PM2.5 concentration prediction method and device and medium

Abstract

The invention discloses a PM2.5 concentration prediction method and device and a medium, and relates to the technical field of pollutant prediction, and the method comprises the steps: building a PM2.5 prediction model based on a CNN and a bidirectional GRU neural network and based on a one-dimensional convolutional neural network CNN and a bidirectional GRU neural network; the meteorological training data tensor is sent to a PM2.5 prediction model for training; the one-dimensional convolutional neural network CNN respectively performs local feature learning and dimension reduction on each input variable time sequence, and forms a low-dimensional feature sequence through convolution and pooling operation in sequence; inputting the feature sequence into a bidirectional GRU neural network, and learning the feature sequence from the time positive sequence and the time negative sequence by the bidirectional GRU neural network; the meteorological test data tensor is sent to a trained PM2.5prediction model for prediction, and a PM2.5 prediction concentration value is obtained. According to the model, the speed and lightweight characteristics of the convolutional neural network and the sequential sensitivity of the RNN are effectively utilized, more data volume is allowed to be checked during training, and the prediction accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of pollutant prediction, in particular to a PM2.5 concentration prediction method, device and medium. Background technique [0002] Nowadays, many cities suffer from regular large-scale smog, which affects people's daily travel and even causes serious harm to people's health. PM2.5 is the main component of smog. The primary task of controlling smog and improving air quality is to control PM2.5. PM2.5 concentration prediction is the main content of air quality prediction. It is of great significance to effectively grasp the reliable information of PM2.5 concentration changes and realize efficient and accurate prediction of air pollution prevention and control. Changes in air pollution can usually be reflected by many meteorological factors, such as temperature, humidity, wind direction, wind speed, snowfall, rainfall, etc. Therefore, making full use of meteorological information and establishing a PM2.5 pred...

AI Technical Summary

Problems solved by technology

Statistical methods include regression models, exponential smoothing models, ARIMA models, and multi-layer linear regression models, etc. Due to the limited ability of these methods to model nonlinear data, the prediction accuracy cannot meet the requirements; shallow machine learning methods include artificial neural networks, decision-making Trees, Random Forests, Support Vector Machines, Bayesian Networks, etc. These methods have excellent performance in prediction tasks, but they also have problems such as insufficient representation ability, easy to fall into local optimal solutions, and slow convergence speed. They are not suitable for Processing large sample data; in recent years, with the improvement of GPU performance and the gradual maturity of deep learning theory, deep learning algorithms have shown strong capabilities in predicting tasks. The commonly used models are recurrent neural networks and their variants. Such as Long Short-Term Memory (Long Short-Term Memory, LSTM), Gated Recurrent Unit (Gated RecurrentUnit, GRU), etc.

Images