Investigating Deep Learning Knowledge Transfer in Streamflow Prediction From Global to Local Catchment
Top Cited Papers
Open Access
- 6 February 2026
- journal article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62 (2)
Abstract
Accurate streamflow prediction is critical for flood forecasting and water resource management, particularly in data‐scarce regions. Deep learning models like Long Short‐Term Memory (LSTM) offer a bridge to hydrologic regionalization utilizing climate data and catchment characteristics to improve behavioral insights and constrain predictive uncertainties. Here we evaluate transfer learning (TL) approaches using 441 “donor” basins from regions rich in quality hydrological data (Scotland GB‐SCT; Switzerland CH; and Canada's British Columbia; BC) to pre‐train LSTM runoff models by fine‐tuning in data‐poor areas like CA (36 target basins). Pairing measured streamflow (lagged) records with global climate data (ERA‐5) boosted the explanatory power of LSTM predictions especially in snowmelt and glacier‐influenced basins. A K‐Means clustering algorithm was applied to categorize basins into five hydrologically meaningful Clusters (labeled 1–5) based on catchment attributes. The results show that TL‐LSTM models perform better when pre‐trained using Clusters compared to the locally trained model (NSE = 0.85 and KGE = 0.80). The LSTM model trained on basins Cluster 3 data (LSTM 3 ) most closely resembling those in the target region yielded the most accurate predictions. Fine‐tuning with limited local data substantially improved prediction accuracy in the validation split (blind‐tested and treated as “ungauged”), evidencing that even short‐records of local data can enhance a regional model of hydrological behavior. These results demonstrate that TL‐LSTM can effectively enhance streamflow prediction in data‐scarce regions. These insights advance understanding of cross‐basin generalization and support the development of efficient, scalable modeling strategies for hydrological prediction in regions with limited observational data.Keywords
This publication has 47 references indexed in Scilit:
- Coping with data scarcity in extreme flood forecasting: A deep generative modeling approachAdvances in Water Resources, 2025
- Combining global precipitation data and machine learning to predict flood peaks in ungauged areas with similar climateAdvances in Water Resources, 2024
- Machine learning method is an alternative for the hydrological model in an alpine catchment in the Tianshan region, Central AsiaJournal of Hydrology: Regional Studies, 2023
- How to enhance hydrological predictions in hydrologically distinct watersheds of the Indian subcontinent?Hydrological Processes, 2023
- Utilization of the Long Short-Term Memory network for predicting streamflow in ungauged basins in KoreaEcological Engineering, 2022
- Deep learning approaches for improving prediction of daily stream temperature in data‐scarce, unmonitored, and dammed basinsHydrological Processes, 2021
- Semi-arid River Basin Flood: Causes, Damages, and Measures2020
- Regionalization of hydrological modeling for predicting streamflow in ungauged catchments: A comprehensive reviewWIREs Water, 2020
- A unified approach for process‐based hydrologic modeling: 2. Model implementation and case studiesWater Resources Research, 2015
- Application of Neural Networks to Runoff Prediction1994