{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:08:34Z","timestamp":1773814114197,"version":"3.50.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007511","name":"Rey Juan Carlos University","doi-asserted-by":"publisher","award":["[2024]\/SOLCON-134827"],"award-info":[{"award-number":["[2024]\/SOLCON-134827"]}],"id":[{"id":"10.13039\/501100007511","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Environmental Modelling &amp; Software"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.envsoft.2025.106771","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T16:55:48Z","timestamp":1763657748000},"page":"106771","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive Graph Neural Network\u2013transformer model for high-resolution PM2.5 forecasting and spatial extrapolation"],"prefix":"10.1016","volume":"196","author":[{"given":"Daniel","family":"Velez-Serrano","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1315-4386","authenticated-orcid":false,"given":"Alejandro","family":"Alvaro-Meca","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.envsoft.2025.106771_b1","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1175\/1520-0450(1996)035<0601:IMFAOS>2.0.CO;2","article-title":"Improved magnus form approximation of saturation vapor pressure","volume":"35","author":"Alduchov","year":"1996","journal-title":"J. Appl. Meteorol. Clim."},{"key":"10.1016\/j.envsoft.2025.106771_b2","series-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"issue":"4","key":"10.1016\/j.envsoft.2025.106771_b3","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1145\/235815.235821","article-title":"The quickhull algorithm for convex hulls","volume":"22","author":"Barber","year":"1996","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.envsoft.2025.106771_b4","series-title":"Time Series Analysis: Forecasting and Control","author":"Box","year":"1976"},{"key":"10.1016\/j.envsoft.2025.106771_b5","series-title":"Exponential Smoothing for Predicting Demand","author":"Brown","year":"1959"},{"issue":"2","key":"10.1016\/j.envsoft.2025.106771_b6","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s10182-012-0196-3","article-title":"Spatio-temporal modeling of particulate matter concentration through the spde approach","volume":"97","author":"Cameletti","year":"2013","journal-title":"AStA Adv. Stat. Anal."},{"key":"10.1016\/j.envsoft.2025.106771_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130400","article-title":"Spatio-temporal prediction using graph neural networks: A survey","volume":"643","author":"Capone","year":"2025","journal-title":"Neurocomputing"},{"issue":"5","key":"10.1016\/j.envsoft.2025.106771_b8","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph20054077","article-title":"Pm2.5 concentration prediction model: A cnn\u2013rf ensemble framework","volume":"20","author":"Chen","year":"2023","journal-title":"Int. J. Environ. Res. Public Health"},{"issue":"3","key":"10.1016\/j.envsoft.2025.106771_b9","doi-asserted-by":"crossref","DOI":"10.3390\/ijgi13030079","article-title":"Hourly pm2.5 concentration prediction based on empirical mode decomposition and geographically weighted neural network","volume":"13","author":"Chen","year":"2024","journal-title":"ISPRS Int. J. Geo-Information"},{"issue":"7","key":"10.1016\/j.envsoft.2025.106771_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.apr.2023.101781","article-title":"Estimation of fine-resolution pm2.5 concentrations using the inla-spde method","volume":"14","author":"Chen","year":"2023","journal-title":"Atmospheric Pollut. Res."},{"key":"10.1016\/j.envsoft.2025.106771_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.envpol.2024.125404","article-title":"Regional pm2.5 prediction with hybrid directed graph neural networks and spatio-temporal fusion of meteorological factors","volume":"366","author":"Chen","year":"2025","journal-title":"Environ. Pollut."},{"key":"10.1016\/j.envsoft.2025.106771_b12","article-title":"Comparative analysis of transformer-based and traditional models for long-term air-quality forecasting","volume":"414","author":"Cui","year":"2023","journal-title":"J. Clean. Prod."},{"issue":"8002","key":"10.1016\/j.envsoft.2025.106771_b13","article-title":"The mutagenic forces shaping the genomes of lung cancer in never smokers","volume":"626","author":"D\u00edaz-Gay","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.envsoft.2025.106771_b14","series-title":"Multiple Classifier Systems","first-page":"1","article-title":"Ensemble methods in machine learning","volume":"vol. 1857","author":"Dietterich","year":"2000"},{"key":"10.1016\/j.envsoft.2025.106771_b15","article-title":"Transformer architectures for air-quality forecasting: Capturing long-range dependencies","volume":"290","author":"Dong","year":"2024","journal-title":"Atmos. Environ."},{"key":"10.1016\/j.envsoft.2025.106771_b16","series-title":"Catboost: gradient boosting with categorical features support","author":"Dorogush","year":"2018"},{"key":"10.1016\/j.envsoft.2025.106771_b17","article-title":"Hybrid sarima-lstm model for pm2.5 forecasting across temporal scales","volume":"333","author":"Duan","year":"2023","journal-title":"J. Environ. Manag."},{"key":"10.1016\/j.envsoft.2025.106771_b18","article-title":"Lstm vs arima for long-term air pollution forecasting: A comparative study","volume":"324","author":"Fatima","year":"2025","journal-title":"Environ. Pollut."},{"key":"10.1016\/j.envsoft.2025.106771_b19","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","article-title":"Spatio-temporal field neural networks for air quality inference","author":"Feng","year":"2024"},{"key":"10.1016\/j.envsoft.2025.106771_b20","unstructured":"Gilmer, J., Schoenholz, S.S., et al., 2017. Neural message passing for quantum chemistry. In: ICML."},{"key":"10.1016\/j.envsoft.2025.106771_b21","series-title":"Advances in Neural Information Processing Systems","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.envsoft.2025.106771_b22","author":"Institut national de l\u2019environnement industriel et des risques (Ineris)","year":"2025"},{"key":"10.1016\/j.envsoft.2025.106771_b23","article-title":"A comprehensive review of machine learning methods for air pollution time series forecasting","volume":"318","author":"Jalali","year":"2025","journal-title":"Atmos. Environ."},{"key":"10.1016\/j.envsoft.2025.106771_b24","doi-asserted-by":"crossref","first-page":"10848","DOI":"10.1038\/s41467-024-55080-6","article-title":"Differential effects of fine particulate matter constituents on acute coronary syndrome onset","volume":"15","author":"Jiang","year":"2024","journal-title":"Nat. Commun."},{"issue":"23","key":"10.1016\/j.envsoft.2025.106771_b25","doi-asserted-by":"crossref","DOI":"10.3390\/su162310206","article-title":"A novel hybrid approach: Integrating bayesian spde and deep learning for enhanced spatiotemporal modeling of pm2.5 concentrations in urban airsheds for sustainable climate action and public health","volume":"16","author":"Johnson","year":"2024","journal-title":"Sustainability"},{"key":"10.1016\/j.envsoft.2025.106771_b26","article-title":"Evaluation of statistical and deep learning models for pm2.5 forecasting at multiple temporal scales","volume":"903","author":"Karnati","year":"2025","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envsoft.2025.106771_b27","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.envsoft.2025.106771_b28","unstructured":"Li, Y., et al., 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: ICLR."},{"issue":"4","key":"10.1016\/j.envsoft.2025.106771_b29","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/j.1467-9868.2011.00777.x","article-title":"An explicit link between Gaussian fields and Gaussian Markov random fields: The stochastic partial differential equation approach (with discussion).","volume":"73","author":"Lindgren","year":"2011","journal-title":"J. R. Stat. Soc. B"},{"key":"10.1016\/j.envsoft.2025.106771_b30","doi-asserted-by":"crossref","first-page":"12636","DOI":"10.1038\/s41598-024-63620-9","article-title":"Pm2.5 concentration prediction based on eemd-alstm","volume":"14","author":"Liu","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.envsoft.2025.106771_b31","series-title":"Episodios naturales de part\u00edculas 2023","author":"Ministerio para la Transici\u00f3n Ecol\u00f3gica y el Reto Demogr\u00e1fico","year":"2023"},{"key":"10.1016\/j.envsoft.2025.106771_b32","series-title":"ERA5-land hourly data from 1950 to 1980. copernicus climate change service (C3S) climate data store (CDS)","author":"Mu\u00f1oz Sabater","year":"2025"},{"key":"10.1016\/j.envsoft.2025.106771_b33","article-title":"Hybrid sarima\u2013lstm models for air-quality forecasting in urban environments","volume":"16","author":"Necula","year":"2025","journal-title":"Atmospheric Pollut. Res."},{"key":"10.1016\/j.envsoft.2025.106771_b34","series-title":"Computational Geometry - an Introduction","author":"Preparata","year":"1985"},{"key":"10.1016\/j.envsoft.2025.106771_b35","series-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","first-page":"2627","article-title":"A dual-stage attention-based recurrent neural network for time series prediction","author":"Qin","year":"2017"},{"key":"10.1016\/j.envsoft.2025.106771_b36","first-page":"7796","article-title":"Deep state space models for time series forecasting","volume":"vol. 31","author":"Rangapuram","year":"2018"},{"key":"10.1016\/j.envsoft.2025.106771_b37","series-title":"Gaussian Processes for Machine Learning","author":"Rasmussen","year":"2006"},{"key":"10.1016\/j.envsoft.2025.106771_b38","series-title":"SAS viya documentation","author":"SAS Institute Inc.","year":"2025"},{"key":"10.1016\/j.envsoft.2025.106771_b39","series-title":"Applied Computational Geometry: Towards Geometric Engineering","first-page":"203","article-title":"Triangle: Engineering a 2d quality mesh generator and delaunay triangulator","volume":"vol. 1148","author":"Shewchuk","year":"1996"},{"key":"10.1016\/j.envsoft.2025.106771_b40","first-page":"5998","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"issue":"2","key":"10.1016\/j.envsoft.2025.106771_b41","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"issue":"1","key":"10.1016\/j.envsoft.2025.106771_b42","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.envsoft.2025.106771_b43","article-title":"Informer-based deep learning for long-term air quality forecasting","volume":"242","author":"Wu","year":"2025","journal-title":"Environ. Res."},{"key":"10.1016\/j.envsoft.2025.106771_b44","series-title":"Proceedings - 2023 Asia-Europe Conference on Electronics, Data Processing and Informatics","article-title":"Prediction of pm2.5 concentration based on cnnlstm deep learning model","author":"Xie","year":"2023"},{"key":"10.1016\/j.envsoft.2025.106771_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.envsoft.2025.106501","article-title":"A graph neural network and transformer-based model for pm2.5 prediction through spatiotemporal correlation","volume":"191","author":"Ye","year":"2025","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.envsoft.2025.106771_b46","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., Zhu, Z., 2018. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In: IJCAI.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"10.1016\/j.envsoft.2025.106771_b47","article-title":"Air pollution prediction with graph neural networks considering geographic and meteorological factors","volume":"155","author":"Zhan","year":"2022","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.envsoft.2025.106771_b48","article-title":"Deep learning for air quality forecasting: A systematic survey","volume":"178","author":"Zhang","year":"2024","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.envsoft.2025.106771_b49","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1038\/s41893-025-01533-9","article-title":"Respiratory risks from wildfire-specific pm2.5 across multiple countries and territories","volume":"8","author":"Zhang","year":"2025","journal-title":"Nat. Sustain."},{"key":"10.1016\/j.envsoft.2025.106771_b50","article-title":"Long-range air-quality forecasting using transformers: A case study in East Asia","volume":"167","author":"Zhang","year":"2023","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.envsoft.2025.106771_b51","doi-asserted-by":"crossref","unstructured":"Zheng, C., Fan, X., Wang, C., Qi, J., 2020. Gman: A graph multi-attention network for traffic prediction. In: AAAI.","DOI":"10.1609\/aaai.v34i01.5477"}],"container-title":["Environmental Modelling &amp; Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1364815225004554?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1364815225004554?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:14:40Z","timestamp":1773810880000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1364815225004554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":51,"alternative-id":["S1364815225004554"],"URL":"https:\/\/doi.org\/10.1016\/j.envsoft.2025.106771","relation":{},"ISSN":["1364-8152"],"issn-type":[{"value":"1364-8152","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive Graph Neural Network\u2013transformer model for high-resolution PM2.5 forecasting and spatial extrapolation","name":"articletitle","label":"Article Title"},{"value":"Environmental Modelling & Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.envsoft.2025.106771","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"106771"}}