Identifying long-term winter wheat planting areas using decision tree-derived ensemble learning models and multi-source data

To provide high-quality data support for agricultural policy-making and grain subsidies, this study presents an efficient method for extracting winter wheat planting areas using Landsat series satellite imagery and monthly maximum normalized difference vegetation index (NDVI) stacks. Three ensemble decision-tree algorithms—Random Forest, XGBoost, and CatBoost—were compared. The best model achieved 91% cross-validation accuracy, with a strong statistical validation accuracy in terms of its municipal-scale validation R2 = 0.91 (MAE = 49,650 hm2; RMSE = 64,440 hm²) and county-scale R2 = 0.84 (MAE = 7125 hm2, RMSE = 9875 hm2). A spatiotemporal analysis revealed a notable decline in winter wheat area in Shandong Province, which was concentrated in its western and southern regions. The cultivation centre shifted westwards, and then northwards, and the landscape patterns transitioned from large, aggregated patches to small, dispersed patches. This trend of decreasing intensification level for the winter wheat planting regions poses challenges for achieving water-saving and intensive land management goals. These trends are influenced by climate, topography, and socioeconomic factors, as well as agricultural policies. The proposed method offers robust support for attaining large-scale crop monitoring and sustainable agricultural management. • Ensemble models (RF, XGBoost, and CatBoost) accurately mapped winter wheat planting areas.• An optimized sampling strategy effectively reduced the reliance on annual field data collection schemes.• A decreasing intensification level was detected for winter wheat planting regions.• The spatiotemporal dynamics and key factors influencing wheat cultivation were captured. Ensemble models (RF, XGBoost, and CatBoost) accurately mapped winter wheat planting areas. An optimized sampling strategy effectively reduced the reliance on annual field data collection schemes. A decreasing intensification level was detected for winter wheat planting regions. The spatiotemporal dynamics and key factors influencing wheat cultivation were captured.

为给农业政策制定与粮食补贴提供高质量数据支撑，本研究提出一种利用Landsat系列卫星影像与月度最大值归一化差分植被指数（Normalized Difference Vegetation Index，NDVI）堆叠数据提取冬小麦种植面积的高效方法。本研究对三种集成决策树算法——随机森林（Random Forest）、XGBoost及CatBoost——进行了对比。最优模型的交叉验证准确率达91%，在市级尺度验证中展现出优异的统计验证性能：市级验证R²=0.91（平均绝对误差（Mean Absolute Error，MAE）=49650 公顷，均方根误差（Root Mean Square Error，RMSE）=64440 公顷），县级验证R²=0.84（MAE=7125 公顷，RMSE=9875 公顷）。时空分析显示，山东省冬小麦种植面积显著下降，且集中分布于鲁西与鲁南地区；种植重心先西移、再北移，景观格局由大型连片斑块逐步向小型分散斑块转变。冬小麦种植区集约化水平持续降低的趋势，对实现节水与土地集约管理目标构成挑战。该趋势受到气候、地形、社会经济因素与农业政策的共同影响。本研究提出的方法可为大规模作物监测与可持续农业管理提供坚实支撑。
• 集成模型（随机森林（Random Forest）、XGBoost、CatBoost）可精准绘制冬小麦种植面积分布
• 优化后的采样策略有效降低了对年度野外数据采集方案的依赖
• 检测到冬小麦种植区集约化水平呈下降趋势
• 揭示了冬小麦种植的时空动态特征及其关键影响因素
• 集成模型（随机森林（Random Forest）、XGBoost、CatBoost）可精准绘制冬小麦种植面积分布
• 优化后的采样策略有效降低了对年度野外数据采集方案的依赖
• 检测到冬小麦种植区集约化水平呈下降趋势
• 揭示了冬小麦种植的时空动态特征及其关键影响因素