Deep Spatio-temporal Learning Model for Air Quality Forecasting

In recent years, air pollution has seriously affected people’s production and life, so the air prediction has become a research hotspot in recent years. When analyzing air data, it is found that this type of data has not only temporal correlation, but also spatial correlation. For these temporal and...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computers, communications & control communications & control, 2021-04, Vol.16 (2)
Main Authors: Zhang, Lei, Li, Dong, Guo, Quansheng, Pan, Jiaxing
Format: Article
Language:English
Subjects:
Air pollution
Air pollution forecasting
Air quality
Economic forecasting
Image processing
Learning
Mathematical models
Outdoor air quality
Predictions
Video
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, air pollution has seriously affected people’s production and life, so the air prediction has become a research hotspot in recent years. When analyzing air data, it is found that this type of data has not only temporal correlation, but also spatial correlation. For these temporal and spatial characteristics, this paper studies deep spatio-temporal learning method to global prediction. The purpose is to learn the evolution rule behind the spatio-temporal sequence, and give an estimation for future state. To be specific, we propose two novel forecasting models based on video processing technology: Spatio-temporal Orthogonal Cube model (STOR-cube) and Spatio-temporal Dynamic Advection model (ST-DA), which effectively capture the spatio-temporal correlation and accurately predict the long-term air quality. STOR-cube contains three branches, i.e., a spatial branch for capturing moving objects, a temporal branch for processing motion, and an output branch for coupling the first two mutually orthogonal branches to generate a prediction frame. ST-DA constructs a spatio-temporal reasoning network to learn the characteristics of the spatio-temporal domain, and its impact on the future is explicitly modeled by pixel motion. Experiments results on the real-world datasets demonstrate our proposed approach significantly outperforms the state-of-the-art ones. Moreover, our model can be extended to other spatio-temporal data prediction tasks.
ISSN:1841-9836
1841-9844
DOI:10.15837/ijccc.2021.2.4111