AcuGIS
/
AR1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
AR1/docs/analysis-tools/kde.md

1.4 KiB
Raw Blame History

Kernel Density Estimation (KDE)

Generate density surfaces from point data using kernel density estimation.

Overview

KDE creates a continuous density surface from point data, showing where points are concentrated. Higher values indicate greater point density.

Inputs

  • Dataset: Point dataset
  • Bandwidth: Smoothing parameter (default: auto-calculated)
  • Cell Size: Output raster cell size (default: auto-calculated)
  • Weight Field (optional): Field to weight points

Outputs

Raster dataset containing:

  • Density values for each cell
  • Higher values indicate greater point density
  • Proper spatial reference

Algorithm

  1. Calculate optimal bandwidth (if not specified)
  2. Create output raster grid
  3. For each cell, calculate kernel-weighted sum of nearby points
  4. Store density values in raster

Example

{
  "dataset_id": 123,
  "bandwidth": 1000,
  "cell_size": 100
}

Background Jobs

This analysis runs as a background job.

Use Cases

  • Population density mapping
  • Crime hotspot visualization
  • Species distribution modeling
  • Event density analysis

Notes

  • Bandwidth controls smoothing (larger = smoother)
  • Cell size controls output resolution
  • Weight field allows importance weighting
  • Results are sensitive to bandwidth selection

Related Documentation