Evaluating the long short-term memory (LSTM) network for discharge prediction under changing climate conditions

Abstract

Better understanding the predictive capabilities of hydrological models under contrasting climate conditions will enable more robust decision-making. Here, we tested the ability of the long short-term memory (LSTM) for daily discharge prediction under changing conditions using six snow-influenced catchments in Switzerland. We benchmarked the LSTM using the Hydrologiska Byråns Vattenbalansavdelning (HBV) bucket-type model with two parameterizations. We compared the model performance under changing conditions against constant conditions and tested the impact of the time-series size used in calibration on the model performance. When calibrated, the LSTM resulted in a much better fit than the HBV. However, in validation, the performance of the LSTM dropped considerably, and the fit was as good or poorer than the HBV performance in validation. Using longer time series in calibration improved the robustness of the LSTM, whereas HBV needed fewer data to ensure a robust parameterization. When using the maximum number of years in calibration, the LSTM was considered robust to simulate discharges in a drier period than the one used in calibration. Overall, the HBV was found to be less sensitive for applications under contrasted climates than the data-driven model. However, other LSTM modeling setups might be able to improve the transferability between different conditions. HIGHLIGHTS The long short-term memory (LSTM) had good predictive accuracy in both the calibration and validation periods; however, it is always less robust than the HBV model.; When using the maximum number of years in calibration, the LSTM was robust enough in its application under changing conditions when applied in a condition drier than the one used in calibration.;

Keywords

• climate transposability
• data-driven model
• differential split-sample test
• model calibration
• model robustness