Documents
Assess crop health from NDVI time series. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.
Assess crop health from NDVI time series. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.
Assess crop health from NDVI time series.
python scripts/crop_condition_monitor.py --ndvi ndvi1.tif ndvi2.tif ndvi3.tif
python scripts/crop_condition_monitor.py --ndvi ndvi1.tif ndvi2.tif --dates 2024-04-01,2024-05-01
python scripts/crop_condition_monitor.py --ndvi ndvi1.tif ndvi2.tif --output-dir my_output
| Argument | Required | Default | Description |
|---|---|---|---|
--ndvi | Yes | — | One or more NDVI rasters (chronological order, same grid) |
--dates | No | — | Optional comma-separated acquisition dates matching --ndvi files (ISO YYYY-MM-DD) |
--output-dir, -o | No | crop-output | Directory to write outputs |
| File | Description |
|---|---|
crop-report.json | Machine-readable crop condition stats (mean NDVI, anomaly area) |
report.html | Human-readable HTML report |
output-manifest.json | Run metadata + result summary |
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Argument error |
| 7 | Processing failure |
When --bbox (or --aoi-file) and --date-range are provided, this skill
auto-downloads a small set of Sentinel-2 L2A (sentinel-2-l2a) visual
previews from the Microsoft Planetary Computer STAC catalog (no API key
required) and uses them as the multi-temporal NDVI stack.
The downloaded files are written to /downloaded/ and the
downstream monitor_crop analysis runs on them. The output-manifest.json
records data_source / collection / bbox / date_range / fetched_at for
traceability.
python scripts/crop_condition_monitor.py \
--bbox 116.4,39.6,116.6,39.8 \
--date-range 2024-06-01,2024-06-30 \
--output-dir my_output
Monitor forest canopy vitality decline, drought stress, pest damage, or wind throw from multi-temporal spectral indices. Distinguishes short-term fluctuations from persistent decline using historical baselines, persistence state machines, and climate attribution. Use when assessing forest health, detecting anomalies, or planning field sampling.
Fuses crop distribution, hazard intensity, and NDVI anomaly to estimate agricultural disaster impact. Classifies damage severity (mild/moderate/severe) and generates field-level damage maps. Use when assessing flood/drought/heat impact on crops.
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.
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.
Detect forest disturbance from multi-temporal NDVI. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.
融合 NDVI/NDRE/LST 多指数健康评分、历史偏差异常检测与空间聚类，输出作物健康等级栅格。Fuses NDVI/NDRE/LST into a health score with historical anomaly detection and spatial clustering.