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
• DOI: 10.5194/hess-28-917-2024
• ISSN: 1607-7938; 1027-5606

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 dynamics. In this study, we explore 10 different network structures to uncover their data utilization mechanisms and to maximize the potential of deep learning for soil moisture prediction, including three basic feature extractors and seven diverse hybrid structures, six of which are applied to soil moisture prediction for the first time. We compare the predictive abilities and computational costs of the models across different soil textures and depths systematically. Furthermore, we exploit the interpretability of the models to gain insights into their workings and attempt to advance our understanding of deep learning in soil moisture dynamics. For soil moisture forecasting, our results demonstrate that the temporal modeling capability of long short-term memory (LSTM) is well suited. Furthermore, the improved accuracy achieved by feature attention LSTM (FA-LSTM) and the generative-adversarial-network-based LSTM (GAN-LSTM), along with the Shapley (SHAP) additive explanations analysis, help us discover the effectiveness of attention mechanisms and the benefits of adversarial training in feature extraction. These findings provide effective network design principles. The Shapley values also reveal varying data leveraging approaches among different models. The t-distributed stochastic neighbor embedding (t-SNE) visualization illustrates differences in encoded features across models. In summary, our comprehensive study provides insights into soil moisture prediction and highlights the importance of the appropriate model design for specific soil moisture prediction tasks. We also hope this work serves as a reference for deep learning studies in other hydrology problems. The codes of 3 machine learning and 10 deep learning models are open source.