A Hybrid Physics-Guided Deep Learning Modeling Framework for Predicting Surface Soil Moisture

<p>Accurate prediction of surface soil moisture (SSM) is vital for understanding the complex interactions between terrestrial and atmospheric processes, with significant implications for weather forecasting, agriculture, and water management. In this study, we introduce an innovative Physics-Guided Deep Learning (PGDL) model by integrating the process-based insights of the Terrestrial Ecosystem Model (TEM) with the dynamic predictive capabilities of Long Short-Term Memory (LSTM) networks to improve the SSM prediction. The PGDL model leverages the complementary strengths of the deterministic framework of TEM and the data-driven prowess of LSTM, providing predictions that are deeply rooted in physical processes while capturing complex patterns in data. Our analysis, conducted across carefully selected sites within unique vegetation types over the continental United States, evaluates the PGDL model against traditional process-based (PB) models and deep-learning (DL) approaches. Results demonstrate the PGDL model is superior in capturing SSM dynamics, with significantly lower RMSE and higher R² values compared to PB and DL predictions. Our results show that the PGDL modeling framework improves the predictive accuracy of DL models and the physical interpretability of PB models, which can serve as a robust tool to predict SSM dynamics.</p>

准确预测表层土壤湿度（surface soil moisture, SSM）对于理解陆地与大气过程间的复杂交互至关重要，其在天气预报、农业及水资源管理领域均具有重要意义。本研究提出一种创新的物理引导深度学习（Physics-Guided Deep Learning, PGDL）模型，将陆地生态系统模型（Terrestrial Ecosystem Model, TEM）的过程驱动机理与长短期记忆（Long Short-Term Memory, LSTM）网络的动态预测能力相结合，以提升SSM的预测性能。该PGDL模型充分利用了TEM的确定性框架与LSTM的数据驱动优势二者的互补特性，所生成的预测结果既根植于物理过程，又能捕捉数据中的复杂模式。我们在美国本土针对经精心遴选的不同植被类型站点开展分析，将PGDL模型与传统基于过程（process-based, PB）模型及深度学习（deep-learning, DL）方法进行对比评估。实验结果表明，PGDL模型在捕捉SSM动态变化方面表现更优，相较于PB及DL预测模型，其均方根误差（RMSE）显著更低，决定系数（R²）更高。本研究结果显示，PGDL建模框架同时提升了深度学习模型的预测精度与基于过程模型的物理可解释性，可作为一种可靠工具用于预测SSM的动态变化。

搜集汇总

背景与挑战

背景概述

该数据集介绍了一种用于预测表层土壤湿度的物理引导深度学习混合建模框架，通过结合基于过程的陆地生态系统模型和长短期记忆网络，提高了预测准确性和物理可解释性。评估结果显示，该模型在多个美国站点上优于传统方法，具有更低的误差和更高的拟合度。