Surface water quality index prediction method and device based on graph neural network

Abstract

The invention discloses a surface water quality index prediction method and device based on a graph neural network. The method comprises the following steps: collecting and preprocessing water quality index monitoring data and weather data; contructing a station diagram based on geographic position data and hydrological data of a surface water quality index monitoring station, and performing parameter optimization on a water quality index prediction network composed of a diagram convolutional neural network, a sequence codec constructed based on LSTM and a multi-layer perceptron according to preprocessed water quality index monitoring data, weather data and the station diagram; after parameter optimization is finished, taking the water quality index prediction network with determined parameters as a water quality index prediction model; and utilizing the water quality index prediction model to realize water quality index prediction based on the preprocessed water quality index monitoring data and weather data. According to the method, the surface water quality index is predicted by combining a graph convolutional neural network and a sequence codec architecture, and the method has a wide application prospect in the fields of sanitation and health, environmental governance and the like.

Description

technical field [0001] The invention belongs to the field of surface water quality index prediction, and in particular relates to a graph neural network-based surface water quality index prediction method and device. Background technique [0002] Water pollution is a worldwide problem. In developing countries, about 1 billion people do not have access to clean water due to excessive discharge of pollutants and failure of regulatory systems. Drinking polluted water can induce gastrointestinal lesions and cause great harm to human health. Water pollution can also severely damage the living environment of aquatic organisms. For example, most of the chemicals that cause water pollution can cause aquatic organisms to be poisoned to death. The surface water quality index monitoring station can obtain the water quality index status of the water area in real time. Mining the implicit information in the big data of the ecological environment can realize the prediction of high-preci...

AI Technical Summary

Problems solved by technology

However, the existing deep learning-based water quality index prediction methods often do not consider the impact of hydrological factors on water quality indexes, nor do they consider the complex dependencies of multiple sites on the water network.

Images