Documents
Detect and classify cropland changes from before/after NDVI rasters. Identifies suspected construction, water, forest, and bare soil changes and generates compliance investigation materials. Use when the user wants to check farmland for unauthorized changes, monitor cropland conversion, or generate compliance reports.
Detect and classify cropland changes from before/after NDVI rasters. Identifies suspected construction, water, forest, and bare soil changes and generates compliance investigation materials. Use when the user wants to check farmland for unauthorized changes, monitor cropland conversion, or generate compliance reports.
Detects and classifies cropland changes from multi-temporal NDVI rasters.
python scripts/cropland_change_compliance.py --before-ndvi before.tif --after-ndvi after.tif
python scripts/cropland_change_compliance.py --before-ndvi b.tif --after-ndvi a.tif --ndvi-threshold 0.2
| File | Description |
|---|---|
report.html | Compliance report |
compliance-report.json | Detailed results |
suspected_changes.geojson | Suspected change findings |
output-manifest.json | Machine-readable manifest |
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Argument error |
| 7 | Processing failure |
| Flag | Type | Default | Required | Description |
|---|---|---|---|---|
--before-ndvi | path | None | (yes unless --synthetic) | Path to before-period NDVI raster (GeoTIFF) |
--after-ndvi | path | None | (yes unless --synthetic) | Path to after-period NDVI raster (GeoTIFF) |
--ndvi-threshold | float | 0.15 | no | Minimum |
--rules | path | None | no | Custom compliance rules JSON |
--synthetic | flag | False | no | Run with synthetic demo data (no real inputs needed) |
--output-dir / -o | path | compliance-output | no | Output directory |
本 skill 可自动从 Microsoft Planetary Computer 下载数据 (无需 API key):
python cropland_change_compliance.py --bbox 116,39,117,40 --date-range 2024-06-01,2024-06-30 --output-dir
--bbox W,S,E,N: WGS-84 边界框 (西, 南, 东, 北)--date-range START,END: 日期范围 (YYYY-MM-DD,YYYY-MM-DD)--aoi-file : 替代 --bbox 的 GeoJSON 多边形--cache-dir : 缓存目录 (默认 ~/.geoskill_cache)当用户只给 --bbox + --date-range (没有 --image) 时，skill 自动下载数据。
当用户给 --image 时，走原文件路径 (向后兼容)。
Multi-year cropland abandonment detection using NDVI time series. Identifies suspected abandoned cropland based on consecutive years without cultivation signals. Use when screening for abandoned fields, generating field verification lists, or monitoring cultivation continuity.
Assess crop health from NDVI time series. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.
高分辨率作物识别叠加申报地块做差异检测，核查补贴合规性。Verifies subsidy compliance by overlaying high-resolution crop classification on declared parcels for difference detection.
Identify major crop types from multi-temporal optical/SAR imagery using phenological features. Produces pixel/field-level classification, area statistics, and confidence maps. Use when mapping crop distributions, estimating planted areas, or generating agricultural intelligence from remote sensing data.
Topology-aware cadastral parcel change detection between two epochs. Identifies new, deleted, expanded, reduced, split, and merged parcels from cadastral vector data (宗地/地块/调查图斑). Use when comparing two epochs of land parcels, auditing boundary changes, or generating cadastral change ledgers.
Monitor wetland extent, inundation frequency, and land cover transitions to identify degradation, recovery, and human encroachment. Use when the user wants to track wetland changes over time, assess wetland health, or detect conversion of wetlands to other land covers.