{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:28:27Z","timestamp":1783146507263,"version":"3.54.6"},"reference-count":39,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T00:00:00Z","timestamp":1675036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173007"],"award-info":[{"award-number":["62173007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006008"],"award-info":[{"award-number":["62006008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903009"],"award-info":[{"award-number":["61903009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The environment and development are major issues of general concern. After much suffering from the harm of environmental pollution, human beings began to pay attention to environmental protection and started to carry out pollutant prediction research. A large number of air pollutant predictions have tried to predict pollutants by revealing their evolution patterns, emphasizing the fitting analysis of time series but ignoring the spatial transmission effect of adjacent areas, leading to low prediction accuracy. To solve this problem, we propose a time series prediction network with the self-optimization ability of a spatio-temporal graph neural network (BGGRU) to mine the changing pattern of the time series and the spatial propagation effect. The proposed network includes spatial and temporal modules. The spatial module uses a graph sampling and aggregation network (GraphSAGE) in order to extract the spatial information of the data. The temporal module uses a Bayesian graph gated recurrent unit (BGraphGRU), which applies a graph network to the gated recurrent unit (GRU) so as to fit the data\u2019s temporal information. In addition, this study used Bayesian optimization to solve the problem of the model\u2019s inaccuracy caused by inappropriate hyperparameters of the model. The high accuracy of the proposed method was verified by the actual PM2.5 data of Beijing, China, which provided an effective method for predicting the PM2.5 concentration.<\/jats:p>","DOI":"10.3390\/e25020247","type":"journal-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T04:31:27Z","timestamp":1675053087000},"page":"247","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":90,"title":["Deep Spatio-Temporal Graph Network with Self-Optimization for Air Quality Prediction"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-0077","authenticated-orcid":false,"given":"Xue-Bo","family":"Jin","sequence":"first","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Yao","family":"Wang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-3467","authenticated-orcid":false,"given":"Jian-Lei","family":"Kong","sequence":"additional","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8047-1010","authenticated-orcid":false,"given":"Yu-Ting","family":"Bai","sequence":"additional","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting-Li","family":"Su","sequence":"additional","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China"},{"name":"China Light Industry Key Laboratory of Industrial Internet and Big Data, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasun","family":"Chakrabarti","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, ITM SLS Baroda University, Vadodara 391510, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/sj.jea.7500071","article-title":"Indoor\/outdoor PM10 and PM2.5 in Bangkok, Thailand","volume":"10","author":"Tsai","year":"2000","journal-title":"J. Expo. Sci. Environ. Epidemiol."},{"key":"ref_2","first-page":"3540","article-title":"Predicting air quality: Improvements through advanced methods to integrate models and measurements","volume":"227","author":"Gregory","year":"2007","journal-title":"J. Comput. Phys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1279565","DOI":"10.1155\/2019\/1279565","article-title":"Atmospheric PM2.5 concentration prediction based on time series and interactive multiple model approach","volume":"2019","author":"Li","year":"2019","journal-title":"Adv. Meteorol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6610273","DOI":"10.1155\/2021\/6610273","article-title":"Appling an Improved Method Based on ARIMA Model to Predict the Short-Term Electricity Consumption Transmitted by the Internet of Things (IoT)","volume":"2021","author":"Guo","year":"2021","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4655","DOI":"10.1007\/s11071-021-06471-7","article-title":"Comparison of an artificial neural network and Gompertz model for predicting the dynamics of deaths from COVID-19 in M\u00e9xico","volume":"104","author":"Conde","year":"2021","journal-title":"Nonlinear Dyn."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1007\/s11071-019-05252-7","article-title":"Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm","volume":"98","author":"Zhang","year":"2019","journal-title":"Nonlinear Dyn."},{"key":"ref_7","first-page":"98","article-title":"Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR","volume":"47","author":"Fang","year":"2021","journal-title":"Arch. Environ. Prot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/72.279188","article-title":"Recurrent neural networks and robust time series prediction","volume":"5","author":"Connor","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.neucom.2020.10.027","article-title":"Prediction Intervals Estimation of Solar Generation Based on Gated Recurrent Unit and Kernel Density Estimation","volume":"453","author":"Pan","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/j.neucom.2018.08.067","article-title":"LSTM-based Traffic Flow Prediction with Missing Data","volume":"318","author":"Tian","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_11","unstructured":"Shao, B.J., Zico, K., and Vladlen, K. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv."},{"key":"ref_12","unstructured":"Bruna, J., Zaremba, W., and Szlam, A. (2014, January 14\u201316). Spectral network sand locally connected network son graphs. Proceedings of the 2nd International Conferenceon Learning Representations, Banff, AB, Canada."},{"key":"ref_13","unstructured":"Veliovic, P., and CucurullG, C.A. (May, January 30). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ifacol.2021.10.047","article-title":"Energy consumption prediction of cold source system based on GraphSAG","volume":"54","author":"Zhiwen","year":"2021","journal-title":"IFAC-Pap. OnLine"},{"key":"ref_15","unstructured":"Gori, M., Monfardini, G., and Scarselli, F. (August, January 31). A new model for learningin graph domains. Proceedings of the International Joint Conference on Neural Networks, Montreal, QC, Canada."},{"key":"ref_16","unstructured":"Snoek, J., Larochelle, H., and Adams, R.P. (2012, January 3\u20136). Practical Bayesian optimization of machine learning algorithms. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4175","DOI":"10.1002\/2017JD028052","article-title":"Time Series Forecasting of Air Quality Based on Regional Numerical Modeling in Hong Kong","volume":"123","author":"Tong","year":"2018","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"956","DOI":"10.4209\/aaqr.2019.11.0586","article-title":"Prediction of Potentially High PM2.5 Concentrations in Chengdu, China","volume":"20","author":"Zeng","year":"2020","journal-title":"Aerosol Air Qual. Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shahriar, S.A., Kayes, I., and Hasan, K. (2021). Potential of ARIMA-ANN, ARIMA-SVM, DT and CatBoost for atmospheric PM2.5 forecasting in Bangladesh. Atmosphere, 12.","DOI":"10.3390\/atmos12010100"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s11869-020-00945-0","article-title":"A support vector machine model to forecast ground-level PM2.5 in a highly populated city with a complex terrain. Air Quality","volume":"14","author":"Caroline","year":"2021","journal-title":"Atmos. Health"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"117534","DOI":"10.1016\/j.atmosenv.2020.117534","article-title":"Analysis and accurate prediction of ambient PM2.5 in China using Multi-layer Perceptron","volume":"232","author":"Rui","year":"2020","journal-title":"Atmos. Environ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20050","DOI":"10.1109\/ACCESS.2019.2897028","article-title":"A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration","volume":"7","author":"Qin","year":"2019","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.4209\/aaqr.2018.12.0450","article-title":"Evaluation of Different Machine Learning Approaches to Forecasting PM2.5 Mass Concentrations","volume":"19","author":"Hamed","year":"2019","journal-title":"Aerosol Air Qual. Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nagrecha, K. (2020, January 16\u201318). Sensor-Based Air Pollution Prediction Using Deep CNN-LSTM. Proceedings of the 2020 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA.","DOI":"10.1109\/CSCI51800.2020.00127"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhao, P., and Zettsu, K. (2020, January 10\u201313). MASTGN: Multi-Attention Spatio-Temporal Graph Networks for Air Pollution Prediction. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.","DOI":"10.1109\/BigData50022.2020.9378156"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, Y., and Zhang, J. (2020, January 3\u20136). PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network for PM2.5 Forecasting. Proceedings of the 28th International Conference on Advances in Geographic Information Systems, Seattle, WA, USA.","DOI":"10.1145\/3397536.3422208"},{"key":"ref_27","first-page":"118569","article-title":"A theory-guided graph networks based PM2.5 forecasting method","volume":"V293","author":"Hz","year":"2022","journal-title":"Environ. Pollut."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"17081","DOI":"10.1007\/s00521-021-06300-3","article-title":"Near-surface PM2.5 prediction combining the complex network characterization and graph convolution neural network","volume":"33","author":"Zhao","year":"2021","journal-title":"Neural Comput. Applic"},{"key":"ref_29","unstructured":"Hamilton, W.L., Ying, R., and Leskovec, J. (2017). Inductive Representation Learning on Large Graphs. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jin, X.B., Zheng, W.Z., and Kong, J.L. (2021). Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization. Energies, 14.","DOI":"10.3390\/en14061596"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.neucom.2020.03.011","article-title":"Probabilistic forecasting with temporal convolutional neural network","volume":"399","author":"Chen","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"116225","DOI":"10.1016\/j.energy.2019.116225","article-title":"Photovoltaic power forecasting based LSTM-Convolutional Network","volume":"189","author":"Wang","year":"2019","journal-title":"Energy"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"11920","DOI":"10.1007\/s11356-021-16227-w","article-title":"Air quality prediction using CNN+LSTM-based hybrid deep learning architecture","volume":"29","author":"Gilik","year":"2022","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liao, W., and Chang, Y. (2018). Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting. Energies, 11.","DOI":"10.3390\/en11082163"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"182283","DOI":"10.1109\/ACCESS.2020.3027977","article-title":"Hybrid Bidirectional LSTM Model for Short-Term Wind Speed Interval Prediction","volume":"8","author":"Saeed","year":"2020","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101019","DOI":"10.1016\/j.ecoinf.2019.101019","article-title":"Predicting air quality with deep learning LSTM: Towards comprehensive models","volume":"55","author":"Navares","year":"2019","journal-title":"Ecol. Inform."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"49424","DOI":"10.1109\/ACCESS.2020.2980002","article-title":"Rapid Prediction of Respiratory Motion Based on Bidirectional Gated Recurrent Unit Network","volume":"8","author":"Yu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"012035","DOI":"10.1088\/1742-6596\/1631\/1\/012035","article-title":"A Practical Application for Text-Based Sentiment Analysis Based on Bayes-LSTM Model","volume":"1631","author":"Li","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Jin, X.B., Gong, W.T., and Kong, J.L. (2022). A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting. Entropy, 24.","DOI":"10.3390\/e24030335"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/2\/247\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:19:46Z","timestamp":1760120386000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/2\/247"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,30]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["e25020247"],"URL":"https:\/\/doi.org\/10.3390\/e25020247","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,30]]}}}