Disaster response

Sample: Disaster response, Kathmandu: report

Project: Sample: Disaster response, Kathmandu
Goal: Describe the project Sample: Disaster response, Kathmandu: run the analyses that tell the most about its data, draw every result, and write a cited report.
Run: 2199067b-8747-4c82-b083-7c3d54abda8f (running, 11 agent run(s))
Generated: 2026-10-18T05:36:27Z, version 1
Model cost: USD 0.0000 over 0 model call(s)

Data used

Timeline

The timeline counts 2,900 dated events in Damage assessments, Road status, Relief distributions and 1 more per day, from 2026-09-02 to 2026-09-22 12345. By dataset: Damage assessments 2,000; Ward needs by day 420; Relief distributions 320; Road status 160 1. The trend is -3.48 events per day; the second half of the days has 1,177 against 1,586 in the first (-25.8%) 1. The project's documents name 1 date inside this span, drawn as dotted lines; the most named is 2026-09-14 (Situation report No 6. 4, page 1, 1 mention) 6.

Busiest days

• 2026-09-05: 181 events 1
• 2026-09-04: 170 events 1
• 2026-09-03: 164 events 1

Quietest days

• 2026-09-21: 96 events 1
• 2026-09-22: 102 events 1
• 2026-09-20: 104 events 1

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 7. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 7.

Why it was run on this data. 320 points: Getis-Ord Gi* tests whether the concentrations in Relief distributions are statistically significant 8.

What it found. Hot spot analysis was performed using the Relief distributions layer 10. The resulting analysis generated 320 features 9 and took 5 milliseconds to complete 9. The total billing cost for this operation was 0.0564 9.

Findings

• Evidenced: Hot spots on Relief distributions: Hot spot analysis: 1 layer saved: Hot spot analysis: Relief distributions (320 features) 910.
• Evidenced: It reported result, count 320; result, elapsed ms 5; result, excluded null 0; result, distance band m 1,000; billing, cost 0.0564; billing, list price 0.0564 9.

Tool gp_hot_spots; parameters {"field": "households_served", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "aggregation": "hexagon", "cell_size_m": 1000.0, "distance_band_m": 1000.0}

Hot spots

What this analysis is. Hot spot analysis: Getis-Ord Gi* hot and cold spots with z-scores, p-values and confidence bins 7. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 7.

Why it was run on this data. 60 points: Getis-Ord Gi* tests whether the concentrations in Water points are statistically significant 11.

What it found. The hot spot analysis used "Water points" as its input 13. The process saved one layer titled "Hot spot analysis: Water points (20 features)" 12. Results for the analysis indicated 20 bins and 20 counts, based on a cell size of 2,000 m 12. The final billing cost associated with this analysis was 0.0512 12.

Findings

• Evidenced: Hot spots on Water points: Hot spot analysis: 1 layer saved: Hot spot analysis: Water points (20 features) 1213.
• Evidenced: It reported result, bins 20; result, count 20; result, elapsed ms 3; result, cell size m 2,000; result, incidents used 60; result, distance band m 2,000 12.

Tool gp_hot_spots; parameters {"project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Water points (2a061d8c)"}, "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 7. In ArcGIS it is Find Hot Spots or Hot Spot Analysis (Getis-Ord Gi*); in QGIS, qgis:hotspot (plugin) 7.

Why it was run on this data. 2000 points: Getis-Ord Gi* tests whether the concentrations in Damage assessments are statistically significant 14.

What it found. The hot spot analysis successfully generated one saved layer titled "Hot spot analysis: Damage assessments" 15.

Findings

• Evidenced: Hot spots on Damage assessments: Hot spot analysis: 1 layer saved: Hot spot analysis: Damage assessments (2000 features) 1516.
• Evidenced: It reported result, count 2,000; result, elapsed ms 35; result, excluded null 0; result, distance band m 500; billing, cost 0.09; billing, list price 0.09 15.

Tool gp_hot_spots; parameters {"field": "people_displaced", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Damage assessments (26bd99f3)"}, "aggregation": "hexagon", "cell_size_m": 500.0, "distance_band_m": 500.0}

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 17. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 17.

Why it was run on this data. Relief distributions carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per day 18.

What it found. Space time hot spots on Relief distributions: Emerging hot spots: 1 layer saved: Emerging hot spots: Relief distributions (54 features) 1019. It reported result, count 54; result, elapsed ms 10; result, resolution 8; result, features used 320; result, time neighbors 0; billing, cost 0.116 19.

Findings

• Evidenced: Space time hot spots on Relief distributions: Emerging hot spots: 1 layer saved: Emerging hot spots: Relief distributions (54 features) 1019.
• Evidenced: It reported result, count 54; result, elapsed ms 10; result, resolution 8; result, features used 320; result, time neighbors 0; billing, cost 0.116 19.

Tool gp_space_time_hot_spots; parameters {"agg": "sum", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "interval": "day", "bin_shape": "h3", "resolution": 8, "time_field": "date", "value_field": "households_served"}

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 17. In ArcGIS it is Emerging Hot Spot Analysis or Create Space Time Cube 17.

Why it was run on this data. Damage assessments carry dates in 'assessed_at': emerging hot spot analysis finds new, intensifying and fading hot spots per day 20.

What it found. Space time hot spots on Damage assessments: Emerging hot spots: 1 layer saved: Emerging hot spots: Damage assessments (87 features) 1621. It reported result, count 87; result, elapsed ms 18; result, resolution 8; result, features used 2,000; result, time neighbors 0; billing, cost 0.2 21.

Findings

• Evidenced: Space time hot spots on Damage assessments: Emerging hot spots: 1 layer saved: Emerging hot spots: Damage assessments (87 features) 1621.
• Evidenced: It reported result, count 87; result, elapsed ms 18; result, resolution 8; result, features used 2,000; result, time neighbors 0; billing, cost 0.2 21.

Tool gp_space_time_hot_spots; parameters {"agg": "sum", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Damage assessments (26bd99f3)"}, "interval": "day", "bin_shape": "h3", "resolution": 8, "time_field": "assessed_at", "value_field": "people_displaced"}

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 22. In ArcGIS it is Repeat and Near Repeat Classification or Near Repeat Calculator 22.

Why it was run on this data. Near repeat analysis tests whether Relief distributions close in space also follow each other within 3 days 23.

What it found. Near repeat on Relief distributions: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Relief distributions (320 features) 1024. It reported result, days 3; result, count 320; result, chains 41; result, distance m 500; result, elapsed ms 13; result, pairs linked 742 24.

Findings

• Evidenced: Near repeat on Relief distributions: Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Relief distributions (320 features) 1024.
• Evidenced: It reported result, days 3; result, count 320; result, chains 41; result, distance m 500; result, elapsed ms 13; result, pairs linked 742 24.

Tool gp_near_repeat; parameters {"days": 3, "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "distance_m": 500.0, "time_field": "date"}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 25. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 25.

Why it was run on this data. Count Shelters inside each feature of Wards by type; the counts map as a choropleth (natural breaks, sequential colors) 26.

What it found. Summarize within on Shelters, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 272829. It reported result, count 20; result, elapsed ms 0; billing, cost 0.01092; billing, list price 0.01092; billing, upstream cost 0 27.

Findings

• Evidenced: Summarize within on Shelters, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 272829.
• Evidenced: It reported result, count 20; result, elapsed ms 0; billing, cost 0.01092; billing, list price 0.01092; billing, upstream cost 0 27.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "capacity"}], "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Shelters (ee1b31b2)"}, "group_by": "type", "polygons": {"layer": "Wards (b338e26e)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 25. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 25.

Why it was run on this data. Count Shelters inside each feature of Wards by type; the counts map as a choropleth (natural breaks, sequential colors) 26.

What it found. Summarize within on Relief distributions, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 102930. It reported result, count 20; result, elapsed ms 1; billing, cost 0.01682; billing, list price 0.01682; billing, upstream cost 0 30.

Findings

• Evidenced: Summarize within on Relief distributions, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 102930.
• Evidenced: It reported result, count 20; result, elapsed ms 1; billing, cost 0.01682; billing, list price 0.01682; billing, upstream cost 0 30.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "households_served"}], "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "group_by": "item", "polygons": {"layer": "Wards (b338e26e)"}}

Summarize within

What this analysis is. Summarize within: Count and aggregate the features inside each polygon (or bin), proportionally for lines and polygons 25. In ArcGIS it is Summarize Within or Aggregate Points; in QGIS, native:countpointsinpolygon or native:sumlinelengths 25.

Why it was run on this data. Count Shelters inside each feature of Wards by type; the counts map as a choropleth (natural breaks, sequential colors) 26.

What it found. Summarize within on Health posts, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 293132. It reported result, count 20; result, elapsed ms 0; billing, cost 0.01082; billing, list price 0.01082; billing, upstream cost 0 31.

Findings

• Evidenced: Summarize within on Health posts, Wards: Summarize within: 1 layer saved: Summarize within: Wards (20 features) 293132.
• Evidenced: It reported result, count 20; result, elapsed ms 0; billing, cost 0.01082; billing, list price 0.01082; billing, upstream cost 0 31.

Tool gp_summarize_within; parameters {"stats": [{"stat": "sum", "field": "beds"}], "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Health posts (7aed59a8)"}, "group_by": "functional", "polygons": {"layer": "Wards (b338e26e)"}}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Shelters and separates noise 34.

What it found. The gp_find_point_clusters tool was used on the Shelters data 28 to identify point clusters. The process resulted in a count of 25 clusters and 2 noise points 35. The output contained 2 layers, specifically listing "Shelters (25 features)" and "cluster hulls (1 feature)" 35. The computation was efficient, completing in an elapsed time of 4 ms 35.

Findings

• Evidenced: Find point clusters on Shelters: Find point clusters: 2 layers saved: Find point clusters: Shelters (25 features); Find point clusters: cluster hulls (1 feature) 2835.
• Evidenced: It reported result, count 25; result, noise 2; result, distance m 2,000; result, elapsed ms 4; result, min points 3; billing, cost 0.0505 35.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Shelters (ee1b31b2)"}, "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 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Relief distributions and separates noise 36.

What it found. Find point clusters on Relief distributions: Find point clusters: 2 layers saved: Find point clusters: Relief distributions (320 features); Find point clusters: cluster hulls (21 features) 1037. It reported result, count 320; result, noise 12; result, distance m 500; result, elapsed ms 10; result, min points 8; billing, cost 0.0564 37.

Findings

• Evidenced: Find point clusters on Relief distributions: Find point clusters: 2 layers saved: Find point clusters: Relief distributions (320 features); Find point clusters: cluster hulls (21 features) 1037.
• Evidenced: It reported result, count 320; result, noise 12; result, distance m 500; result, elapsed ms 10; result, min points 8; billing, cost 0.0564 37.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "distance_m": 500.0, "min_points": 8}

Find point clusters

What this analysis is. Find point clusters: Density-based clusters (DBSCAN, HDBSCAN or OPTICS, optionally space-time) with hulls and noise 33. In ArcGIS it is Find Point Clusters or Density-based Clustering; in QGIS, native:dbscanclustering or native:stdbscanclustering 33.

Why it was run on this data. DBSCAN finds dense groups of Health posts and separates noise 38.

What it found. Find point clusters on Health posts: Find point clusters: 2 layers saved: Find point clusters: Health posts (20 features); Find point clusters: cluster hulls (2 features) 3239. It reported result, count 20; result, noise 1; result, distance m 2,000; result, elapsed ms 1; result, min points 3; billing, cost 0.0504 39.

Findings

• Evidenced: Find point clusters on Health posts: Find point clusters: 2 layers saved: Find point clusters: Health posts (20 features); Find point clusters: cluster hulls (2 features) 3239.
• Evidenced: It reported result, count 20; result, noise 1; result, distance m 2,000; result, elapsed ms 1; result, min points 3; billing, cost 0.0504 39.

Tool gp_find_point_clusters; parameters {"method": "dbscan", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Health posts (7aed59a8)"}, "distance_m": 2000.0, "min_points": 3}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 40. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 40.

Why it was run on this data. 25 points in Shelters: a density surface shows where they concentrate 41.

What it found. Calculate density on Shelters: Calculate density: 1 layer saved: Calculate density: Shelters (90 features) 2842. It reported result, count 90; result, elapsed ms 4; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 0.8364 42.

Findings

• Evidenced: Calculate density on Shelters: Calculate density: 1 layer saved: Calculate density: Shelters (90 features) 2842.
• Evidenced: It reported result, count 90; result, elapsed ms 4; result, bandwidth m 2,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 0.8364 42.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Shelters (ee1b31b2)"}, "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 40. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 40.

Why it was run on this data. 320 points in Relief distributions: a density surface shows where they concentrate 43.

What it found. Calculate density on Relief distributions: Calculate density: 1 layer saved: Calculate density: Relief distributions (222 features) 1044. It reported result, count 222; result, elapsed ms 7; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 5,070 44.

Findings

• Evidenced: Calculate density on Relief distributions: Calculate density: 1 layer saved: Calculate density: Relief distributions (222 features) 1044.
• Evidenced: It reported result, count 222; result, elapsed ms 7; result, bandwidth m 1,000; result, cell size m 500; result, excluded null 0; result, max density per km2 5,070 44.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Relief distributions (83cbe688)"}, "bandwidth_m": 1000.0, "cell_size_m": 500.0, "weight_field": "households_served"}

Calculate density

What this analysis is. Calculate density: Kernel density per square kilometer on a grid 40. In ArcGIS it is Calculate Density or Kernel Density; in QGIS, native:heatmapkerneldensityestimation 40.

Why it was run on this data. 20 points in Health posts: a density surface shows where they concentrate 45.

What it found. The density was calculated using the gp_calculate_density tool 46, processing the Health posts layer 32 across 228 features 46.

Findings

• Evidenced: Calculate density on Health posts: Calculate density: 1 layer saved: Calculate density: Health posts (228 features) 3246.
• Evidenced: It reported result, count 228; result, elapsed ms 6; result, bandwidth m 5,000; result, cell size m 1,000; result, excluded null 0; result, max density per km2 6.578 46.

Tool gp_calculate_density; parameters {"kernel": "quartic", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Health posts (7aed59a8)"}, "bandwidth_m": 5000.0, "cell_size_m": 1000.0, "weight_field": "beds"}

Outliers

What this analysis is. Find outliers: Anselin local Moran’s I: HH, LL clusters and HL, LH outliers 47. In ArcGIS it is Find Outliers or Cluster and Outlier Analysis (Anselin Local Moran’s I) 47.

Why it was run on this data. Local Moran's I maps clusters and outliers of 'population' 48.

What it found. Outliers on Wards: Find outliers: 1 layer saved: Find outliers: Wards (20 features) 2949. It reported result, count 20; result, elapsed ms 4; result, permutations 199; result, excluded null 0; result, distance band m 1,735; billing, cost 0.0506 49.

Findings

• Evidenced: Outliers on Wards: Find outliers: 1 layer saved: Find outliers: Wards (20 features) 2949.
• Evidenced: It reported result, count 20; result, elapsed ms 4; result, permutations 199; result, excluded null 0; result, distance band m 1,735; billing, cost 0.0506 49.

Tool gp_outliers; parameters {"field": "population", "project": "affd1e20-248c-4f96-b09d-48d3027477be", "features": {"layer": "Wards (b338e26e)"}, "aggregation": "hexagon"}

Maps and charts

The run also made 20 map image(s) 5051525354555657585960616263646566676869 and 26 chart(s) 7071727374757677787980818283848586878889909192939495.

What the map shows. The map illustrates the results of an emerging hot spot analysis for relief distributions, categorizing areas based on detected patterns. The legend indicates that "Sporadic hot spot" areas are colored orange, while regions with "No pattern detected" are 53

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

Changes since the last run

This is the first report of this project.

Sources

1. 1Rendering: Chart: Timeline: events per day by dataset. 84 rows id 9bebc2a3-106c-4b25-9db2-00e0031eb8f3
2. 2Dataset: Damage assessments. vector, 2000 rows id f5a03720-aeb0-4ef8-aac1-6cee065b688a
3. 3Dataset: Road status. vector, 160 rows id f3c7c4b5-fd2f-4d56-9b57-5acf7a4d0374
4. 4Dataset: Relief distributions. vector, 320 rows id 27e9cd9e-cac7-4864-8dbe-27172247ad35
5. 5Dataset: Ward needs by day. table, 420 rows id b8f0859d-75f2-425c-a636-bd120d62d172
6. 6Document page: Situation report No. 4, page 1. 2026-09-14 id c492201b-e67e-4ae4-b97c-58a6ff283bc1:1
7. 7Catalog: 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
8. 8Plan: Hot spots of Relief distributions (the Start plan's candidate c_2bd4e1c1361d). 320 points: Getis-Ord Gi* tests whether the concentrations in Relief distributions are statistically significant. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_2bd4e1c1361d
9. 9Tool result: gp_hot_spots, step 0. Hot spot analysis: 1 layer saved: Hot spot analysis: Relief distributions (320 features). id 312e7d93-9021-497b-95d6-33778143cdfe:0
10. 10Layer: Relief distributions. 320 features id 83cbe688-753d-41e3-963d-5ac6a237060b
11. 11Plan: Hot spots of Water points (the Start plan's candidate c_0814d71ea2c0). 60 points: Getis-Ord Gi* tests whether the concentrations in Water points are statistically significant. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_0814d71ea2c0
12. 12Tool result: gp_hot_spots, step 1. Hot spot analysis: 1 layer saved: Hot spot analysis: Water points (20 features). id 312e7d93-9021-497b-95d6-33778143cdfe:1
13. 13Layer: Water points. 60 features id 2a061d8c-77a7-4d5f-9dfd-426a08595f03
14. 14Plan: Hot spots of Damage assessments (the Start plan's candidate c_5240b7fee4b7). 2000 points: Getis-Ord Gi* tests whether the concentrations in Damage assessments are statistically significant. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_5240b7fee4b7
15. 15Tool result: gp_hot_spots, step 2. Hot spot analysis: 1 layer saved: Hot spot analysis: Damage assessments (2000 features). id 312e7d93-9021-497b-95d6-33778143cdfe:2
16. 16Layer: Damage assessments. 2,000 features id 26bd99f3-3f2e-40d8-9e45-68835e95f651
17. 17Catalog: 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
18. 18Plan: Space time hot spots of Relief distributions (the Start plan's candidate c_a90b274940ea). Relief distributions carry dates in 'date': emerging hot spot analysis finds new, intensifying and fading hot spots per day. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_a90b274940ea
19. 19Tool result: gp_space_time_hot_spots, step 0. Emerging hot spots: 1 layer saved: Emerging hot spots: Relief distributions (54 features). id 6a511518-66af-49c2-9961-06cf7330178d:0
20. 20Plan: Space time hot spots of Damage assessments (the Start plan's candidate c_e9b3cd3966d9). Damage assessments carry dates in 'assessed_at': emerging hot spot analysis finds new, intensifying and fading hot spots per day. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_e9b3cd3966d9
21. 21Tool result: gp_space_time_hot_spots, step 1. Emerging hot spots: 1 layer saved: Emerging hot spots: Damage assessments (87 features). id 6a511518-66af-49c2-9961-06cf7330178d:1
22. 22Catalog: 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
23. 23Plan: Near repeat of Relief distributions (the Start plan's candidate c_d2196a8324bf). Near repeat analysis tests whether Relief distributions close in space also follow each other within 3 days. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_d2196a8324bf
24. 24Tool result: gp_near_repeat, step 2. Repeat and near repeat classification: 1 layer saved: Repeat and near repeat classification: Relief distributions (320 features). id 6a511518-66af-49c2-9961-06cf7330178d:2
25. 25Catalog: 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
26. 26Plan: Shelters per feature of Wards (the Start plan's candidate c_51fb9e92bbf5). Count Shelters inside each feature of Wards by type; the counts map as a choropleth (natural breaks, sequential colors). id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_51fb9e92bbf5
27. 27Tool result: gp_summarize_within, step 0. Summarize within: 1 layer saved: Summarize within: Wards (20 features). id 0979c79d-77b1-475d-a7be-e19a6678cb6f:0
28. 28Layer: Shelters. 25 features id ee1b31b2-fece-4bec-a323-47ac9bdb3e6e
29. 29Layer: Wards. 20 features id b338e26e-89d1-4de4-af0b-e9e1f797c2dd
30. 30Tool result: gp_summarize_within, step 1. Summarize within: 1 layer saved: Summarize within: Wards (20 features). id 0979c79d-77b1-475d-a7be-e19a6678cb6f:1
31. 31Tool result: gp_summarize_within, step 2. Summarize within: 1 layer saved: Summarize within: Wards (20 features). id 0979c79d-77b1-475d-a7be-e19a6678cb6f:2
32. 32Layer: Health posts. 20 features id 7aed59a8-fdc9-4dca-9da9-530aea39fdf7
33. 33Catalog: 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
34. 34Plan: Cluster points of Shelters (the Start plan's candidate c_f692379d6a4c). DBSCAN finds dense groups of Shelters and separates noise. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_f692379d6a4c
35. 35Tool result: gp_find_point_clusters, step 0. Find point clusters: 2 layers saved: Find point clusters: Shelters (25 features); Find point clusters: cluster hulls (1 feature). id e8b434c3-b356-440a-9abe-58d49d66cc97:0
36. 36Plan: Cluster points of Relief distributions (the Start plan's candidate c_349573557ecd). DBSCAN finds dense groups of Relief distributions and separates noise. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_349573557ecd
37. 37Tool result: gp_find_point_clusters, step 1. Find point clusters: 2 layers saved: Find point clusters: Relief distributions (320 features); Find point clusters: cluster hulls (21 features). id e8b434c3-b356-440a-9abe-58d49d66cc97:1
38. 38Plan: Cluster points of Health posts (the Start plan's candidate c_ff423f0ff11e). DBSCAN finds dense groups of Health posts and separates noise. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_ff423f0ff11e
39. 39Tool result: gp_find_point_clusters, step 2. Find point clusters: 2 layers saved: Find point clusters: Health posts (20 features); Find point clusters: cluster hulls (2 features). id e8b434c3-b356-440a-9abe-58d49d66cc97:2
40. 40Catalog: 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
41. 41Plan: Kernel density of Shelters (the Start plan's candidate c_af35bc95bb98). 25 points in Shelters: a density surface shows where they concentrate. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_af35bc95bb98
42. 42Tool result: gp_calculate_density, step 0. Calculate density: 1 layer saved: Calculate density: Shelters (90 features). id dd271da2-1bea-419c-8888-9b686b947d5a:0
43. 43Plan: Kernel density of Relief distributions (the Start plan's candidate c_346097776d28). 320 points in Relief distributions: a density surface shows where they concentrate. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_346097776d28
44. 44Tool result: gp_calculate_density, step 1. Calculate density: 1 layer saved: Calculate density: Relief distributions (222 features). id dd271da2-1bea-419c-8888-9b686b947d5a:1
45. 45Plan: Kernel density of Health posts (the Start plan's candidate c_18ec87c25f18). 20 points in Health posts: a density surface shows where they concentrate. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_18ec87c25f18
46. 46Tool result: gp_calculate_density, step 2. Calculate density: 1 layer saved: Calculate density: Health posts (228 features). id dd271da2-1bea-419c-8888-9b686b947d5a:2
47. 47Catalog: 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
48. 48Plan: Local morans i of Wards (the Start plan's candidate c_de4b9b365cb7). Local Moran's I maps clusters and outliers of 'population'. id 5a15d461-f147-4d9e-923e-64f1e88fcd39:c_de4b9b365cb7
49. 49Tool result: gp_outliers, step 0. Find outliers: 1 layer saved: Find outliers: Wards (20 features). id 82ada6bc-afff-4238-9ffd-a1a3201c03ab:0
50. 50Rendering: Map: Hot spot analysis: Relief distributions id 9390dd7d-eb52-4fef-b240-a9e39c60419a
51. 51Rendering: Map: Hot spot analysis: Water points id c442f0af-9418-4ebb-bfcb-511695a7dfa4
52. 52Rendering: Map: Hot spot analysis: Damage assessments id bf47cbcc-a7c2-4872-8e54-35d0ac4ff377
53. 53Rendering: Map: Emerging hot spots: Relief distributions id 25f4f54c-4c45-48cf-a569-65f18477854c
54. 54Rendering: Map: Emerging hot spots: Damage assessments id 6a4358fa-15b6-48b5-8954-acdaa394ce25
55. 55Rendering: Map: Repeat and near repeat classification: Relief distributions id 9939dbb6-e3f8-4379-ac14-09eaa503d896
56. 56Rendering: Map: Summarize within: Wards id 7e37ed6c-8912-44a3-bf3e-ee68208d7033
57. 57Rendering: Map: Summarize within: Wards id be38a33a-5f20-4c0b-8912-57fa7895a19e
58. 58Rendering: Map: Summarize within: Wards id b5d154ed-f63d-4d53-9377-fa605622ef5a
59. 59Rendering: Map: Find point clusters: Shelters id c9d2bd3b-593e-4289-8016-4c68db15e487
60. 60Rendering: Map: Find point clusters: cluster hulls id 6a3bb4df-0c93-47d3-ac5d-799d9cc55d97
61. 61Rendering: Map: Find point clusters: Relief distributions id 7e541131-6f4c-4bb1-b407-1446d58780c9
62. 62Rendering: Map: Find point clusters: cluster hulls id 38f01879-759a-4a13-835c-d8b021e78321
63. 63Rendering: Map: Find point clusters: Health posts id 3e2a4e84-8386-4533-beff-b52a92b8455a
64. 64Rendering: Map: Find point clusters: cluster hulls id 2e4605ac-3908-4fc6-9ef3-f84a99eee64a
65. 65Rendering: Map: Calculate density: Shelters id 4c369f35-f8c0-44c2-af51-a805408d3d2c
66. 66Rendering: Map: Calculate density: Relief distributions id 1fe838e1-34dc-4443-9b06-a8e4dfca95b1
67. 67Rendering: Map: Calculate density: Health posts id 757ffe50-e313-4da5-9be2-6dc7c3f38b2c
68. 68Rendering: Map: Wards by population id 74dd8da4-312d-43c5-85e7-bb2fb6224f53
69. 69Rendering: Map: Find outliers: Wards id 7bf81023-a30e-4346-ab12-ff2513b7947f
70. 70Rendering: Chart: Water points over time (litres_per_day). 7 rows id be19f3c9-7c18-4737-8ac1-c4b65ed62211
71. 71Rendering: Chart: Relief distributions over time (date). 76 rows id 2be61f8a-8348-49a8-8c78-1ea19f2626a3
72. 72Rendering: Chart: Ward needs by day over time (date). 126 rows id 3683d15b-0f5f-4034-99d3-c60bbd06867c
73. 73Rendering: Chart: Hot spot analysis: Relief distributions. 7 rows id 8a54330c-390f-456b-b3e3-6ba7256e4df3
74. 74Rendering: Chart: Hot spot analysis: Water points. 7 rows id beea2a8b-78df-4622-919a-df7a4d7bf1a9
75. 75Rendering: Chart: Hot spot analysis: Damage assessments. 30 rows id b6ec9de8-9bcf-49e9-ba5e-2e62a12c8ca5
76. 76Rendering: Chart: Emerging hot spots: Relief distributions. 7 rows id bde631a0-88da-4ec0-881b-6dc66cb32acc
77. 77Rendering: Chart: Emerging hot spots: Damage assessments. 8 rows id 5060f9d4-d1f0-4a03-b624-4e1aa484e60d
78. 78Rendering: Chart: Repeat and near repeat classification: Relief distributions. 76 rows id ad7da8c7-ed67-45e8-86ad-6f21ca29cbfd
79. 79Rendering: Chart: Summarize within: Wards. 6 rows id eb5740e9-38f8-42ba-9d54-b9bec7d81080
80. 80Rendering: Chart: Summarize within: Wards. 6 rows id 87ce8246-fadd-470c-b5a7-eb0629fc5ea3
81. 81Rendering: Chart: Summarize within: Wards. 6 rows id 190869f4-a9ae-4fed-a451-67bc4560549c
82. 82Rendering: Chart: Find point clusters: Shelters. 2 rows id 7be17c77-d4b9-4caf-8e86-10eb6d9d53e2
83. 83Rendering: Chart: Find point clusters: cluster hulls. 1 rows id 382198e8-9ac9-4b75-9e8e-ef34700f25cd
84. 84Rendering: Chart: Find point clusters: Relief distributions. 22 rows id bae50ece-0f0f-4399-87fd-3618eed224a5
85. 85Rendering: Chart: Find point clusters: cluster hulls. 21 rows id 7bff01e1-9aeb-448c-8822-197f969c18f3
86. 86Rendering: Chart: Find point clusters: Health posts. 3 rows id c1d4618b-97c3-444b-b7e7-445c2a95bc45
87. 87Rendering: Chart: Find point clusters: cluster hulls. 2 rows id 004552ff-ca8c-4bd5-9838-b11d434b85b3
88. 88Rendering: Chart: Calculate density: Shelters. 8 rows id 4716859b-53cb-4d5a-8441-47de226233ed
89. 89Rendering: Chart: Calculate density: Relief distributions. 9 rows id a66c3a3a-0d79-4a90-8ba8-25684b82f78c
90. 90Rendering: Chart: Calculate density: Health posts. 9 rows id 6d33660c-fb55-4ce5-9407-14cede82f1f7
91. 91Rendering: Chart: Find outliers: Wards. 20 rows id 2c943aea-f0e1-4d2e-9a74-b1f3a68cccaf
92. 92Rendering: Chart: Find point clusters: Relief distributions over time. 76 rows id ae09526f-b719-40fa-9352-7253703419e6
93. 93Rendering: Chart: Repeat and near repeat classification: Relief distributions over time. 76 rows id d25012cc-f981-414f-b270-f5188a23b23a
94. 94Rendering: Chart: Hot spot analysis: Damage assessments over time. 126 rows id dddbf0f7-9186-4260-86f0-90b42b3a2b7c
95. 95Rendering: Chart: Hot spot analysis: Relief distributions over time. 76 rows id 75a753b2-7ec0-435d-93af-df87c5a2fdf9
96. 96Dataset: Wards. vector, 20 rows id cd24d135-3a85-486d-b85d-aad5c710434a
97. 97Dataset: Shelters. vector, 25 rows id 1a4488fc-1d07-4261-9f0e-01b2b1f2dca2
98. 98Dataset: Water points. vector, 60 rows id c5cb6996-b665-4741-91b9-eb2b235d60b3
99. 99Dataset: Health posts. vector, 20 rows id 8e654bff-294d-4ad6-be89-593de050aebf
100. 100Dataset: Shelter register. table, 25 rows id 71a97a94-2ec4-4a02-b6d8-66a6192053f9
101. 101Dataset: Situation report No. 4. document, ? rows id 919b6864-e3dc-42c9-b9dc-71340dbf1f59
102. 102Record: Sample: Disaster response, Kathmandu id affd1e20-248c-4f96-b09d-48d3027477be
103. 103Layer: Hot spot analysis: Relief distributions. 320 features id 9e5f578c-630b-43eb-8ebe-8545f6fca7c2
104. 104Layer: Hot spot analysis: Water points. 20 features id bb294769-aa54-4b53-b8ab-a11a9895ae52
105. 105Layer: Hot spot analysis: Damage assessments. 2,000 features id 363b8c44-c958-4210-beb4-e032340f3591
106. 106Layer: Emerging hot spots: Relief distributions. 54 features id 6f8363b7-e1a7-432e-b17e-f0e1a5b04c12
107. 107Layer: Emerging hot spots: Damage assessments. 87 features id 26abf030-7544-4caa-a068-87e5fbf6fc76
108. 108Layer: Repeat and near repeat classification: Relief distributions. 320 features id 176d38bd-d5dd-4e59-bcf4-f4f67c442f05
109. 109Layer: Summarize within: Wards. 20 features id 59ed06c8-19f7-4cdc-bf0a-93f1af3df0bb
110. 110Layer: Summarize within: Wards. 20 features id 60eb7f4c-9283-4a68-b158-7fe6014e035b
111. 111Layer: Summarize within: Wards. 20 features id d2a68fd2-e432-4366-8c8c-79cfc7fbd916
112. 112Layer: Find point clusters: Shelters. 25 features id db7ac08f-e31a-41c7-b06d-b7bc5b1ddae1
113. 113Layer: Find point clusters: cluster hulls. 1 features id 1a61db01-7dbf-4a4b-a14e-619c2d2130e2
114. 114Layer: Find point clusters: Relief distributions. 320 features id 80a3b728-2f6b-44e4-962f-eac228b32051
115. 115Layer: Find point clusters: cluster hulls. 21 features id ab1e3ae7-0d91-4e6a-8a58-5afda7d572e8
116. 116Layer: Find point clusters: Health posts. 20 features id f387abca-2c2c-4945-9f86-d310b94a5d2e
117. 117Layer: Find point clusters: cluster hulls. 2 features id 0ee12d31-db24-4ae2-ba77-bea3bd72c010
118. 118Layer: Calculate density: Shelters. 90 features id 70bc6150-3af3-4110-ba8a-60400c37bf40
119. 119Layer: Calculate density: Relief distributions. 222 features id 3d315b62-8343-4e06-9cb9-c92f6b2c53e0
120. 120Layer: Calculate density: Health posts. 228 features id dc129652-f329-497f-8a85-b1a55c7c00b4
121. 121Document: Situation report No. 4 id c492201b-e67e-4ae4-b97c-58a6ff283bc1
122. 122Layer: Find outliers: Wards. 20 features id a6dabb92-ab09-424d-95b6-28b66295aba0