Time-space domain correlation prediction method for air pollutant concentration

Abstract

The invention relates to a time-space domain correlation prediction method for air pollutant concentration, which comprises the steps of S1, constructing a prediction model based on a residual error network and a convolutional LSTM network by taking PM2.5 as a sample for target pollutant prediction; s2, selecting appropriate training and testing data from the environment monitoring data to complete initialization of the prediction model; s3, training the prediction model stage by stage to obtain a neural network prediction model capable of accurately predicting PM2.5; s4, selecting hyper-parameters (the number of layers, the number of nodes and the learning rate) of the model by utilizing the verification set until the model is optimal; and S5, carrying out urban PM2.5 prediction by utilizing the verified prediction model. Compared with the prior art, the method has the advantages that the convolutional LSTM network is used as a middle layer, deep space-time association feature extraction is performed on spatial features extracted by the bottom ResNet network, accordingly, the prediction performance of the network model can be improved, the hidden state of the convolutional LSTM can be received by the aid of the full connection layer, and a final prediction result can be generated.

Description

Technical field [0001] The invention relates to a method for predicting the concentration of urban air pollutants, in particular to a method for predicting the concentration of air pollutants in time-space domains. Background technique [0002] In recent years, the increasingly serious air pollution problem has aroused widespread concern around the world. Pollutants such as PM2.5 and PM10 have a huge impact on people's life and health. The problem of air pollution is becoming increasingly prominent. Air pollution analysis and prediction are complex and dynamic, involving multiple departments, regions and fields. To accurately predict air pollution, it is necessary to process a large amount of environmental data and environmental information related to it. Various organizations attach importance to and focus on the improvement of air pollution response and treatment capabilities, among which air pollution prediction technology is one of the focus issues currently concerned. At p...

AI Technical Summary

Problems solved by technology

However, in the face of the high dimensionality of air pollution data, the high diversity of influencing factors, and the massive pollution detection data, traditional numerical analysis models have encountered the following key problems: (1) The data sources used in the analysis models are too single, and most of them are only built on On a single set of pollution data, there is a lack of comprehensive consideration of other environmental factors, such as weather data; (2) In terms of space and time dimensions, traditional models lack the ability to mine the internal spatiotemporal correlation characteristics of pollution data, and cannot achieve deep internal data analysis. Contact extraction and response to the impact of abrupt weather environment; (3) The large-scale data application capacity of the model is limited, and it is difficult to mine the spatio-temporal correlation of pollutants from the perspective of big data

Images