Description
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.
Cite this work
Researchers should cite this work as follows:
- Xuan Xi; Qianlai Zhuang; Liu, X. (2024). A Hybrid Physics-Guided Deep Learning Modeling Framework for Predicting Surface Soil Moisture. (Version 2.0). Purdue University Research Repository. doi:10.4231/SBB0-V865
Tags
Notes
In this version, we mainly made two changes.
1. We calibrated the process-based (PB) model and updated the PB outputs. We added the surface soil moisture (SSM) simulations from the calibrated PB model into the data files.
2. We removed results for one site with soil types that were not included in this study and updated our data and codes correspondingly.