Research on runoff process vectorization and integration of deep learning algorithms for flood forecasting.

Accurate multi-step ahead flood forecasting is crucial for flood prevention and mitigation efforts as well as optimizing water resource management. In this study, we propose a Runoff Process Vectorization (RPV) method and integrate it with three Deep Learning (DL) models, namely Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Transformer, to develop a series of RPV-DL flood forecasting models, namely RPV-LSTM, RPV-TCN, and RPV-Transformer models. The models are evaluated using observed flood runoff data from nine typical basins in the middle Yellow River region. The key findings are as follows: Under the same lead time conditions, the RPV-DL models outperform the DL models in terms of Nash-Sutcliffe efficiency coefficient, root mean square error, and relative error for peak flows in the nine typical basins of the middle Yellow River region. Based on the comprehensive evaluation results of the train and test periods, the RPV-DL model outperforms the DL model by an average of 2.82%-22.21% in terms of NSE across nine basins, with RMSE and RE reductions of 10.86-28.81% and 36.14%-51.35%, respectively. The vectorization method significantly improves the accuracy of DL flood forecasting, and the RPV-DL models exhibit better predictive performance, particularly when the lead time is 4h-6h. When the lead time is 4-6h, the percentage improvement in NSE is 9.77%, 15.07%, and 17.94%. The RPV-TCN model shows superior performance in overcoming forecast errors among the nine basins. The research findings provide scientific evidence for flood prevention and mitigation efforts in river basins.

Research on machine learning hybrid framework by coupling grid-based runoff generation model and runoff process vectorization for flood forecasting.

One of the important non-engineering measures for flood forecasting and disaster reduction in watersheds is the application of machine learning flood prediction models, with Long Short-Term Memory (LSTM) being one of the most representative time series prediction models. However, the LSTM model has issues of underestimating peak flows and poor robustness in flood forecasting applications. Therefore, based on a thorough analysis of complex underlying surface attributes, this study proposes a framework for distinguishing runoff models and integrates a Grid-based Runoff Generation Model (GRGM). Simultaneously considering the time series characteristics of runoff processes, including rising, peak, and recession, a runoff process vectorization (RPV) method is proposed. In this study, a hybrid deep learning flood forecasting framework, GRGM-RPV-LSTM, is constructed by coupling the GRGM, RPV, and LSTM neural network models. Taking the Jialu River in the Zhongmu station control basin as an example, the model is validated using 18 instances of measured floods and compared with the LSTM and GRGM-LSTM models. The study shows that the GRGM model has a relative error and average coefficient of determination for simulating runoff of 8.41% and 0.976, respectively, indicating that considering the spatial distribution of runoff patterns leads to more accurate runoff calculations. Under the same lead time conditions, the GRGM-RPV-LSTM hybrid forecasting model has a Nash efficiency coefficient greater than 0.9, demonstrating better simulation performance compared to the GRGM-LSTM and LSTM models. As the lead time increases, the GRGM-RPV-LSTM model provides more accurate peak flow predictions and exhibits better robustness. The research findings can provide scientific basis for coordinated management of flood control and disaster reduction in watersheds.

Application of a hybrid algorithm of LSTM and Transformer based on random search optimization for improving rainfall-runoff simulation.

Flood forecasting using traditional physical hydrology models requires consideration of multiple complex physical processes including the spatio-temporal distribution of rainfall, the spatial heterogeneity of watershed sub-surface characteristics, and runoff generation and routing behaviours. Data-driven models offer novel solutions to these challenges, though they are hindered by difficulties in hyperparameter selection and a decline in prediction stability as the lead time extends. This study introduces a hybrid model, the RS-LSTM-Transformer, which combines Random Search (RS), Long Short-Term Memory networks (LSTM), and the Transformer architecture. Applied to the typical Jingle watershed in the middle reaches of the Yellow River, this model utilises rainfall and runoff data from basin sites to simulate flood processes, and its outcomes are compared against those from RS-LSTM, RS-Transformer, RS-BP, and RS-MLP models. It was evaluated against RS-LSTM, RS-Transformer, RS-BP, and RS-MLP models using the Nash-Sutcliffe Efficiency Coefficient (NSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Bias percentage as metrics. At a 1-h lead time during calibration and validation, the RS-LSTM-Transformer model achieved NSE, RMSE, MAE, and Bias values of 0.970, 14.001m3/s, 5.304m3/s, 0.501% and 0.953, 14.124m3/s, 6.365m3/s, 0.523%, respectively. These results demonstrate the model's superior simulation capabilities and robustness, providing more accurate peak flow forecasts as the lead time increases. The study highlights the RS-LSTM-Transformer model's potential in flood forecasting and the advantages of integrating various data-driven approaches for innovative modelling.