GeoBitLarge Spatial Model

Logistics

Last-mile delivery stops, routes and delays

Madrid, Spainsynthetic data, real placeMaps, charts and report
The question

Where and when do delivery delays build up, and which zones and routes are getting worse over time?

A parcel carrier uploads its depots, eight weeks of delivery stops with delays, the routes driven, delivery zones, lockers, loading bays, roadworks, and daily route performance and the vehicle fleet as tables. It wants to know where and when delays build up and which zones and routes need attention.

40.4168, -3.7038data covers about 8 by 7 km
10datasets uploaded
21output layers
22maps made
28charts made
47findings
454 sStart run time

Every map and chart this run made is here. 22 map images, 28 charts and the cited report (PDF, Word, Markdown), as exported on 2026-10-22.

Findings (first few)

  • Evidenced: The timeline counts 3,740 dated events in Delivery stops, Roadworks, Route performance by day per week, from week of 2026-06-22 to week of 2026-09-14 1234.
  • Evidenced: By dataset: Delivery stops 2,000; Route performance by day 1,728; Roadworks 12 1.
  • Evidenced: The trend is +51.2 events per week; the second half of the weeks has 2,801 against 472 in the first (+493.4%) 1.
  • Evidenced: 1 of the 13 weeks had no events 1.
  • Evidenced: Change point detection found no shift in the counts 5.

What Start ran

Describe mode, the local model only (no paid model); run status succeeded, 8 analyst agents.

gp_calculate_densitygp_change_point_detectiongp_find_point_clustersgp_hot_spotsgp_line_densitygp_measuregp_near_repeatgp_outliersgp_space_time_hot_spotsgp_spatial_autocorrelationgp_summarize_within

Maps

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

Emerging hot spots: Delivery stops
Emerging hot spots: Delivery stopsFig. 2
Repeat and near repeat classification: Delivery stops
Repeat and near repeat classification: Delivery stopsFig. 3
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 4
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 5
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 6
Hot spot analysis: Delivery stops
Hot spot analysis: Delivery stopsFig. 7
Hot spot analysis: Parcel lockers
Hot spot analysis: Parcel lockersFig. 8
Hot spot analysis: Loading bays
Hot spot analysis: Loading baysFig. 9
Calculate density: Delivery stops
Calculate density: Delivery stopsFig. 10
Calculate density: Parcel lockers
Calculate density: Parcel lockersFig. 11
Calculate density: Loading bays
Calculate density: Loading baysFig. 12
Find point clusters: Delivery stops
Find point clusters: Delivery stopsFig. 13
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 14
Find point clusters: Parcel lockers
Find point clusters: Parcel lockersFig. 15
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 16
Find point clusters: Loading bays
Find point clusters: Loading baysFig. 17
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 18
Delivery zones by parcels_per_day
Delivery zones by parcels_per_dayFig. 19
Find outliers: Delivery zones
Find outliers: Delivery zonesFig. 20
Areas and lengths: Routes
Areas and lengths: RoutesFig. 21
Areas and lengths: Roadworks
Areas and lengths: RoadworksFig. 22
Line density: Routes
Line density: RoutesFig. 23

Charts

Every chart image this run exported.

Delivery zones over time (parcels_per_day)
Delivery zones over time (parcels_per_day)Fig. 24
Roadworks over time (start_date)
Roadworks over time (start_date)Fig. 25
Route performance by day over time (date)
Route performance by day over time (date)Fig. 26
Vehicle fleet over time (model_year)
Vehicle fleet over time (model_year)Fig. 27
Emerging hot spots: Delivery stops
Emerging hot spots: Delivery stopsFig. 28
Repeat and near repeat classification: Delivery stops
Repeat and near repeat classification: Delivery stopsFig. 29
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 30
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 31
Summarize within: Delivery zones
Summarize within: Delivery zonesFig. 32
Hot spot analysis: Delivery stops
Hot spot analysis: Delivery stopsFig. 33
Hot spot analysis: Parcel lockers
Hot spot analysis: Parcel lockersFig. 34
Hot spot analysis: Loading bays
Hot spot analysis: Loading baysFig. 35
Calculate density: Delivery stops
Calculate density: Delivery stopsFig. 36
Calculate density: Parcel lockers
Calculate density: Parcel lockersFig. 37
Calculate density: Loading bays
Calculate density: Loading baysFig. 38
Find point clusters: Delivery stops
Find point clusters: Delivery stopsFig. 39
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 40
Find point clusters: Parcel lockers
Find point clusters: Parcel lockersFig. 41
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 42
Find point clusters: Loading bays
Find point clusters: Loading baysFig. 43
Find point clusters: cluster hulls
Find point clusters: cluster hullsFig. 44
Find outliers: Delivery zones
Find outliers: Delivery zonesFig. 45
Areas and lengths: Routes
Areas and lengths: RoutesFig. 46
Areas and lengths: Roadworks
Areas and lengths: RoadworksFig. 47
Areas and lengths: Roadworks over time
Areas and lengths: Roadworks over timeFig. 48
Find point clusters: Delivery stops over time
Find point clusters: Delivery stops over timeFig. 49
Repeat and near repeat classification: Delivery stops over time
Repeat and near repeat classification: Delivery stops over timeFig. 50
Timeline: events per week by dataset
Timeline: events per week by datasetFig. 1

The cited report

Sample: Logistics, Madrid: report

Project: Sample: Logistics, Madrid
Goal: Describe the project Sample: Logistics, Madrid: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: a282190f-59a4-4a74-8816-0f88c1c06122 (running, 11 agent run(s))
Generated: 2026-10-18T05:22:18Z, version 1
Model cost: USD 0.0000 over 0 model call(s)

Data used

DataKindRowsTime spanSummarySource
Delivery zonesvector, Polygon1010 polygon (area) features; 'parcels_per_day' 1,219 to 4,832 (mean 2062); 'households' 26,833 to 106,313 (mean 4.537e+04); named by 'name' (e.g. Barrio Norte, Las Flores, El Molino); total area 56.04 km2; extent -3.7513,40.3850 to -3.6564,40.4486. Areas (Delivery zones) with parcels_per_day to compare and map.110
Depotsvector, Point33 point features; 'vans' 23 to 32 (mean 28.33); 'cargo_bikes' 4 to 14 (mean 8.333); 'dock_doors' 8 to 15 (mean 12.67); named by 'name' (e.g. Depot Norte, Depot Sur, Depot Este); extent -3.7276,40.3903 to -3.6643,40.4387. Point locations of Depots.111
Routesvector, LineString3636 line features; 'vehicle' has 3 values (top: van 23, cargo bike 10, electric van 3); 'distance_km' 9.14 to 35.39 (mean 19.79); 'planned_min' 142 to 378 (mean 237.6); total length 712.7 km; extent -3.7501,40.3857 to -3.6573,40.4480. Lines (Routes) such as routes or networks.112
Delivery stopsvector, Point2,0002026-07-27 to 2026-09-192,000 point features; dated by 'delivered_at' from 2026-07-27 to 2026-09-19; 'status' has 2 values (top: delivered 1877, failed 123); 'delay_min' -10 to 59 (mean 10.29); 'parcels' 1 to 3 (mean 1.583); extent -3.7499,40.3856 to -3.6567,40.4475. Dated point events by status: where and when Delivery stops happen.2
Parcel lockersvector, Point4545 point features; 'host' has 3 values (top: supermarket 16, metro 15, gas station 14); 'compartments' 40 to 90 (mean 60); 'utilization_pct' 35.3 to 97.3 (mean 60.95); extent -3.7492,40.3915 to -3.6578,40.4475. Point locations of Parcel lockers by host.113
Loading baysvector, Point6060 point features; 'enforced' has 2 values (top: True 43, False 17); 'max_minutes' 15 to 30 (mean 21.83); extent -3.7497,40.3880 to -3.6596,40.4477. Point locations of Loading bays by enforced.114
Roadworksvector, LineString122026-06-27 to 2026-09-0312 line features; dated by 'start_date' from 2026-06-27 to 2026-09-03; 'type' has 3 values (top: water main 6, resurfacing 3, metro 3); 'lanes_closed' 1 to 2 (mean 1.333); total length 4.26 km; extent -3.7212,40.3883 to -3.6585,40.4349. Lines (Roadworks) such as routes or networks.3
Route performance by daytable1,7282026-07-27 to 2026-09-19Table of 1,728 rows and 6 columns without geometry; dated by 'date' from 2026-07-27 to 2026-09-19; 'on_time_pct' 59.4 to 99.7 (mean 85.51); 'avg_delay_min' 0 to 24.5 (mean 8.212); 'failed_stops' 0 to 7 (mean 1.513). A table of Route performance by day without locations.4
Vehicle fleettable60Table of 60 rows and 6 columns without geometry; 'type' has 3 values (top: van 32, electric van 21, cargo bike 7); 'capacity_parcels' 35 to 160 (mean 104.4); 'range_km' 60 to 320 (mean 206.7); 'model_year' 2,017 to 2,026 (mean 2022). A table of Vehicle fleet without locations.115
Operations reviewdocument1-page md document 'Operations review: August and September 2026'; language en; mentions 5 place(s): Depot Este (2), El Molino (1), 40.41805, -3.70570 (1), Depot Sur (1), La Estacion (1). A document about Depot Este, El Molino, 40.41805, -3.70570.116
Sample: Logistics, Madridrecord117
Emerging hot spots: Delivery stopslayer, Polygon88118
Repeat and near repeat classification: Delivery stopslayer, Point2,000119
Summarize within: Delivery zoneslayer, Polygon10120
Summarize within: Delivery zoneslayer, Polygon10121
Summarize within: Delivery zoneslayer, Polygon10122
Hot spot analysis: Delivery stopslayer, Polygon254123
Hot spot analysis: Parcel lockerslayer, Polygon19124
Hot spot analysis: Loading bayslayer, Polygon19125
Calculate density: Delivery stopslayer, Polygon1,654126
Calculate density: Parcel lockerslayer, Polygon99127
Calculate density: Loading bayslayer, Polygon101128
Find point clusters: Delivery stopslayer, Point2,000129
Find point clusters: cluster hullslayer, Polygon2130
Find point clusters: Parcel lockerslayer, Point45131
Find point clusters: cluster hullslayer, Polygon1132
Find point clusters: Loading bayslayer, Point60133
Find point clusters: cluster hullslayer, Polygon6134
Find outliers: Delivery zoneslayer, Polygon10135
Areas and lengths: Routeslayer, LineString36136
Areas and lengths: Roadworkslayer, LineString12137
Line density: Routeslayer, Polygon480138

Timeline

Timeline: events per week by dataset
Figure 1. Timeline: events per week by dataset 1. Per week, 2026-06-22 to 2026-09-14. Source: Delivery stops, Roadworks, Route performance by day (3,740 features). The data is in the appendix.

The timeline counts 3,740 dated events in Delivery stops, Roadworks, Route performance by day per week, from week of 2026-06-22 to week of 2026-09-14 1234. By dataset: Delivery stops 2,000; Route performance by day 1,728; Roadworks 12 1. The trend is +51.2 events per week; the second half of the weeks has 2,801 against 472 in the first (+493.4%) 1. 1 of the 13 weeks had no events 1. Change point detection found no shift in the counts 5.

Busiest weeks

  • week of 2026-08-24: 491 events 1
  • week of 2026-09-07: 471 events 1
  • week of 2026-08-03: 467 events 1

Quietest weeks with events

  • week of 2026-06-22: 1 event 1
  • week of 2026-07-13: 1 event 1
  • week of 2026-07-06: 2 events 1

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 6. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 6.

Why it was run on this data. Delivery stops carry dates in 'delivered_at': emerging hot spot analysis finds new, intensifying and fading hot spots per week 7.

What it found. Space time hot spots on Delivery stops: Emerging hot spots: 1 layer saved: Emerging hot spots: Delivery stops (88 features) 89. It reported result, count 88; result, elapsed ms 15; result, resolution 8; result, features used 2,000; result, time neighbors 0; billing, cost 0.2 8.

ResultValue
result, count88
result, elapsed ms15
result, resolution8
result, features used2,000
result, time neighbors0
billing, cost0.2
billing, list price0.2
billing, upstream cost0

Findings

  • Evidenced: Space time hot spots on Delivery stops: Emerging hot spots: 1 layer saved: Emerging hot spots: Delivery stops (88 features) 89.
  • Evidenced: It reported result, count 88; result, elapsed ms 15; result, resolution 8; result, features used 2,000; result, time neighbors 0; billing, cost 0.2 8.

Tool gp_space_time_hot_spots; parameters {"project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "interval": "week", "bin_shape": "h3", "resolution": 8, "time_field": "delivered_at"}

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 10. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 10.

Why it was run on this data. Near repeat analysis tests whether Delivery stops close in space also follow each other within 5 days 11.

What it found. Near repeat on Delivery stops: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Delivery stops (2000 features) 912. It reported result, days 5; result, count 2,000; result, chains 276; result, distance m 200; result, elapsed ms 48; result, pairs linked 1,743 12.

ResultValue
result, days5
result, count2,000
result, chains276
result, distance m200
result, elapsed ms48
result, pairs linked1,743
billing, cost0.11
billing, list price0.11
billing, upstream cost0

Findings

  • Evidenced: Near repeat on Delivery stops: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Delivery stops (2000 features) 912.
  • Evidenced: It reported result, days 5; result, count 2,000; result, chains 276; result, distance m 200; result, elapsed ms 48; result, pairs linked 1,743 12.

Tool gp_near_repeat; parameters {"days": 5, "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "distance_m": 200.0, "time_field": "delivered_at"}

Change point detection

What this analysis is. Change point detection: When did the level, count, trend or variability change 13? For the whole study area or for every bin 13. In ArcGIS it is Change Point Detection 13.

Why it was run on this data. Change point detection finds when the weekly count of Delivery stops shifted 14.

What it found. Change point detection on Delivery stops: Change point detection: done; no map output 59. It reported result, n changes 0; result, elapsed ms 4; result, events used 2,000; billing, cost 0.11; billing, list price 0.11; billing, upstream cost 0 5.

ResultValue
result, n changes0
result, elapsed ms4
result, events used2,000
billing, cost0.11
billing, list price0.11
billing, upstream cost0

Findings

  • Evidenced: Change point detection on Delivery stops: Change point detection: done; no map output 59.
  • Evidenced: It reported result, n changes 0; result, elapsed ms 4; result, events used 2,000; billing, cost 0.11; billing, list price 0.11; billing, upstream cost 0 5.

Tool gp_change_point_detection; parameters {"method": "count", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "interval": "week", "time_field": "delivered_at"}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 15. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 15.

Why it was run on this data. Count Depots inside each feature of Delivery zones; the counts map as a choropleth (natural breaks, sequential colors) 16.

What it found. Summarize within on Depots, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 171819. It reported result, count 10; result, elapsed ms 0; billing, cost 0.01028; billing, list price 0.01028; billing, upstream cost 0 17.

ResultValue
result, count10
result, elapsed ms0
billing, cost0.01028
billing, list price0.01028
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Depots, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 171819.
  • Evidenced: It reported result, count 10; result, elapsed ms 0; billing, cost 0.01028; billing, list price 0.01028; billing, upstream cost 0 17.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "vans"}], "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Depots (84d3272c)"}, "polygons": {"layer": "Delivery zones (bfcf8b53)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 15. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 15.

Why it was run on this data. Count Depots inside each feature of Delivery zones; the counts map as a choropleth (natural breaks, sequential colors) 16.

What it found. Summarize within on Delivery stops, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 91920. It reported result, count 10; result, elapsed ms 4; billing, cost 0.05022; billing, list price 0.05022; billing, upstream cost 0 20.

ResultValue
result, count10
result, elapsed ms4
billing, cost0.05022
billing, list price0.05022
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Delivery stops, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 91920.
  • Evidenced: It reported result, count 10; result, elapsed ms 4; billing, cost 0.05022; billing, list price 0.05022; billing, upstream cost 0 20.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "delay_min"}], "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "group_by": "status", "polygons": {"layer": "Delivery zones (bfcf8b53)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 15. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 15.

Why it was run on this data. Count Depots inside each feature of Delivery zones; the counts map as a choropleth (natural breaks, sequential colors) 16.

What it found. Summarize within on Parcel lockers, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 192122. It reported result, count 10; result, elapsed ms 0; billing, cost 0.01112; billing, list price 0.01112; billing, upstream cost 0 21.

ResultValue
result, count10
result, elapsed ms0
billing, cost0.01112
billing, list price0.01112
billing, upstream cost0

Findings

  • Evidenced: Summarize within on Parcel lockers, Delivery zones: Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features) 192122.
  • Evidenced: It reported result, count 10; result, elapsed ms 0; billing, cost 0.01112; billing, list price 0.01112; billing, upstream cost 0 21.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "compartments"}], "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Parcel lockers (4e9e11a9)"}, "group_by": "host", "polygons": {"layer": "Delivery zones (bfcf8b53)"}}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 23. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 23.

Why it was run on this data. 2000 points: Getis-Ord Gi* tests whether the concentrations in Delivery stops are statistically significant 24.

What it found. The hot spot analysis was conducted using the Delivery stops layer 9 and the gp_hot_spots tool 25. The process produced 254 features and calculated a count of 254 results 25. For this analysis, 2,000 incidents were utilized, and the resulting cell size was 500 m 25. The total billing cost for the analysis was 0.09 25.

ResultValue
result, bins254
result, count254
result, elapsed ms23
result, cell size m500
result, incidents used2,000
result, distance band m500
billing, cost0.09
billing, list price0.09
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Delivery stops: Hot spot analysis: 1 layer saved: Hot spot analysis: Delivery stops (254 features) 925.
  • Evidenced: It reported result, bins 254; result, count 254; result, elapsed ms 23; result, cell size m 500; result, incidents used 2,000; result, distance band m 500 25.

Tool gp_hot_spots; parameters {"project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "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 23. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 23.

Why it was run on this data. 45 points: Getis-Ord Gi* tests whether the concentrations in Parcel lockers are statistically significant 26.

What it found. The hot spot analysis was conducted using the Parcel lockers layer 22. The analysis produced 1 layer, titled "Hot spot analysis: Parcel lockers (19 features)" 27. Key results showed the analysis generated 19 bins containing 19 features 27. The operation took 2 milliseconds to complete, and the resulting cell size and distance band were both 2,000 meters 27.

ResultValue
result, bins19
result, count19
result, elapsed ms2
result, cell size m2,000
result, incidents used45
result, distance band m2,000
billing, cost0.0509
billing, list price0.0509
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Parcel lockers: Hot spot analysis: 1 layer saved: Hot spot analysis: Parcel lockers (19 features) 2227.
  • Evidenced: It reported result, bins 19; result, count 19; result, elapsed ms 2; result, cell size m 2,000; result, incidents used 45; result, distance band m 2,000 27.

Tool gp_hot_spots; parameters {"project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Parcel lockers (4e9e11a9)"}, "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 23. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 23.

Why it was run on this data. 60 points: Getis-Ord Gi* tests whether the concentrations in Loading bays are statistically significant 28.

What it found. Hot spots on Loading bays: Hot spot analysis: 1 layer saved: Hot spot analysis: Loading bays (19 features) 2930. It reported result, bins 19; result, count 19; result, elapsed ms 2; result, cell size m 2,000; result, incidents used 60; result, distance band m 2,000 29.

ResultValue
result, bins19
result, count19
result, elapsed ms2
result, cell size m2,000
result, incidents used60
result, distance band m2,000
billing, cost0.0512
billing, list price0.0512
billing, upstream cost0

Findings

  • Evidenced: Hot spots on Loading bays: Hot spot analysis: 1 layer saved: Hot spot analysis: Loading bays (19 features) 2930.
  • Evidenced: It reported result, bins 19; result, count 19; result, elapsed ms 2; result, cell size m 2,000; result, incidents used 60; result, distance band m 2,000 29.

Tool gp_hot_spots; parameters {"project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Loading bays (16574f8d)"}, "aggregation": "hexagon", "cell_size_m": 2000.0, "distance_band_m": 2000.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 31. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 31.

Why it was run on this data. 2000 points in Delivery stops: a density surface shows where they concentrate 32.

What it found. Calculate density on Delivery stops: Calculate density: 1 layer saved: Calculate density: Delivery stops (1654 features) 933. It reported result, count 1,654; result, elapsed ms 74; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 396 33.

ResultValue
result, count1,654
result, elapsed ms74
result, bandwidth m500
result, cell size m200
result, excluded null0
result, max density per km2396
billing, cost0.09
billing, list price0.09
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Delivery stops: Calculate density: 1 layer saved: Calculate density: Delivery stops (1654 features) 933.
  • Evidenced: It reported result, count 1,654; result, elapsed ms 74; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 396 33.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "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 31. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 31.

Why it was run on this data. 45 points in Parcel lockers: a density surface shows where they concentrate 34.

What it found. The calculation of density using the gp_calculate_density tool analyzed the Parcel lockers layer 22 and processed 99 features 35. The process required an elapsed time of 5 ms 35, identifying a maximum density of 1.381 per km² 35.

ResultValue
result, count99
result, elapsed ms5
result, bandwidth m2,000
result, cell size m1,000
result, excluded null0
result, max density per km21.381
billing, cost0.0509
billing, list price0.0509
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Parcel lockers: Calculate density: 1 layer saved: Calculate density: Parcel lockers (99 features) 2235.
  • Evidenced: It reported result, count 99; result, elapsed ms 5; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1.381 35.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Parcel lockers (4e9e11a9)"}, "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 31. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 31.

Why it was run on this data. 60 points in Loading bays: a density surface shows where they concentrate 36.

What it found. The density calculation used the Loading bays dataset 30. This process analyzed 101 features and reported a total bandwidth of 2,000 meters 37. The maximum density calculated across the layers was 1.929 per km² 37.

ResultValue
result, count101
result, elapsed ms5
result, bandwidth m2,000
result, cell size m1,000
result, excluded null0
result, max density per km21.929
billing, cost0.0512
billing, list price0.0512
billing, upstream cost0

Findings

  • Evidenced: Calculate density on Loading bays: Calculate density: 1 layer saved: Calculate density: Loading bays (101 features) 3037.
  • Evidenced: It reported result, count 101; result, elapsed ms 5; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 1.929 37.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Loading bays (16574f8d)"}, "bandwidth_m": 2000.0, "cell_size_m": 1000.0}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 38. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 38.

Why it was run on this data. DBSCAN finds dense groups of Delivery stops and separates noise 39.

What it found. Find point clusters on Delivery stops: Find point clusters: 2 layers saved: Find point clusters: Delivery stops (2000 features); Find point clusters: cluster hulls (2 features) 940. It reported result, count 2,000; result, noise 1,570; result, distance m 200; result, elapsed ms 214; result, min points 20; billing, cost 0.09 40.

ResultValue
result, count2,000
result, noise1,570
result, distance m200
result, elapsed ms214
result, min points20
billing, cost0.09
billing, list price0.09
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Delivery stops: Find point clusters: 2 layers saved: Find point clusters: Delivery stops (2000 features); Find point clusters: cluster hulls (2 features) 940.
  • Evidenced: It reported result, count 2,000; result, noise 1,570; result, distance m 200; result, elapsed ms 214; result, min points 20; billing, cost 0.09 40.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery stops (ba8073d9)"}, "distance_m": 200.0, "min_points": 20}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 38. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 38.

Why it was run on this data. DBSCAN finds dense groups of Parcel lockers and separates noise 41.

What it found. Find point clusters on Parcel lockers: Find point clusters: 2 layers saved: Find point clusters: Parcel lockers (45 features); Find point clusters: cluster hulls (1 feature) 2242. It reported result, count 45; result, noise 1; result, distance m 2,000; result, elapsed ms 2; result, min points 3; billing, cost 0.0509 42.

ResultValue
result, count45
result, noise1
result, distance m2,000
result, elapsed ms2
result, min points3
billing, cost0.0509
billing, list price0.0509
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Parcel lockers: Find point clusters: 2 layers saved: Find point clusters: Parcel lockers (45 features); Find point clusters: cluster hulls (1 feature) 2242.
  • Evidenced: It reported result, count 45; result, noise 1; result, distance m 2,000; result, elapsed ms 2; result, min points 3; billing, cost 0.0509 42.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Parcel lockers (4e9e11a9)"}, "distance_m": 2000.0, "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 38. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 38.

Why it was run on this data. DBSCAN finds dense groups of Loading bays and separates noise 43.

What it found. Find point clusters on Loading bays: Find point clusters: 2 layers saved: Find point clusters: Loading bays (60 features); Find point clusters: cluster hulls (6 features) 3044. It reported result, count 60; result, noise 7; result, distance m 1,000; result, elapsed ms 4; result, min points 3; billing, cost 0.0512 44.

ResultValue
result, count60
result, noise7
result, distance m1,000
result, elapsed ms4
result, min points3
billing, cost0.0512
billing, list price0.0512
billing, upstream cost0

Findings

  • Evidenced: Find point clusters on Loading bays: Find point clusters: 2 layers saved: Find point clusters: Loading bays (60 features); Find point clusters: cluster hulls (6 features) 3044.
  • Evidenced: It reported result, count 60; result, noise 7; result, distance m 1,000; result, elapsed ms 4; result, min points 3; billing, cost 0.0512 44.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Loading bays (16574f8d)"}, "distance_m": 1000.0, "min_points": 3}

Outliers

What this analysis is. Find outliers: Anselin local Moran’s I: HH, LL clusters and HL, LH outliers 45. In ArcGIS it is Find Outliers or Cluster and Outlier Analysis (Anselin Local Moran’s I) 45.

Why it was run on this data. Local Moran's I maps clusters and outliers of 'parcels_per_day' 46.

What it found. Outliers on Delivery zones: Find outliers: 1 layer saved: Find outliers: Delivery zones (10 features) 1947. It reported result, count 10; result, elapsed ms 4; result, permutations 199; result, excluded null 0; result, distance band m 2,661; billing, cost 0.0503 47.

ResultValue
result, count10
result, elapsed ms4
result, permutations199
result, excluded null0
result, distance band m2,661
billing, cost0.0503
billing, list price0.0503
billing, upstream cost0

Findings

  • Evidenced: Outliers on Delivery zones: Find outliers: 1 layer saved: Find outliers: Delivery zones (10 features) 1947.
  • Evidenced: It reported result, count 10; result, elapsed ms 4; result, permutations 199; result, excluded null 0; result, distance band m 2,661; billing, cost 0.0503 47.

Tool gp_outliers; parameters {"field": "parcels_per_day", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery zones (bfcf8b53)"}, "aggregation": "hexagon"}

Spatial autocorrelation

What this analysis is. Spatial autocorrelation: Global Moran’s I: is the pattern clustered, dispersed or random 48. In ArcGIS it is Spatial Autocorrelation (Global Moran’s I) 48.

Why it was run on this data. Global Moran's I says whether similar values of 'parcels_per_day' sit next to each other 49.

What it found. Spatial autocorrelation on Delivery zones: Spatial autocorrelation: done; no map output 1950. It reported result, n 10; result, p value 0.1412; result, z score 1.471; result, morans i 0.09356; result, variance 0.01935; result, elapsed ms 2 50.

ResultValue
result, n10
result, p value0.1412
result, z score1.471
result, morans i0.09356
result, variance0.01935
result, elapsed ms2
result, expected i-0.1111
result, excluded null0
result, distance band m2,661
result, p value normality0.421
result, z score normality0.8046
result, variance normality0.06471
billing, cost0.02
billing, list price0.02
billing, upstream cost0

Findings

  • Evidenced: Spatial autocorrelation on Delivery zones: Spatial autocorrelation: done; no map output 1950.
  • Evidenced: It reported result, n 10; result, p value 0.1412; result, z score 1.471; result, morans i 0.09356; result, variance 0.01935; result, elapsed ms 2 50.

Tool gp_spatial_autocorrelation; parameters {"field": "parcels_per_day", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Delivery zones (bfcf8b53)"}}

Measure

What this analysis is. Areas and lengths: Geodesic area, perimeter and length of each feature 51. In ArcGIS it is Areas And Lengths or Calculate Geometry; in QGIS, qgis:exportaddgeometrycolumns 51.

Why it was run on this data. Lengths of the 36 lines of Routes (total and per feature) 52.

What it found. Measure on Routes: Areas and lengths: 1 layer saved: Areas and lengths: Routes (36 features) 5354. It reported result, count 36; result, elapsed ms 7; billing, cost 0.01; billing, list price 0.01; billing, upstream cost 0 53.

ResultValue
result, count36
result, elapsed ms7
billing, cost0.01
billing, list price0.01
billing, upstream cost0

Findings

  • Evidenced: Measure on Routes: Areas and lengths: 1 layer saved: Areas and lengths: Routes (36 features) 5354.
  • Evidenced: It reported result, count 36; result, elapsed ms 7; billing, cost 0.01; billing, list price 0.01; billing, upstream cost 0 53.

Tool gp_measure; parameters {"units": "metric", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Routes (93de6e09)"}}

Measure

What this analysis is. Areas and lengths: Geodesic area, perimeter and length of each feature 51. In ArcGIS it is Areas And Lengths or Calculate Geometry; in QGIS, qgis:exportaddgeometrycolumns 51.

Why it was run on this data. Lengths of the 12 lines of Roadworks (total and per feature) 55.

What it found. The gp_measure tool was utilized with the Roadworks layer as input 57. The tool saved the areas and lengths for Roadworks, which contained 12 features 56. The process resulted in a count of 12 features and took 0 elapsed ms 56.

ResultValue
result, count12
result, elapsed ms0
billing, cost0.01
billing, list price0.01
billing, upstream cost0

Findings

  • Evidenced: Measure on Roadworks: Areas and lengths: 1 layer saved: Areas and lengths: Roadworks (12 features) 5657.
  • Evidenced: It reported result, count 12; result, elapsed ms 0; billing, cost 0.01; billing, list price 0.01; billing, upstream cost 0 56.

Tool gp_measure; parameters {"units": "metric", "project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Roadworks (50ecfc27)"}}

Line density

What this analysis is. Line density: Length of lines per unit area around each cell (km per square km), optionally weighted by a field 58. In ArcGIS it is Line Density; in QGIS, qgis:linedensity 58.

Why it was run on this data. Line density shows where Routes are densest 59.

What it found. Line density on Routes: Line density: 1 layer saved: Line density: Routes (480 features) 5460. It reported result, count 480; result, radius m 2,000; result, elapsed ms 69; result, cell size m 500; result, total length km 712.7; result, max density km per km2 20.21 60.

ResultValue
result, count480
result, radius m2,000
result, elapsed ms69
result, cell size m500
result, total length km712.7
result, max density km per km220.21
billing, cost0.05072
billing, list price0.05072
billing, upstream cost0

Findings

  • Evidenced: Line density on Routes: Line density: 1 layer saved: Line density: Routes (480 features) 5460.
  • Evidenced: It reported result, count 480; result, radius m 2,000; result, elapsed ms 69; result, cell size m 500; result, total length km 712.7; result, max density km per km2 20.21 60.

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

Tool gp_line_density; parameters {"project": "55917da2-e619-41aa-b6a1-e521a75b705c", "features": {"layer": "Routes (93de6e09)"}, "radius_m": 2000.0, "cell_size_m": 500.0}

Maps and charts

The run also made 22 map image(s) 61626364656667686970717273747576777879808182 and 27 chart(s) 8384858687888990919293949596979899100101102103104105106107108109.

Emerging hot spots: Delivery stops
Figure 2. Emerging hot spots: Delivery stops 61
Repeat and near repeat classification: Delivery stops
Figure 3. Repeat and near repeat classification: Delivery stops 62
Summarize within: Delivery zones
Figure 4. Summarize within: Delivery zones 63
Summarize within: Delivery zones
Figure 5. Summarize within: Delivery zones 64
Summarize within: Delivery zones
Figure 6. Summarize within: Delivery zones 65
Hot spot analysis: Delivery stops
Figure 7. Hot spot analysis: Delivery stops 66
Hot spot analysis: Parcel lockers
Figure 8. Hot spot analysis: Parcel lockers 67
Hot spot analysis: Loading bays
Figure 9. Hot spot analysis: Loading bays 68
Calculate density: Delivery stops
Figure 10. Calculate density: Delivery stops 69
Calculate density: Parcel lockers
Figure 11. Calculate density: Parcel lockers 70
Calculate density: Loading bays
Figure 12. Calculate density: Loading bays 71
Find point clusters: Delivery stops
Figure 13. Find point clusters: Delivery stops 72
Find point clusters: cluster hulls
Figure 14. Find point clusters: cluster hulls 73
Find point clusters: Parcel lockers
Figure 15. Find point clusters: Parcel lockers 74
Find point clusters: cluster hulls
Figure 16. Find point clusters: cluster hulls 75
Find point clusters: Loading bays
Figure 17. Find point clusters: Loading bays 76
Find point clusters: cluster hulls
Figure 18. Find point clusters: cluster hulls 77
Delivery zones by parcels_per_day
Figure 19. Delivery zones by parcels_per_day 78
Find outliers: Delivery zones
Figure 20. Find outliers: Delivery zones 79
Areas and lengths: Routes
Figure 21. Areas and lengths: Routes 80
Areas and lengths: Roadworks
Figure 22. Areas and lengths: Roadworks 81
Line density: Routes
Figure 23. Line density: Routes 82

What the map shows. The map shows the emerging hot spots for delivery stops, categorizing intensity 61

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

Delivery zones over time (parcels_per_day)
Figure 24. Delivery zones over time (parcels_per_day) 83. Source: Delivery zones (10 features). The data is in the appendix.
Roadworks over time (start_date)
Figure 25. Roadworks over time (start_date) 84. Per week, 2026-06-22 to 2026-08-31. Source: Roadworks (12 features). The data is in the appendix.
Route performance by day over time (date)
Figure 26. Route performance by day over time (date) 85. Per week, 2026-07-27 to 2026-09-14. Source: Route performance by day (1,728 features). The data is in the appendix.
Vehicle fleet over time (model_year)
Figure 27. Vehicle fleet over time (model_year) 86. Source: Vehicle fleet (60 features). The data is in the appendix.
Emerging hot spots: Delivery stops
Figure 28. Emerging hot spots: Delivery stops 87. Source: Emerging hot spots: Delivery stops (88 features). The data is in the appendix.
Repeat and near repeat classification: Delivery stops
Figure 29. Repeat and near repeat classification: Delivery stops 88. Per week, 2026-07-27 to 2026-09-14. Source: Repeat and near repeat classification: Delivery stops (2,000 features). The data is in the appendix.
Summarize within: Delivery zones
Figure 30. Summarize within: Delivery zones 89. Source: Summarize within: Delivery zones (10 features). The data is in the appendix.
Summarize within: Delivery zones
Figure 31. Summarize within: Delivery zones 90. Source: Summarize within: Delivery zones (10 features). The data is in the appendix.
Summarize within: Delivery zones
Figure 32. Summarize within: Delivery zones 91. Source: Summarize within: Delivery zones (10 features). The data is in the appendix.
Hot spot analysis: Delivery stops
Figure 33. Hot spot analysis: Delivery stops 92. Source: Hot spot analysis: Delivery stops (254 features). The data is in the appendix.
Hot spot analysis: Parcel lockers
Figure 34. Hot spot analysis: Parcel lockers 93. Source: Hot spot analysis: Parcel lockers (19 features). The data is in the appendix.
Hot spot analysis: Loading bays
Figure 35. Hot spot analysis: Loading bays 94. Source: Hot spot analysis: Loading bays (19 features). The data is in the appendix.
Calculate density: Delivery stops
Figure 36. Calculate density: Delivery stops 95. Source: Calculate density: Delivery stops (1,654 features). The data is in the appendix.
Calculate density: Parcel lockers
Figure 37. Calculate density: Parcel lockers 96. Source: Calculate density: Parcel lockers (99 features). The data is in the appendix.
Calculate density: Loading bays
Figure 38. Calculate density: Loading bays 97. Source: Calculate density: Loading bays (101 features). The data is in the appendix.
Find point clusters: Delivery stops
Figure 39. Find point clusters: Delivery stops 98. Period: 2026-07-27 to 2026-09-19 (delivered_at). Source: Find point clusters: Delivery stops (2,000 features). The data is in the appendix.
Find point clusters: cluster hulls
Figure 40. Find point clusters: cluster hulls 99. Source: Find point clusters: cluster hulls (2 features). The data is in the appendix.
Find point clusters: Parcel lockers
Figure 41. Find point clusters: Parcel lockers 100. Source: Find point clusters: Parcel lockers (45 features). The data is in the appendix.
Find point clusters: cluster hulls
Figure 42. Find point clusters: cluster hulls 101. Source: Find point clusters: cluster hulls (1 features). The data is in the appendix.
Find point clusters: Loading bays
Figure 43. Find point clusters: Loading bays 102. Source: Find point clusters: Loading bays (60 features). The data is in the appendix.
Find point clusters: cluster hulls
Figure 44. Find point clusters: cluster hulls 103. Source: Find point clusters: cluster hulls (6 features). The data is in the appendix.
Find outliers: Delivery zones
Figure 45. Find outliers: Delivery zones 104. Source: Find outliers: Delivery zones (10 features). The data is in the appendix.
Areas and lengths: Routes
Figure 46. Areas and lengths: Routes 105. Source: Areas and lengths: Routes (36 features). The data is in the appendix.
Areas and lengths: Roadworks
Figure 47. Areas and lengths: Roadworks 106. Per week, 2026-08-03 to 2026-11-16. Source: Areas and lengths: Roadworks (12 features). The data is in the appendix.
Areas and lengths: Roadworks over time
Figure 48. Areas and lengths: Roadworks over time 107. Per week, 2026-08-03 to 2026-11-16. Source: Areas and lengths: Roadworks (12 features). The data is in the appendix.
Find point clusters: Delivery stops over time
Figure 49. Find point clusters: Delivery stops over time 108. Per week, 2026-07-27 to 2026-09-14. Source: Find point clusters: Delivery stops (2,000 features). The data is in the appendix.
Repeat and near repeat classification: Delivery stops over time
Figure 50. Repeat and near repeat classification: Delivery stops over time 109. Per week, 2026-07-27 to 2026-09-14. Source: Repeat and near repeat classification: Delivery stops (2,000 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 week by dataset. 39 rows id 1521b52f-2ba2-4bbc-a8f6-ccfe5e7fdf7f
  2. 2Dataset: Delivery stops. vector, 2000 rows id b701b76f-6822-4c92-82fe-b4acdce6c331
  3. 3Dataset: Roadworks. vector, 12 rows id 6fda682d-6a14-4d92-9cdd-cdcabec36863
  4. 4Dataset: Route performance by day. table, 1728 rows id 93163425-d292-4c3d-9bd8-2e8681a816c2
  5. 5Tool result: gp_change_point_detection, step 2. Change point detection: done; no map output. id 0bc1c879-b643-4a1a-9035-72f62d929ae4:2
  6. 6Catalog: 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
  7. 7Plan: Space time hot spots of Delivery stops (the Start plan's candidate c_24901805ebc9). Delivery stops carry dates in 'delivered_at': emerging hot spot analysis finds new, intensifying and fading hot spots per week. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_24901805ebc9
  8. 8Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Delivery stops (88 features). id 0bc1c879-b643-4a1a-9035-72f62d929ae4:0
  9. 9Layer: Delivery stops. 2,000 features id ba8073d9-f217-4175-acc5-437aabf37b16
  10. 10Catalog: 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
  11. 11Plan: Near repeat of Delivery stops (the Start plan's candidate c_07c2356dde76). Near repeat analysis tests whether Delivery stops close in space also follow each other within 5 days. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_07c2356dde76
  12. 12Tool result: gp_near_repeat, step 1. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Delivery stops (2000 features). id 0bc1c879-b643-4a1a-9035-72f62d929ae4:1
  13. 13Catalog: Change point detection (operation catalog, gp_change_point_detection). When did the level, count, trend or variability change? For the whole study area or for every bin. ArcGIS: Change Point Detection. id gp_change_point_detection
  14. 14Plan: Change points of Delivery stops (the Start plan's candidate c_e6c80aa728e2). Change point detection finds when the weekly count of Delivery stops shifted. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_e6c80aa728e2
  15. 15Catalog: 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
  16. 16Plan: Depots per feature of Delivery zones (the Start plan's candidate c_63970c31d3b8). Count Depots inside each feature of Delivery zones; the counts map as a choropleth (natural breaks, sequential colors). id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_63970c31d3b8
  17. 17Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features). id 06830d85-af54-42ad-b4e3-68502ee43e45:0
  18. 18Layer: Depots. 3 features id 84d3272c-9902-4e4b-a3a0-899c3b10edb7
  19. 19Layer: Delivery zones. 10 features id bfcf8b53-48d2-44c7-b00e-a89315aee1b5
  20. 20Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features). id 06830d85-af54-42ad-b4e3-68502ee43e45:1
  21. 21Tool result: gp_summarize_within, step 2. Summarize within: 1 layer saved: Summarize within: Delivery zones (10 features). id 06830d85-af54-42ad-b4e3-68502ee43e45:2
  22. 22Layer: Parcel lockers. 45 features id 4e9e11a9-8154-47b8-a5ce-2ba3dbf5f3e6
  23. 23Catalog: 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
  24. 24Plan: Hot spots of Delivery stops (the Start plan's candidate c_90d2c6f9911f). 2000 points: Getis-Ord Gi* tests whether the concentrations in Delivery stops are statistically significant. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_90d2c6f9911f
  25. 25Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Delivery stops (254 features). id baba02b7-1f72-470f-802a-5d9cf0a96e0e:0
  26. 26Plan: Hot spots of Parcel lockers (the Start plan's candidate c_7f159ca7fe80). 45 points: Getis-Ord Gi* tests whether the concentrations in Parcel lockers are statistically significant. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_7f159ca7fe80
  27. 27Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Parcel lockers (19 features). id baba02b7-1f72-470f-802a-5d9cf0a96e0e:1
  28. 28Plan: Hot spots of Loading bays (the Start plan's candidate c_be4560f0ca20). 60 points: Getis-Ord Gi* tests whether the concentrations in Loading bays are statistically significant. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_be4560f0ca20
  29. 29Tool result: gp_hot_spots, step 2. Hot spot analysis: 1 layer saved: Hot spot analysis: Loading bays (19 features). id baba02b7-1f72-470f-802a-5d9cf0a96e0e:2
  30. 30Layer: Loading bays. 60 features id 16574f8d-1ab3-403e-bf7c-ef2918a3168a
  31. 31Catalog: 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
  32. 32Plan: Kernel density of Delivery stops (the Start plan's candidate c_b00e122abf70). 2000 points in Delivery stops: a density surface shows where they concentrate. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_b00e122abf70
  33. 33Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Delivery stops (1654 features). id 5426b1e3-5d44-4200-ad65-fcd6b9219354:0
  34. 34Plan: Kernel density of Parcel lockers (the Start plan's candidate c_d0abfcdb6ebd). 45 points in Parcel lockers: a density surface shows where they concentrate. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_d0abfcdb6ebd
  35. 35Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Parcel lockers (99 features). id 5426b1e3-5d44-4200-ad65-fcd6b9219354:1
  36. 36Plan: Kernel density of Loading bays (the Start plan's candidate c_f4d285023245). 60 points in Loading bays: a density surface shows where they concentrate. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_f4d285023245
  37. 37Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Loading bays (101 features). id 5426b1e3-5d44-4200-ad65-fcd6b9219354:2
  38. 38Catalog: 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
  39. 39Plan: Cluster points of Delivery stops (the Start plan's candidate c_ecc06546584b). DBSCAN finds dense groups of Delivery stops and separates noise. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_ecc06546584b
  40. 40Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Delivery stops (2000 features); Find point clusters: cluster hulls (2 features). id 95a73131-a24c-4f4f-9468-8e9fb0e8dd34:0
  41. 41Plan: Cluster points of Parcel lockers (the Start plan's candidate c_ea1cd80d3915). DBSCAN finds dense groups of Parcel lockers and separates noise. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_ea1cd80d3915
  42. 42Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Parcel lockers (45 features); Find point clusters: cluster hulls (1 feature). id 95a73131-a24c-4f4f-9468-8e9fb0e8dd34:1
  43. 43Plan: Cluster points of Loading bays (the Start plan's candidate c_d272c4a82a27). DBSCAN finds dense groups of Loading bays and separates noise. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_d272c4a82a27
  44. 44Tool result: gp_find_point_clusters, step 2. Find point clusters: 2 layers saved: Find point clusters: Loading bays (60 features); Find point clusters: cluster hulls (6 features). id 95a73131-a24c-4f4f-9468-8e9fb0e8dd34:2
  45. 45Catalog: Find outliers (operation catalog, gp_outliers). Anselin local Moran’s I: HH, LL clusters and HL, LH outliers. ArcGIS: Find Outliers, Cluster and Outlier Analysis (Anselin Local Moran’s I). id gp_outliers
  46. 46Plan: Local morans i of Delivery zones (the Start plan's candidate c_0bac5b3b8830). Local Moran's I maps clusters and outliers of 'parcels_per_day'. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_0bac5b3b8830
  47. 47Tool result: gp_outliers, step 0. Find outliers: 1 layer saved: Find outliers: Delivery zones (10 features). id 4c008862-b527-4c01-a253-53d590dcfc30:0
  48. 48Catalog: Spatial autocorrelation (operation catalog, gp_spatial_autocorrelation). Global Moran’s I: is the pattern clustered, dispersed or random. ArcGIS: Spatial Autocorrelation (Global Moran’s I). id gp_spatial_autocorrelation
  49. 49Plan: Global morans i of Delivery zones (the Start plan's candidate c_49e20ce52312). Global Moran's I says whether similar values of 'parcels_per_day' sit next to each other. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_49e20ce52312
  50. 50Tool result: gp_spatial_autocorrelation, step 1. Spatial autocorrelation: done; no map output. id 4c008862-b527-4c01-a253-53d590dcfc30:1
  51. 51Catalog: Areas and lengths (operation catalog, gp_measure). Geodesic area, perimeter and length of each feature. ArcGIS: Areas And Lengths, Calculate Geometry. QGIS: qgis:exportaddgeometrycolumns. id gp_measure
  52. 52Plan: Length stats of Routes (the Start plan's candidate c_85d40397c2bc). Lengths of the 36 lines of Routes (total and per feature). id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_85d40397c2bc
  53. 53Tool result: gp_measure, step 0. Areas and lengths: 1 layer saved: Areas and lengths: Routes (36 features). id 91b1b73d-cdc4-44e3-a35d-b8f649d4d58d:0
  54. 54Layer: Routes. 36 features id 93de6e09-79b3-40e9-8b57-4b7906bd7eef
  55. 55Plan: Length stats of Roadworks (the Start plan's candidate c_a7200769644e). Lengths of the 12 lines of Roadworks (total and per feature). id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_a7200769644e
  56. 56Tool result: gp_measure, step 1. Areas and lengths: 1 layer saved: Areas and lengths: Roadworks (12 features). id 91b1b73d-cdc4-44e3-a35d-b8f649d4d58d:1
  57. 57Layer: Roadworks. 12 features id 50ecfc27-2fb7-43a7-a97c-62847d89632e
  58. 58Catalog: Line density (operation catalog, gp_line_density). Length of lines per unit area around each cell (km per square km), optionally weighted by a field. ArcGIS: Line Density. QGIS: qgis:linedensity. id gp_line_density
  59. 59Plan: Line density of Routes (the Start plan's candidate c_42f6ef8679a2). Line density shows where Routes are densest. id 99a0ba18-4245-45ac-a729-8f0ed736c8b0:c_42f6ef8679a2
  60. 60Tool result: gp_line_density, step 2. Line density: 1 layer saved: Line density: Routes (480 features). id 91b1b73d-cdc4-44e3-a35d-b8f649d4d58d:2
  61. 61Rendering: Map: Emerging hot spots: Delivery stops id f1d06252-1aff-40b3-8003-f6b25228a418
  62. 62Rendering: Map: Repeat and near repeat classification: Delivery stops id 56dbe991-5135-48c1-bc6c-7d3b6a07d808
  63. 63Rendering: Map: Summarize within: Delivery zones id 858fe721-2926-4049-9403-b702f7c1d708
  64. 64Rendering: Map: Summarize within: Delivery zones id 2824f9fd-2587-4fb5-a77e-a3aa3900d97b
  65. 65Rendering: Map: Summarize within: Delivery zones id 27fa5b0d-6371-4492-98c5-31025c68e575
  66. 66Rendering: Map: Hot spot analysis: Delivery stops id 2bacb0be-de03-4c38-bf8f-0ae5de932ab2
  67. 67Rendering: Map: Hot spot analysis: Parcel lockers id 518d4c2b-80c3-42d9-bc31-0561cedde38a
  68. 68Rendering: Map: Hot spot analysis: Loading bays id 3bd8a3a6-8e83-4ea2-b732-5258f2917d5b
  69. 69Rendering: Map: Calculate density: Delivery stops id e5664686-25ef-412b-ba05-b9ff052753ba
  70. 70Rendering: Map: Calculate density: Parcel lockers id 9153e49e-e4a6-473d-9b9a-0c99aa981559
  71. 71Rendering: Map: Calculate density: Loading bays id 089aef48-4d04-4e2b-adf3-1b5f5ba6339b
  72. 72Rendering: Map: Find point clusters: Delivery stops id 7e2737d2-52c9-41a9-ba06-a22cd7165f20
  73. 73Rendering: Map: Find point clusters: cluster hulls id 4f3cc889-cd88-4ebf-a131-f8a38db74f3a
  74. 74Rendering: Map: Find point clusters: Parcel lockers id 980074f9-34f5-41ca-b730-bf16feeff400
  75. 75Rendering: Map: Find point clusters: cluster hulls id 7a66f851-f7b6-4f69-9d38-1eabeffea2a6
  76. 76Rendering: Map: Find point clusters: Loading bays id ce8ded9c-4170-4c0f-89c3-9e2f0139076b
  77. 77Rendering: Map: Find point clusters: cluster hulls id 3a1bb395-8af7-4e6b-92e6-5049fe664a97
  78. 78Rendering: Map: Delivery zones by parcels_per_day id 69ec72f2-551e-4c36-9de4-64b8694296ea
  79. 79Rendering: Map: Find outliers: Delivery zones id 784a0e29-5811-4741-945d-714d4fcd467c
  80. 80Rendering: Map: Areas and lengths: Routes id 79d6c4d8-5815-4392-acf3-1f691e6cd92c
  81. 81Rendering: Map: Areas and lengths: Roadworks id 639ec0fd-16fb-4b55-80ad-9ccaac010750
  82. 82Rendering: Map: Line density: Routes id c697b1c6-e2a2-4247-a4b7-0e7df7e97f00
  83. 83Rendering: Chart: Delivery zones over time (parcels_per_day). 5 rows id 3c505c95-3e52-4c5e-b196-a568f2171052
  84. 84Rendering: Chart: Roadworks over time (start_date). 33 rows id b39779d1-1e2b-44ac-aabb-76eb01c77d35
  85. 85Rendering: Chart: Route performance by day over time (date). 8 rows id b65bccae-a1a1-4e72-ad21-f8677654af9e
  86. 86Rendering: Chart: Vehicle fleet over time (model_year). 7 rows id 931218d3-0ce6-4d63-b966-4d7ecca4f72b
  87. 87Rendering: Chart: Emerging hot spots: Delivery stops. 8 rows id 001edf48-ce03-4110-b451-7e47cefb2ce2
  88. 88Rendering: Chart: Repeat and near repeat classification: Delivery stops. 16 rows id 2613f13d-0205-403c-968f-467d6b8f18f2
  89. 89Rendering: Chart: Summarize within: Delivery zones. 5 rows id 40091302-ced6-4853-a28e-c0ab84bba36e
  90. 90Rendering: Chart: Summarize within: Delivery zones. 5 rows id c26a03d2-ecac-406f-b1c6-cb323c8972c6
  91. 91Rendering: Chart: Summarize within: Delivery zones. 5 rows id 2e9694e1-5c83-4efa-9ca3-1f148701edd0
  92. 92Rendering: Chart: Hot spot analysis: Delivery stops. 12 rows id 6f99017b-7c08-476b-b981-9fa925479410
  93. 93Rendering: Chart: Hot spot analysis: Parcel lockers. 6 rows id 20343f2f-b6eb-4043-a48d-0151b407e909
  94. 94Rendering: Chart: Hot spot analysis: Loading bays. 6 rows id c1c9a919-b186-4232-8d8b-b7389924e9cd
  95. 95Rendering: Chart: Calculate density: Delivery stops. 12 rows id 0ba97a70-8aad-48cf-87c2-76cf7c7397ac
  96. 96Rendering: Chart: Calculate density: Parcel lockers. 8 rows id 497850ae-e8d8-417c-a07d-29a5ca46284e
  97. 97Rendering: Chart: Calculate density: Loading bays. 8 rows id 35ec39ed-b26e-42b1-bc59-ed94b99f9552
  98. 98Rendering: Chart: Find point clusters: Delivery stops. 3 rows id 38539886-bc2b-42a5-a72d-5568be187825
  99. 99Rendering: Chart: Find point clusters: cluster hulls. 2 rows id 338c3b9e-35ed-4db2-8bc0-a3a861c4c0a5
  100. 100Rendering: Chart: Find point clusters: Parcel lockers. 2 rows id 07017722-d2cb-4819-a0c1-8678ecaa6069
  101. 101Rendering: Chart: Find point clusters: cluster hulls. 1 rows id df1f8b27-67ba-452d-9903-5fb39e94536e
  102. 102Rendering: Chart: Find point clusters: Loading bays. 7 rows id 55877d31-670a-4414-b3d9-a5a94c031ea2
  103. 103Rendering: Chart: Find point clusters: cluster hulls. 6 rows id e2598c9e-3c2b-436e-aee2-463caf5d80d5
  104. 104Rendering: Chart: Find outliers: Delivery zones. 10 rows id 91935639-db85-4e93-abb1-ebacc5cbe28f
  105. 105Rendering: Chart: Areas and lengths: Routes. 7 rows id 35bb3975-be91-41d8-b635-b9396a602106
  106. 106Rendering: Chart: Areas and lengths: Roadworks. 48 rows id 0a975f43-6acf-4887-afda-2a66d1ef8d59
  107. 107Rendering: Chart: Areas and lengths: Roadworks over time. 48 rows id 9f61cad0-7d51-4311-a916-62ea61f27aa8
  108. 108Rendering: Chart: Find point clusters: Delivery stops over time. 16 rows id 71c46175-748d-4398-9f7d-e07e43524c4c
  109. 109Rendering: Chart: Repeat and near repeat classification: Delivery stops over time. 16 rows id 7f6f8dcd-9739-475e-8a73-e687a2eed73e
  110. 110Dataset: Delivery zones. vector, 10 rows id ad6ace2b-b87b-4426-b59c-fe04636a404c
  111. 111Dataset: Depots. vector, 3 rows id 01a5d86e-7877-46c0-b8d7-c7125ff945d6
  112. 112Dataset: Routes. vector, 36 rows id 6b02543e-134e-4798-8c55-7433740f3a99
  113. 113Dataset: Parcel lockers. vector, 45 rows id bec44bb9-e98a-4cba-ad40-4738c680b667
  114. 114Dataset: Loading bays. vector, 60 rows id c8f85255-787a-4380-8e60-7b2d51723499
  115. 115Dataset: Vehicle fleet. table, 60 rows id 247c930d-b071-44b8-abcc-a946270b0521
  116. 116Dataset: Operations review. document, ? rows id db8eab40-ac85-4720-ba18-144f3cb5e953
  117. 117Record: Sample: Logistics, Madrid id 55917da2-e619-41aa-b6a1-e521a75b705c
  118. 118Layer: Emerging hot spots: Delivery stops. 88 features id 3eda3d63-4109-4ada-a0a5-a28cb0adffff
  119. 119Layer: Repeat and near repeat classification: Delivery stops. 2,000 features id 16311f39-dfc9-4fec-9ba4-5ab359b9d89b
  120. 120Layer: Summarize within: Delivery zones. 10 features id eaca5331-e8c9-435a-bd13-b434e2db618e
  121. 121Layer: Summarize within: Delivery zones. 10 features id ddf33542-ad9c-48ca-92aa-bb183fc2175b
  122. 122Layer: Summarize within: Delivery zones. 10 features id 7f9be9fb-5f32-4d00-b86c-2ccbc578ecc5
  123. 123Layer: Hot spot analysis: Delivery stops. 254 features id 277a1b72-5c43-4bb2-8a19-af8ab6d8cc80
  124. 124Layer: Hot spot analysis: Parcel lockers. 19 features id 169714e0-714b-4884-8a02-53783c9c7f03
  125. 125Layer: Hot spot analysis: Loading bays. 19 features id 4caff2b6-ee3f-4415-bdc9-5fa9437fd063
  126. 126Layer: Calculate density: Delivery stops. 1,654 features id 99dbaab0-d5d0-4b45-987b-d2c43d1d09c8
  127. 127Layer: Calculate density: Parcel lockers. 99 features id 472257d0-327b-4c9e-a4a8-480595dc3856
  128. 128Layer: Calculate density: Loading bays. 101 features id b6afbc2f-7942-4c9b-94f7-38c291b44345
  129. 129Layer: Find point clusters: Delivery stops. 2,000 features id cc731b64-afbe-4a38-943f-995b6107d190
  130. 130Layer: Find point clusters: cluster hulls. 2 features id 436a36cd-df6c-4e32-a0cc-26d50a8c6585
  131. 131Layer: Find point clusters: Parcel lockers. 45 features id 5e40b4a8-a526-40ac-b338-c5f4ebf27f56
  132. 132Layer: Find point clusters: cluster hulls. 1 features id 5ab85912-f47a-4fb3-b798-991d03f36a1b
  133. 133Layer: Find point clusters: Loading bays. 60 features id 90a837e8-38e5-46ee-a786-10b7fcae3bc0
  134. 134Layer: Find point clusters: cluster hulls. 6 features id 4e2df776-301c-492e-bb6b-6813e216076d
  135. 135Layer: Find outliers: Delivery zones. 10 features id 5e638f0b-04fd-4df9-a5c9-b3d338aebaea
  136. 136Layer: Areas and lengths: Routes. 36 features id 8b07f80e-053c-4638-867e-d4f875f2ab43
  137. 137Layer: Areas and lengths: Roadworks. 12 features id 2ce6988d-7414-430d-b0b9-ede487fe0343
  138. 138Layer: Line density: Routes. 480 features id 90fa509b-1446-4abc-b818-41008be35963
Appendix: the data behind the chartsShow

Figure 1. Timeline: events per week by dataset 1

periodseriesvalue
2026-06-22Delivery stops0
2026-06-22Route performance by day0
2026-06-22Roadworks1
2026-06-29Delivery stops0
2026-06-29Route performance by day0
2026-06-29Roadworks0
2026-07-06Delivery stops0
2026-07-06Route performance by day0
2026-07-06Roadworks2
2026-07-13Delivery stops0
2026-07-13Route performance by day0
2026-07-13Roadworks1
2026-07-20Delivery stops0
2026-07-20Route performance by day0
2026-07-20Roadworks3
2026-07-27Delivery stops248
2026-07-27Route performance by day216
2026-07-27Roadworks1
2026-08-03Delivery stops251
2026-08-03Route performance by day216
2026-08-03Roadworks0
2026-08-10Delivery stops242
2026-08-10Route performance by day216
2026-08-10Roadworks1
2026-08-17Delivery stops248
2026-08-17Route performance by day216
2026-08-17Roadworks0
2026-08-24Delivery stops274
2026-08-24Route performance by day216
2026-08-24Roadworks1
2026-08-31Delivery stops238
2026-08-31Route performance by day216
2026-08-31Roadworks2
2026-09-07Delivery stops255
2026-09-07Route performance by day216
2026-09-07Roadworks0
2026-09-14Delivery stops244
2026-09-14Route performance by day216
2026-09-14Roadworks0

Figure 24. Delivery zones over time (parcels_per_day) 83

bin_startbin_endcount
1,2191,9426
1,9422,6643
2,6643,3870
3,3874,1090
4,1094,8321

Figure 25. Roadworks over time (start_date) 84

periodseriesvalue
2026-06-22water main1
2026-06-22metro0
2026-06-22resurfacing0
2026-06-29water main0
2026-06-29metro0
2026-06-29resurfacing0
2026-07-06water main1
2026-07-06metro0
2026-07-06resurfacing1
2026-07-13water main1
2026-07-13metro0
2026-07-13resurfacing0
2026-07-20water main0
2026-07-20metro2
2026-07-20resurfacing1
2026-07-27water main1
2026-07-27metro0
2026-07-27resurfacing0
2026-08-03water main0
2026-08-03metro0
2026-08-03resurfacing0
2026-08-10water main1
2026-08-10metro0
2026-08-10resurfacing0
2026-08-17water main0
2026-08-17metro0
2026-08-17resurfacing0
2026-08-24water main1
2026-08-24metro0
2026-08-24resurfacing0
2026-08-31water main0
2026-08-31metro1
2026-08-31resurfacing1

Figure 26. Route performance by day over time (date) 85

periodvalue
2026-07-27216
2026-08-03216
2026-08-10216
2026-08-17216
2026-08-24216
2026-08-31216
2026-09-07216
2026-09-14216

Figure 27. Vehicle fleet over time (model_year) 86

bin_startbin_endcount
3552.8613
52.8670.710
70.7188.570
88.57106.413
106.4124.320
124.3142.10
142.116014

Figure 28. Emerging hot spots: Delivery stops 87

bin_startbin_endcount
-1.381-0.545720
-0.54570.289528
0.28951.12517
1.1251.9611
1.962.7953
2.7953.6315
3.6314.4661
4.4665.3013

Figure 29. Repeat and near repeat classification: Delivery stops 88

periodseriesvalue
2026-07-27delivered238
2026-07-27failed10
2026-08-03delivered227
2026-08-03failed24
2026-08-10delivered229
2026-08-10failed13
2026-08-17delivered233
2026-08-17failed15
2026-08-24delivered253
2026-08-24failed21
2026-08-31delivered222
2026-08-31failed16
2026-09-07delivered241
2026-09-07failed14
2026-09-14delivered234
2026-09-14failed10

Figure 30. Summarize within: Delivery zones 89

bin_startbin_endcount
00.27
0.20.40
0.40.60
0.60.80
0.813

Figure 31. Summarize within: Delivery zones 90

bin_startbin_endcount
62145.26
145.2228.41
228.4311.61
311.6394.80
394.84782

Figure 32. Summarize within: Delivery zones 91

bin_startbin_endcount
13.25
3.25.42
5.47.61
7.69.81
9.8121

Figure 33. Hot spot analysis: Delivery stops 92

bin_startbin_endbandband_labelcount
-1-0.5not_significantNot significant50
-0.50not_significantNot significant127
00.5not_significantNot significant41
0.51not_significantNot significant11
11.5not_significantNot significant13
1.52hot_90Hot spot, 90% confidence4
1.52not_significantNot significant1
22.5hot_95Hot spot, 95% confidence3
44.5hot_99Hot spot, 99% confidence1
5.56hot_99Hot spot, 99% confidence1
6.57hot_99Hot spot, 99% confidence1
7.58hot_99Hot spot, 99% confidence1

Figure 34. Hot spot analysis: Parcel lockers 93

bin_startbin_endbandband_labelcount
-2-1.5not_significantNot significant2
-1-0.5not_significantNot significant6
-0.50not_significantNot significant1
00.5not_significantNot significant5
11.5not_significantNot significant3
1.52hot_90Hot spot, 90% confidence2

Figure 35. Hot spot analysis: Loading bays 94

bin_startbin_endbandband_labelcount
-1.5-1not_significantNot significant3
-1-0.5not_significantNot significant5
-0.50not_significantNot significant2
00.5not_significantNot significant3
0.51not_significantNot significant4
1.52hot_90Hot spot, 90% confidence2

Figure 36. Calculate density: Delivery stops 95

bin_startbin_endcount
03.667129
3.6677.333155
7.33311113
1114.67149
14.6718.33156
18.3322115
2225.67154
25.6729.33152
29.3333116
3336.67154
36.6740.33156
40.3344105

Figure 37. Calculate density: Parcel lockers 96

bin_startbin_endcount
2.197e-050.172632
0.17260.345115
0.34510.517711
0.51770.690315
0.69030.86289
0.86281.0356
1.0351.2088
1.2081.3813

Figure 38. Calculate density: Loading bays 97

bin_startbin_endcount
3.822e-070.241235
0.24120.482315
0.48230.723512
0.72350.964713
0.96471.20611
1.2061.4476
1.4471.6886
1.6881.9293

Figure 39. Find point clusters: Delivery stops 98

clusterfeaturesfractionshare
Noise1,5700.78578.5%
04020.20120.1%
1280.0141.4%

Figure 40. Find point clusters: cluster hulls 99

clusterfeaturesfractionshare
010.550.0%
110.550.0%

Figure 41. Find point clusters: Parcel lockers 100

clusterfeaturesfractionshare
0440.977897.8%
Noise10.022222.2%

Figure 42. Find point clusters: cluster hulls 101

clusterfeaturesfractionshare
011100.0%

Figure 43. Find point clusters: Loading bays 102

clusterfeaturesfractionshare
2160.266726.7%
1150.2525.0%
0120.220.0%
Noise70.116711.7%
540.066676.7%
330.055.0%
430.055.0%

Figure 44. Find point clusters: cluster hulls 103

clusterfeaturesfractionshare
010.166716.7%
110.166716.7%
210.166716.7%
310.166716.7%
410.166716.7%
510.166716.7%

Figure 45. Find outliers: Delivery zones 104

valuelagtype
-0.2612-0.2991NS
-0.3242-0.2814NS
0.0467-0.2927NS
0.1170.7266NS
2.8620.117NS
-0.8708-0.1672NS
-0.0732-0.3384NS
-0.6094-0.1465NS
-0.2323-0.6321NS
-0.6549-0.2323NS

Figure 46. Areas and lengths: Routes 105

bin_startbin_endcount
9,1451.29e+046
1.29e+041.665e+042
1.665e+042.04e+0411
2.04e+042.415e+0410
2.415e+042.79e+044
2.79e+043.165e+042
3.165e+043.54e+041

Figure 47. Areas and lengths: Roadworks 106

periodseriesvalue
2026-08-03water main1
2026-08-03metro0
2026-08-03resurfacing0
2026-08-10water main0
2026-08-10metro0
2026-08-10resurfacing0
2026-08-17water main1
2026-08-17metro0
2026-08-17resurfacing1
2026-08-24water main1
2026-08-24metro0
2026-08-24resurfacing0
2026-08-31water main0
2026-08-31metro1
2026-08-31resurfacing0
2026-09-07water main0
2026-09-07metro0
2026-09-07resurfacing0
2026-09-14water main0
2026-09-14metro0
2026-09-14resurfacing0
2026-09-21water main0
2026-09-21metro0
2026-09-21resurfacing0
2026-09-28water main1
2026-09-28metro0
2026-09-28resurfacing1
2026-10-05water main0
2026-10-05metro0
2026-10-05resurfacing0
2026-10-12water main1
2026-10-12metro1
2026-10-12resurfacing0
2026-10-19water main0
2026-10-19metro0
2026-10-19resurfacing0
2026-10-26water main0
2026-10-26metro0
2026-10-26resurfacing0
2026-11-02water main0
2026-11-02metro0
2026-11-02resurfacing1
2026-11-09water main0
2026-11-09metro0
2026-11-09resurfacing0
2026-11-16water main1
2026-11-16metro1
2026-11-16resurfacing0

Figure 48. Areas and lengths: Roadworks over time 107

periodseriesvalue
2026-08-03water main1
2026-08-03metro0
2026-08-03resurfacing0
2026-08-10water main0
2026-08-10metro0
2026-08-10resurfacing0
2026-08-17water main1
2026-08-17metro0
2026-08-17resurfacing1
2026-08-24water main1
2026-08-24metro0
2026-08-24resurfacing0
2026-08-31water main0
2026-08-31metro1
2026-08-31resurfacing0
2026-09-07water main0
2026-09-07metro0
2026-09-07resurfacing0
2026-09-14water main0
2026-09-14metro0
2026-09-14resurfacing0
2026-09-21water main0
2026-09-21metro0
2026-09-21resurfacing0
2026-09-28water main1
2026-09-28metro0
2026-09-28resurfacing1
2026-10-05water main0
2026-10-05metro0
2026-10-05resurfacing0
2026-10-12water main1
2026-10-12metro1
2026-10-12resurfacing0
2026-10-19water main0
2026-10-19metro0
2026-10-19resurfacing0
2026-10-26water main0
2026-10-26metro0
2026-10-26resurfacing0
2026-11-02water main0
2026-11-02metro0
2026-11-02resurfacing1
2026-11-09water main0
2026-11-09metro0
2026-11-09resurfacing0
2026-11-16water main1
2026-11-16metro1
2026-11-16resurfacing0

Figure 49. Find point clusters: Delivery stops over time 108

periodseriesvalue
2026-07-27delivered238
2026-07-27failed10
2026-08-03delivered227
2026-08-03failed24
2026-08-10delivered229
2026-08-10failed13
2026-08-17delivered233
2026-08-17failed15
2026-08-24delivered253
2026-08-24failed21
2026-08-31delivered222
2026-08-31failed16
2026-09-07delivered241
2026-09-07failed14
2026-09-14delivered234
2026-09-14failed10

Figure 50. Repeat and near repeat classification: Delivery stops over time 109

periodseriesvalue
2026-07-27delivered238
2026-07-27failed10
2026-08-03delivered227
2026-08-03failed24
2026-08-10delivered229
2026-08-10failed13
2026-08-17delivered233
2026-08-17failed15
2026-08-24delivered253
2026-08-24failed21
2026-08-31delivered222
2026-08-31failed16
2026-09-07delivered241
2026-09-07failed14
2026-09-14delivered234
2026-09-14failed10

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
Delivery zones
Delivery zones with daily parcel volume.		vector, Polygon10delivery_zones.geojson
Depots
Delivery depots with vans, cargo bikes and dock doors.		vector, Point3depots.geojson
Routes
Routes driven on a sample day, from the depot through the stops.		vector, LineString36routes.geojson
Delivery stops
Eight weeks of delivery stops with status and delay against the promised window. Dated by delivered_at (minute).		vector, Point2,0002026-07-27
to 2026-09-19		delivery_stops.geojson
Parcel lockers
Parcel lockers with use.		vector, Point45parcel_lockers.geojson
Loading bays
On-street loading bays.		vector, Point60loading_bays.geojson
Roadworks
Roadworks by start date with lanes closed. Dated by start_date (day).		vector, LineString122026-06-27
to 2026-09-03		roadworks.geojson
Route performance by day
Daily on-time share, delay and failed stops per route (joins to Routes on route_id). Dated by date (day).		table1,7282026-07-27
to 2026-09-19		route_performance_daily.csv
Vehicle fleet
The vehicle fleet per depot (joins to Depots on depot_id).		table60fleet.csv
Operations review
A review naming depots, zones and the old town.		documentoperations_review.md, operations_review.pdf

What the data was built to show

  • Delays grow week by week in El Molino (Z03), behind the roadworks.
  • Failed deliveries cluster in the old town near 40.41805, -3.70570.
  • No deliveries on Sundays; Fridays are the busiest days.

Expected analysis families: space_time, hot_spots, density, aggregation, clusters.

How the product read each dataset

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

  • Delivery zones: 10 polygon (area) features; 'parcels_per_day' 1,219 to 4,832 (mean 2062); 'households' 26,833 to 106,313 (mean 4.537e+04); named by 'name' (e.g. Barrio Norte, Las Flores, El Molino); total area 56.04 km2; extent -3.7513,40.3850 to -3.6564,40.4486.
  • Depots: 3 point features; 'vans' 23 to 32 (mean 28.33); 'cargo_bikes' 4 to 14 (mean 8.333); 'dock_doors' 8 to 15 (mean 12.67); named by 'name' (e.g. Depot Norte, Depot Sur, Depot Este); extent -3.7276,40.3903 to -3.6643,40.4387.
  • Routes: 36 line features; 'vehicle' has 3 values (top: van 23, cargo bike 10, electric van 3); 'distance_km' 9.14 to 35.39 (mean 19.79); 'planned_min' 142 to 378 (mean 237.6); total length 712.7 km; extent -3.7501,40.3857 to -3.6573,40.4480.
  • Delivery stops: 2,000 point features; dated by 'delivered_at' from 2026-07-27 to 2026-09-19; 'status' has 2 values (top: delivered 1877, failed 123); 'delay_min' -10 to 59 (mean 10.29); 'parcels' 1 to 3 (mean 1.583); extent -3.7499,40.3856 to -3.6567,40.4475.
  • Parcel lockers: 45 point features; 'host' has 3 values (top: supermarket 16, metro 15, gas station 14); 'compartments' 40 to 90 (mean 60); 'utilization_pct' 35.3 to 97.3 (mean 60.95); extent -3.7492,40.3915 to -3.6578,40.4475.
  • Loading bays: 60 point features; 'enforced' has 2 values (top: True 43, False 17); 'max_minutes' 15 to 30 (mean 21.83); extent -3.7497,40.3880 to -3.6596,40.4477.
  • Roadworks: 12 line features; dated by 'start_date' from 2026-06-27 to 2026-09-03; 'type' has 3 values (top: water main 6, resurfacing 3, metro 3); 'lanes_closed' 1 to 2 (mean 1.333); total length 4.26 km; extent -3.7212,40.3883 to -3.6585,40.4349.
  • Route performance by day: Table of 1,728 rows and 6 columns without geometry; dated by 'date' from 2026-07-27 to 2026-09-19; 'on_time_pct' 59.4 to 99.7 (mean 85.51); 'avg_delay_min' 0 to 24.5 (mean 8.212); 'failed_stops' 0 to 7 (mean 1.513).
  • Vehicle fleet: Table of 60 rows and 6 columns without geometry; 'type' has 3 values (top: van 32, electric van 21, cargo bike 7); 'capacity_parcels' 35 to 160 (mean 104.4); 'range_km' 60 to 320 (mean 206.7); 'model_year' 2,017 to 2,026 (mean 2022).
  • Operations review: 1-page md document 'Operations review: August and September 2026'; language en; mentions 5 place(s): Depot Este (2), El Molino (1), 40.41805, -3.70570 (1), Depot Sur (1), La Estacion (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