Deep learning architecture for air quality predictions

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air qu...

Full description

Saved in:
Bibliographic Details
Published in:Environmental science and pollution research international Vol. 23; no. 22; pp. 22408 - 22417
Main Authors: Li, Xiang, Peng, Ling, Hu, Yuan, Shao, Jing, Chi, Tianhe
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2016
Springer Nature B.V
Subjects:
Air Pollutants - chemistry
Air pollution
Air Pollution - analysis
Air quality
Algorithms
Aquatic Pollution
Artificial intelligence
Atmospheric Protection/Air Quality Control/Air Pollution
Deep learning
Developing countries
Earth and Environmental Science
Ecotoxicology
Environment
Environmental Chemistry
Environmental Health
human health
Humans
industrialization
LDCs
Methods
Models, Theoretical
Neural networks
Neural Networks (Computer)
Outdoor air quality
Pollutants
prediction
Prediction models
Regression analysis
Research Article
Seasons
Spatial discrimination learning
Sustainable development
Time series
time series analysis
Urbanization
Waste Water Technology
Water Management
Water Pollution Control
Beijing China
China
Deep learning
Stacked autoencoder (SAE)
Layer-wise pre-training
Air quality prediction
Spatiotemporal features
BP algorithm
ISSN:0944-1344, 1614-7499
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0944-1344
1614-7499
DOI:10.1007/s11356-016-7812-9