Electricity utility

Substations, feeders and outages through storm season

Houston, Texas, United Statessynthetic data, real placeMaps, charts and report

The question

Where are outages concentrated, how do they change over time through storm season, and which service areas are least reliable?

A distribution utility uploads its substations, feeder lines, service areas, two years of outages, vegetation work orders, critical customers and poles, yearly feeder reliability and asset ages, and a storm season report. It wants to know where outages concentrate, how they change through storm season and which feeders are weakest.

29.7604, -95.3698data covers about 10 by 8 km

10datasets uploaded

19output layers

20maps made

29charts made

41findings

418 sStart run time

Every map and chart this run made is here. 20 map images, 29 charts and the cited report (PDF, Word, Markdown), as exported on 2026-10-22.

Findings (first few)

Evidenced: The timeline counts 2,446 dated events in Outages, Vegetation work orders, Feeder reliability by year per quarter, from Q1 2022 to Q3 2026 1 2 3 4.
Evidenced: By dataset: Outages 1,650; Vegetation work orders 480; Feeder reliability by year 316 1.
Evidenced: The trend is +19.6 events per quarter; the second half of the quarters has 2,209 against 237 in the first (+832.1%) 1.
Evidenced: 8 of the 19 quarters had no events 1.
Evidenced: The project's documents name 1 date inside this span, drawn as dotted lines; the most named is 2025-08-22 (Storm season reliability report, page 1, 1 mention) 5.

What Start ran

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

gp_calculate_densitygp_find_point_clustersgp_hot_spotsgp_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: Vegetation work ordersFig. 3

Hot spot analysis: Vegetation work ordersFig. 6

Calculate density: Vegetation work ordersFig. 9

Find point clusters: cluster hullsFig. 14

Find point clusters: Vegetation work ordersFig. 17

Repeat and near repeat classification: OutagesFig. 21

Charts

Every chart image this run exported.

Feeder lines over time (install_year)Fig. 22

Vegetation work orders over time (date)Fig. 23

Feeder reliability by year over time (year)Fig. 25

Transformer assets over time (install_year)Fig. 26

Repeat and near repeat classification: Outages over timeFig. 46

Find point clusters: Vegetation work orders over timeFig. 47

Find point clusters: Outages over timeFig. 48

Hot spot analysis: Outages over timeFig. 49

Timeline: events per quarter by datasetFig. 1

The cited report

Sample: Electricity utility, Houston: report

Project: Sample: Electricity utility, Houston
Goal: Describe the project Sample: Electricity utility, Houston: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: 370b2dd2-5561-44b3-aa6f-5fe633bbe222 (running, 11 agent run(s))
Generated: 2026-10-18T05:29:19Z, version 1
Model cost: USD 0.0000 over 0 model call(s)

Data used

Data	Kind	Rows	Time span	Summary	Source
Substations	vector, Point	14		14 point features; 'voltage_kv' 35 to 69 (mean 64.14); 'capacity_mva' 40 to 120 (mean 68.57); 'commissioned' 1,970 to 2,017 (mean 1994); named by 'name' (e.g. Juniper Rise Substation, Kingsmead Substation, Larchfield Substation); extent -95.4070,29.7335 to -95.3261,29.7908. Point locations of Substations.	98
Feeder lines	vector, LineString	79		79 line features; 'construction' has 2 values (top: overhead 46, underground 33); 'conductor' has 4 values (top: 1/0 ACSR 24, 477 AAC 21, 750 Cu UG 19); 'install_year' 1,964 to 2,022 (mean 1990); 'voltage_kv' 12.47 to 12.47 (mean 12.47); 'length_m' 540 to 3,063 (mean 1690); total length 133.5 km; extent -95.4215,29.7253 to -95.3181,29.7966. Lines (Feeder lines) such as routes or networks.	99
Service areas	vector, Polygon	14		14 polygon (area) features; 'customers' 4,420 to 13,419 (mean 7965); 'peak_load_mw' 17.1 to 50.9 (mean 36.91); named by 'name' (e.g. Juniper Rise Substation area, Kingsmead Substation area, Larchfield Substation area); total area 79.96 km2; extent -95.4223,29.7234 to -95.3173,29.7974. Areas (Service areas) with customers to compare and map.	100
Outages	vector, Point	1,650	2024-10-01 to 2026-09-30	1,650 point features; dated by 'started_at' from 2024-10-01 to 2026-09-30; 'cause' has 6 values (top: vegetation 644, equipment 427, weather 343); 'duration_min' 10 to 2,740 (mean 195); 'customers_affected' 6 to 3,173 (mean 234.9); extent -95.4212,29.7255 to -95.3187,29.7961. Dated point events by cause: where and when Outages happen.	2
Vegetation work orders	vector, Point	480	2024-10-04 to 2026-09-21	480 point features; dated by 'date' from 2024-10-04 to 2026-09-21; 'trim_type' has 3 values (top: hazard tree 161, cycle trim 160, hot spot 159); 'spans' 1 to 12 (mean 6.692); 'cost_usd' 566 to 12,478 (mean 2667); extent -95.4210,29.7258 to -95.3186,29.7961. Dated point events by trim_type: where and when Vegetation work orders happen.	3
Critical customers	vector, Point	60		60 point features; 'type' has 5 values (top: water plant 20, emergency shelter 11, fire station 10); 'backup_generator' has 2 values (top: False 39, True 21); 'priority' 1 to 3 (mean 1.683); extent -95.4198,29.7261 to -95.3218,29.7961. Point locations of Critical customers by type.	101
Poles	vector, Point	450		450 point features; 'material' has 3 values (top: wood 207, concrete 131, steel 112); 'inspection_grade' has 4 values (top: B 187, D 95, A 87); 'install_year' 1,967 to 2,024 (mean 2001); extent -95.4214,29.7313 to -95.3201,29.7964. Point locations of Poles by material.	102
Feeder reliability by year	table	316	2022-01-01 to 2025-01-01	Table of 316 rows and 6 columns without geometry; dated by 'year' from 2022-01-01 to 2025-01-01; 'saidi_min' 35.2 to 486.9 (mean 121.6); 'saifi' 0.45 to 2.49 (mean 1.177); 'caidi_min' 29.3 to 391 (mean 106.5). A table of Feeder reliability by year without locations.	4
Transformer assets	table	300		Table of 300 rows and 6 columns without geometry; 'mount' has 2 values (top: pole 164, pad 136); 'kva' 25 to 167 (mean 83.32); 'install_year' 1,970 to 2,024 (mean 1997); 'condition_score' 1 to 10 (mean 5.301). A table of Transformer assets without locations.	103
Storm season reliability report	document			1-page pdf document 'Storm season reliability report'; language en; mentions 3 place(s): Juniper Rise Substation (2), Kingsmead Substation (1), Larchfield Substation (1). A document about Juniper Rise Substation, Kingsmead Substation, Larchfield Substation.	104
Sample: Electricity utility, Houston	record				105
Emerging hot spots: Outages	layer, Polygon	100			106
Emerging hot spots: Vegetation work orders	layer, Polygon	89			107
Hot spot analysis: Poles	layer, Polygon	79			108
Hot spot analysis: Outages	layer, Point	1,650			109
Hot spot analysis: Vegetation work orders	layer, Polygon	86			110
Calculate density: Poles	layer, Polygon	344			111
Calculate density: Outages	layer, Polygon	1,588			112
Calculate density: Vegetation work orders	layer, Polygon	350			113
Summarize within: Service areas	layer, Polygon	14			114
Summarize within: Service areas	layer, Polygon	14			115
Summarize within: Service areas	layer, Polygon	14			116
Find point clusters: Poles	layer, Point	450			117
Find point clusters: cluster hulls	layer, Polygon	12			118
Find point clusters: Outages	layer, Point	1,650			119
Find point clusters: cluster hulls	layer, Polygon	12			120
Find point clusters: Vegetation work orders	layer, Point	480			121
Find point clusters: cluster hulls	layer, Polygon	9			122
Find outliers: Service areas	layer, Polygon	14			123
Repeat and near repeat classification: Outages	layer, Point	1,650			124

Timeline

The timeline counts 2,446 dated events in Outages, Vegetation work orders, Feeder reliability by year per quarter, from Q1 2022 to Q3 2026 1 2 3 4. By dataset: Outages 1,650; Vegetation work orders 480; Feeder reliability by year 316 1. The trend is +19.6 events per quarter; the second half of the quarters has 2,209 against 237 in the first (+832.1%) 1. 8 of the 19 quarters had no events 1. The project's documents name 1 date inside this span, drawn as dotted lines; the most named is 2025-08-22 (Storm season reliability report, page 1, 1 mention) 5.

Busiest quarters

Q3 2025: 425 events 1
Q3 2026: 310 events 1
Q1 2025: 290 events 1

Quietest quarters with events

Q1 2022: 79 events 1
Q1 2023: 79 events 1
Q1 2024: 79 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. Outages carry dates in 'started_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month 7.

What it found. The gp_space_time_hot_spots tool utilized the Outages input 9 and generated a result with 100 features 8.

Result	Value
result, count	100
result, elapsed ms	17
result, resolution	8
result, features used	1,650
result, time neighbors	0
billing, cost	0.1825
billing, list price	0.1825
billing, upstream cost	0

Findings

Evidenced: Space time hot spots on Outages: Emerging hot spots: 1 layer saved: Emerging hot spots: Outages (100 features) 8 9.
Evidenced: It reported result, count 100; result, elapsed ms 17; result, resolution 8; result, features used 1,650; result, time neighbors 0; billing, cost 0.1825 8.

Tool gp_space_time_hot_spots; parameters {"agg": "sum", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "interval": "month", "bin_shape": "h3", "resolution": 8, "time_field": "started_at", "value_field": "customers_affected"}

Space time hot spots

Why it was run on this data. Vegetation work orders carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per month 10.

What it found. Space time hot spots on Vegetation work orders: Emerging hot spots: 1 layer saved: Emerging hot spots: Vegetation work orders (89 features) 11 12. It reported result, count 89; result, elapsed ms 12; result, resolution 8; result, features used 480; result, time neighbors 0; billing, cost 0.124 11.

Result	Value
result, count	89
result, elapsed ms	12
result, resolution	8
result, features used	480
result, time neighbors	0
billing, cost	0.124
billing, list price	0.124
billing, upstream cost	0

Findings

Evidenced: Space time hot spots on Vegetation work orders: Emerging hot spots: 1 layer saved: Emerging hot spots: Vegetation work orders (89 features) 11 12.
Evidenced: It reported result, count 89; result, elapsed ms 12; result, resolution 8; result, features used 480; result, time neighbors 0; billing, cost 0.124 11.

Tool gp_space_time_hot_spots; parameters {"project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Vegetation work orders (d3eba75a)"}, "interval": "month", "bin_shape": "h3", "resolution": 8, "time_field": "date"}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 13. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 13.

Why it was run on this data. 450 points: Getis-Ord Gi* tests whether the concentrations in Poles are statistically significant 14.

What it found. Hot spots on Poles: Hot spot analysis: 1 layer saved: Hot spot analysis: Poles (79 features) 15 16. It reported result, bins 79; result, count 79; result, elapsed ms 5; result, cell size m 1,000; result, incidents used 450; result, distance band m 1,000 15.

Result	Value
result, bins	79
result, count	79
result, elapsed ms	5
result, cell size m	1,000
result, incidents used	450
result, distance band m	1,000
billing, cost	0.059
billing, list price	0.059
billing, upstream cost	0

Findings

Evidenced: Hot spots on Poles: Hot spot analysis: 1 layer saved: Hot spot analysis: Poles (79 features) 15 16.
Evidenced: It reported result, bins 79; result, count 79; result, elapsed ms 5; result, cell size m 1,000; result, incidents used 450; result, distance band m 1,000 15.

Tool gp_hot_spots; parameters {"project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Poles (cb7cbff1)"}, "aggregation": "hexagon", "cell_size_m": 1000.0, "distance_band_m": 1000.0}

Hot spots

Why it was run on this data. 1650 points: Getis-Ord Gi* tests whether the concentrations in Outages are statistically significant 17.

What it found. The hot spot analysis used the Outages layer as the input data 9. The analysis generated a total of 1,650 features, with the process completing in 27 ms 18.

Result	Value
result, count	1,650
result, elapsed ms	27
result, excluded null	0
result, distance band m	500
billing, cost	0.083
billing, list price	0.083
billing, upstream cost	0

Findings

Evidenced: Hot spots on Outages: Hot spot analysis: 1 layer saved: Hot spot analysis: Outages (1650 features) 9 18.
Evidenced: It reported result, count 1,650; result, elapsed ms 27; result, excluded null 0; result, distance band m 500; billing, cost 0.083; billing, list price 0.083 18.

Tool gp_hot_spots; parameters {"field": "customers_affected", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

Hot spots

Why it was run on this data. 480 points: Getis-Ord Gi* tests whether the concentrations in Vegetation work orders are statistically significant 19.

What it found. Hot spots on Vegetation work orders: Hot spot analysis: 1 layer saved: Hot spot analysis: Vegetation work orders (86 features) 12 20. It reported result, bins 86; result, count 86; result, elapsed ms 6; result, cell size m 1,000; result, incidents used 480; result, distance band m 1,000 20.

Result	Value
result, bins	86
result, count	86
result, elapsed ms	6
result, cell size m	1,000
result, incidents used	480
result, distance band m	1,000
billing, cost	0.0596
billing, list price	0.0596
billing, upstream cost	0

Findings

Evidenced: Hot spots on Vegetation work orders: Hot spot analysis: 1 layer saved: Hot spot analysis: Vegetation work orders (86 features) 12 20.
Evidenced: It reported result, bins 86; result, count 86; result, elapsed ms 6; result, cell size m 1,000; result, incidents used 480; result, distance band m 1,000 20.

Tool gp_hot_spots; parameters {"project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Vegetation work orders (d3eba75a)"}, "aggregation": "hexagon", "cell_size_m": 1000.0, "distance_band_m": 1000.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 21. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 21.

Why it was run on this data. 450 points in Poles: a density surface shows where they concentrate 22.

What it found. Calculate density on Poles: Calculate density: 1 layer saved: Calculate density: Poles (344 features) 16 23. It reported result, count 344; result, elapsed ms 10; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 24.11 23.

Result	Value
result, count	344
result, elapsed ms	10
result, bandwidth m	1,000
result, cell size m	500
result, excluded null	0
result, max density per km2	24.11
billing, cost	0.059
billing, list price	0.059
billing, upstream cost	0

Findings

Evidenced: Calculate density on Poles: Calculate density: 1 layer saved: Calculate density: Poles (344 features) 16 23.
Evidenced: It reported result, count 344; result, elapsed ms 10; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 24.11 23.

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

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Poles (cb7cbff1)"}, "bandwidth_m": 1000.0, "cell_size_m": 500.0}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 21. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 21.

Why it was run on this data. 1650 points in Outages: a density surface shows where they concentrate 24.

What it found. Calculate density on Outages: Calculate density: 1 layer saved: Calculate density: Outages (1588 features) 9 25. It reported result, count 1,588; result, elapsed ms 45; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 4.538e+04 25.

Result	Value
result, count	1,588
result, elapsed ms	45
result, bandwidth m	500
result, cell size m	200
result, excluded null	0
result, max density per km2	4.538e+04
billing, cost	0.083
billing, list price	0.083
billing, upstream cost	0

Findings

Evidenced: Calculate density on Outages: Calculate density: 1 layer saved: Calculate density: Outages (1588 features) 9 25.
Evidenced: It reported result, count 1,588; result, elapsed ms 45; result, bandwidth m 500; result, cell size m 200; result, excluded null 0; result, max density per km2 4.538e+04 25.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "bandwidth_m": 500.0, "cell_size_m": 200.0, "weight_field": "customers_affected"}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 21. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 21.

Why it was run on this data. 480 points in Vegetation work orders: a density surface shows where they concentrate 26.

What it found. The maximum density calculated was 24.16 per km2 27.

Result	Value
result, count	350
result, elapsed ms	10
result, bandwidth m	1,000
result, cell size m	500
result, excluded null	0
result, max density per km2	24.16
billing, cost	0.0596
billing, list price	0.0596
billing, upstream cost	0

Findings

Evidenced: Calculate density on Vegetation work orders: Calculate density: 1 layer saved: Calculate density: Vegetation work orders (350 features) 12 27.
Evidenced: It reported result, count 350; result, elapsed ms 10; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 24.16 27.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Vegetation work orders (d3eba75a)"}, "bandwidth_m": 1000.0, "cell_size_m": 500.0}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 28. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 28.

Why it was run on this data. Count Poles inside each feature of Service areas by material; the counts map as a choropleth (natural breaks, sequential colors) 29.

What it found. Summarize within on Poles, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 16 30 31. It reported result, count 14; result, elapsed ms 1; billing, cost 0.0193; billing, list price 0.0193; billing, upstream cost 0 30.

Result	Value
result, count	14
result, elapsed ms	1
billing, cost	0.0193
billing, list price	0.0193
billing, upstream cost	0

Findings

Evidenced: Summarize within on Poles, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 16 30 31.
Evidenced: It reported result, count 14; result, elapsed ms 1; billing, cost 0.0193; billing, list price 0.0193; billing, upstream cost 0 30.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "install_year"}], "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Poles (cb7cbff1)"}, "group_by": "material", "polygons": {"layer": "Service areas (af824cfb)"}}

Summarize within

Why it was run on this data. Count Poles inside each feature of Service areas by material; the counts map as a choropleth (natural breaks, sequential colors) 29.

What it found. Summarize within on Outages, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 9 31 32. It reported result, count 14; result, elapsed ms 3; billing, cost 0.0433; billing, list price 0.0433; billing, upstream cost 0 32.

Result	Value
result, count	14
result, elapsed ms	3
billing, cost	0.0433
billing, list price	0.0433
billing, upstream cost	0

Findings

Evidenced: Summarize within on Outages, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 9 31 32.
Evidenced: It reported result, count 14; result, elapsed ms 3; billing, cost 0.0433; billing, list price 0.0433; billing, upstream cost 0 32.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "customers_affected"}], "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "group_by": "cause", "polygons": {"layer": "Service areas (af824cfb)"}}

Summarize within

Why it was run on this data. Count Poles inside each feature of Service areas by material; the counts map as a choropleth (natural breaks, sequential colors) 29.

What it found. Summarize within on Vegetation work orders, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 12 31 33. It reported result, count 14; result, elapsed ms 1; billing, cost 0.0199; billing, list price 0.0199; billing, upstream cost 0 33.

Result	Value
result, count	14
result, elapsed ms	1
billing, cost	0.0199
billing, list price	0.0199
billing, upstream cost	0

Findings

Evidenced: Summarize within on Vegetation work orders, Service areas: Summarize within: 1 layer saved: Summarize within: Service areas (14 features) 12 31 33.
Evidenced: It reported result, count 14; result, elapsed ms 1; billing, cost 0.0199; billing, list price 0.0199; billing, upstream cost 0 33.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "spans"}], "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Vegetation work orders (d3eba75a)"}, "group_by": "trim_type", "polygons": {"layer": "Service areas (af824cfb)"}}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 34. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 34.

Why it was run on this data. DBSCAN finds dense groups of Poles and separates noise 35.

What it found. Find point clusters on Poles: Find point clusters: 2 layers saved: Find point clusters: Poles (450 features); Find point clusters: cluster hulls (12 features) 16 36. It reported result, count 450; result, noise 149; result, distance m 500; result, elapsed ms 9; result, min points 11; billing, cost 0.059 36.

Result	Value
result, count	450
result, noise	149
result, distance m	500
result, elapsed ms	9
result, min points	11
billing, cost	0.059
billing, list price	0.059
billing, upstream cost	0

Findings

Evidenced: Find point clusters on Poles: Find point clusters: 2 layers saved: Find point clusters: Poles (450 features); Find point clusters: cluster hulls (12 features) 16 36.
Evidenced: It reported result, count 450; result, noise 149; result, distance m 500; result, elapsed ms 9; result, min points 11; billing, cost 0.059 36.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Poles (cb7cbff1)"}, "distance_m": 500.0, "min_points": 11}

Find point clusters

Why it was run on this data. DBSCAN finds dense groups of Outages and separates noise 37.

What it found. Find point clusters on Outages: Find point clusters: 2 layers saved: Find point clusters: Outages (1650 features); Find point clusters: cluster hulls (12 features) 9 38. It reported result, count 1,650; result, noise 985; result, distance m 200; result, elapsed ms 22; result, min points 20; billing, cost 0.083 38.

Result	Value
result, count	1,650
result, noise	985
result, distance m	200
result, elapsed ms	22
result, min points	20
billing, cost	0.083
billing, list price	0.083
billing, upstream cost	0

Findings

Evidenced: Find point clusters on Outages: Find point clusters: 2 layers saved: Find point clusters: Outages (1650 features); Find point clusters: cluster hulls (12 features) 9 38.
Evidenced: It reported result, count 1,650; result, noise 985; result, distance m 200; result, elapsed ms 22; result, min points 20; billing, cost 0.083 38.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "distance_m": 200.0, "min_points": 20}

Find point clusters

Why it was run on this data. DBSCAN finds dense groups of Vegetation work orders and separates noise 39.

What it found. Find point clusters on Vegetation work orders: Find point clusters: 2 layers saved: Find point clusters: Vegetation work orders (480 features); Find point clusters: cluster hulls (9 features) 12 40. It reported result, count 480; result, noise 157; result, distance m 500; result, elapsed ms 9; result, min points 12; billing, cost 0.0596 40.

Result	Value
result, count	480
result, noise	157
result, distance m	500
result, elapsed ms	9
result, min points	12
billing, cost	0.0596
billing, list price	0.0596
billing, upstream cost	0

Findings

Evidenced: Find point clusters on Vegetation work orders: Find point clusters: 2 layers saved: Find point clusters: Vegetation work orders (480 features); Find point clusters: cluster hulls (9 features) 12 40.
Evidenced: It reported result, count 480; result, noise 157; result, distance m 500; result, elapsed ms 9; result, min points 12; billing, cost 0.0596 40.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Vegetation work orders (d3eba75a)"}, "distance_m": 500.0, "min_points": 12}

Outliers

What this analysis is. Find outliers: Anselin local Moran’s I: HH, LL clusters and HL, LH outliers 41. In ArcGIS it is Find Outliers or Cluster and Outlier Analysis (Anselin Local Moran’s I) 41.

Why it was run on this data. Local Moran's I maps clusters and outliers of 'customers' 42.

What it found. Outliers on Service areas: Find outliers: 1 layer saved: Find outliers: Service areas (14 features) 31 43. It reported result, count 14; result, elapsed ms 2; result, permutations 199; result, excluded null 0; result, distance band m 2,472; billing, cost 0.05042 43.

Result	Value
result, count	14
result, elapsed ms	2
result, permutations	199
result, excluded null	0
result, distance band m	2,472
billing, cost	0.05042
billing, list price	0.05042
billing, upstream cost	0

Findings

Evidenced: Outliers on Service areas: Find outliers: 1 layer saved: Find outliers: Service areas (14 features) 31 43.
Evidenced: It reported result, count 14; result, elapsed ms 2; result, permutations 199; result, excluded null 0; result, distance band m 2,472; billing, cost 0.05042 43.

Tool gp_outliers; parameters {"field": "customers", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Service areas (af824cfb)"}, "aggregation": "hexagon"}

Spatial autocorrelation

What this analysis is. Spatial autocorrelation: Global Moran’s I: is the pattern clustered, dispersed or random 44. In ArcGIS it is Spatial Autocorrelation (Global Moran’s I) 44.

Why it was run on this data. Global Moran's I says whether similar values of 'customers' sit next to each other 45.

What it found. The spatial autocorrelation tool was run using Service areas 31, yielding a Moran's I of 0.02059 46. Analysis of this result showed a p value of 0.6627 46 and a z score of 0.4361 46. Furthermore, the expected I value for the analysis was calculated to be -0.07692 46.

Result	Value
result, n	14
result, p value	0.6627
result, z score	0.4361
result, morans i	0.02059
result, variance	0.04999
result, elapsed ms	1
result, expected i	-0.07692
result, excluded null	0
result, distance band m	2,472
result, p value normality	0.671
result, z score normality	0.4248
result, variance normality	0.05269
billing, cost	0.02
billing, list price	0.02
billing, upstream cost	0

Findings

Evidenced: Spatial autocorrelation on Service areas: Spatial autocorrelation: done; no map output 31 46.
Evidenced: It reported result, n 14; result, p value 0.6627; result, z score 0.4361; result, morans i 0.02059; result, variance 0.04999; result, elapsed ms 1 46.

Tool gp_spatial_autocorrelation; parameters {"field": "customers", "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Service areas (af824cfb)"}}

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 47. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 47.

Why it was run on this data. Near repeat analysis tests whether Outages close in space also follow each other within 30 days 48.

What it found. Near repeat on Outages: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Outages (1650 features) 9 49. It reported result, days 30; result, count 1,650; result, chains 266; result, distance m 200; result, elapsed ms 42; result, pairs linked 1,171 49.

Result	Value
result, days	30
result, count	1,650
result, chains	266
result, distance m	200
result, elapsed ms	42
result, pairs linked	1,171
billing, cost	0.0995
billing, list price	0.0995
billing, upstream cost	0

Findings

Evidenced: Near repeat on Outages: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Outages (1650 features) 9 49.
Evidenced: It reported result, days 30; result, count 1,650; result, chains 266; result, distance m 200; result, elapsed ms 42; result, pairs linked 1,171 49.

Tool gp_near_repeat; parameters {"days": 30, "project": "99e378b8-9e64-42f5-8930-fca7c2a73f57", "features": {"layer": "Outages (74249532)"}, "distance_m": 200.0, "time_field": "started_at"}

Maps and charts

The run also made 20 map image(s) 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 and 28 chart(s) 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97.

What the map shows. The map visualizes a hot spot analysis for vegetation work orders, classifying areas as having a pattern or having none. The majority of 51

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

Changes since the last run

This is the first report of this project.

Sources

1Rendering: Chart: Timeline: events per quarter by dataset. 57 rows id 4819230f-295d-49a7-99bf-6b7163fc6b06
2Dataset: Outages. vector, 1650 rows id 39df98b3-8a4f-4af6-838d-170705e0bb48
3Dataset: Vegetation work orders. vector, 480 rows id 3aea1163-22b4-4a72-88d7-bcae1ecdad23
4Dataset: Feeder reliability by year. table, 316 rows id 887eeeea-0f49-451b-93f4-5d68b309bfad
5Document page: Storm season reliability report, page 1. 22 August 2025 id 32e35a86-4090-49ec-8ae9-87f7b6be0d6b:1
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
7Plan: Space time hot spots of Outages (the Start plan's candidate c_de6ee55db604). Outages carry dates in 'started_at': emerging hot spot analysis finds new, intensifying and fading hot spots per month. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_de6ee55db604
8Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Outages (100 features). id 7e39f2a8-86e1-4856-b7a7-61e069df845f:0
9Layer: Outages. 1,650 features id 74249532-c045-44c9-a616-0fafb7c162a0
10Plan: Space time hot spots of Vegetation work orders (the Start plan's candidate c_90f82b668b6e). Vegetation work orders carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per month. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_90f82b668b6e
11Tool result: gp_space_time_hot_spots, step 1. Emerging hot spots: 1 layer saved: Emerging hot spots: Vegetation work orders (89 features). id 7e39f2a8-86e1-4856-b7a7-61e069df845f:1
12Layer: Vegetation work orders. 480 features id d3eba75a-4345-496b-b3c1-cfad466d3d73
13Catalog: 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
14Plan: Hot spots of Poles (the Start plan's candidate c_8543237d7e01). 450 points: Getis-Ord Gi* tests whether the concentrations in Poles are statistically significant. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_8543237d7e01
15Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Poles (79 features). id dd7f4187-7acb-4060-a294-8f874d038e7b:0
16Layer: Poles. 450 features id cb7cbff1-729f-45fd-bbbc-a31c0a2b6043
17Plan: Hot spots of Outages (the Start plan's candidate c_2edeaea7ec43). 1650 points: Getis-Ord Gi* tests whether the concentrations in Outages are statistically significant. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_2edeaea7ec43
18Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Outages (1650 features). id dd7f4187-7acb-4060-a294-8f874d038e7b:1
19Plan: Hot spots of Vegetation work orders (the Start plan's candidate c_63c929cc68f4). 480 points: Getis-Ord Gi* tests whether the concentrations in Vegetation work orders are statistically significant. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_63c929cc68f4
20Tool result: gp_hot_spots, step 2. Hot spot analysis: 1 layer saved: Hot spot analysis: Vegetation work orders (86 features). id dd7f4187-7acb-4060-a294-8f874d038e7b:2
21Catalog: 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
22Plan: Kernel density of Poles (the Start plan's candidate c_39401f3daf3b). 450 points in Poles: a density surface shows where they concentrate. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_39401f3daf3b
23Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Poles (344 features). id cddccd9e-fca2-4947-ac52-4a032f65ccd9:0
24Plan: Kernel density of Outages (the Start plan's candidate c_5f4ad3832af3). 1650 points in Outages: a density surface shows where they concentrate. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_5f4ad3832af3
25Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Outages (1588 features). id cddccd9e-fca2-4947-ac52-4a032f65ccd9:1
26Plan: Kernel density of Vegetation work orders (the Start plan's candidate c_fcff6300c7b4). 480 points in Vegetation work orders: a density surface shows where they concentrate. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_fcff6300c7b4
27Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Vegetation work orders (350 features). id cddccd9e-fca2-4947-ac52-4a032f65ccd9:2
28Catalog: 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
29Plan: Poles per feature of Service areas (the Start plan's candidate c_0abb031a5451). Count Poles inside each feature of Service areas by material; the counts map as a choropleth (natural breaks, sequential colors). id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_0abb031a5451
30Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Service areas (14 features). id 7abde2bd-08d7-47d0-ac4b-96744e82d444:0
31Layer: Service areas. 14 features id af824cfb-eb9c-4c01-a5c2-df454a844893
32Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Service areas (14 features). id 7abde2bd-08d7-47d0-ac4b-96744e82d444:1
33Tool result: gp_summarize_within, step 2. Summarize within: 1 layer saved: Summarize within: Service areas (14 features). id 7abde2bd-08d7-47d0-ac4b-96744e82d444:2
34Catalog: 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
35Plan: Cluster points of Poles (the Start plan's candidate c_49349f7319f8). DBSCAN finds dense groups of Poles and separates noise. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_49349f7319f8
36Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Poles (450 features); Find point clusters: cluster hulls (12 features). id a1a5ebf4-55fc-498c-bc42-232278d7fd50:0
37Plan: Cluster points of Outages (the Start plan's candidate c_9d082d10c718). DBSCAN finds dense groups of Outages and separates noise. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_9d082d10c718
38Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Outages (1650 features); Find point clusters: cluster hulls (12 features). id a1a5ebf4-55fc-498c-bc42-232278d7fd50:1
39Plan: Cluster points of Vegetation work orders (the Start plan's candidate c_ec3997c2afdb). DBSCAN finds dense groups of Vegetation work orders and separates noise. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_ec3997c2afdb
40Tool result: gp_find_point_clusters, step 2. Find point clusters: 2 layers saved: Find point clusters: Vegetation work orders (480 features); Find point clusters: cluster hulls (9 features). id a1a5ebf4-55fc-498c-bc42-232278d7fd50:2
41Catalog: 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
42Plan: Local morans i of Service areas (the Start plan's candidate c_14f3a517187f). Local Moran's I maps clusters and outliers of 'customers'. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_14f3a517187f
43Tool result: gp_outliers, step 0. Find outliers: 1 layer saved: Find outliers: Service areas (14 features). id 0eeb802a-0001-4240-800b-19f28e01e992:0
44Catalog: 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
45Plan: Global morans i of Service areas (the Start plan's candidate c_ce02f9951480). Global Moran's I says whether similar values of 'customers' sit next to each other. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_ce02f9951480
46Tool result: gp_spatial_autocorrelation, step 1. Spatial autocorrelation: done; no map output. id 0eeb802a-0001-4240-800b-19f28e01e992:1
47Catalog: 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
48Plan: Near repeat of Outages (the Start plan's candidate c_c8acd413fa13). Near repeat analysis tests whether Outages close in space also follow each other within 30 days. id a5b6c9d4-e26f-4c51-adac-5b8547525805:c_c8acd413fa13
49Tool result: gp_near_repeat, step 0. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Outages (1650 features). id 7d19f92c-f4e9-48f3-93b0-dae3bf87b4ee:0
50Rendering: Map: Emerging hot spots: Outages id 85c7e950-dc12-47d7-9698-4f3e33d102c5
51Rendering: Map: Emerging hot spots: Vegetation work orders id d57a1eed-7833-4fa0-ba3b-1d34a14adf8d
52Rendering: Map: Hot spot analysis: Poles id 9c171d35-6e8a-404e-b179-3a277cac6680
53Rendering: Map: Hot spot analysis: Outages id 8b2915ad-3dc8-4c93-8998-6f8c60edde26
54Rendering: Map: Hot spot analysis: Vegetation work orders id 1951c285-f42c-4fe7-a12b-c61e0f8e89b1
55Rendering: Map: Calculate density: Poles id 77494a3a-e8bf-4ba9-8c9f-bbca3ed39699
56Rendering: Map: Calculate density: Outages id 2539e062-6c7a-48d8-915c-ceb004cf1c30
57Rendering: Map: Calculate density: Vegetation work orders id 90718fcc-1e9e-4189-b307-dd23cdc248d7
58Rendering: Map: Summarize within: Service areas id aaf8c40e-6ba8-477d-9349-b080f65d9f6f
59Rendering: Map: Summarize within: Service areas id 205c58ca-663e-465b-b5da-e58df3a3a282
60Rendering: Map: Summarize within: Service areas id baad37d3-dcec-4a96-add7-fa1a886f6434
61Rendering: Map: Find point clusters: Poles id 244f950b-322a-4f47-9af0-a30ad8fb8bad
62Rendering: Map: Find point clusters: cluster hulls id d83dd986-dc80-4bfd-886c-ff9fb5202ae7
63Rendering: Map: Find point clusters: Outages id a84598e8-6ff6-4f96-960b-18389e35387e
64Rendering: Map: Find point clusters: cluster hulls id f19bdfd5-1091-44cd-baae-dbac01077b12
65Rendering: Map: Find point clusters: Vegetation work orders id f99266a6-079b-44d5-852d-676355c69c8f
66Rendering: Map: Find point clusters: cluster hulls id d61dc500-d849-4c67-8699-7c2b54d04ac2
67Rendering: Map: Service areas by customers id 053475d3-62c9-4ca9-9150-1780c6628edd
68Rendering: Map: Find outliers: Service areas id 40748e31-9982-4c38-83df-2e829b1cd052
69Rendering: Map: Repeat and near repeat classification: Outages id 2dd79f43-b1db-44d1-b050-cb0ad8062f39
70Rendering: Chart: Feeder lines over time (install_year). 8 rows id a6ddfbd0-4d56-4fd4-95e4-dccff9b3fe14
71Rendering: Chart: Vegetation work orders over time (date). 72 rows id fe31e6f1-8de6-4739-b859-5ca5639a090e
72Rendering: Chart: Poles over time (install_year). 10 rows id 1a338811-8c8f-4624-affb-5f6f2a386c21
73Rendering: Chart: Feeder reliability by year over time (year). 37 rows id 81342282-782d-4f77-a6ab-c97a78fe8806
74Rendering: Chart: Transformer assets over time (install_year). 10 rows id 8b1d0ff4-f186-4254-b010-9684ed1844c3
75Rendering: Chart: Emerging hot spots: Outages. 8 rows id d57c5b66-d8b2-462a-85ae-76e9926eb3b1
76Rendering: Chart: Emerging hot spots: Vegetation work orders. 8 rows id d126a2b6-196d-4f93-93d5-5ce7f5d9f891
77Rendering: Chart: Hot spot analysis: Poles. 9 rows id b3100e77-5cbe-4a62-b253-290a5d536bb5
78Rendering: Chart: Hot spot analysis: Outages. 18 rows id cec85df8-5d0a-4af6-ba88-696eca4ce437
79Rendering: Chart: Hot spot analysis: Vegetation work orders. 10 rows id 1a614d2a-305a-4dfc-a43d-d303a95fb7b7
80Rendering: Chart: Calculate density: Poles. 10 rows id 2ea4b4d0-a10d-4113-b8f2-fb2372244db4
81Rendering: Chart: Calculate density: Outages. 12 rows id a201fc49-4d81-4320-8155-2f3eb69bd7da
82Rendering: Chart: Calculate density: Vegetation work orders. 10 rows id 1a66e57b-240e-4644-ab5f-f5d3fceeebe6
83Rendering: Chart: Summarize within: Service areas. 5 rows id ac78768b-6dc9-4d58-b972-2cf6dec976ea
84Rendering: Chart: Summarize within: Service areas. 5 rows id 0ee3a30f-bde2-4bb4-9019-791dd822ac96
85Rendering: Chart: Summarize within: Service areas. 5 rows id 1cd10d51-b513-49a7-b54f-6694f693c6a5
86Rendering: Chart: Find point clusters: Poles. 13 rows id 4d716dc4-27b8-4ca0-8c8b-b4246f0cf77f
87Rendering: Chart: Find point clusters: cluster hulls. 12 rows id d68e61ee-9527-48bd-93b1-e6d214930ddb
88Rendering: Chart: Find point clusters: Outages. 13 rows id 658b2721-1008-4707-8089-5fc9e67e755d
89Rendering: Chart: Find point clusters: cluster hulls. 12 rows id 3c8e6159-5e84-4f48-a0a3-71bc429bc627
90Rendering: Chart: Find point clusters: Vegetation work orders. 10 rows id 77d5d6a0-286e-48b2-83b6-f1379a2b6e25
91Rendering: Chart: Find point clusters: cluster hulls. 9 rows id ebdaf978-c973-42d9-b815-55c700b8af71
92Rendering: Chart: Find outliers: Service areas. 14 rows id c9960c12-89e8-43ab-83aa-898a65c8d7e1
93Rendering: Chart: Repeat and near repeat classification: Outages. 144 rows id 59506424-cd43-4c06-82b9-310f05aa3ef1
94Rendering: Chart: Repeat and near repeat classification: Outages over time. 144 rows id e21c9039-2700-4091-9c70-031cd03ca122
95Rendering: Chart: Find point clusters: Vegetation work orders over time. 144 rows id 17f450e3-64de-4bba-a8b9-1f01286c5da9
96Rendering: Chart: Find point clusters: Outages over time. 144 rows id 7c632546-38e2-4ef7-a37f-a50b9e7200a4
97Rendering: Chart: Hot spot analysis: Outages over time. 144 rows id 89489499-b4a2-4e58-b157-ba3c649aecd2
98Dataset: Substations. vector, 14 rows id f259f42c-1706-41ba-a78a-1361f3914e06
99Dataset: Feeder lines. vector, 79 rows id ecfb48ff-6d02-430b-9ebb-f111ab17967c
100Dataset: Service areas. vector, 14 rows id f3d1d854-cd9c-48c7-8f7a-a2e854a8ceb6
101Dataset: Critical customers. vector, 60 rows id e19506c9-69b8-4925-bb88-2c0235b75a70
102Dataset: Poles. vector, 450 rows id 3786e568-d7a4-4d47-b594-453c79329fb0
103Dataset: Transformer assets. table, 300 rows id 2e9131d9-123c-4a43-986c-82f9c9221692
104Dataset: Storm season reliability report. document, ? rows id b535c355-1229-4d0f-9126-2fe58457bcec
105Record: Sample: Electricity utility, Houston id 99e378b8-9e64-42f5-8930-fca7c2a73f57
106Layer: Emerging hot spots: Outages. 100 features id c053bfd3-6311-4cf3-a811-669d5782bdb3
107Layer: Emerging hot spots: Vegetation work orders. 89 features id 1cbdbfca-5f5d-4277-87ce-4d482b63ec8e
108Layer: Hot spot analysis: Poles. 79 features id ddab229d-5eab-4322-8c2b-76442371347b
109Layer: Hot spot analysis: Outages. 1,650 features id 152d5bad-10c2-42e3-98ef-f598b1d425bd
110Layer: Hot spot analysis: Vegetation work orders. 86 features id aa682980-c78f-45bf-a39c-e6c25235ecf0
111Layer: Calculate density: Poles. 344 features id 092a4943-ffb6-462a-afdb-cfca08b63795
112Layer: Calculate density: Outages. 1,588 features id c9cfc32c-1601-4e5a-9160-a0a02112b586
113Layer: Calculate density: Vegetation work orders. 350 features id c3b70581-64dc-4b78-82c2-af051c400b18
114Layer: Summarize within: Service areas. 14 features id 080e40ba-f7ec-49b3-856b-2145df7839bf
115Layer: Summarize within: Service areas. 14 features id 9f88918e-62a5-4499-b99b-d19d559ee0a7
116Layer: Summarize within: Service areas. 14 features id a4302e84-efd6-417d-9791-39532ad03ea3
117Layer: Find point clusters: Poles. 450 features id d8bd47c0-3090-477e-9f4e-99798bfd2778
118Layer: Find point clusters: cluster hulls. 12 features id 99b9ab3e-1fc2-4630-afb7-f5a5db637828
119Layer: Find point clusters: Outages. 1,650 features id 402ad5f6-a892-490a-a647-e6e94f591e27
120Layer: Find point clusters: cluster hulls. 12 features id 56caa497-390e-42c8-9f4d-6813ec441e8c
121Layer: Find point clusters: Vegetation work orders. 480 features id 9ab95317-7431-4636-b94c-06bb41924b25
122Layer: Find point clusters: cluster hulls. 9 features id 134428d0-3eb6-4afb-b65a-2f63ca197338
123Layer: Find outliers: Service areas. 14 features id 31a2a6ae-e1c2-4384-bdb2-7d30ebff9f80
124Layer: Repeat and near repeat classification: Outages. 1,650 features id 9fd9267d-3aae-4cac-90a0-3de6c177fa4f

Appendix: the data behind the chartsShow

Figure 1. Timeline: events per quarter by dataset 1

period	series	value
2022-01-01	Outages	0
2022-01-01	Vegetation work orders	0
2022-01-01	Feeder reliability by year	79
2022-04-01	Outages	0
2022-04-01	Vegetation work orders	0
2022-04-01	Feeder reliability by year	0
2022-07-01	Outages	0
2022-07-01	Vegetation work orders	0
2022-07-01	Feeder reliability by year	0
2022-10-01	Outages	0
2022-10-01	Vegetation work orders	0
2022-10-01	Feeder reliability by year	0
2023-01-01	Outages	0
2023-01-01	Vegetation work orders	0
2023-01-01	Feeder reliability by year	79
2023-04-01	Outages	0
2023-04-01	Vegetation work orders	0
2023-04-01	Feeder reliability by year	0
2023-07-01	Outages	0
2023-07-01	Vegetation work orders	0
2023-07-01	Feeder reliability by year	0
2023-10-01	Outages	0
2023-10-01	Vegetation work orders	0
2023-10-01	Feeder reliability by year	0
2024-01-01	Outages	0
2024-01-01	Vegetation work orders	0
2024-01-01	Feeder reliability by year	79
2024-04-01	Outages	0
2024-04-01	Vegetation work orders	0
2024-04-01	Feeder reliability by year	0
2024-07-01	Outages	0
2024-07-01	Vegetation work orders	0
2024-07-01	Feeder reliability by year	0
2024-10-01	Outages	163
2024-10-01	Vegetation work orders	45
2024-10-01	Feeder reliability by year	0
2025-01-01	Outages	151
2025-01-01	Vegetation work orders	60
2025-01-01	Feeder reliability by year	79
2025-04-01	Outages	160
2025-04-01	Vegetation work orders	79
2025-04-01	Feeder reliability by year	0
2025-07-01	Outages	384
2025-07-01	Vegetation work orders	41
2025-07-01	Feeder reliability by year	0
2025-10-01	Outages	185
2025-10-01	Vegetation work orders	48
2025-10-01	Feeder reliability by year	0
2026-01-01	Outages	168
2026-01-01	Vegetation work orders	72
2026-01-01	Feeder reliability by year	0
2026-04-01	Outages	176
2026-04-01	Vegetation work orders	88
2026-04-01	Feeder reliability by year	0
2026-07-01	Outages	263
2026-07-01	Vegetation work orders	47
2026-07-01	Feeder reliability by year	0

Figure 22. Feeder lines over time (install_year) 70

bin_start	bin_end	count
1,964	1,971	12
1,971	1,978	16
1,978	1,986	10
1,986	1,993	6
1,993	2,000	14
2,000	2,008	10
2,008	2,015	2
2,015	2,022	9

Figure 23. Vegetation work orders over time (date) 71

period	series	value
2024-10-01	hazard tree	2
2024-10-01	cycle trim	4
2024-10-01	hot spot	5
2024-11-01	hazard tree	5
2024-11-01	cycle trim	4
2024-11-01	hot spot	3
2024-12-01	hazard tree	9
2024-12-01	cycle trim	6
2024-12-01	hot spot	7
2025-01-01	hazard tree	2
2025-01-01	cycle trim	6
2025-01-01	hot spot	5
2025-02-01	hazard tree	8
2025-02-01	cycle trim	5
2025-02-01	hot spot	4
2025-03-01	hazard tree	11
2025-03-01	cycle trim	16
2025-03-01	hot spot	3
2025-04-01	hazard tree	10
2025-04-01	cycle trim	16
2025-04-01	hot spot	10
2025-05-01	hazard tree	10
2025-05-01	cycle trim	8
2025-05-01	hot spot	7
2025-06-01	hazard tree	7
2025-06-01	cycle trim	4
2025-06-01	hot spot	7
2025-07-01	hazard tree	6
2025-07-01	cycle trim	5
2025-07-01	hot spot	9
2025-08-01	hazard tree	1
2025-08-01	cycle trim	5
2025-08-01	hot spot	3
2025-09-01	hazard tree	3
2025-09-01	cycle trim	6
2025-09-01	hot spot	3
2025-10-01	hazard tree	4
2025-10-01	cycle trim	6
2025-10-01	hot spot	6
2025-11-01	hazard tree	1
2025-11-01	cycle trim	2
2025-11-01	hot spot	6
2025-12-01	hazard tree	8
2025-12-01	cycle trim	9
2025-12-01	hot spot	6
2026-01-01	hazard tree	13
2026-01-01	cycle trim	4
2026-01-01	hot spot	12
2026-02-01	hazard tree	6
2026-02-01	cycle trim	7
2026-02-01	hot spot	10
2026-03-01	hazard tree	8
2026-03-01	cycle trim	5
2026-03-01	hot spot	7
2026-04-01	hazard tree	12
2026-04-01	cycle trim	15
2026-04-01	hot spot	11
2026-05-01	hazard tree	10
2026-05-01	cycle trim	5
2026-05-01	hot spot	10
2026-06-01	hazard tree	12
2026-06-01	cycle trim	5
2026-06-01	hot spot	8
2026-07-01	hazard tree	5
2026-07-01	cycle trim	8
2026-07-01	hot spot	8
2026-08-01	hazard tree	5
2026-08-01	cycle trim	4
2026-08-01	hot spot	4
2026-09-01	hazard tree	3
2026-09-01	cycle trim	5
2026-09-01	hot spot	5

Figure 24. Poles over time (install_year) 72

bin_start	bin_end	count
1,967	1,973	15
1,973	1,978	30
1,978	1,984	44
1,984	1,990	34
1,990	1,996	36
1,996	2,001	45
2,001	2,007	55
2,007	2,013	50
2,013	2,018	52
2,018	2,024	89

Figure 25. Feeder reliability by year over time (year) 73

period	value
2022-01-01	79
2022-02-01	0
2022-03-01	0
2022-04-01	0
2022-05-01	0
2022-06-01	0
2022-07-01	0
2022-08-01	0
2022-09-01	0
2022-10-01	0
2022-11-01	0
2022-12-01	0
2023-01-01	79
2023-02-01	0
2023-03-01	0
2023-04-01	0
2023-05-01	0
2023-06-01	0
2023-07-01	0
2023-08-01	0
2023-09-01	0
2023-10-01	0
2023-11-01	0
2023-12-01	0
2024-01-01	79
2024-02-01	0
2024-03-01	0
2024-04-01	0
2024-05-01	0
2024-06-01	0
2024-07-01	0
2024-08-01	0
2024-09-01	0
2024-10-01	0
2024-11-01	0
2024-12-01	0
2025-01-01	79

Figure 26. Transformer assets over time (install_year) 74

bin_start	bin_end	count
25	39.2	66
39.2	53.4	59
53.4	67.6	0
67.6	81.8	61
81.8	96	0
96	110.2	48
110.2	124.4	0
124.4	138.6	0
138.6	152.8	0
152.8	167	66

Figure 27. Emerging hot spots: Outages 75

bin_start	bin_end	count
-1.044	-0.2486	36
-0.2486	0.5467	20
0.5467	1.342	21
1.342	2.138	10
2.138	2.933	4
2.933	3.728	5
3.728	4.524	3
4.524	5.319	1

Figure 28. Emerging hot spots: Vegetation work orders 76

bin_start	bin_end	count
-0.951	-0.5264	39
-0.5264	-0.1017	28
-0.1017	0.3229	1
0.3229	0.7475	9
0.7475	1.172	1
1.172	1.597	1
1.597	2.021	9
2.021	2.446	1

Figure 29. Hot spot analysis: Poles 77

bin_start	bin_end	band	band_label	count
-1	-0.5	not_significant	Not significant	33
-0.5	0	not_significant	Not significant	13
0	0.5	not_significant	Not significant	13
0.5	1	not_significant	Not significant	5
1	1.5	not_significant	Not significant	10
1.5	2	hot_90	Hot spot, 90% confidence	1
2	2.5	hot_95	Hot spot, 95% confidence	2
3	3.5	hot_99	Hot spot, 99% confidence	1
3.5	4	hot_99	Hot spot, 99% confidence	1

Figure 30. Hot spot analysis: Outages 78

bin_start	bin_end	band	band_label	count
-2.5	-2	cold_95	Cold spot, 95% confidence	6
-2	-1.5	cold_90	Cold spot, 90% confidence	45
-2	-1.5	cold_95	Cold spot, 95% confidence	1
-2	-1.5	not_significant	Not significant	18
-1.5	-1	not_significant	Not significant	179
-1	-0.5	not_significant	Not significant	376
-0.5	0	not_significant	Not significant	330
0	0.5	not_significant	Not significant	246
0.5	1	not_significant	Not significant	205
1	1.5	not_significant	Not significant	160
1.5	2	hot_90	Hot spot, 90% confidence	25
1.5	2	hot_95	Hot spot, 95% confidence	3
1.5	2	not_significant	Not significant	15
2	2.5	hot_95	Hot spot, 95% confidence	28
2.5	3	hot_95	Hot spot, 95% confidence	3
2.5	3	hot_99	Hot spot, 99% confidence	7
3	3.5	hot_99	Hot spot, 99% confidence	2
3.5	4	hot_99	Hot spot, 99% confidence	1

Figure 31. Hot spot analysis: Vegetation work orders 79

bin_start	bin_end	band	band_label	count
-1	-0.5	not_significant	Not significant	33
-0.5	0	not_significant	Not significant	17
0	0.5	not_significant	Not significant	13
0.5	1	not_significant	Not significant	10
1	1.5	not_significant	Not significant	5
1.5	2	hot_90	Hot spot, 90% confidence	2
1.5	2	not_significant	Not significant	2
2	2.5	hot_95	Hot spot, 95% confidence	2
2.5	3	hot_99	Hot spot, 99% confidence	1
4	4.5	hot_99	Hot spot, 99% confidence	1

Figure 32. Calculate density: Poles 80

bin_start	bin_end	count
0	2.3	18
2.3	4.6	28
4.6	6.9	33
6.9	9.2	51
9.2	11.5	36
11.5	13.8	33
13.8	16.1	50
16.1	18.4	34
18.4	20.7	32
20.7	23	29

Figure 33. Calculate density: Outages 81

bin_start	bin_end	count
0	4.5	37
4.5	9	59
9	13.5	160
13.5	18	118
18	22.5	189
22.5	27	166
27	31.5	179
31.5	36	129
36	40.5	190
40.5	45	144
45	49.5	137
49.5	54	80

Figure 34. Calculate density: Vegetation work orders 82

bin_start	bin_end	count
0	2.3	18
2.3	4.6	27
4.6	6.9	34
6.9	9.2	53
9.2	11.5	38
11.5	13.8	32
13.8	16.1	52
16.1	18.4	32
18.4	20.7	32
20.7	23	32

Figure 35. Summarize within: Service areas 83

bin_start	bin_end	count
19	24.6	3
24.6	30.2	4
30.2	35.8	3
35.8	41.4	1
41.4	47	3

Figure 36. Summarize within: Service areas 84

bin_start	bin_end	count
57	85.8	4
85.8	114.6	5
114.6	143.4	0
143.4	172.2	2
172.2	201	3

Figure 37. Summarize within: Service areas 85

bin_start	bin_end	count
18	26	7
26	34	1
34	42	1
42	50	1
50	58	4

Figure 38. Find point clusters: Poles 86

cluster	features	fraction	share
Noise	149	0.3311	33.1%
2	49	0.1089	10.9%
5	35	0.07778	7.8%
4	34	0.07556	7.6%
6	31	0.06889	6.9%
8	26	0.05778	5.8%
3	23	0.05111	5.1%
7	21	0.04667	4.7%
9	19	0.04222	4.2%
11	17	0.03778	3.8%
0	16	0.03556	3.6%
1	15	0.03333	3.3%
10	15	0.03333	3.3%

Figure 39. Find point clusters: cluster hulls 87

cluster	features	fraction	share
0	1	0.08333	8.3%
1	1	0.08333	8.3%
10	1	0.08333	8.3%
11	1	0.08333	8.3%
2	1	0.08333	8.3%
3	1	0.08333	8.3%
4	1	0.08333	8.3%
5	1	0.08333	8.3%
6	1	0.08333	8.3%
7	1	0.08333	8.3%
8	1	0.08333	8.3%
9	1	0.08333	8.3%

Figure 40. Find point clusters: Outages 88

cluster	features	fraction	share
Noise	985	0.597	59.7%
5	121	0.07333	7.3%
0	112	0.06788	6.8%
1	81	0.04909	4.9%
7	76	0.04606	4.6%
3	56	0.03394	3.4%
4	54	0.03273	3.3%
6	34	0.02061	2.1%
8	34	0.02061	2.1%
2	32	0.01939	1.9%
9	31	0.01879	1.9%
10	20	0.01212	1.2%
11	14	0.008485	0.8%

Figure 41. Find point clusters: cluster hulls 89

cluster	features	fraction	share
0	1	0.08333	8.3%
1	1	0.08333	8.3%
10	1	0.08333	8.3%
11	1	0.08333	8.3%
2	1	0.08333	8.3%
3	1	0.08333	8.3%
4	1	0.08333	8.3%
5	1	0.08333	8.3%
6	1	0.08333	8.3%
7	1	0.08333	8.3%
8	1	0.08333	8.3%
9	1	0.08333	8.3%

Figure 42. Find point clusters: Vegetation work orders 90

cluster	features	fraction	share
Noise	157	0.3271	32.7%
0	83	0.1729	17.3%
1	56	0.1167	11.7%
2	39	0.08125	8.1%
4	36	0.075	7.5%
7	36	0.075	7.5%
6	20	0.04167	4.2%
3	19	0.03958	4.0%
5	19	0.03958	4.0%
8	15	0.03125	3.1%

Figure 43. Find point clusters: cluster hulls 91

cluster	features	fraction	share
0	1	0.1111	11.1%
1	1	0.1111	11.1%
2	1	0.1111	11.1%
3	1	0.1111	11.1%
4	1	0.1111	11.1%
5	1	0.1111	11.1%
6	1	0.1111	11.1%
7	1	0.1111	11.1%
8	1	0.1111	11.1%

Figure 44. Find outliers: Service areas 92

value	lag	type
-0.3267	2.336	NS
0.129	0.5255	NS
-1.064	-0.2187	NS
-0.2187	-0.8003	NS
-0.4868	-0.5612	NS
0.642	-1.518	NS
1.464	0.129	NS
2.336	-0.3267	NS
-0.289	-0.0449	NS
0.4018	0.129	NS
-1.361	-0.2016	NS
-1.518	0.0776	NS
0.1915	-0.4868	NS
0.1007	-0.924	NS

Figure 45. Repeat and near repeat classification: Outages 93

period	series	value
2024-10-01	vegetation	28
2024-10-01	equipment	31
2024-10-01	weather	12
2024-10-01	animal	10
2024-10-01	unknown	6
2024-10-01	Other	1
2024-11-01	vegetation	13
2024-11-01	equipment	15
2024-11-01	weather	5
2024-11-01	animal	3
2024-11-01	unknown	2
2024-11-01	Other	1
2024-12-01	vegetation	15
2024-12-01	equipment	10
2024-12-01	weather	8
2024-12-01	animal	2
2024-12-01	unknown	1
2024-12-01	Other	0
2025-01-01	vegetation	20
2025-01-01	equipment	19
2025-01-01	weather	7
2025-01-01	animal	4
2025-01-01	unknown	3
2025-01-01	Other	1
2025-02-01	vegetation	25
2025-02-01	equipment	15
2025-02-01	weather	9
2025-02-01	animal	2
2025-02-01	unknown	2
2025-02-01	Other	2
2025-03-01	vegetation	25
2025-03-01	equipment	8
2025-03-01	weather	3
2025-03-01	animal	3
2025-03-01	unknown	2
2025-03-01	Other	1
2025-04-01	vegetation	15
2025-04-01	equipment	6
2025-04-01	weather	6
2025-04-01	animal	7
2025-04-01	unknown	4
2025-04-01	Other	1
2025-05-01	vegetation	22
2025-05-01	equipment	9
2025-05-01	weather	12
2025-05-01	animal	3
2025-05-01	unknown	2
2025-05-01	Other	0
2025-06-01	vegetation	28
2025-06-01	equipment	24
2025-06-01	weather	7
2025-06-01	animal	6
2025-06-01	unknown	5
2025-06-01	Other	3
2025-07-01	vegetation	37
2025-07-01	equipment	20
2025-07-01	weather	9
2025-07-01	animal	3
2025-07-01	unknown	5
2025-07-01	Other	2
2025-08-01	vegetation	26
2025-08-01	equipment	30
2025-08-01	weather	143
2025-08-01	animal	4
2025-08-01	unknown	1
2025-08-01	Other	3
2025-09-01	vegetation	50
2025-09-01	equipment	26
2025-09-01	weather	13
2025-09-01	animal	6
2025-09-01	unknown	0
2025-09-01	Other	6
2025-10-01	vegetation	43
2025-10-01	equipment	28
2025-10-01	weather	16
2025-10-01	animal	8
2025-10-01	unknown	4
2025-10-01	Other	3
2025-11-01	vegetation	18
2025-11-01	equipment	14
2025-11-01	weather	7
2025-11-01	animal	2
2025-11-01	unknown	3
2025-11-01	Other	1
2025-12-01	vegetation	18
2025-12-01	equipment	11
2025-12-01	weather	6
2025-12-01	animal	3
2025-12-01	unknown	0
2025-12-01	Other	0
2026-01-01	vegetation	39
2026-01-01	equipment	15
2026-01-01	weather	6
2026-01-01	animal	8
2026-01-01	unknown	7
2026-01-01	Other	4
2026-02-01	vegetation	23
2026-02-01	equipment	12
2026-02-01	weather	6
2026-02-01	animal	3
2026-02-01	unknown	3
2026-02-01	Other	2
2026-03-01	vegetation	19
2026-03-01	equipment	9
2026-03-01	weather	5
2026-03-01	animal	4
2026-03-01	unknown	3
2026-03-01	Other	0
2026-04-01	vegetation	23
2026-04-01	equipment	12
2026-04-01	weather	6
2026-04-01	animal	4
2026-04-01	unknown	4
2026-04-01	Other	0
2026-05-01	vegetation	18
2026-05-01	equipment	5
2026-05-01	weather	3
2026-05-01	animal	5
2026-05-01	unknown	2
2026-05-01	Other	2
2026-06-01	vegetation	38
2026-06-01	equipment	32
2026-06-01	weather	12
2026-06-01	animal	5
2026-06-01	unknown	2
2026-06-01	Other	3
2026-07-01	vegetation	39
2026-07-01	equipment	27
2026-07-01	weather	13
2026-07-01	animal	7
2026-07-01	unknown	5
2026-07-01	Other	5
2026-08-01	vegetation	33
2026-08-01	equipment	24
2026-08-01	weather	5
2026-08-01	animal	10
2026-08-01	unknown	1
2026-08-01	Other	1
2026-09-01	vegetation	29
2026-09-01	equipment	25
2026-09-01	weather	24
2026-09-01	animal	7
2026-09-01	unknown	7
2026-09-01	Other	1

Figure 46. Repeat and near repeat classification: Outages over time 94

period	series	value
2024-10-01	vegetation	28
2024-10-01	equipment	31
2024-10-01	weather	12
2024-10-01	animal	10
2024-10-01	unknown	6
2024-10-01	Other	1
2024-11-01	vegetation	13
2024-11-01	equipment	15
2024-11-01	weather	5
2024-11-01	animal	3
2024-11-01	unknown	2
2024-11-01	Other	1
2024-12-01	vegetation	15
2024-12-01	equipment	10
2024-12-01	weather	8
2024-12-01	animal	2
2024-12-01	unknown	1
2024-12-01	Other	0
2025-01-01	vegetation	20
2025-01-01	equipment	19
2025-01-01	weather	7
2025-01-01	animal	4
2025-01-01	unknown	3
2025-01-01	Other	1
2025-02-01	vegetation	25
2025-02-01	equipment	15
2025-02-01	weather	9
2025-02-01	animal	2
2025-02-01	unknown	2
2025-02-01	Other	2
2025-03-01	vegetation	25
2025-03-01	equipment	8
2025-03-01	weather	3
2025-03-01	animal	3
2025-03-01	unknown	2
2025-03-01	Other	1
2025-04-01	vegetation	15
2025-04-01	equipment	6
2025-04-01	weather	6
2025-04-01	animal	7
2025-04-01	unknown	4
2025-04-01	Other	1
2025-05-01	vegetation	22
2025-05-01	equipment	9
2025-05-01	weather	12
2025-05-01	animal	3
2025-05-01	unknown	2
2025-05-01	Other	0
2025-06-01	vegetation	28
2025-06-01	equipment	24
2025-06-01	weather	7
2025-06-01	animal	6
2025-06-01	unknown	5
2025-06-01	Other	3
2025-07-01	vegetation	37
2025-07-01	equipment	20
2025-07-01	weather	9
2025-07-01	animal	3
2025-07-01	unknown	5
2025-07-01	Other	2
2025-08-01	vegetation	26
2025-08-01	equipment	30
2025-08-01	weather	143
2025-08-01	animal	4
2025-08-01	unknown	1
2025-08-01	Other	3
2025-09-01	vegetation	50
2025-09-01	equipment	26
2025-09-01	weather	13
2025-09-01	animal	6
2025-09-01	unknown	0
2025-09-01	Other	6
2025-10-01	vegetation	43
2025-10-01	equipment	28
2025-10-01	weather	16
2025-10-01	animal	8
2025-10-01	unknown	4
2025-10-01	Other	3
2025-11-01	vegetation	18
2025-11-01	equipment	14
2025-11-01	weather	7
2025-11-01	animal	2
2025-11-01	unknown	3
2025-11-01	Other	1
2025-12-01	vegetation	18
2025-12-01	equipment	11
2025-12-01	weather	6
2025-12-01	animal	3
2025-12-01	unknown	0
2025-12-01	Other	0
2026-01-01	vegetation	39
2026-01-01	equipment	15
2026-01-01	weather	6
2026-01-01	animal	8
2026-01-01	unknown	7
2026-01-01	Other	4
2026-02-01	vegetation	23
2026-02-01	equipment	12
2026-02-01	weather	6
2026-02-01	animal	3
2026-02-01	unknown	3
2026-02-01	Other	2
2026-03-01	vegetation	19
2026-03-01	equipment	9
2026-03-01	weather	5
2026-03-01	animal	4
2026-03-01	unknown	3
2026-03-01	Other	0
2026-04-01	vegetation	23
2026-04-01	equipment	12
2026-04-01	weather	6
2026-04-01	animal	4
2026-04-01	unknown	4
2026-04-01	Other	0
2026-05-01	vegetation	18
2026-05-01	equipment	5
2026-05-01	weather	3
2026-05-01	animal	5
2026-05-01	unknown	2
2026-05-01	Other	2
2026-06-01	vegetation	38
2026-06-01	equipment	32
2026-06-01	weather	12
2026-06-01	animal	5
2026-06-01	unknown	2
2026-06-01	Other	3
2026-07-01	vegetation	39
2026-07-01	equipment	27
2026-07-01	weather	13
2026-07-01	animal	7
2026-07-01	unknown	5
2026-07-01	Other	5
2026-08-01	vegetation	33
2026-08-01	equipment	24
2026-08-01	weather	5
2026-08-01	animal	10
2026-08-01	unknown	1
2026-08-01	Other	1
2026-09-01	vegetation	29
2026-09-01	equipment	25
2026-09-01	weather	24
2026-09-01	animal	7
2026-09-01	unknown	7
2026-09-01	Other	1

Figure 47. Find point clusters: Vegetation work orders over time 95

period	series	value
2024-10-01	11	2
2024-10-01	6	0
2024-10-01	9	2
2024-10-01	12	0
2024-10-01	4	1
2024-10-01	Other	6
2024-11-01	11	0
2024-11-01	6	3
2024-11-01	9	0
2024-11-01	12	1
2024-11-01	4	1
2024-11-01	Other	7
2024-12-01	11	5
2024-12-01	6	0
2024-12-01	9	1
2024-12-01	12	3
2024-12-01	4	3
2024-12-01	Other	10
2025-01-01	11	2
2025-01-01	6	3
2025-01-01	9	0
2025-01-01	12	0
2025-01-01	4	3
2025-01-01	Other	5
2025-02-01	11	1
2025-02-01	6	2
2025-02-01	9	1
2025-02-01	12	2
2025-02-01	4	1
2025-02-01	Other	10
2025-03-01	11	1
2025-03-01	6	3
2025-03-01	9	5
2025-03-01	12	3
2025-03-01	4	2
2025-03-01	Other	16
2025-04-01	11	4
2025-04-01	6	3
2025-04-01	9	3
2025-04-01	12	3
2025-04-01	4	6
2025-04-01	Other	17
2025-05-01	11	2
2025-05-01	6	0
2025-05-01	9	2
2025-05-01	12	3
2025-05-01	4	2
2025-05-01	Other	16
2025-06-01	11	1
2025-06-01	6	1
2025-06-01	9	3
2025-06-01	12	1
2025-06-01	4	1
2025-06-01	Other	11
2025-07-01	11	2
2025-07-01	6	4
2025-07-01	9	4
2025-07-01	12	1
2025-07-01	4	2
2025-07-01	Other	7
2025-08-01	11	1
2025-08-01	6	0
2025-08-01	9	1
2025-08-01	12	0
2025-08-01	4	0
2025-08-01	Other	7
2025-09-01	11	1
2025-09-01	6	1
2025-09-01	9	2
2025-09-01	12	1
2025-09-01	4	2
2025-09-01	Other	5
2025-10-01	11	1
2025-10-01	6	3
2025-10-01	9	0
2025-10-01	12	2
2025-10-01	4	1
2025-10-01	Other	9
2025-11-01	11	1
2025-11-01	6	0
2025-11-01	9	1
2025-11-01	12	2
2025-11-01	4	2
2025-11-01	Other	3
2025-12-01	11	1
2025-12-01	6	3
2025-12-01	9	1
2025-12-01	12	3
2025-12-01	4	1
2025-12-01	Other	14
2026-01-01	11	3
2026-01-01	6	6
2026-01-01	9	1
2026-01-01	12	3
2026-01-01	4	2
2026-01-01	Other	14
2026-02-01	11	3
2026-02-01	6	2
2026-02-01	9	3
2026-02-01	12	3
2026-02-01	4	3
2026-02-01	Other	9
2026-03-01	11	1
2026-03-01	6	0
2026-03-01	9	2
2026-03-01	12	1
2026-03-01	4	4
2026-03-01	Other	12
2026-04-01	11	2
2026-04-01	6	4
2026-04-01	9	5
2026-04-01	12	3
2026-04-01	4	2
2026-04-01	Other	22
2026-05-01	11	3
2026-05-01	6	3
2026-05-01	9	1
2026-05-01	12	0
2026-05-01	4	1
2026-05-01	Other	17
2026-06-01	11	3
2026-06-01	6	1
2026-06-01	9	3
2026-06-01	12	2
2026-06-01	4	1
2026-06-01	Other	15
2026-07-01	11	2
2026-07-01	6	0
2026-07-01	9	0
2026-07-01	12	2
2026-07-01	4	1
2026-07-01	Other	16
2026-08-01	11	1
2026-08-01	6	2
2026-08-01	9	2
2026-08-01	12	0
2026-08-01	4	0
2026-08-01	Other	8
2026-09-01	11	3
2026-09-01	6	1
2026-09-01	9	0
2026-09-01	12	3
2026-09-01	4	0
2026-09-01	Other	6

Figure 48. Find point clusters: Outages over time 96

period	series	value
2024-10-01	vegetation	28
2024-10-01	equipment	31
2024-10-01	weather	12
2024-10-01	animal	10
2024-10-01	unknown	6
2024-10-01	Other	1
2024-11-01	vegetation	13
2024-11-01	equipment	15
2024-11-01	weather	5
2024-11-01	animal	3
2024-11-01	unknown	2
2024-11-01	Other	1
2024-12-01	vegetation	15
2024-12-01	equipment	10
2024-12-01	weather	8
2024-12-01	animal	2
2024-12-01	unknown	1
2024-12-01	Other	0
2025-01-01	vegetation	20
2025-01-01	equipment	19
2025-01-01	weather	7
2025-01-01	animal	4
2025-01-01	unknown	3
2025-01-01	Other	1
2025-02-01	vegetation	25
2025-02-01	equipment	15
2025-02-01	weather	9
2025-02-01	animal	2
2025-02-01	unknown	2
2025-02-01	Other	2
2025-03-01	vegetation	25
2025-03-01	equipment	8
2025-03-01	weather	3
2025-03-01	animal	3
2025-03-01	unknown	2
2025-03-01	Other	1
2025-04-01	vegetation	15
2025-04-01	equipment	6
2025-04-01	weather	6
2025-04-01	animal	7
2025-04-01	unknown	4
2025-04-01	Other	1
2025-05-01	vegetation	22
2025-05-01	equipment	9
2025-05-01	weather	12
2025-05-01	animal	3
2025-05-01	unknown	2
2025-05-01	Other	0
2025-06-01	vegetation	28
2025-06-01	equipment	24
2025-06-01	weather	7
2025-06-01	animal	6
2025-06-01	unknown	5
2025-06-01	Other	3
2025-07-01	vegetation	37
2025-07-01	equipment	20
2025-07-01	weather	9
2025-07-01	animal	3
2025-07-01	unknown	5
2025-07-01	Other	2
2025-08-01	vegetation	26
2025-08-01	equipment	30
2025-08-01	weather	143
2025-08-01	animal	4
2025-08-01	unknown	1
2025-08-01	Other	3
2025-09-01	vegetation	50
2025-09-01	equipment	26
2025-09-01	weather	13
2025-09-01	animal	6
2025-09-01	unknown	0
2025-09-01	Other	6
2025-10-01	vegetation	43
2025-10-01	equipment	28
2025-10-01	weather	16
2025-10-01	animal	8
2025-10-01	unknown	4
2025-10-01	Other	3
2025-11-01	vegetation	18
2025-11-01	equipment	14
2025-11-01	weather	7
2025-11-01	animal	2
2025-11-01	unknown	3
2025-11-01	Other	1
2025-12-01	vegetation	18
2025-12-01	equipment	11
2025-12-01	weather	6
2025-12-01	animal	3
2025-12-01	unknown	0
2025-12-01	Other	0
2026-01-01	vegetation	39
2026-01-01	equipment	15
2026-01-01	weather	6
2026-01-01	animal	8
2026-01-01	unknown	7
2026-01-01	Other	4
2026-02-01	vegetation	23
2026-02-01	equipment	12
2026-02-01	weather	6
2026-02-01	animal	3
2026-02-01	unknown	3
2026-02-01	Other	2
2026-03-01	vegetation	19
2026-03-01	equipment	9
2026-03-01	weather	5
2026-03-01	animal	4
2026-03-01	unknown	3
2026-03-01	Other	0
2026-04-01	vegetation	23
2026-04-01	equipment	12
2026-04-01	weather	6
2026-04-01	animal	4
2026-04-01	unknown	4
2026-04-01	Other	0
2026-05-01	vegetation	18
2026-05-01	equipment	5
2026-05-01	weather	3
2026-05-01	animal	5
2026-05-01	unknown	2
2026-05-01	Other	2
2026-06-01	vegetation	38
2026-06-01	equipment	32
2026-06-01	weather	12
2026-06-01	animal	5
2026-06-01	unknown	2
2026-06-01	Other	3
2026-07-01	vegetation	39
2026-07-01	equipment	27
2026-07-01	weather	13
2026-07-01	animal	7
2026-07-01	unknown	5
2026-07-01	Other	5
2026-08-01	vegetation	33
2026-08-01	equipment	24
2026-08-01	weather	5
2026-08-01	animal	10
2026-08-01	unknown	1
2026-08-01	Other	1
2026-09-01	vegetation	29
2026-09-01	equipment	25
2026-09-01	weather	24
2026-09-01	animal	7
2026-09-01	unknown	7
2026-09-01	Other	1

Figure 49. Hot spot analysis: Outages over time 97

period	series	value
2024-10-01	vegetation	28
2024-10-01	equipment	31
2024-10-01	weather	12
2024-10-01	animal	10
2024-10-01	unknown	6
2024-10-01	Other	1
2024-11-01	vegetation	13
2024-11-01	equipment	15
2024-11-01	weather	5
2024-11-01	animal	3
2024-11-01	unknown	2
2024-11-01	Other	1
2024-12-01	vegetation	15
2024-12-01	equipment	10
2024-12-01	weather	8
2024-12-01	animal	2
2024-12-01	unknown	1
2024-12-01	Other	0
2025-01-01	vegetation	20
2025-01-01	equipment	19
2025-01-01	weather	7
2025-01-01	animal	4
2025-01-01	unknown	3
2025-01-01	Other	1
2025-02-01	vegetation	25
2025-02-01	equipment	15
2025-02-01	weather	9
2025-02-01	animal	2
2025-02-01	unknown	2
2025-02-01	Other	2
2025-03-01	vegetation	25
2025-03-01	equipment	8
2025-03-01	weather	3
2025-03-01	animal	3
2025-03-01	unknown	2
2025-03-01	Other	1
2025-04-01	vegetation	15
2025-04-01	equipment	6
2025-04-01	weather	6
2025-04-01	animal	7
2025-04-01	unknown	4
2025-04-01	Other	1
2025-05-01	vegetation	22
2025-05-01	equipment	9
2025-05-01	weather	12
2025-05-01	animal	3
2025-05-01	unknown	2
2025-05-01	Other	0
2025-06-01	vegetation	28
2025-06-01	equipment	24
2025-06-01	weather	7
2025-06-01	animal	6
2025-06-01	unknown	5
2025-06-01	Other	3
2025-07-01	vegetation	37
2025-07-01	equipment	20
2025-07-01	weather	9
2025-07-01	animal	3
2025-07-01	unknown	5
2025-07-01	Other	2
2025-08-01	vegetation	26
2025-08-01	equipment	30
2025-08-01	weather	143
2025-08-01	animal	4
2025-08-01	unknown	1
2025-08-01	Other	3
2025-09-01	vegetation	50
2025-09-01	equipment	26
2025-09-01	weather	13
2025-09-01	animal	6
2025-09-01	unknown	0
2025-09-01	Other	6
2025-10-01	vegetation	43
2025-10-01	equipment	28
2025-10-01	weather	16
2025-10-01	animal	8
2025-10-01	unknown	4
2025-10-01	Other	3
2025-11-01	vegetation	18
2025-11-01	equipment	14
2025-11-01	weather	7
2025-11-01	animal	2
2025-11-01	unknown	3
2025-11-01	Other	1
2025-12-01	vegetation	18
2025-12-01	equipment	11
2025-12-01	weather	6
2025-12-01	animal	3
2025-12-01	unknown	0
2025-12-01	Other	0
2026-01-01	vegetation	39
2026-01-01	equipment	15
2026-01-01	weather	6
2026-01-01	animal	8
2026-01-01	unknown	7
2026-01-01	Other	4
2026-02-01	vegetation	23
2026-02-01	equipment	12
2026-02-01	weather	6
2026-02-01	animal	3
2026-02-01	unknown	3
2026-02-01	Other	2
2026-03-01	vegetation	19
2026-03-01	equipment	9
2026-03-01	weather	5
2026-03-01	animal	4
2026-03-01	unknown	3
2026-03-01	Other	0
2026-04-01	vegetation	23
2026-04-01	equipment	12
2026-04-01	weather	6
2026-04-01	animal	4
2026-04-01	unknown	4
2026-04-01	Other	0
2026-05-01	vegetation	18
2026-05-01	equipment	5
2026-05-01	weather	3
2026-05-01	animal	5
2026-05-01	unknown	2
2026-05-01	Other	2
2026-06-01	vegetation	38
2026-06-01	equipment	32
2026-06-01	weather	12
2026-06-01	animal	5
2026-06-01	unknown	2
2026-06-01	Other	3
2026-07-01	vegetation	39
2026-07-01	equipment	27
2026-07-01	weather	13
2026-07-01	animal	7
2026-07-01	unknown	5
2026-07-01	Other	5
2026-08-01	vegetation	33
2026-08-01	equipment	24
2026-08-01	weather	5
2026-08-01	animal	10
2026-08-01	unknown	1
2026-08-01	Other	1
2026-09-01	vegetation	29
2026-09-01	equipment	25
2026-09-01	weather	24
2026-09-01	animal	7
2026-09-01	unknown	7
2026-09-01	Other	1

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.

Dataset	Kind	Rows	Time span	File
Substations Distribution substations.	vector, Point	14		substations.geojson
Feeder lines Primary feeder lines with construction and install year.	vector, LineString	79		feeders.geojson
Service areas Service area of each substation.	vector, Polygon	14		service_areas.geojson
Outages Unplanned outages with cause, duration and customers affected. Dated by `started_at` (minute).	vector, Point	1,650	2024-10-01 to 2026-09-30	outages.geojson
Vegetation work orders Completed tree trimming work orders by day. Dated by `date` (day).	vector, Point	480	2024-10-04 to 2026-09-21	vegetation_work_orders.geojson
Critical customers Customers with life-safety priority.	vector, Point	60		critical_customers.geojson
Poles Distribution poles with material and inspection grade.	vector, Point	450		poles.geojson
Feeder reliability by year Yearly reliability indices per feeder (joins to Feeder lines on feeder_id). Dated by `year` (year).	table	316	2022-01-01 to 2025-01-01	feeder_reliability.csv
Transformer assets Distribution transformers per substation (joins to Substations on substation_id).	table	300		transformer_assets.csv
Storm season reliability report A report naming substations and the storm.	document			storm_season_report.pdf, storm_season_report.md

What the data was built to show

Outages rise every storm season (June to October) and spike on 2025-08-20 to 2025-08-22.
Vegetation and equipment outages cluster on the old overhead feeders in the west (near Juniper Rise Substation).
Feeder reliability (SAIDI) is worst on the same feeders and worsens in 2025.

Expected analysis families: space_time, hot_spots, aggregation, 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.

Substations: 14 point features; 'voltage_kv' 35 to 69 (mean 64.14); 'capacity_mva' 40 to 120 (mean 68.57); 'commissioned' 1,970 to 2,017 (mean 1994); named by 'name' (e.g. Juniper Rise Substation, Kingsmead Substation, Larchfield Substation); extent -95.4070,29.7335 to -95.3261,29.7908.
Feeder lines: 79 line features; 'construction' has 2 values (top: overhead 46, underground 33); 'conductor' has 4 values (top: 1/0 ACSR 24, 477 AAC 21, 750 Cu UG 19); 'install_year' 1,964 to 2,022 (mean 1990); 'voltage_kv' 12.47 to 12.47 (mean 12.47); 'length_m' 540 to 3,063 (mean 1690); total length 133.5 km; extent -95.4215,29.7253 to -95.3181,29.7966.
Service areas: 14 polygon (area) features; 'customers' 4,420 to 13,419 (mean 7965); 'peak_load_mw' 17.1 to 50.9 (mean 36.91); named by 'name' (e.g. Juniper Rise Substation area, Kingsmead Substation area, Larchfield Substation area); total area 79.96 km2; extent -95.4223,29.7234 to -95.3173,29.7974.
Outages: 1,650 point features; dated by 'started_at' from 2024-10-01 to 2026-09-30; 'cause' has 6 values (top: vegetation 644, equipment 427, weather 343); 'duration_min' 10 to 2,740 (mean 195); 'customers_affected' 6 to 3,173 (mean 234.9); extent -95.4212,29.7255 to -95.3187,29.7961.
Vegetation work orders: 480 point features; dated by 'date' from 2024-10-04 to 2026-09-21; 'trim_type' has 3 values (top: hazard tree 161, cycle trim 160, hot spot 159); 'spans' 1 to 12 (mean 6.692); 'cost_usd' 566 to 12,478 (mean 2667); extent -95.4210,29.7258 to -95.3186,29.7961.
Critical customers: 60 point features; 'type' has 5 values (top: water plant 20, emergency shelter 11, fire station 10); 'backup_generator' has 2 values (top: False 39, True 21); 'priority' 1 to 3 (mean 1.683); extent -95.4198,29.7261 to -95.3218,29.7961.
Poles: 450 point features; 'material' has 3 values (top: wood 207, concrete 131, steel 112); 'inspection_grade' has 4 values (top: B 187, D 95, A 87); 'install_year' 1,967 to 2,024 (mean 2001); extent -95.4214,29.7313 to -95.3201,29.7964.
Feeder reliability by year: Table of 316 rows and 6 columns without geometry; dated by 'year' from 2022-01-01 to 2025-01-01; 'saidi_min' 35.2 to 486.9 (mean 121.6); 'saifi' 0.45 to 2.49 (mean 1.177); 'caidi_min' 29.3 to 391 (mean 106.5).
Transformer assets: Table of 300 rows and 6 columns without geometry; 'mount' has 2 values (top: pole 164, pad 136); 'kva' 25 to 167 (mean 83.32); 'install_year' 1,970 to 2,024 (mean 1997); 'condition_score' 1 to 10 (mean 5.301).
Storm season reliability report: 1-page pdf document 'Storm season reliability report'; language en; mentions 3 place(s): Juniper Rise Substation (2), Kingsmead Substation (1), Larchfield Substation (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.