PM2.5 real-time level prediction method and system based on neural net

Abstract

The invention discloses a PM2.5 real-time level prediction method and system based on neural net. The method collects the historical concentration values of air contaminant indexes of PM2.5, O3, CO, PM10, SO2 and NO2 as well as the historical values of atmosphere temperature, moisture and wind force and the like, applies the historical data as the training set to train the neural net model, and build a neural net prediction model based on the neural net comprehensive atmospheric indexes. A mobile equipment terminal sends PM2.5 level real-time request to a server, substituting the real-time-acquired contaminant indexes and atmospheric indexes as the test data into the neural net prediction model for prediction and pushing. The method provides a PM2.5 level query option to the mobile terminal users in the cities with few PM2.5 monitoring points or without PM2.5 monitoring point, reduces the prediction cost of PM2.5, and at the same time conducts the real-time prediction accurate to day and time, thus having good universality.

Description

technical field [0001] The invention relates to the field of environmental pollution prediction, in particular to a neural network-based real-time PM2.5 level prediction method and system. Background technique [0002] PM is the acronym for particulate matter in English. PM2.5 refers to particulate matter in the air with a kinetic equivalent diameter of 2.5 microns or less. PM2.5 pollution to the environment has had a huge impact on people's lives. [0003] The calculation method of PM2.5 mainly adopts physical methods, and the monitoring cost of PM2.5 is relatively high. Therefore, currently in my country, there are few PM2.5 observation points, and most cities have no observation points. At present, there are many studies on PM2.5 prediction analysis, and most of the prediction methods adopt linear methods. For example, based on gene expression and Logistic regression model, the linear model prediction method is mainly used, which can effectively predict the concentrati...

AI Technical Summary

Problems solved by technology

Since the neural network is a statistical model with good generalization ability and can better simulate the change process of pollutants and atmospheric factors, many researchers have made some progress in using neural network for simulation prediction. Fewer indicators, lower prediction accuracy

[0005] Considering that it is not only pollutants that have an impact on PM2.5, atmospheric factors may also have an impact on PM2.5, some researchers have analyzed other atmospheric factors that may have an impact on PM2.5, and analyzed the impact of different index factors on PM2.5. The impact of PM2.5 prediction, but there is a lack of algorithm models for specific PM2.5 level predictions, and the application of services to mobile end users

At the same time, for cities with few or no monitoring points, it is impossible to provide real-time query services for mobile users

Images