DeepCropMapping: A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping

• Published in: Remote sensing of environment Vol. 247; p. 111946
• Main Authors: Xu, Jinfan, Zhu, Yue, Zhong, Renhai, Lin, Zhixian, Xu, Jialu, Jiang, Hao, Huang, Jingfeng, Li, Haifeng, Lin, Tao
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 15.09.2020; Elsevier BV
• Subjects: Agricultural land; Agricultural production; agricultural productivity; Agriculture; Algorithms; Classification; Computer applications; confidence interval; Confidence intervals; Corn; Corn belt; Corn Belt region; Cover crops; Crop mapping; Crop production; cropland; Crops; Decision trees; Deep learning; environment; Growing season; Landsat; Landsat satellites; Learning algorithms; Long short-term memory; Machine learning; Mapping; Model accuracy; Model generalization; Model testing; Multilayer perceptrons; neural networks; Remote sensing; Satellite observation; Soybeans; Spatial analysis; Spatial memory; Time series; time series analysis; Transformers; uncertainty; Corn Belt region; Deep learning; Long short-term memory; Model generalization; Crop mapping; Remote sensing; Time series

Accurate crop mapping provides important and timely information for decision support on the estimation of crop production at large scale. Most existing crop-specific cover products based on remote sensing data and machine learning algorithms cannot serve large agriculture production areas as a resul...