Data and code used in the article "A deep learning method for predicting soil moisture in unsaturated areas based on physical constraints"

Data and code used in the article "A deep learning method for predicting soil moisture in unsaturated areas based on physical constraints", specifically included are water content data from 55 in situ observations for the years 2018-2020 (observation frequency of 5min or 10min), and example code for implementing LSTM and PIDL using python (mainly the tensorflow library).These data can help the reader to better understand and replicate our research. All the data and code has been uploaded. The paper has been published in Water Resources Research, and the citation is: Wang, Y., Wang, W., Ma, Z., Zhao, M., Li, W., Hou, X., et al. (2023). A deep learning approach based on physical constraints for predicting soil moisture in unsaturated zones. Water Resources Research,59, e2023WR035194. https://doi.org/10.1029/2023WR035194本论文《基于物理约束的深度学习方法预测非饱和区土壤含水率》（A deep learning method for predicting soil moisture in unsaturated areas based on physical constraints）所配套使用的数据集与代码，具体包含2018-2020年间55个原位观测点的土壤含水率数据，观测频率为5分钟或10分钟；同时附带基于Python（主要使用TensorFlow库）实现长短期记忆网络（Long Short-Term Memory, LSTM）与物理约束深度学习（Physics-Informed Deep Learning, PIDL）的示例代码。本数据集与代码可帮助读者更好地理解并复现本项研究，所有数据与代码均已上传。 本论文已发表于《水资源研究》（Water Resources Research），引用信息如下： Wang, Y., Wang, W., Ma, Z., Zhao, M., Li, W., Hou, X., 等. (2023). 基于物理约束的深度学习方法预测非饱和区土壤含水率. Water Resources Research, 59, e2023WR035194. https://doi.org/10.1029/2023WR035194