Air quality prediction method and device, equipment and storage medium

Abstract

The invention provides an air quality prediction method and device, equipment and a storage medium, and relates to the technical field of neural networks. The method comprises the steps: obtaining original air quality data to obtain a training sample; employing the training sample to carry out multiple training on a preset BP neural network, and obtaining a plurality of training results; and selecting a weight and a threshold value in the optimal single hidden layer in the training, constructing an air quality prediction model, inputting to-be-predicted data into the air quality prediction model for prediction, and obtaining an air quality prediction result. According to the embodiment of the invention, the BP neural network is optimized by using the genetic algorithm to make up for the defects of training failure, low convergence rate and the like caused by local minimization in the existing BP neural network, so that the BP neural network can obtain the optimal individual according to the genetic algorithm to update the weight and threshold of the network, the number of iterations of the network is greatly reduced, and the convergence speed of the network is accelerated; and the method shows good performance, and the prediction accuracy is effectively improved.

Description

Technical field [0001] The present application relates to the technical field of neural network, and in particular, the present application relates to an air quality prediction method, a device, a device, and a storage medium. Background technique [0002] Air is human dependence, the quality of air quality is the weight of the world concerned. In recent years, with the threat of air pollution to human health, urban air problems have also begun to raise more and more attention. The latest data released by the World Health Organization in May 2014 shows that the outdoor air quality of most cities around the world has not only reached the security standards developed by the organization, but the situation of contamination is still intensifying, urban air pollution has become the most important thing in the world today. One of the public health challenges. [0003] Traditional air quality prediction methods have been too complicated, and the calculated computing resources are too mu...

AI Technical Summary

Problems solved by technology

While this method is highly effective, it is limited by the fact that there may be certain deviations in the input parameters, and real-time correction processing is required. Therefore, its operating efficiency needs to be further improved in practical applications.

Images