A Hybrid Runoff Forecasting Framework Integrating Hydrological Physics and Data-Driven Models
Open Access
- 11 December 2025
- journal article
- research article
- Published by MDPI AG in Sustainability
- Vol. 17 (24) , 11120
Abstract
Runoff forecasting is essential for flood control, disaster mitigation, and sustainable water resources management. However, runoff processes are highly nonlinear and uncertain due to multiple interacting meteorological and underlying surface factors. Current models can be divided into process-driven and data-driven types. The former offers clear physical interpretability but involves complex calibration and simplifications, while the latter captures nonlinear relationships effectively but lacks physical consistency. To integrate their strengths, this study constructs process-based models and data-driven models, and proposes two hybrid strategies: (1) incorporating intermediate variables from physical models, such as soil moisture and runoff yield, as additional features for data-driven models, and (2) embedding physics-based constraints and synthetic data into loss functions. Using the Songxi River Basin as a case study, results show that both hybrid strategies significantly outperform standalone models. SHapley Additive exPlanations (SHAP)-based interpretability analysis further reveals the contribution mechanisms of key physical variables. This study demonstrates that coupling physical processes with data-driven learning effectively enhances runoff forecasting accuracy and offers a promising paradigm to support sustainable watershed management, climate-resilient water regulation, and flood risk reduction.Keywords
Funding Information
- China Huaneng Group (HNKJ22-H87)
This publication has 45 references indexed in Scilit:
- Improving flood hazard susceptibility assessment by integrating hydrodynamic modeling with remote sensing and ensemble machine learningNatural Hazards, 2025
- Sensitivity analysis of a 2D flood inundation model. A case study of Tous DamEnvironmental Earth Sciences, 2024
- A review of deep learning and machine learning techniques for hydrological inflow forecastingEnvironment, Development and Sustainability, 2023
- Study on Water Quality Prediction of Urban Reservoir by Coupled CEEMDAN Decomposition and LSTM Neural Network ModelWater Resources Management, 2022
- Effect of GCM credibility on water resource system robustness under climate change based on decision scalingAdvances in Water Resources, 2021
- Improving the flood forecasting capability of the Xinanjiang model for small- and medium-sized ungauged catchments in South ChinaNatural Hazards, 2021
- Integrating satellite and climate data to predict wheat yield in Australia using machine learning approachesAgricultural and Forest Meteorology, 2019
- Estimating the daily pollen concentration in the atmosphere using machine learning and NEXRAD weather radar dataEnvironmental Monitoring and Assessment, 2019
- Insurance risk assessment in the face of climate change: Integrating data science and statisticsWIREs Computational Statistics, 2019
- Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of ChinaAgricultural and Forest Meteorology, 2018