Research on the Monitoring Method of Atmospheric Particle Pollutant Concentration Based on Genetic Neural Network

Abstract

Atmospheric environment is one of the important environments for human survival. With the continuous improvement of the degree of industrialization, while promoting the rise of economic prosperity, it has also caused serious environmental pollution problems to us. Therefore, environmental monitoring has become a hot spot, and the application of wireless sensor networks provides a great development space for the monitoring of polluting gas emission sources. Therefore, people have higher and higher requirements for real-time monitoring technology of polluting gas emissions. In order to more comprehensively understand and grasp the changing trend of air pollutants, and provide more comprehensive and timely information for air pollution prevention and control, it is imperative to carry out air pollutant forecast research. Atmospheric pollution forecast is the basis of atmospheric environmental planning, evaluation and management. It can provide basic data for urban environmental management, pollution control, environmental planning, urban construction and public health, so as to take necessary control and preventive measures. With the rapid development of wireless sensor networks, in order to monitor air pollution in real time and effectively, this paper builds an automatic air pollution monitoring system based on neural networks. Compared with the traditional multiple linear regression model, the neural network model can capture the nonlinear influence law between pollutant concentration and meteorological factors, and can better predict the mass concentration of particulate matter. Choosing meteorological parameters and pollution source intensity variables can describe the real-time change of atmospheric particulate matter mass concentration more accurately, and the prediction accuracy of particulate matter mass concentration is higher. The neural network prediction model is not only suitable for general pollution concentration, but also accurate for predicting the mass concentration of particulate matter in high pollution period.