Approaches for enhancing extrapolability in process-based and data-driven models in hydrology

TL;DR

This paper reviews methods to improve the ability of hydrological models, both process-based and data-driven, to accurately predict in conditions outside their training data, emphasizing techniques like transfer learning and domain adaptation.

Contribution

It provides a comprehensive comparison of strategies to assess and enhance the extrapolability of hydrological models, highlighting recent advances and future prospects.

Findings

Deep learning and transfer learning improve model extrapolation.

Similarity-based methods help evaluate ungauged region predictions.

Interdisciplinary approaches strengthen model reliability.

Abstract

The application of process-based and data-driven hydrological models is crucial in modern hydrological research, especially for predicting key water cycle variables such as runoff, evapotranspiration (ET), and soil moisture. These models provide a scientific basis for water resource management, flood forecasting, and ecological protection. Process-based models simulate the physical mechanisms of watershed hydrological processes, while data-driven models leverage large datasets and advanced machine learning algorithms. This paper reviewed and compared methods for assessing and enhancing the extrapolability of both model types, discussing their prospects and limitations. Key strategies include the use of leave-one-out cross-validation and similarity-based methods to evaluate model performance in ungauged regions. Deep learning, transfer learning, and domain adaptation techniques are also promising in their potential to improve model predictions in data-sparse and extreme conditions. Interdisciplinary collaboration and continuous algorithmic advancements are also important to strengthen the global applicability and reliability of hydrological models.