A Construction Method of Combined Air Quality Forecasting Model

Abstract

The invention brings forward a constructing method of a combined air quality forecasting model, wherein the method is based on a BP neural network and multi-element stepwise regression. The method comprises the following steps: (1), establishing a BP neural network forecasting module based on a training sample set; (2), carrying out severe-pollution scene determination based on the BP neural network forecasting result; to be specific, (21), defining a severe-pollution scene; (22), establishing a determination equation; (23), carrying out determination by using a neural network forecasting value; and (24), carrying out determination on the determination equation based on the neural network forecasting value determination result; (3), establishing a severe-pollution multi-element stepwise regression forecasting model according to the severe-pollution scene determination result; and (4), with combination of the forecasting determination process, outputting a forecasting result. According to the invention, the forecasting precision of the urban air quality, especially the early-warning forecasting of the severe-pollution scene, is improved comprehensively; and thus stable air quality precision forecasting under different pollution degrees can be realized.

Description

technical field [0001] The invention relates to the field of environmental quality prediction and early warning, in particular to a method for constructing a combined urban air quality prediction model under high pollution scenarios. Background technique [0002] Carrying out air quality forecasting model research, especially the high pollution emergency mechanism of air quality forecasting and early warning is the basic work that the existing environmental protection departments urgently need to carry out. The development of air quality forecasting is an important symbol of the improvement of air quality monitoring and environmental management in my country, and it is also a symbol of the degree of civilization of a city. A stable and high-precision urban air quality forecast model, especially the forecast and early warning capabilities under high pollution scenarios, can not only provide guidance for residents' travel and production work, but also provide basic data and su...

AI Technical Summary

Problems solved by technology

However, since the non-parametric model of BP neural network is not sensitive to extreme value performance, its forecast error for high-concentration pollution periods is relatively large

Therefore, only using the BP neural network model cannot achieve stable and accurate forecasting under high pollution levels

[0004] The above-mentioned various forecasting methods have limitations, and the forecasting effect for different degrees of pollution cannot achieve the desired effect.

Although the BP neural network has a high forecast accuracy rate for general pollution weather scenarios, the forecast error for heavy pollution scenarios with increasingly obvious regional characteristics is also high

Images