Physics-Informed Data-Driven Model for Predicting Streamflow: A Case Study of the Voshmgir Basin, Iran

Accurate rainfall-runoff modeling is crucial for water resource management. However, the available models require more field-measured data to produce accurate results, which has been a long-term issue in hydrological modeling. Machine learning (ML) have shown superiority field over statistical models. The primary aim of present study was advance new coupled model combining model-driven and ML simulation Voshmgir basin northern Iran. Rainfall-runoff from 2002 2007 were collected tropical rainfall measuring mission (TRMM) satellite Iran resources management company. findings revealed that could not fully describe river runoff patterns during investigated time period. extreme machine support vector regression showed similar performances 1-day-ahead rainfall–runoff forecasting, while long short-term memory (LSTM) outperformed these two Our results demonstrated physically based LSTM other models, particularly forecasting. methodology be potentially applied same properties catchment.