Knowledge-guided graph machine learning improves corn yield mapping in the U.S. Midwest

作者：Jie Yang, Licheng Liu, Qi Yang, Xiaowei Jia, Bin Peng, Kaiyu Guan, Zhenong Jin · 发表于：Remote Sensing of Environment · 年份：2026 · DOI：10.1016/j.rse.2026.115287 · 被引用次数：5 · 研究领域：Soil Geostatistics and Mapping、Remote Sensing in Agriculture、Smart Agriculture and AI

Accurate large-scale crop yield mapping is crucial for understanding how weather and climate variability affect food security. While temporal deep learning models have achieved notable success in extracting time-series features for yield mapping, they often struggle to model spatial dependencies, such as yield spatial autocorrelations and the influence of time-invariant variables (e.g., soil properties and topography). To address this limitation, we propose KGML-Graph, a knowledge-guided graph machine learning framework that integrates spatial learning with temporal structures to explicitly capture these underutilized spatial dependencies. We incorporate knowledge-guided edge weights, derived from historical yield correlations, into the graph structure to identify patterns among counties with similar yield dynamics and enhance model training. The framework was evaluated using data from 627 counties across the U.S. Corn Belt from 2000 to 2020, benchmarking against Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Temporal Convolutional Neural Network (TempCNN). Results show that KGML-Graph outperformed benchmarks in cross-year testing, reducing RMSE by at least 10.8%, and improved R 2 by at least 9.3% in temporal extrapolation during 2017–2020. Furthermore, it demonstrated superior spatial transferability by maintaining accuracy in unseen regions and significantly reducing spatial autocorrelation in estimation residuals. Under extreme climatic conditions, the mode...