# change-detection

> Claude/Codex skill by [@muend](https://omgskills.com/library/muend/index.md) · 35 stars · Updated 2026-10-17

Change analysis, once the observations are comparable. Not for cases whose blocker is comparability itself: mixed sensors, product levels or processing baselines to remote-sensing-analysis, undocumented vertical datums to point-cloud-lidar, multi-decade archive trends over large areas to google-earth-engine. Matching product level does not prove comparability. Otherwise invoke for what, where or how much changed: two-scene comparison, deforestation, urban growth, disaster damage, parcel-change audits, bi-temporal differencing, post-classification comparison, adjusted area, break detection in a series in hand (BFAST/LandTrendr/CCDC). Seasonal mismatch is this skill's own confounder; a documented datum with a stated accuracy budget is settled comparability. Keep both.

Tags: agent-skills, ai, ai-agents, claude-code, codex, geoai, geospatial, gis, github-copilot, google-earth-engine, lidar, machine-learning, postgis, remote-sensing, spatial-analysis, spatial-data-science

## Install

```sh
git clone https://github.com/muend/geoai-skills /tmp/geoai-skills && ln -s /tmp/geoai-skills/skills/change-detection ~/.claude/skills/change-detection
```

## From README

Change Detection & Spatio-temporal Analysis Purpose: separate real surface change from the four great impostors — misregistration, radiometric drift, phenology, and classification error. Every method below exists to control one of them; skipping the controls produces confident maps of nothing. Preconditions (where change detection is won or lost) Preconditions 1 and 2 are checked here but established elsewhere. When either fails, the owning skill leads and this skill resumes once comparable observations exist. Precondition 3 is this skill's own problem and is never a reason to route away. Co-registration: sub-pixel alignment between dates (AROSICS or manual tie-points). Half a pixel of shift creates edge-shaped phantom change everywhere. Verify: flicker-compare crisp features. For elevation surfaces or point clouds, vertical datum agreement, co-registration and the vertical-accuracy budget belong to point-cloud-lidar — a datum offset is not subsidence.

## Links

- HTML page: https://omgskills.com/library/muend/geoai-skills/skills/change-detection/
- GitHub: https://github.com/muend/geoai-skills
- Author: [@muend](https://omgskills.com/library/muend/index.md)

## More from this repo

- [arcgis-pro-automation](https://omgskills.com/library/muend/geoai-skills/skills/arcgis-pro-automation/index.md) — Automate controlled local ArcGIS Pro and ArcPy workflows through arcgis-mcp-bridge: inspect .aprx projects and file...
   - [@muend](https://omgskills.com/library/muend/index.md) · 35 stars
- [cartography-geoviz](https://omgskills.com/library/muend/geoai-skills/skills/cartography-geoviz/index.md) — Always invoke before answering any request to create, compare, design, or review a user-facing map, even if the request...
   - [@muend](https://omgskills.com/library/muend/index.md) · 35 stars
- [geo-data-engineering](https://omgskills.com/library/muend/geoai-skills/skills/geo-data-engineering/index.md) — Always invoke when geospatial data must be acquired, prepared, repaired, scaled, or moved through a repeatable pipeline.
   - [@muend](https://omgskills.com/library/muend/index.md) · 35 stars