; increase id aa0bd809-0fe9-498d-b9f1-719c7c0e70f8:0
  27. 27Catalog: Compute change raster (analysis catalog, im_compute_change_raster). Pixel value or spectral change between two co-registered images: difference, relative difference, absolute difference, log ratio (radar, dB), Euclidean spectral distance, spectral angle (radians) or the band with most change. Clouds and shadows are masked when the images have id im_compute_change_raster
  28. 28Plan: Compute change raster of Satellite scene 2026-04-15 and Satellite scene 2026-08-15 (the Start plan's candidate c_c88ddec02454). A change raster between Satellite scene 2026-04-15 (2026-04-15) and Satellite scene 2026-08-15 (2026-08-15): where and how much the pixels changed. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_c88ddec02454
  29. 29Tool result: im_compute_change_raster, step 1. Compute change raster: created Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15 (300 x 250 cells, 20.00 m). mean 0.02217; std 0.03434; min -0.037; max 0.116; masked pixels 0. id aa0bd809-0fe9-498d-b9f1-719c7c0e70f8:1
  30. 30Catalog: Hot spot analysis (operation catalog, gp_hot_spots). Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins. ArcGIS: Find Hot Spots, Hot Spot Analysis (Getis-Ord Gi*). QGIS: qgis:hotspot (plugin). id gp_hot_spots
  31. 31Plan: Hot spots of Pest scouting (the Start plan's candidate c_e6241d85c30d). 520 points: Getis-Ord Gi* tests whether the concentrations in Pest scouting are statistically significant. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_e6241d85c30d
  32. 32Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Pest scouting (134 features). id abe0cc5c-b82d-4992-9626-cf301845c602:0
  33. 33Plan: Hot spots of Wells (the Start plan's candidate c_5a29d39e7d24). 40 points: Getis-Ord Gi* tests whether the concentrations in Wells are statistically significant. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_5a29d39e7d24
  34. 34Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Wells (13 features). id abe0cc5c-b82d-4992-9626-cf301845c602:1
  35. 35Plan: Hot spots of Soil samples (the Start plan's candidate c_236d56d345ee). 600 points: Getis-Ord Gi* tests whether the concentrations in Soil samples are statistically significant. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_236d56d345ee
  36. 36Tool result: gp_hot_spots, step 2. Hot spot analysis: 1 layer saved: Hot spot analysis: Soil samples (139 features). id abe0cc5c-b82d-4992-9626-cf301845c602:2
  37. 37Catalog: Calculate density (operation catalog, gp_calculate_density). Kernel density per square kilometer on a grid. ArcGIS: Calculate Density, Kernel Density. QGIS: native:heatmapkerneldensityestimation. id gp_calculate_density
  38. 38Plan: Kernel density of Pest scouting (the Start plan's candidate c_a69023aa1d48). 520 points in Pest scouting: a density surface shows where they concentrate. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_a69023aa1d48
  39. 39Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Pest scouting (937 features). id 0aef980e-7aff-47d5-becc-3abd115d0df6:0
  40. 40Plan: Kernel density of Wells (the Start plan's candidate c_f362031aa57c). 40 points in Wells: a density surface shows where they concentrate. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_f362031aa57c
  41. 41Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Wells (75 features). id 0aef980e-7aff-47d5-becc-3abd115d0df6:1
  42. 42Plan: Kernel density of Soil samples (the Start plan's candidate c_031ecade8328). 600 points in Soil samples: a density surface shows where they concentrate. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_031ecade8328
  43. 43Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Soil samples (953 features). id 0aef980e-7aff-47d5-becc-3abd115d0df6:2
  44. 44Catalog: Find point clusters (operation catalog, gp_find_point_clusters). Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise. ArcGIS: Find Point Clusters, Density-based Clustering. QGIS: native:dbscanclustering, native:stdbscanclustering. id gp_find_point_clusters
  45. 45Plan: Cluster points of Pest scouting (the Start plan's candidate c_d5b8ebbc13e3). DBSCAN finds dense groups of Pest scouting and separates noise. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_d5b8ebbc13e3
  46. 46Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Pest scouting (520 features); Find point clusters: cluster hulls (4 features). id d3e49c76-baed-436b-aed4-42467a2d8691:0
  47. 47Plan: Cluster points of Wells (the Start plan's candidate c_cb6793249bdf). DBSCAN finds dense groups of Wells and separates noise. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_cb6793249bdf
  48. 48Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Wells (40 features); Find point clusters: cluster hulls (5 features). id d3e49c76-baed-436b-aed4-42467a2d8691:1
  49. 49Plan: Cluster points of Soil samples (the Start plan's candidate c_c62ca5d55d3c). DBSCAN finds dense groups of Soil samples and separates noise. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_c62ca5d55d3c
  50. 50Tool result: gp_find_point_clusters, step 2. Find point clusters: 1 layer saved: Find point clusters: Soil samples (600 features). id d3e49c76-baed-436b-aed4-42467a2d8691:2
  51. 51Catalog: Zonal statistics (analysis catalog, rs_zonal_statistics). count/min/max/mean/std/sum/median/majority per polygon as a table and as GeoJSON. ArcGIS: Zonal Statistics as Table (polygons). id rs_zonal_statistics
  52. 52Plan: Zonal statistics of Satellite scene 2026-04-15 and Fields (the Start plan's candidate c_e314d28606e4). Statistics of Satellite scene 2026-04-15 inside each feature of Fields. id ae3647a3-d230-4a37-b0e8-19aa34415db3:c_e314d28606e4
  53. 53Tool result: rs_zonal_statistics, step 0. Zonal statistics: 60 row(s). zones 60. id 65e47d44-0efb-439a-97dd-b6f970b5def8:0
  54. 54Tool result: rs_zonal_statistics, step 1. Zonal statistics: 60 row(s). zones 60. id 65e47d44-0efb-439a-97dd-b6f970b5def8:1
  55. 55Rendering: Map: Summarize within: Fields id 7230104f-7ded-41b5-8137-03d3472c4fda
  56. 56Rendering: Map: Summarize within: Fields id 8653af7e-4e73-4408-a171-1f6950196dca
  57. 57Rendering: Map: Summarize within: Fields id 7cd707d4-3613-4819-8d43-7e3c43279eac
  58. 58Rendering: Map: Emerging hot spots: Pest scouting id b78dba51-33f9-4ea8-835a-48251bebd889
  59. 59Rendering: Map: Emerging hot spots: Soil samples id 391b8c8e-89d7-4099-a7bb-e45b7ee88e6b
  60. 60Rendering: Map: Repeat and near repeat classification: Pest scouting id 90157d45-c4a6-4d1d-9dcf-b704c93e0eb5
  61. 61Rendering: Map: NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15 id 0de86fc2-8ff8-4ce7-b077-43a5ab4bb376
  62. 62Rendering: Map: NDVI decrease / increase id e74e322f-5c79-4f18-a2f6-d502e8b31d86
  63. 63Rendering: Map: NDVI change polygons id 89e60139-e1e3-409e-8bc0-bcf9c32a5e30
  64. 64Rendering: Map: Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15 id df6ad400-4033-420c-8150-f286d0d0ce02
  65. 65Rendering: Map: Fields by planted_year id b7bcce2d-b7d0-4b90-bed2-1e960095b8f5
  66. 66Rendering: Map: Hot spot analysis: Pest scouting id 3a23b5af-27f8-49c6-bf66-fa49b20a08aa
  67. 67Rendering: Map: Hot spot analysis: Wells id cd3c7db8-cfb5-4aed-809a-15a9c2e1ee04
  68. 68Rendering: Map: Hot spot analysis: Soil samples id 94b47520-81ad-4a35-9ed1-2ed221c66501
  69. 69Rendering: Map: Calculate density: Pest scouting id bf1a8ba7-ca53-469d-b24c-54ae7dbb680b
  70. 70Rendering: Map: Calculate density: Wells id fa642946-bff5-47a9-a9cd-c67b1f2f7bfe
  71. 71Rendering: Map: Calculate density: Soil samples id 8413c226-61fc-4fdd-92b1-023ff3edb997
  72. 72Rendering: Map: Find point clusters: Pest scouting id 51fe83ea-2c87-4a9e-8844-7feb42f6f11a
  73. 73Rendering: Map: Find point clusters: cluster hulls id e7e8fe55-e846-4d44-a326-06cac7e2cfca
  74. 74Rendering: Map: Find point clusters: Wells id fed095c7-3edc-4fd2-a373-d17fc6251739
  75. 75Rendering: Map: Find point clusters: cluster hulls id 400e2024-a606-405d-8c29-65b08ce86104
  76. 76Rendering: Map: Find point clusters: Soil samples id 37d0f2ff-28af-4ea5-88ad-7955526003bf
  77. 77Rendering: Chart: Fields over time (planted_year). 1 rows id 4fae63f6-4165-4c37-9583-b5e8b7fbe000
  78. 78Rendering: Chart: Field operations over time (date). 140 rows id 2b4ce56e-b8f2-4990-87a1-8e81d44ab30b
  79. 79Rendering: Chart: Summarize within: Fields. 1 rows id f44f0c04-6401-435e-908e-61b78a5cedb0
  80. 80Rendering: Chart: Summarize within: Fields. 7 rows id e36c7df7-7eb0-4113-a898-84173c1635a7
  81. 81Rendering: Chart: Summarize within: Fields. 1 rows id b56c5a2b-ea58-4c97-871a-e80878d78549
  82. 82Rendering: Chart: Emerging hot spots: Pest scouting. 7 rows id 314c5791-c320-418e-8128-46033cad4c68
  83. 83Rendering: Chart: Emerging hot spots: Soil samples. 7 rows id 212eb454-b769-41a6-8a5f-e897a360eff2
  84. 84Rendering: Chart: Repeat and near repeat classification: Pest scouting. 100 rows id 4ec337e3-0fad-4735-a5cd-35ba6454f64c
  85. 85Rendering: Chart: NDVI change polygons. 9 rows id b6caeb8f-73bd-4c12-bb71-811ad9d4f4fc
  86. 86Rendering: Chart: Hot spot analysis: Pest scouting. 11 rows id 11c79607-7ed1-452c-ab6e-436e1580c59b
  87. 87Rendering: Chart: Hot spot analysis: Wells. 7 rows id 5e81ab47-dc6c-4c0b-bf73-cb9a953888c8
  88. 88Rendering: Chart: Hot spot analysis: Soil samples. 10 rows id aa8f7bb7-d4a0-4160-acf0-4c3df1175537
  89. 89Rendering: Chart: Calculate density: Pest scouting. 11 rows id cb76c785-37e5-43e8-8f0d-40da98f49b28
  90. 90Rendering: Chart: Calculate density: Wells. 8 rows id 542ea61d-ff29-475d-b5fa-ebe52baa7deb
  91. 91Rendering: Chart: Calculate density: Soil samples. 11 rows id 07136eeb-2846-4054-ab99-30695bfabe15
  92. 92Rendering: Chart: Find point clusters: Pest scouting. 5 rows id 281d1a9c-7ff6-4172-a7c6-6af005d6f6bb
  93. 93Rendering: Chart: Find point clusters: cluster hulls. 4 rows id 133c6e8d-eb2d-492b-8bbb-1a76f6947626
  94. 94Rendering: Chart: Find point clusters: Wells. 5 rows id 647d827f-dbff-458c-b5c6-646ed6c20169
  95. 95Rendering: Chart: Find point clusters: cluster hulls. 5 rows id ca4b1c22-b048-4fd3-8fe4-a0d9efa5b4ae
  96. 96Rendering: Chart: Find point clusters: Soil samples. 1 rows id fec77e96-06d0-41b0-93d3-a8270db698ce
  97. 97Rendering: Chart: Find point clusters: Soil samples over time. 22 rows id 4fc7d651-51f3-4c40-90d5-b49a93b06ea2
  98. 98Rendering: Chart: Find point clusters: Pest scouting over time. 100 rows id 9aedbf91-7578-44d6-98ab-cb2d3aa2bc15
  99. 99Rendering: Chart: Repeat and near repeat classification: Pest scouting over time. 100 rows id 32669449-e850-4080-86e2-4007127d571f
  100. 100Dataset: Fields. vector, 60 rows id ae5ec258-e5f4-4d17-bdc8-60502e957eff
  101. 101Dataset: Satellite scene 2026-04-15. raster, ? rows id afcb6073-f5d0-4e9b-9733-f8ff25683e32
  102. 102Dataset: Satellite scene 2026-08-15. raster, ? rows id e159db17-63d9-49cf-89e5-b0ae9c8b48a2
  103. 103Dataset: Irrigation canals. vector, 5 rows id 97634f60-fee7-4f4e-a64e-637edfb86b11
  104. 104Dataset: Wells. vector, 40 rows id 74fc7b42-f33b-42ca-8b5d-9cfcb97c141a
  105. 105Dataset: Weather stations. vector, 3 rows id 0f5f59b7-502a-40bb-b75d-bdadd47f3080
  106. 106Dataset: Agronomist season notes. document, ? rows id d84db76e-6efd-462b-9106-b94192b7b788
  107. 107Record: Sample: Agriculture, Fresno County id c0ff746c-cbbb-48c5-a026-444453a7b463
  108. 108Layer: Summarize within: Fields. 60 features id b2fdbfbb-e5aa-42e7-94a1-89a27706bffe
  109. 109Layer: Summarize within: Fields. 60 features id 4f0023ee-b3ec-488f-bf30-f0fc9b0f5b3a
  110. 110Layer: Summarize within: Fields. 60 features id 951c1d69-082b-442b-a64e-e85bf3484a2f
  111. 111Layer: Emerging hot spots: Pest scouting. 48 features id 0be5bf67-1fa9-4a8c-83c8-e34bc93079d1
  112. 112Layer: Emerging hot spots: Soil samples. 51 features id 2a629716-c8ab-4b63-9c37-e87b9441d065
  113. 113Layer: Repeat and near repeat classification: Pest scouting. 520 features id fe782344-23a8-476a-b62d-d355ef2335ff
  114. 114Layer: NDVI change Satellite scene 2026-04-15 to Satellite scene 2026-08-15. 0 features id 8e44c499-3d6d-40a2-bf98-2aadc140cd8a
  115. 115Layer: NDVI decrease / increase. 0 features id bb4c7791-d581-4575-8cb4-3ef1435080f6
  116. 116Layer: NDVI change polygons. 175 features id f16ca8cc-e568-476b-891d-77e47b995583
  117. 117Layer: Difference Satellite scene 2026-04-15 to Satellite scene 2026-08-15. 0 features id a67372cb-7b7e-4c71-947c-5b97fba5d52f
  118. 118Layer: Hot spot analysis: Pest scouting. 134 features id 9e178787-e1af-447d-b9a8-b00743fc24e6
  119. 119Layer: Hot spot analysis: Wells. 13 features id d441f28d-a4a4-41b6-ae29-45dd731e936a
  120. 120Layer: Hot spot analysis: Soil samples. 139 features id 8e554e35-3a16-4452-9c1b-514be82182a7
  121. 121Layer: Calculate density: Pest scouting. 937 features id c70c03ec-c02f-4e66-b411-9818647d6aeb
  122. 122Layer: Calculate density: Wells. 75 features id 5b6288ae-67ae-41cd-84c7-b081bfc8198d
  123. 123Layer: Calculate density: Soil samples. 953 features id 1b537a1d-851e-429a-a0a3-2796431cad1c
  124. 124Layer: Find point clusters: Pest scouting. 520 features id 531e30e6-075f-4448-8903-ceb10bcec608
  125. 125Layer: Find point clusters: cluster hulls. 4 features id 3290f356-6d63-4379-ad57-5da11d5df04b
  126. 126Layer: Find point clusters: Wells. 40 features id 4497616c-038d-4f7d-bfd7-4a1fba479ca8
  127. 127Layer: Find point clusters: cluster hulls. 5 features id 973c4eb5-10d8-4c78-81b4-8d4b2dce4966
  128. 128Layer: Find point clusters: Soil samples. 600 features id a1768046-65e4-431b-b327-112b2874c867
Appendix: the data behind the chartsShow

Figure 1. Timeline: events per quarter by dataset 1

periodseriesvalue
2021-01-01Soil samples0
2021-01-01Pest scouting0
2021-01-01Yields by season60
2021-01-01Field operations0
2021-04-01Soil samples0
2021-04-01Pest scouting0
2021-04-01Yields by season0
2021-04-01Field operations0
2021-07-01Soil samples0
2021-07-01Pest scouting0
2021-07-01Yields by season0
2021-07-01Field operations0
2021-10-01Soil samples0
2021-10-01Pest scouting0
2021-10-01Yields by season0
2021-10-01Field operations0
2022-01-01Soil samples0
2022-01-01Pest scouting0
2022-01-01Yields by season60
2022-01-01Field operations0
2022-04-01Soil samples0
2022-04-01Pest scouting0
2022-04-01Yields by season0
2022-04-01Field operations0
2022-07-01Soil samples0
2022-07-01Pest scouting0
2022-07-01Yields by season0
2022-07-01Field operations0
2022-10-01Soil samples0
2022-10-01Pest scouting0
2022-10-01Yields by season0
2022-10-01Field operations0
2023-01-01Soil samples0
2023-01-01Pest scouting0
2023-01-01Yields by season60
2023-01-01Field operations0
2023-04-01Soil samples0
2023-04-01Pest scouting0
2023-04-01Yields by season0
2023-04-01Field operations0
2023-07-01Soil samples0
2023-07-01Pest scouting0
2023-07-01Yields by season0
2023-07-01Field operations0
2023-10-01Soil samples0
2023-10-01Pest scouting0
2023-10-01Yields by season0
2023-10-01Field operations0
2024-01-01Soil samples0
2024-01-01Pest scouting0
2024-01-01Yields by season60
2024-01-01Field operations0
2024-04-01Soil samples0
2024-04-01Pest scouting0
2024-04-01Yields by season0
2024-04-01Field operations0
2024-07-01Soil samples0
2024-07-01Pest scouting0
2024-07-01Yields by season0
2024-07-01Field operations0
2024-10-01Soil samples0
2024-10-01Pest scouting0
2024-10-01Yields by season0
2024-10-01Field operations0
2025-01-01Soil samples0
2025-01-01Pest scouting0
2025-01-01Yields by season60
2025-01-01Field operations0
2025-04-01Soil samples0
2025-04-01Pest scouting0
2025-04-01Yields by season0
2025-04-01Field operations0
2025-07-01Soil samples0
2025-07-01Pest scouting0
2025-07-01Yields by season0
2025-07-01Field operations0
2025-10-01Soil samples392
2025-10-01Pest scouting0
2025-10-01Yields by season0
2025-10-01Field operations0
2026-01-01Soil samples208
2026-01-01Pest scouting0
2026-01-01Yields by season0
2026-01-01Field operations78
2026-04-01Soil samples0
2026-04-01Pest scouting198
2026-04-01Yields by season0
2026-04-01Field operations103
2026-07-01Soil samples0
2026-07-01Pest scouting322
2026-07-01Yields by season0
2026-07-01Field operations91

Figure 24. Fields over time (planted_year) 77

bin_startbin_endcount
43.143.160

Figure 25. Field operations over time (date) 78

periodseriesvalue
2026-01-26cultivate2
2026-01-26irrigate1
2026-01-26spray0
2026-01-26fertilize1
2026-02-02cultivate4
2026-02-02irrigate4
2026-02-02spray1
2026-02-02fertilize2
2026-02-09cultivate1
2026-02-09irrigate1
2026-02-09spray6
2026-02-09fertilize1
2026-02-16cultivate3
2026-02-16irrigate1
2026-02-16spray1
2026-02-16fertilize1
2026-02-23cultivate2
2026-02-23irrigate4
2026-02-23spray7
2026-02-23fertilize2
2026-03-02cultivate4
2026-03-02irrigate1
2026-03-02spray2
2026-03-02fertilize1
2026-03-09cultivate4
2026-03-09irrigate1
2026-03-09spray2
2026-03-09fertilize0
2026-03-16cultivate3
2026-03-16irrigate2
2026-03-16spray3
2026-03-16fertilize3
2026-03-23cultivate3
2026-03-23irrigate1
2026-03-23spray2
2026-03-23fertilize1
2026-03-30cultivate2
2026-03-30irrigate1
2026-03-30spray2
2026-03-30fertilize1
2026-04-06cultivate2
2026-04-06irrigate1
2026-04-06spray4
2026-04-06fertilize2
2026-04-13cultivate0
2026-04-13irrigate2
2026-04-13spray3
2026-04-13fertilize1
2026-04-20cultivate3
2026-04-20irrigate3
2026-04-20spray3
2026-04-20fertilize1
2026-04-27cultivate1
2026-04-27irrigate5
2026-04-27spray1
2026-04-27fertilize2
2026-05-04cultivate2
2026-05-04irrigate3
2026-05-04spray0
2026-05-04fertilize3
2026-05-11cultivate4
2026-05-11irrigate1
2026-05-11spray2
2026-05-11fertilize1
2026-05-18cultivate2
2026-05-18irrigate2
2026-05-18spray3
2026-05-18fertilize2
2026-05-25cultivate1
2026-05-25irrigate1
2026-05-25spray0
2026-05-25fertilize3
2026-06-01cultivate2
2026-06-01irrigate0
2026-06-01spray3
2026-06-01fertilize4
2026-06-08cultivate5
2026-06-08irrigate6
2026-06-08spray0
2026-06-08fertilize1
2026-06-15cultivate2
2026-06-15irrigate0
2026-06-15spray1
2026-06-15fertilize1
2026-06-22cultivate2
2026-06-22irrigate3
2026-06-22spray0
2026-06-22fertilize3
2026-06-29cultivate1
2026-06-29irrigate5
2026-06-29spray1
2026-06-29fertilize1
2026-07-06cultivate3
2026-07-06irrigate0
2026-07-06spray2
2026-07-06fertilize1
2026-07-13cultivate2
2026-07-13irrigate4
2026-07-13spray0
2026-07-13fertilize1
2026-07-20cultivate0
2026-07-20irrigate3
2026-07-20spray1
2026-07-20fertilize1
2026-07-27cultivate1
2026-07-27irrigate0
2026-07-27spray2
2026-07-27fertilize2
2026-08-03cultivate3
2026-08-03irrigate5
2026-08-03spray2
2026-08-03fertilize2
2026-08-10cultivate3
2026-08-10irrigate1
2026-08-10spray1
2026-08-10fertilize2
2026-08-17cultivate1
2026-08-17irrigate2
2026-08-17spray2
2026-08-17fertilize6
2026-08-24cultivate0
2026-08-24irrigate0
2026-08-24spray3
2026-08-24fertilize1
2026-08-31cultivate1
2026-08-31irrigate0
2026-08-31spray0
2026-08-31fertilize1
2026-09-07cultivate3
2026-09-07irrigate1
2026-09-07spray1
2026-09-07fertilize0
2026-09-14cultivate0
2026-09-14irrigate2
2026-09-14spray2
2026-09-14fertilize3
2026-09-21cultivate2
2026-09-21irrigate1
2026-09-21spray4
2026-09-21fertilize5

Figure 26. Summarize within: Fields 79

bin_startbin_endcount
43.143.160

Figure 27. Summarize within: Fields 80

bin_startbin_endcount
29.14343
9.14316.2913
16.2923.433
23.4330.570
30.5737.710
37.7144.860
44.86521

Figure 28. Summarize within: Fields 81

bin_startbin_endcount
43.143.160

Figure 29. Emerging hot spots: Pest scouting 82

bin_startbin_endcount
-0.586-0.411128
-0.4111-0.236310
-0.2363-0.061430
-0.061430.11344
0.11340.28830
0.28830.46315
0.46310.6381

Figure 30. Emerging hot spots: Soil samples 83

bin_startbin_endcount
-1.356-0.780714
-0.7807-0.20540
-0.20540.369914
0.36990.945111
0.94511.525
1.522.0960
2.0962.6717

Figure 31. Repeat and near repeat classification: Pest scouting 84

periodseriesvalue
2026-03-30aphid1
2026-03-30navel orangeworm2
2026-03-30lygus3
2026-03-30mites0
2026-04-06aphid3
2026-04-06navel orangeworm2
2026-04-06lygus3
2026-04-06mites4
2026-04-13aphid3
2026-04-13navel orangeworm7
2026-04-13lygus4
2026-04-13mites8
2026-04-20aphid2
2026-04-20navel orangeworm2
2026-04-20lygus5
2026-04-20mites3
2026-04-27aphid2
2026-04-27navel orangeworm3
2026-04-27lygus2
2026-04-27mites4
2026-05-04aphid5
2026-05-04navel orangeworm9
2026-05-04lygus4
2026-05-04mites6
2026-05-11aphid4
2026-05-11navel orangeworm2
2026-05-11lygus6
2026-05-11mites2
2026-05-18aphid3
2026-05-18navel orangeworm5
2026-05-18lygus2
2026-05-18mites1
2026-05-25aphid2
2026-05-25navel orangeworm4
2026-05-25lygus8
2026-05-25mites5
2026-06-01aphid3
2026-06-01navel orangeworm3
2026-06-01lygus3
2026-06-01mites3
2026-06-08aphid11
2026-06-08navel orangeworm6
2026-06-08lygus2
2026-06-08mites4
2026-06-15aphid3
2026-06-15navel orangeworm3
2026-06-15lygus1
2026-06-15mites6
2026-06-22aphid3
2026-06-22navel orangeworm5
2026-06-22lygus1
2026-06-22mites4
2026-06-29aphid5
2026-06-29navel orangeworm4
2026-06-29lygus4
2026-06-29mites2
2026-07-06aphid86
2026-07-06navel orangeworm5
2026-07-06lygus5
2026-07-06mites7
2026-07-13aphid61
2026-07-13navel orangeworm9
2026-07-13lygus5
2026-07-13mites4
2026-07-20aphid3
2026-07-20navel orangeworm5
2026-07-20lygus5
2026-07-20mites1
2026-07-27aphid5
2026-07-27navel orangeworm2
2026-07-27lygus6
2026-07-27mites7
2026-08-03aphid5
2026-08-03navel orangeworm5
2026-08-03lygus5
2026-08-03mites3
2026-08-10aphid1
2026-08-10navel orangeworm8
2026-08-10lygus5
2026-08-10mites1
2026-08-17aphid6
2026-08-17navel orangeworm6
2026-08-17lygus4
2026-08-17mites1
2026-08-24aphid8
2026-08-24navel orangeworm4
2026-08-24lygus1
2026-08-24mites3
2026-08-31aphid5
2026-08-31navel orangeworm5
2026-08-31lygus5
2026-08-31mites2
2026-09-07aphid4
2026-09-07navel orangeworm3
2026-09-07lygus2
2026-09-07mites0
2026-09-14aphid1
2026-09-14navel orangeworm1
2026-09-14lygus1
2026-09-14mites2

Figure 32. NDVI change polygons 85

bin_startbin_endcount
0.044.933151
4.9339.8270
9.82714.720
14.7219.610
19.6124.510
24.5129.40
29.434.290
34.2939.190
39.1944.0824

Figure 33. Hot spot analysis: Pest scouting 86

bin_startbin_endbandband_labelcount
-1-0.5not_significantNot significant30
-0.50not_significantNot significant47
00.5not_significantNot significant36
0.51not_significantNot significant8
11.5not_significantNot significant6
22.5hot_95Hot spot, 95% confidence1
2.53hot_95Hot spot, 95% confidence2
2.53hot_99Hot spot, 99% confidence1
33.5hot_99Hot spot, 99% confidence1
4.55hot_99Hot spot, 99% confidence1
5.56hot_99Hot spot, 99% confidence1

Figure 34. Hot spot analysis: Wells 87

bin_startbin_endbandband_labelcount
-1.5-1not_significantNot significant1
-1-0.5not_significantNot significant4
-0.50not_significantNot significant3
00.5not_significantNot significant2
0.51not_significantNot significant1
1.52hot_90Hot spot, 90% confidence1
22.5hot_95Hot spot, 95% confidence1

Figure 35. Hot spot analysis: Soil samples 88

bin_startbin_endbandband_labelcount
-2-1.5not_significantNot significant16
-1.5-1not_significantNot significant11
-1-0.5not_significantNot significant9
-0.50not_significantNot significant38
00.5not_significantNot significant17
0.51not_significantNot significant29
11.5not_significantNot significant10
1.52hot_90Hot spot, 90% confidence5
22.5hot_95Hot spot, 95% confidence3
2.53hot_99Hot spot, 99% confidence1

Figure 36. Calculate density: Pest scouting 89

bin_startbin_endcount
03.09189
3.0916.18287
6.1829.27387
9.27312.3683
12.3615.4584
15.4518.5584
18.5521.6481
21.6424.7384
24.7327.8284
27.8230.9186
30.913488

Figure 37. Calculate density: Wells 90

bin_startbin_endcount
0.0017530.206324
0.20630.410813
0.41080.61549
0.61540.81999
0.81991.0247
1.0241.2294
1.2291.4336
1.4331.6383

Figure 38. Calculate density: Soil samples 91

bin_startbin_endcount
0368
3687
6986
91287
121587
151887
182186
212484
242786
273086
3033109

Figure 39. Find point clusters: Pest scouting 92

clusterfeaturesfractionshare
12720.523152.3%
Noise1130.217321.7%
0690.132713.3%
2370.071157.1%
3290.055775.6%

Figure 40. Find point clusters: cluster hulls 93

clusterfeaturesfractionshare
010.2525.0%
110.2525.0%
210.2525.0%
310.2525.0%

Figure 41. Find point clusters: Wells 94

clusterfeaturesfractionshare
1170.42542.5%
0120.330.0%
250.12512.5%
330.0757.5%
430.0757.5%

Figure 42. Find point clusters: cluster hulls 95

clusterfeaturesfractionshare
010.220.0%
110.220.0%
210.220.0%
310.220.0%
410.220.0%

Figure 43. Find point clusters: Soil samples 96

clusterfeaturesfractionshare
Noise6001100.0%

Figure 44. Find point clusters: Soil samples over time 97

periodvalue
2025-09-2916
2025-10-0625
2025-10-1334
2025-10-2028
2025-10-2726
2025-11-0336
2025-11-1033
2025-11-1723
2025-11-2431
2025-12-0126
2025-12-0829
2025-12-1530
2025-12-2235
2025-12-2934
2026-01-0526
2026-01-1227
2026-01-1919
2026-01-2622
2026-02-0226
2026-02-0924
2026-02-1631
2026-02-2319

Figure 45. Find point clusters: Pest scouting over time 98

periodseriesvalue
2026-03-30aphid1
2026-03-30navel orangeworm2
2026-03-30lygus3
2026-03-30mites0
2026-04-06aphid3
2026-04-06navel orangeworm2
2026-04-06lygus3
2026-04-06mites4
2026-04-13aphid3
2026-04-13navel orangeworm7
2026-04-13lygus4
2026-04-13mites8
2026-04-20aphid2
2026-04-20navel orangeworm2
2026-04-20lygus5
2026-04-20mites3
2026-04-27aphid2
2026-04-27navel orangeworm3
2026-04-27lygus2
2026-04-27mites4
2026-05-04aphid5
2026-05-04navel orangeworm9
2026-05-04lygus4
2026-05-04mites6
2026-05-11aphid4
2026-05-11navel orangeworm2
2026-05-11lygus6
2026-05-11mites2
2026-05-18aphid3
2026-05-18navel orangeworm5
2026-05-18lygus2
2026-05-18mites1
2026-05-25aphid2
2026-05-25navel orangeworm4
2026-05-25lygus8
2026-05-25mites5
2026-06-01aphid3
2026-06-01navel orangeworm3
2026-06-01lygus3
2026-06-01mites3
2026-06-08aphid11
2026-06-08navel orangeworm6
2026-06-08lygus2
2026-06-08mites4
2026-06-15aphid3
2026-06-15navel orangeworm3
2026-06-15lygus1
2026-06-15mites6
2026-06-22aphid3
2026-06-22navel orangeworm5
2026-06-22lygus1
2026-06-22mites4
2026-06-29aphid5
2026-06-29navel orangeworm4
2026-06-29lygus4
2026-06-29mites2
2026-07-06aphid86
2026-07-06navel orangeworm5
2026-07-06lygus5
2026-07-06mites7
2026-07-13aphid61
2026-07-13navel orangeworm9
2026-07-13lygus5
2026-07-13mites4
2026-07-20aphid3
2026-07-20navel orangeworm5
2026-07-20lygus5
2026-07-20mites1
2026-07-27aphid5
2026-07-27navel orangeworm2
2026-07-27lygus6
2026-07-27mites7
2026-08-03aphid5
2026-08-03navel orangeworm5
2026-08-03lygus5
2026-08-03mites3
2026-08-10aphid1
2026-08-10navel orangeworm8
2026-08-10lygus5
2026-08-10mites1
2026-08-17aphid6
2026-08-17navel orangeworm6
2026-08-17lygus4
2026-08-17mites1
2026-08-24aphid8
2026-08-24navel orangeworm4
2026-08-24lygus1
2026-08-24mites3
2026-08-31aphid5
2026-08-31navel orangeworm5
2026-08-31lygus5
2026-08-31mites2
2026-09-07aphid4
2026-09-07navel orangeworm3
2026-09-07lygus2
2026-09-07mites0
2026-09-14aphid1
2026-09-14navel orangeworm1
2026-09-14lygus1
2026-09-14mites2

Figure 46. Repeat and near repeat classification: Pest scouting over time 99

periodseriesvalue
2026-03-30aphid1
2026-03-30navel orangeworm2
2026-03-30lygus3
2026-03-30mites0
2026-04-06aphid3
2026-04-06navel orangeworm2
2026-04-06lygus3
2026-04-06mites4
2026-04-13aphid3
2026-04-13navel orangeworm7
2026-04-13lygus4
2026-04-13mites8
2026-04-20aphid2
2026-04-20navel orangeworm2
2026-04-20lygus5
2026-04-20mites3
2026-04-27aphid2
2026-04-27navel orangeworm3
2026-04-27lygus2
2026-04-27mites4
2026-05-04aphid5
2026-05-04navel orangeworm9
2026-05-04lygus4
2026-05-04mites6
2026-05-11aphid4
2026-05-11navel orangeworm2
2026-05-11lygus6
2026-05-11mites2
2026-05-18aphid3
2026-05-18navel orangeworm5
2026-05-18lygus2
2026-05-18mites1
2026-05-25aphid2
2026-05-25navel orangeworm4
2026-05-25lygus8
2026-05-25mites5
2026-06-01aphid3
2026-06-01navel orangeworm3
2026-06-01lygus3
2026-06-01mites3
2026-06-08aphid11
2026-06-08navel orangeworm6
2026-06-08lygus2
2026-06-08mites4
2026-06-15aphid3
2026-06-15navel orangeworm3
2026-06-15lygus1
2026-06-15mites6
2026-06-22aphid3
2026-06-22navel orangeworm5
2026-06-22lygus1
2026-06-22mites4
2026-06-29aphid5
2026-06-29navel orangeworm4
2026-06-29lygus4
2026-06-29mites2
2026-07-06aphid86
2026-07-06navel orangeworm5
2026-07-06lygus5
2026-07-06mites7
2026-07-13aphid61
2026-07-13navel orangeworm9
2026-07-13lygus5
2026-07-13mites4
2026-07-20aphid3
2026-07-20navel orangeworm5
2026-07-20lygus5
2026-07-20mites1
2026-07-27aphid5
2026-07-27navel orangeworm2
2026-07-27lygus6
2026-07-27mites7
2026-08-03aphid5
2026-08-03navel orangeworm5
2026-08-03lygus5
2026-08-03mites3
2026-08-10aphid1
2026-08-10navel orangeworm8
2026-08-10lygus5
2026-08-10mites1
2026-08-17aphid6
2026-08-17navel orangeworm6
2026-08-17lygus4
2026-08-17mites1
2026-08-24aphid8
2026-08-24navel orangeworm4
2026-08-24lygus1
2026-08-24mites3
2026-08-31aphid5
2026-08-31navel orangeworm5
2026-08-31lygus5
2026-08-31mites2
2026-09-07aphid4
2026-09-07navel orangeworm3
2026-09-07lygus2
2026-09-07mites0
2026-09-14aphid1
2026-09-14navel orangeworm1
2026-09-14lygus1
2026-09-14mites2

GeoBit Large Spatial Model. Findings are labeled Evidenced (computed by a tool), Inferred (a reading or reasoning) or Unverified (no evidence yet).

The data

The files this sample uploads: synthetic data generated at a real place. Download any of them and add them to a project of your own.

DatasetKindRowsTime spanFile
Fields
Field boundaries with crop and irrigation.		vector, Polygon60fields.geojson
Satellite scene 2026-04-15
A 4-band scene (blue, green, red, near infrared) at 20 m. Acquired 2026-04-15.		raster2026-04-15scene_2026-04-15.tif
Satellite scene 2026-08-15
A 4-band scene (blue, green, red, near infrared) at 20 m. Acquired 2026-08-15.		raster2026-08-15scene_2026-08-15.tif
Soil samples
Soil samples with pH, organic matter, nitrate and salinity. Dated by sampled_on (day).		vector, Point6002025-10-01
to 2026-02-27		soil_samples.geojson
Irrigation canals
Irrigation canals and laterals.		vector, LineString5canals.geojson
Wells
Irrigation wells with depth and water level.		vector, Point40wells.geojson
Pest scouting
Pest scouting observations with trap counts. Dated by observed_at (minute).		vector, Point5202026-04-01
to 2026-09-14		pest_scouting.geojson
Weather stations
On-farm weather stations.		vector, Point3weather_stations.geojson
Yields by season
Yield and applied water per field and season (joins to Fields on field_id). Dated by season (year).		table3002021-01-01
to 2025-01-01		yields_by_season.csv
Field operations
Operations applied per field (joins to Fields on field_id). Dated by date (day).		table2722026-02-01
to 2026-09-27		field_operations.csv
Agronomist season notes
Notes naming fields, wells and a position.		documentagronomist_notes.md, agronomist_notes.pdf

What the data was built to show

  • Eight fields lose vegetation between 2026-04-15 and 2026-08-15 (NDVI change): F001, F010, F017, F018, F032, F039, F050, F052.
  • Soil samples in the south-west are saline (high EC and pH, low organic matter).
  • An aphid outbreak clusters around 36.63833, -120.03368 in the weeks of 6 to 19 July.
  • Yields of the stressed fields drop about a third in 2025.

Expected analysis families: imagery, aggregation, hot_spots, density, map.

How the product read each dataset

The profile written when the data was added, before Start; no model call is needed for it.

  • Fields: 60 polygon (area) features; 'crop' has 5 values (top: tomato 16, almond 16, grape 11); 'irrigation' has 3 values (top: drip 28, micro sprinkler 22, furrow 10); 'area_ha' 43.1 to 43.1 (mean 43.1); 'planted_year' 2,008 to 2,025 (mean 2016); named by 'name' (e.g. Field 001 South, Field 002 South, Field 003 South); total area 25.83 km2; extent -120.0841,36.6269 to -120.0159,36.6731.
  • Satellite scene 2026-04-15: 4-band float32 raster (imagery), 300 x 250 cells; resolution 20; band 1 0.014 to 0.113; acquired 2026-04-15; extent -120.0844,36.6267 to -120.0156,36.6733.
  • Satellite scene 2026-08-15: 4-band float32 raster (imagery), 300 x 250 cells; resolution 20; band 1 0.015 to 0.145; acquired 2026-08-15; extent -120.0844,36.6267 to -120.0156,36.6733.
  • Soil samples: 600 point features; dated by 'sampled_on' from 2025-10-01 to 2026-02-27; 'ph' 6.4 to 9 (mean 7.401); 'organic_matter_pct' 0.11 to 1.99 (mean 1.236); 'nitrate_ppm' 3.6 to 65.5 (mean 17.55); extent -120.0834,36.6274 to -120.0174,36.6729.
  • Irrigation canals: 5 line features; 'type' has 2 values (top: lateral 3, canal 2); 'capacity_cfs' 38 to 232 (mean 143); named by 'name' (e.g. Canal 1, Canal 2, Lateral 1); total length 26.99 km; extent -120.0838,36.6270 to -120.0162,36.6730.
  • Wells: 40 point features; 'depth_ft' 307 to 871 (mean 604.4); 'pump_hp' 75 to 200 (mean 140.6); 'static_level_ft' 120 to 418 (mean 282.7); extent -120.0823,36.6281 to -120.0188,36.6714.
  • Pest scouting: 520 point features; dated by 'observed_at' from 2026-04-01 to 2026-09-14; 'pest' has 4 values (top: aphid 235, navel orangeworm 110, lygus 92); 'threshold_exceeded' has 2 values (top: False 374, True 146); 'count_per_trap' 0 to 13 (mean 4.477); extent -120.0833,36.6271 to -120.0169,36.6728.
  • Weather stations: 3 point features; 'elevation_m' 57 to 65 (mean 61.67); named by 'name' (e.g. Farm weather station 1, Farm weather station 2, Farm weather station 3); extent -120.0663,36.6367 to -120.0366,36.6639.
  • Yields by season: Table of 300 rows and 5 columns without geometry; dated by 'season' from 2021-01-01 to 2025-01-01; 'crop' has 5 values (top: tomato 80, almond 80, grape 55); 'yield_t_ha' 1.19 to 120.7 (mean 33.16); 'water_af_per_acre' 2.6 to 4.2 (mean 3.395).
  • Field operations: Table of 272 rows and 5 columns without geometry; dated by 'date' from 2026-02-01 to 2026-09-27; 'operation' has 4 values (top: cultivate 74, irrigate 68, spray 67); 'product' has 3 values (top: UAN-32 67, sulfur 65, water 64); 'rate' 5.1 to 59.9 (mean 33.66).
  • Agronomist season notes: 1-page md document 'Agronomist season notes, August 2026'; language en; mentions 7 place(s): Field 001 South (1), Field 010 South (1), Field 017 South (1), Field 018 South (1), Field (1).

Run this on your own data.

Sign up at lsm.geobit.ai, add your files, services and documents to a project, and get your own maps, charts and cited report.

Sign up See plans