冠层峰值检测加分水岭分割统计株数，结合经验模型估算产量。Counts plants via canopy peak detection plus watershed segmentation and estimates yield with an empirical model.
Coding
geoskill-crop-rotation-detection
Try it多年度分类编码轮作序列，识别轮作模式并统计频率。Detects crop rotation by encoding multi-year classifications into sequences, recognizing patterns and counting frequencies.
What it does
多年度分类编码轮作序列，识别轮作模式并统计频率。Detects crop rotation by encoding multi-year classifications into sequences, recognizing patterns and counting frequencies.
The skill document
作物轮作检测 | Crop Rotation Detection
(Fill in 2-3 paragraphs of Chinese introduction here: functionality, application scenarios, core algorithm.)
Dependencies / 依赖
pip install 'numpy' 'rasterio'
Usage / 使用方法
Basic usage
python geoskill-crop-rotation-detection.py --bbox 116.0 39.0 117.0 40.0 [other options]
Example 1 (synthetic data, offline)
python geoskill-crop-rotation-detection.py --bbox 116.0 39.0 117.0 40.0 --synthetic --output-dir ./out
Examples 2-5
(Add at least 4 real-world usage examples.)
Output / 输出
| File | Format | Description |
|---|---|---|
result.tif | GeoTIFF | Main output |
output-manifest.json | JSON | Run manifest |
Data Source / 数据源 / Source
(Describe the data source: free satellite data / local input / synthetic.)
Privacy / 隐私声明 / Privacy
- Runs offline by default;
--syntheticmode requires no network at all. - All processing is performed locally; user data is never uploaded.
License / License
MIT
name: geoskill-crop-rotation-detection description: '多年度分类编码轮作序列，识别轮作模式并统计频率。Detects crop rotation by encoding multi-year classifications into sequences, recognizing patterns and counting frequencies.'
作物轮作检测 | Crop Rotation Detection
（在此填写 2-3 段中文介绍：功能、应用场景、核心算法。）
依赖
pip install 'numpy' 'rasterio'
使用方法
基本用法
python geoskill-crop-rotation-detection.py --bbox 116.0 39.0 117.0 40.0 [其他参数]
示例 1（合成数据，离线）
python geoskill-crop-rotation-detection.py --bbox 116.0 39.0 117.0 40.0 --synthetic --output-dir ./out
示例 2-5
（补充至少 4 个真实用法示例。）
输出
| 文件 | 格式 | 说明 |
|---|---|---|
result.tif | GeoTIFF | 主产物 |
output-manifest.json | JSON | 运行清单 |
数据源 / Source
（说明数据来源：免费卫星数据 / 本地输入 / 合成。）
隐私声明 / Privacy
- 默认离线运行，
--synthetic模式完全无网络。 - 所有处理在本地完成，不上传用户数据。
License
MIT
Related skills
基于多时相 SAR 后向散射时序的农作物分类：逐像元时序/统计/物候特征 + 随机森林。SAR crop classification from multi-temporal backscatter time series using per-pixel phenological features and Random Forest. 合成模式生成水稻/小麦/玉米三类时序真值并评估精度，输出分类 GeoTIFF + 面积统计 + 混淆矩阵 JSON。
1 installs
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.
1 installs
基于 CHM 峰值检测与模板匹配统计果树株数与冠幅。Counts orchard trees and crown widths from CHM peak detection and template matching.
1 installs
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.
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.
1 installs