{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:53:26Z","timestamp":1775789606103,"version":"3.50.1"},"reference-count":66,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,13]],"date-time":"2025-07-13T00:00:00Z","timestamp":1752364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xiamen Research Project for the Natural Science Foundation of Xiamen, China","award":["3502Z202472028"],"award-info":[{"award-number":["3502Z202472028"]}]},{"name":"Xiamen Research Project for the Natural Science Foundation of Xiamen, China","award":["3502Z20231042"],"award-info":[{"award-number":["3502Z20231042"]}]},{"name":"Xiamen Science and Technology Plan Project","award":["3502Z202472028"],"award-info":[{"award-number":["3502Z202472028"]}]},{"name":"Xiamen Science and Technology Plan Project","award":["3502Z20231042"],"award-info":[{"award-number":["3502Z20231042"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Air pollution source tracing is vital for effective pollution prevention and control, yet traditional methods often require large amounts of manual data, have limited cross-regional generalizability, and present challenges in capturing complex pollutant interactions. This study introduces AirTrace-SA (Air Pollution Tracing for Source Attribution), a novel hybrid deep learning model designed for the accurate identification and quantification of air pollution sources. AirTrace-SA comprises three main components: a hierarchical feature extractor (HFE) that extracts multi-scale features from chemical components, a source association bridge (SAB) that links chemical features to pollution sources through a multi-step decision mechanism, and a source contribution quantifier (SCQ) based on the TabNet regressor for the precise prediction of source contributions. Evaluated on real air quality datasets from five cities (Lanzhou, Luoyang, Haikou, Urumqi, and Hangzhou), AirTrace-SA achieves an average R2 of 0.88 (ranging from 0.84 to 0.94 across 10-fold cross-validation), an average mean absolute error (MAE) of 0.60 (ranging from 0.46 to 0.78 across five cities), and an average root mean square error (RMSE) of 1.06 (ranging from 0.51 to 1.62 across ten pollution sources). The model outperforms baseline models such as 1D CNN and LightGBM in terms of stability, accuracy, and cross-city generalization. Feature importance analysis identifies the main contributions of source categories, further improving interpretability. By reducing the reliance on labor-intensive data collection and providing scalable, high-precision source tracing, AirTrace-SA offers a powerful tool for environmental management that supports targeted emission reduction strategies and sustainable development.<\/jats:p>","DOI":"10.3390\/info16070603","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T10:55:41Z","timestamp":1752490541000},"page":"603","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AirTrace-SA: Air Pollution Tracing for Source Attribution"],"prefix":"10.3390","volume":"16","author":[{"given":"Wenchuan","family":"Zhao","sequence":"first","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macau SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macau SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"},{"name":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e4","DOI":"10.1016\/S2468-2667(16)30023-8","article-title":"Air pollution and health","volume":"2","author":"Landrigan","year":"2017","journal-title":"Lancet Public Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.tox.2009.04.035","article-title":"Effects of particulate matter (PM10, PM2.5 and PM1) on the cardiovascular system","volume":"261","author":"Polichetti","year":"2009","journal-title":"Toxicology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1116","DOI":"10.1016\/j.jaci.2004.08.030","article-title":"Health effects of air pollution","volume":"114","author":"Bernstein","year":"2004","journal-title":"J. Allergy Clin. Immunol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1080\/13504509.2011.570803","article-title":"The effects of air pollution on urban ecosystems and agriculture","volume":"18","author":"Bell","year":"2001","journal-title":"Int. J. Sustain. Dev. World Ecol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1016\/j.jenvman.2019.06.022","article-title":"Mining of the association rules between industrialization level and air quality to inform high-quality development in China","volume":"246","author":"Li","year":"2019","journal-title":"J. Environ. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, Y.L., and Cao, F. (2015). Fine particulate matter (PM2.5) in China at a city level. Sci. Rep., 5.","DOI":"10.1038\/srep14884"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Niu, Y., Chen, R., and Kan, H. (2017). Air pollution, disease burden, and health economic loss in China. Ambient Air Pollut. Health Impact China, 233\u2013242.","DOI":"10.1007\/978-981-10-5657-4_10"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Amnuaylojaroen, T., and Parasin, N. (2024). Pathogenesis of PM2.5-related disorders in different age groups: Children, adults, and the elderly. Epigenomes, 8.","DOI":"10.3390\/epigenomes8020013"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hung, C.C., Hsiao, H.E., Lin, C.C., and Hsu, H.H. (2023, January 1\u20132). Air Pollution Source Tracing Framework: Leveraging Microsensors and Wind Analysis for Pollution Source Identification. Proceedings of the International Conference on Technologies and Applications of Artificial Intelligence, Yunlin, Taiwan.","DOI":"10.1007\/978-981-97-1714-9_12"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1038\/nature15371","article-title":"The contribution of outdoor air pollution sources to premature mortality on a global scale","volume":"525","author":"Lelieveld","year":"2015","journal-title":"Nature"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cheremisinoff, N.P. (2012). Handbook of Air Pollution Prevention and Control, Elsevier.","DOI":"10.1016\/B978-1-4377-7815-1.00001-1"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Steyn, D.G. (1996). Air pollution in coastal cities. Air Pollution Modeling and Its Application XI, Springer.","DOI":"10.1007\/978-1-4615-5841-5_53"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4029","DOI":"10.1016\/S1352-2310(99)00144-2","article-title":"Air pollution in cities","volume":"33","author":"Mayer","year":"1999","journal-title":"Atmos. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1016\/j.atmosenv.2011.03.018","article-title":"A study of air pollution of city clusters","volume":"45","author":"Gao","year":"2011","journal-title":"Atmos. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1146\/annurev.energy.24.1.329","article-title":"Methods for attributing ambient air pollutants to emission sources","volume":"24","author":"Blanchard","year":"1999","journal-title":"Annu. Rev. Energy Environ."},{"key":"ref_16","unstructured":"Yadav, S., Yadav, A., Singh, A., Goyal, G., Sagwan, A., and Chhikara, S.K. (2015). Application of AI-based tools in air pollution study. Artificial Intelligence for Air Quality Monitoring and Prediction, CRC Press."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1115\/1.2128636","article-title":"Review of the governing equations, computational algorithms, and other components of the Models-3 Community Multiscale Air Quality (CMAQ) modeling system","volume":"59","author":"Byun","year":"2006","journal-title":"Appl. Mech. Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4275","DOI":"10.5194\/acp-20-4275-2020","article-title":"Quantification and evaluation of atmospheric ammonia emissions with different methods: A case study for the Yangtze River Delta region, China","volume":"20","author":"Zhao","year":"2020","journal-title":"Atmos. Chem. Phys."},{"key":"ref_19","first-page":"866","article-title":"Pollutant Sources Contribution Analysis of PM2.5 using The CMB Receptor Model","volume":"36","author":"Koo","year":"2019","journal-title":"J. Korean Appl. Sci. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, G., Ding, C., Jiang, X., Pan, G., Wei, X., and Sun, Y. (2020). Chemical compositions and sources contribution of atmospheric particles at a typical steel industrial urban site. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-64519-x"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2124","DOI":"10.1021\/acs.est.1c06157","article-title":"Data-driven machine learning in environmental pollution: Gains and problems","volume":"56","author":"Liu","year":"2022","journal-title":"Environ. Sci. Technol."},{"key":"ref_22","first-page":"130","article-title":"Decision tree methods: Applications for classification and prediction","volume":"27","author":"Ying","year":"2015","journal-title":"Shanghai Arch. Psychiatry"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"230222","DOI":"10.4209\/aaqr.230222","article-title":"Utilizing Machine Learning-based Classification Models for Tracking Air Pollution Sources: A Case Study in Korea","volume":"24","author":"Choi","year":"2024","journal-title":"Aerosol Air Qual. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J. Insur. Med."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Du, X., Zeng, F., Shi, G., and Feng, Y. (2019, January 8\u201310). Smart pollution source tracing via gradient tree boosting regression. Proceedings of the 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Taiyuan, China.","DOI":"10.1109\/MLBDBI48998.2019.00077"},{"key":"ref_26","unstructured":"Jakkula, V. (2006). Tutorial on Support Vector Machine (SVM), School of EECS, Washington State University."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kaya, K., and G\u00fcnd\u00fcz \u00d6\u011f\u00fcd\u00fcc\u00fc, \u015e. (2020). Deep flexible sequential (DFS) model for air pollution forecasting. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-60102-6"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"106238","DOI":"10.1016\/j.atmosres.2022.106238","article-title":"Application of XGBoost algorithm in the optimization of pollutant concentration","volume":"276","author":"Li","year":"2022","journal-title":"Atmos. Res."},{"key":"ref_30","first-page":"58","article-title":"Air pollution modelling with deep learning: A review","volume":"1","author":"Ayturan","year":"2018","journal-title":"Int. J. Environ. Pollut. Environ. Model."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ragab, M.G., Abdulkadir, S.J., Aziz, N., Al-Tashi, Q., Alyousifi, Y., Alhussian, H., and Alqushaibi, A. (2020). A novel one-dimensional CNN with exponential adaptive gradients for air pollution index prediction. Sustainability, 12.","DOI":"10.3390\/su122310090"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hao, Y., Bi, C., Yang, L., Qiu, X., Li, Y., and Yu, C. (2024, January 18\u201320). Tracing-U-Net: An Attention Based U-Net model for Air Pollution Source Tracing from Sparse Dataset. Proceedings of the 2024 International Conference on Information Technology, Data Science, and Optimization, Xiamen, China.","DOI":"10.1145\/3658549.3658570"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: A search space odyssey","volume":"28","author":"Greff","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e12511","DOI":"10.1111\/exsy.12511","article-title":"Air pollution forecasting based on attention-based LSTM neural network and ensemble learning","volume":"37","author":"Liu","year":"2020","journal-title":"Expert Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., and Pfister, T. (2021, January 2\u20139). Tabnet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref_37","first-page":"549","article-title":"Advantages of hybrid deep learning frameworks in applications with limited data","volume":"8","author":"Gavrishchaka","year":"2018","journal-title":"Int. J. Mach. Learn. Comput."},{"key":"ref_38","unstructured":"Lee, Y. (2023). Source Apportionment and Spatiotemporal Analysis of PM2.5 Using Machine Learning and Receptor Models. [Doctoral Dissertation, Seoul National University]."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"109199","DOI":"10.1016\/j.envint.2024.109199","article-title":"Improving WRF-Chem PM2.5 predictions by combining data assimilation and deep-learning-based bias correction","volume":"195","author":"Ma","year":"2025","journal-title":"Environ. Int."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J., Kim, J., Woo, J.H., and Lee, J.H. (2024). Rapid PM2.5-Induced Health Impact Assessment: A Novel Approach Using Conditional U-Net CMAQ Surrogate Model. Atmosphere, 15.","DOI":"10.20944\/preprints202409.0151.v1"},{"key":"ref_41","first-page":"1916","article-title":"Nonparametric regression using deep neural networks with ReLU activation function","volume":"48","year":"2020","journal-title":"Ann. Statist."},{"key":"ref_42","unstructured":"Martins, A., and Astudillo, R. (2016, January 20\u201322). From softmax to sparsemax: A sparse model of attention and multi-label classification. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.jfineco.2003.02.001","article-title":"The importance of the loss function in option valuation","volume":"72","author":"Christoffersen","year":"2024","journal-title":"J. Financ. Econ."},{"key":"ref_44","unstructured":"Chen, J., Liao, K., Fang, Y., Chen, D., and Wu, J. (2023, January 1\u20135). Tabcaps: A capsule neural network for tabular data classification with bow routing. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wang, R., Fu, B., Fu, G., and Wang, M. (2017, January 14). Deep & cross network for ad click predictions. Proceedings of the ADKDD\u201917, Halifax, NS, Canada.","DOI":"10.1145\/3124749.3124754"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TSMC.1986.4308985","article-title":"Subjective MSE measures","volume":"16","author":"Marmolin","year":"1986","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_47","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., and Liu, T.Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1111\/j.2041-210x.2012.00261.x","article-title":"A general and simple method for obtaining R2 from generalized linear mixed-effects models","volume":"4","author":"Nakagawa","year":"2013","journal-title":"Methods Ecol. Evol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3354\/cr030079","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"Willmott","year":"2005","journal-title":"Clim. Res."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"5481","DOI":"10.5194\/gmd-15-5481-2022","article-title":"Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not","volume":"15","author":"Hodson","year":"2022","journal-title":"Geosci. Model Dev. Discuss."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.envpol.2017.01.030","article-title":"Source apportionment and a novel approach of estimating regional contributions to ambient PM2.5 in Haikou, China","volume":"223","author":"Liu","year":"2017","journal-title":"Environ. Pollut."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1080\/10408340701244649","article-title":"The role of and the place of method validation in the quality assurance and quality control (QA\/QC) system","volume":"37","author":"Konieczka","year":"2007","journal-title":"Crit. Rev. Anal. Chem."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"265","DOI":"10.3155\/1047-3289.58.2.265","article-title":"Source apportionment: Findings from the US supersites program","volume":"58","author":"Watson","year":"2008","journal-title":"J. Air Waste Manage. Assoc."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1741","DOI":"10.5194\/acp-7-1741-2007","article-title":"Evaluation of organic markers for chemical mass balance source apportionment at the Fresno Supersite","volume":"7","author":"Chow","year":"2007","journal-title":"Atmos. Chem. Phys."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"5692","DOI":"10.1016\/j.atmosenv.2011.07.031","article-title":"Estimation of the concentrations of primary and secondary organic carbon in ambient particulate matter: Application of the CMB-Iteration method","volume":"45","author":"Shi","year":"2011","journal-title":"Atmos. Environ."},{"key":"ref_56","unstructured":"Coulter, C.T. (2025, July 01). EPA-CMB8.2 Users Manual, Available online: http:\/\/www.epa.gov\/sites\/default\/files\/2020-10\/documents\/epa-cmb82manual.pdf."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/j.atmosenv.2003.10.018","article-title":"Measurement error models in chemical mass balance analysis of air quality data","volume":"38","author":"Christensen","year":"2004","journal-title":"Atmos. Environ."},{"key":"ref_58","unstructured":"Watson, J.G., Chow, J.C., and Fujita, E. (2004). Protocol for Applying and Validating the CMB Model for PM2.5 and VOC, US Environmental Protection Agency."},{"key":"ref_59","unstructured":"Anguita, D., Ghelardoni, L., Ghio, A., Oneto, L., and Ridella, S. (2012, January 25\u201327). The \u2018K\u2019 in K-fold Cross Validation. Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11222-009-9153-8","article-title":"Estimation of prediction error by using K-fold cross-validation","volume":"21","author":"Fushiki","year":"2011","journal-title":"Stat. Comput."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Purdom, E., and Holmes, S.P. (2005). Error distribution for gene expression data. Stat. Appl. Genet. Mol. Biol., 4.","DOI":"10.2202\/1544-6115.1070"},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"e43","DOI":"10.1002\/imt2.43","article-title":"Complex heatmap visualization","volume":"1","author":"Gu","year":"2002","journal-title":"iMeta"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1016\/j.pmrj.2016.10.018","article-title":"The value of scatter plots","volume":"8","author":"Sainani","year":"2016","journal-title":"PMR"},{"key":"ref_64","unstructured":"Zien, A., Kr\u00e4mer, N., Sonnenburg, S., and R\u00e4tsch, G. The feature importance ranking measure. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases."},{"key":"ref_65","unstructured":"Seinfeld, J.H., and Pandis, S.N. (2016). Atmospheric Chemistry and Physics: From Air Pollution to Climate Change, John Wiley & Sons."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1098\/rsta.2007.2043","article-title":"Marine aerosol production: A review of the current knowledge","volume":"365","year":"2007","journal-title":"Philos. Trans. R. Soc. A"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/603\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:09:22Z","timestamp":1760033362000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":66,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["info16070603"],"URL":"https:\/\/doi.org\/10.3390\/info16070603","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,13]]}}}