Air quality prediction method based on seasonal recurrent neural network

Abstract

The invention provides an air quality prediction method based on a seasonal recurrent neural network. The method comprises the following steps: recording long-time-sequence air quality monitoring station data; preprocessing monitoring station data, analyzing seasonal and periodic change characteristics of air quality long-time sequence monitoring data, and determining seasonal change frequency of the air quality long-time sequence monitoring data; carrying out time sequence decomposition according to seasonal and periodic time sequence change characteristics of the air quality monitoring parameters, and generating a trend component, a seasonal component and a residual component; constructing a large batch of training samples, preliminarily establishing a three-channel recurrent neural network, and obtaining an optimal three-channel recurrent network model through training; predicting the future value of each component according to the historical value by using the optimal three-channel cyclic network model to obtain a trend component predicted value, a seasonal component predicted value and a residual component predicted value; and integrating the prediction results of the components to form a final air quality prediction value sequence.

Description

technical field [0001] The invention relates to the field of electronic information technology, in particular to an air quality prediction method based on a seasonal cyclic neural network. Background technique [0002] At present, the state of air quality and environmental pollution have gradually become hot topics that the whole country and even the world pay close attention to. Air quality problems are mainly manifested as urban air pollution, which has become a worldwide environmental quality governance issue. Understanding and predicting air quality development is of great significance for mass travel, environmental prevention and urban management. Traditional air quality prediction methods such as ARIMA are difficult to accurately extract the nonlinear and complex features of air quality monitoring time series, while the rapidly developing deep learning methods have strong nonlinear fitting capabilities, and can realize complex nonlinear sequences in a data-driven manne...

AI Technical Summary

Problems solved by technology

Traditional air quality prediction methods such as ARIMA are difficult to accurately extract the nonlinear and complex features of air quality monitoring time series, while the rapidly developing deep learning methods have strong nonlinear fitting capabilities, and can realize complex nonlinear sequences in a data-driven manner. Forecasting, however, it does not take into account the periodicity and seasonality of the air quality monitoring time series, and the prediction accuracy and interpretability are limited

Images