Research on the Back Propagation Neural Network Haze Prediction Model Based on Particle Swarm optimization

The haze prediction model based on the BP neural network is feasible, but due to the BP neural network itself, the predicted value of the prediction model has a large error. In order to improve the accuracy of the haze prediction model based on BP neural network, a particle swarm optimization algori...

Full description

Saved in:
Bibliographic Details
Published in2020 International Conference on Computer Engineering and Application (ICCEA) pp. 344 - 348
Main Authors Linlin, Yu, Xinxin, Liu, Li, Su, Qiang, Lin
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2020
Subjects
Atmospheric modeling
Back propagation
Data models
Haze Prediction Model
Meteorology
Neural Network
Neural networks
Particle swarm optimization
Prediction algorithms
Predictive models
Online AccessGet full text

Cover

More Information
Summary:The haze prediction model based on the BP neural network is feasible, but due to the BP neural network itself, the predicted value of the prediction model has a large error. In order to improve the accuracy of the haze prediction model based on BP neural network, a particle swarm optimization algorithm was proposed to optimize the haze prediction model based on BP neural network. The weights and thresholds of the haze prediction model based on BP neural network were optimized by the particle swarm algorithm to improve the accuracy of the prediction value. Under the same conditions as the data sample, haze prediction model based on basic BPNN neural network and haze prediction model based on BP neural network optimized by the particle swarm optimization algorithm were constructed separately. And both models have performed simulation experiments. The experimental results showed that the haze prediction model based on BP neural network optimized by the particle swarm optimization algorithm has higher prediction accuracy.
DOI:10.1109/ICCEA50009.2020.00081