A Survey on Data-Driven Runoff Forecasting Models Based on Neural Networks

As an important branch of time series forecasting, runoff forecasting provides a reliable decision-making basis for the rational use of water resources, economic development and ecological management of river basins. With the revolution of computing power, the data-driven model has become the mainstream runoff forecasting method. This survey will introduce and explore several types of existing neural network for runoff forecasting: convolutional neural network (CNN), recurrent neural network (RNN) and Transformer. The advantages and limitations of these referenced models are also discussed. In addition, this paper also discusses the future improvement directions of runoff forecasting models from the three directions of accuracy, robustness and interpretability. Through plug-and-play lightweight attention mechanism modules, reliable ensemble methods, and forward-looking interpretability methods, the potential of runoff forecasting models can be further tapped to improve the overall performance.

Automated summary

Runoff forecasting, an important branch of time series forecasting, plays a vital role in rational water resource utilization, economic development, and ecological management of river basins. The data-driven model has become the mainstream method for runoff forecasting with the advancement in computing power. This survey explores various neural network models, including convolutional neural network (CNN), recurrent neural network (RNN), and Transformer, for runoff forecasting. The advantages, limitations, and future improvement directions of these models are discussed, focusing on accuracy, robustness, and interpretability.