Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Air quality prediction method and device based on transfer learning

A technology of air quality and transfer learning, applied in forecasting, data processing applications, instruments, etc., can solve problems such as inaccurate prediction model parameters and inaccurate urban air quality predictions

Active Publication Date: 2020-07-28
BEIJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, the limited historical air quality data can easily lead to inaccurate parameters of the trained prediction model; thus resulting in inaccurate predictions of the city's air quality

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Air quality prediction method and device based on transfer learning
  • Air quality prediction method and device based on transfer learning
  • Air quality prediction method and device based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0061] In order to increase the historical air quality data in the case of limited historical air quality data to improve the prediction accuracy of air quality, the model trained based on the historical air quality data of cities with more air quality monitoring stations can be directly transferred to Cities with fewer air quality monitoring stations. However, this kind of migration requires that the two cities must be similar as a whole, especially the cities must be of the same size, resulting in a narrow scope of application. However, the present invention divides the source city and the target city, and determines the matching area to carry out model migration learning, so that the similarity of the city as a whole is not considered when performing migration, even if the size of the two cities is d...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides an air quality prediction method and device based on transfer learning, and the method comprises the steps: obtaining the impact data of a first region in historical time for a plurality of first regions obtained through the division of a target city; for each first region, based on the influence data of the first region and a prediction model correspondingto the first region in a plurality of prediction models obtained by pre-training, obtaining air quality data of the first region at a target time, and taking the obtained air quality data as air quality data of a target city at the target time, wherein the prediction model corresponding to any first region is obtained by training an initial model corresponding to the first region in a plurality of initial models obtained based on transfer learning by using historical air quality data of the first region and historical influence data corresponding to the historical air quality data of the first region. The prediction accuracy of the air quality can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and device for predicting air quality based on transfer learning. Background technique [0002] In recent years, in order to facilitate application scenarios such as life and production, it has become indispensable to predict future air quality. In this regard, for the target city that needs to predict the air quality at the target time, the historical air quality data of the target city can be used in advance to train the prediction model; then based on the impact data of the target city at a specified time interval from the target time and the The prediction model obtains the air quality data of the target city at the target time, so as to realize the prediction of the air quality at the target time. Wherein, the target time is a time in the future relative to the current time; the impact data is data that can affect air quality, for example, d...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06Q50/26G06N3/04
CPCG06Q10/04G06Q50/26G06N3/049G06N3/045
Inventor 刘亮马华东雷田子
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products