Flood flow prediction method of sequential network based on self-attention mechanism

Abstract

The invention discloses a flood flow prediction method of a sequential network based on a self-attention mechanism, and belongs to the technical field of flood flow prediction. The method comprises the following steps: 1, preprocessing historical flood data including flood flow and related flood characteristic factors; 2, constructing a flood prediction model in parallel by using a time convolutional network and a long-short-term memory network; 3, setting related hyper-parameters of the flood prediction model; 4, training the flood prediction model by using the historical flood data, and storing a final model; and 5, applying the trained model to flood prediction, and evaluating a result according to a corresponding index. The prediction method provided by the invention has better robustness, has higher accuracy compared with a traditional long-short-term memory network prediction method, and can effectively complete flood flow prediction of middle and small river basins.

Description

technical field [0001] The invention relates to a flood flow prediction method based on a time series network of a self-attention mechanism, and belongs to the technical field of flood flow prediction. Background technique [0002] Flood is one of the common and widely distributed disasters in nature. It often causes all kinds of huge damage to modern society. The economic loss it brings is incalculable, and it seriously endangers the lives and property safety of the people. Due to the complex mechanism of the flood itself, it has the characteristics of great difficulty in predicting the intensity. Therefore, research on flood flow forecasting has been a hot spot in the past few decades. [0003] Common flood prediction models are generally divided into two categories, hydrological models and data-driven models. Traditional hydrological models explain complex hydrological processes through physical processes. However, this kind of model is often very sensitive to internal...

AI Technical Summary

Problems solved by technology

However, this kind of model is often very sensitive to internal parameters, and requires relevant researchers to have relevant knowledge background of water conservancy. These objective conditions make this kind of method often have some limitations.

Images