Urban VOCs total pollution time sequence prediction method and system, storage medium and equipment

Abstract

The invention discloses an urban VOCs total pollution time sequence prediction method and system, a storage medium and equipment, and the method comprises the steps: preprocessing total VOCs monitoring data, embedding the data for projection, wherein the data comprises position information including year, month and day information, and also including the setting information of holidays and festivals; performing convolution pooling on the obtained data, reducing redundant data, generating an attention probability matrix through a sparse full-self-attention mechanism in an encoder to obtain a feature map, inputting the feature map once repeatedly to obtain the feature map, and transmitting the feature map to a decoder; cutting half of the data, inputting the data, performing the same operation, splicing the feature maps obtained twice to form a finally obtained feature map, and transmitting the finally obtained feature map to the decoder; and masking the data, inputting the data into the decoder, and obtaining a prediction result by the decoder according to the masked input and the prediction result obtained in the previous step. A longer time sequence can be processed, and the information of the time sequence can be extracted more effectively.

Description

technical field [0001] The invention relates to the technical field of environmental monitoring, in particular to a time-series prediction method, system, storage medium and equipment for the total amount of urban VOCs pollution. Background technique [0002] As the scale of the chemical industry expands, chemical pollution tends to rise and aggravate. The environmental protection situation of the chemical industry is severe, and the emission of harmful chemical gas pollutants characterized by volatile organic compounds has become increasingly prominent. At the same time, frequent regional air pollution problems such as haze are closely related to the substandard discharge of industrial waste gas. In response to this problem, a number of technologies have been developed for the monitoring of industrial harmful pollutant gases, mainly including: [0003] (1) Gas chromatography detection, gas chromatography is a laboratory standard analysis method through chromatographic anal...

AI Technical Summary

Problems solved by technology

It has the advantages of real-time measurement of large-scale air pollution, but the system is complex, inconvenient to operate, and expensive, which cannot meet the needs of comprehensive monitoring

[0005] (3) Measurement at fixed monitoring stations, using a variety of pollution sensors deployed in sensitive areas and key areas of industrial parks for pollution monitoring, which collects many types of data and has high measurement accuracy, but the location of the arrangement is fixed, which is greatly affected by meteorological and environmental factors. Limited and sparsely distributed

However, full self-attention networks have several serious problems that prevent them from being directly applicable to long-term series prediction problems, including quadratic level time complexity, high memory usage, and encoder-decoder structure. inherent limitations

Images