A comprehensive study of deep learning for soil moisture prediction

• Published in: Hydrology and earth system sciences Vol. 28; no. 4; pp. 917 - 943
• Main Authors: Wang, Yanling, Shi, Liangsheng, Hu, Yaan, Hu, Xiaolong, Song, Wenxiang, Wang, Lijun
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 27.02.2024; Copernicus Publications
• Subjects: Additives; Agricultural production; Analysis; Boundary conditions; Correlation analysis; Deep learning; Design; Embedding; Feature extraction; Hybrid structures; Hydrologic cycle; Hydrological cycle; Hydrology; Long short-term memory; Machine learning; Moisture content; Network design; Neural networks; Nonlinear systems; Nonlinearity; Performance evaluation; Precipitation; Predictions; Radiation; Soil; Soil dynamics; Soil moisture; Soil moisture dynamics; Soil texture; Soil water; Time series; Water transport

Soil moisture plays a crucial role in the hydrological cycle, but accurately predicting soil moisture presents challenges due to the nonlinearity of soil water transport and the variability of boundary conditions. Deep learning has emerged as a promising approach for simulating soil moisture dynamic...