A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations
The ambient air pollution problem has become more severe as the social economy develops. Abnormal event detection in air quality data can prevent property loss and protect human health. The majority of existing anomaly detection models in air quality data are based on a single variable or a single m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9877800/ |
| _version_ | 1828145836153896960 |
|---|---|
| author | Xiaoling Lin Hongzhang Wang Jing Guo Gang Mei |
| author_facet | Xiaoling Lin Hongzhang Wang Jing Guo Gang Mei |
| author_sort | Xiaoling Lin |
| collection | DOAJ |
| description | The ambient air pollution problem has become more severe as the social economy develops. Abnormal event detection in air quality data can prevent property loss and protect human health. The majority of existing anomaly detection models in air quality data are based on a single variable or a single monitoring station, ignoring spatial correlation and multivariate features of regional air pollutant concentrations. To address the aforementioned issues, this paper proposes a new deep learning approach that combines spatial correlation and temporal correlation of air quality data to detect air quality anomalies. The essential idea of this approach is to use the correlation degree between node information to fuse the spatial correlational feature and temporal correlational feature of air quality data to construct spatiotemporal graph structure data, which are used for anomaly detection in air quality data. In this proposed approach, (1) the weighted adjacency matrix is established to characterize the spatial correlation, and the feature matrix is constructed to characterize the temporal correlation; (2) changes in node information are transformed into changes in edge weights using the correlation degree between node information, and spatiotemporal graph structure data are constructed to characterize the spatiotemporal correlation; and (3) an advanced deep learning model, Context augmented Graph Autoencoder (Con-GAE), is utilized to handle the above spatiotemporal graph structure data and detect abnormal air quality events. The efficiency of the approach is demonstrated by anomaly detection on synthetic test sets produced from real-world datasets. |
| first_indexed | 2024-04-11T20:38:17Z |
| format | Article |
| id | doaj.art-d3d8624c9e1f40e7be1d9ffc668cad7f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T20:38:17Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d3d8624c9e1f40e7be1d9ffc668cad7f2022-12-22T04:04:19ZengIEEEIEEE Access2169-35362022-01-0110940749408810.1109/ACCESS.2022.32042849877800A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal CorrelationsXiaoling Lin0Hongzhang Wang1Jing Guo2Gang Mei3https://orcid.org/0000-0003-0026-5423School of Engineering and Technology, China University of Geosciences (Beijing), Beijing, ChinaCCCC Second Navigation Bureau Third Engineering Company Ltd., Xuzhou, ChinaCCCC Second Navigation Bureau Third Engineering Company Ltd., Xuzhou, ChinaSchool of Engineering and Technology, China University of Geosciences (Beijing), Beijing, ChinaThe ambient air pollution problem has become more severe as the social economy develops. Abnormal event detection in air quality data can prevent property loss and protect human health. The majority of existing anomaly detection models in air quality data are based on a single variable or a single monitoring station, ignoring spatial correlation and multivariate features of regional air pollutant concentrations. To address the aforementioned issues, this paper proposes a new deep learning approach that combines spatial correlation and temporal correlation of air quality data to detect air quality anomalies. The essential idea of this approach is to use the correlation degree between node information to fuse the spatial correlational feature and temporal correlational feature of air quality data to construct spatiotemporal graph structure data, which are used for anomaly detection in air quality data. In this proposed approach, (1) the weighted adjacency matrix is established to characterize the spatial correlation, and the feature matrix is constructed to characterize the temporal correlation; (2) changes in node information are transformed into changes in edge weights using the correlation degree between node information, and spatiotemporal graph structure data are constructed to characterize the spatiotemporal correlation; and (3) an advanced deep learning model, Context augmented Graph Autoencoder (Con-GAE), is utilized to handle the above spatiotemporal graph structure data and detect abnormal air quality events. The efficiency of the approach is demonstrated by anomaly detection on synthetic test sets produced from real-world datasets.https://ieeexplore.ieee.org/document/9877800/Anomaly detectionair qualitydeep learningspatiotemporal correlationsgraph neural networks (GNN) |
| spellingShingle | Xiaoling Lin Hongzhang Wang Jing Guo Gang Mei A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations IEEE Access Anomaly detection air quality deep learning spatiotemporal correlations graph neural networks (GNN) |
| title | A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations |
| title_full | A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations |
| title_fullStr | A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations |
| title_full_unstemmed | A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations |
| title_short | A Deep Learning Approach Using Graph Neural Networks for Anomaly Detection in Air Quality Data Considering Spatiotemporal Correlations |
| title_sort | deep learning approach using graph neural networks for anomaly detection in air quality data considering spatiotemporal correlations |
| topic | Anomaly detection air quality deep learning spatiotemporal correlations graph neural networks (GNN) |
| url | https://ieeexplore.ieee.org/document/9877800/ |
| work_keys_str_mv | AT xiaolinglin adeeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT hongzhangwang adeeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT jingguo adeeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT gangmei adeeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT xiaolinglin deeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT hongzhangwang deeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT jingguo deeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations AT gangmei deeplearningapproachusinggraphneuralnetworksforanomalydetectioninairqualitydataconsideringspatiotemporalcorrelations |