Estimation of base and surface flow using deep neural networks and a hydrologic model in two watersheds of the Chesapeake Bay

• Long-short-term-memory (LSTM) model was used to simulate base and surface flow. • Sub-basin-level LSTM and basin-level LSTM were developed. • Simulation accuracies of LSTM-based and SWAT models were compared. • The sub-basin-level LSTM achieved superior performance for 19-year simulation. • The importance of input features of sub-basin-level LSTM was evaluated.