Empirical Study on Haze Forecasting Model Based on Neural Network

2018 International Conference on Advanced Electronic Materials, Computers and Materials Engineering

材料科学;无线电电子学;计算机科学

Pinghua, Zhang^1

Department of Computer Science and Technology, Hefei Technology College, Hefei, Anhui Province, China^1

关键词: Air monitoring;    BP neural networks;    Empirical studies;    Forecasting modeling;    High-precision;    Index systems;    Prediction model;    Reliable results;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/439/3/032073/pdf
DOI  :  10.1088/1757-899X/439/3/032073

来源: IOP

【 摘 要 】

There are many factors affecting the formation of haze, and the relationship between haze and haze is very complex. The prediction model of BP network with high precision fitting is used to predict the haze based on BP neural network. First, establishing an index system that affects the haze factors. Secondly, the neural network haze prediction model is established. Finally, the BP neural network is used to predict the number of days of the year. The results show that the model has high feasibility and rationality, and has obtained accurate and reliable results, which provides valuable reference for improving the air monitoring of relevant departments.