Atmospheric pollutant concentration prediction method integrating machine learning with LSTM
A technology of air pollutants and machine learning, applied in machine learning, neural learning methods, forecasting, etc., can solve the problem of less spatiotemporal feature mining of data distribution, achieve fast calculation speed, simple data, and improve accuracy
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2019-12-03
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of air pollutant concentration prediction, and in particular relates to an air pollutant concentration prediction method integrating machine learning and LSTM. Background technique
[0002] In recent years, air pollution has gradually become a very serious problem. The continuous deterioration of air quality has caused great harm to people's health and living environment, and people have begun to pay attention to it in their daily lives. Therefore, the prediction of the concentration of air pollutants is very important, but the analysis and prediction of air pollutants are complex, dynamic and random. To make accurate predictions, a large amount of data from multiple fields and departments is involved. Such as meteorological data, industrial data, environmental data, etc. At present, there are a large amount of monitoring data on air pollution sources, pollutants and meteorology in the society. Making full ...
Examples
Embodiment Construction
[0054] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.
[0055] The present invention will be described in detail below with reference to the accompanying drawings and examples.
[0056] The present invention firstly defines the air pollutant concentration prediction.
[0057]Concentration prediction of air pollutants: By learning the relationship between historical pollutant monitoring data, the concentration of air pollutants such as PM2.5, PM10, and SO2 can be predicted within a certain period of time in the future.
[0058] Traditional prediction methods: The predictions based on the physical diffusion model and chemical reaction of pollutants are collectively referred to as traditional prediction methods.
[0059] A prediction method of atmospheric pollutant SO2 concentration that integrates machine learning and LSTM, such as Figure 1-3 as shown,
[0060]...