Hydrological time series prediction using neural architecture search-enhanced dual-stage attention-based Bi-LSTM
Abstract
A Neural Architecture Search-enhanced Dual Stage Attention Bidirectional Long Short-Term Memory (NAS-DSA-BiLSTM) model is proposed to capture nonlinear temporal hydrological patterns and is evaluated at three hydrological stations. The NAS-enhanced model achieved the best performance at Kaptanpasa, with the lowest MSE (11.249–16.224) and the highest R2 values, outperforming LSTM and DNN-LSTM models. Additional evaluations using NSE, sensitivity analysis, and Taylor diagrams confirmed stable and accurate predictions, particularly at Ulucami (NSE = 0.91) and Kaptanpasa (NSE = 0.80), demonstrating the model’s robustness for streamflow forecasting. The proposed model improved MSE by 15–26%, demonstrating robust and reliable streamflow forecasting performance.
Fields of Study & Subjects
Hydrological Forecasting Using AI
Energy Load and Power Forecasting
Stock Market Forecasting Methods
Publication details
- Journal / source
- Hydrological Sciences Journal
- Publisher
- Informa UK Limited
- Volume
- 71
- Issue
- 7
- Pages
- 1430–1448
- Publication date
- 25 March 2026
- Language
- EN