Assessing uncertainty and heterogeneity in machine learning-based spatiotemporal ozone prediction in Beijing-Tianjin- Hebei region in China
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Accurate prediction of spatiotemporal ozone concentration is of great significance to effectively establish advanced early warning systems and regulate air pollution control. However, the comprehensive assessment of uncertainty and heterogeneity in spatiotemporal ozone prediction remains unknown. Here, we systematically analyze the hourly and daily spatiotemporal predictive performances using convolutional long short term memory (ConvLSTM) and deep convolutional generative adversarial network (DCGAN) models over the Beijing-Tianjin-Hebei region in China from 2013 to 2018. In extensive scenarios, our results show that the machine learning-based (ML-based) models achieve better spatiotemporal ozone concentration prediction performance with multiple meteorological conditions. A further comparison to the air pollution model-Nested Air Quality Prediction Modelling System (NAQPMS) and monitoring observations, the ConvLSTM model demonstrates the practical feasibility of identifying high ozone concentration distribution and capturing spatiotemporal ozone variation patterns at a high spatial resolution (here 15 km × 15 km).
Date Issued
2023-07-10
Date Acceptance
2023-03-25
Citation
Science of the Total Environment, 2023, 881, pp.1-13
ISSN
0048-9697
Publisher
Elsevier
Start Page
1
End Page
13
Journal / Book Title
Science of the Total Environment
Volume
881
Copyright Statement
© 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/37011680
PII: S0048-9697(23)01765-5
Subjects
Generative adversarial network
Machine learning
Ozone concentration prediction
Spatiotemporal
Uncertainty
Publication Status
Published
Coverage Spatial
Netherlands
Article Number
163146
Date Publish Online
2023-04-01