{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:11:49Z","timestamp":1781532709007,"version":"3.54.5"},"reference-count":53,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:00:00Z","timestamp":1776124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2026A1515030034"],"award-info":[{"award-number":["2026A1515030034"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42407566"],"award-info":[{"award-number":["42407566"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"award":["42407566"],"award-info":[{"award-number":["42407566"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Reliable air-quality monitoring is essential for urban exposure assessment and environmental policy, yet many downstream applications are hindered by sparse regulatory stations and noisy real-world measurements. While diffusion models have shown promise for probabilistic spatiotemporal imputation, common conditioning strategies can be brittle: purely input-based conditioning may drift from sparse constraints, whereas hard clamping can introduce a clean\u2013noisy mismatch and propagate corrupted readings during reverse sampling. In this work, we propose STGPD (SpatioTemporal Graph Posterior Diffusion), a probabilistic framework that formulates city-scale pollutant reconstruction as posterior sampling on a graph-structured spatiotemporal field. STGPD enforces noise-aware soft consistency by re-noising visible observations to the current diffusion level and fusing a noise-matched measurement term with the model prior via variance-weighted fusion under an explicit observation-noise model. To improve spatial extrapolation in heterogeneous urban environments, we further construct a dual-view graph that combines geographic proximity with functional similarity derived from static descriptors. Experiments on real-world monitoring data in Augsburg, Germany, for PM10 and NO2 show that STGPD provides a robust probabilistic reconstruction framework under extreme sparsity, station outages, and synthetic sensor-noise injection in this sparse-monitoring case study. Compared with strong deterministic and diffusion-based baselines, STGPD achieves improved reconstruction accuracy (MAE\/RMSE) and better-calibrated uncertainty estimates (CRPS) under the current evaluation protocols.<\/jats:p>","DOI":"10.3390\/ijgi15040171","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T10:29:08Z","timestamp":1776162548000},"page":"171","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Noise-Aware Diffusion for City-Scale Air-Quality Reconstruction from Sparse Monitoring Stations"],"prefix":"10.3390","volume":"15","author":[{"given":"Guanglei","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5183-9074","authenticated-orcid":false,"given":"Yuchai","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5502-2974","authenticated-orcid":false,"given":"Xun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiansheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Environmental Health and Pollution Control, Guangdong University of Technology, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1038\/s41612-025-01044-6","article-title":"Adaptive high-resolution mapping of air pollution with a novel implicit 3D representation approach","volume":"8","author":"Zhang","year":"2025","journal-title":"npj Clim. Atmos. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lin, H., Li, S., Niu, J., Yang, J., Wang, Q., Li, W., and Liu, S. (2025). Estimation of Ultrahigh Resolution PM2.5 in Urban Areas by Using 30 m Landsat-8 and Sentinel-2 AOD Retrievals. Remote Sens., 17.","DOI":"10.3390\/rs17152609"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102566","DOI":"10.1016\/j.uclim.2025.102566","article-title":"Urban PM2.5 concentration monitoring: A review of recent advances in ground-based, satellite, model, and machine learning integration","volume":"63","author":"Lolli","year":"2025","journal-title":"Urban Clim."},{"key":"ref_4","first-page":"119","article-title":"A statistical approach to some basic mine valuation problems on the Witwatersrand","volume":"52","author":"Krige","year":"1951","journal-title":"J. S. Afr. Inst. Min. Metall."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Shepard, D. (1968). A two-dimensional interpolation function for irregularly-spaced data. ACM \u201868: Proceedings of the 1968 23rd ACM National Conference, Association for Computing Machinery.","DOI":"10.1145\/800186.810616"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liang, Y., Xia, Y., Ke, S., Wang, Y., Wen, Q., Zhang, J., Zheng, Y., and Zimmermann, R. (2023). AirFormer: Predicting Nationwide Air Quality in China with Transformers. AAAI\u201923\/IAAI\u201923\/EAAI\u201923: Proceedings of the AAAI Conference on Artificial Intelligence, AAAI Press.","DOI":"10.1609\/aaai.v37i12.26676"},{"key":"ref_7","first-page":"120804","article-title":"MSTGAN: A Multi-scale Spatiotemporal Graph Adversarial Network for Air Quality Prediction","volume":"676","author":"Deng","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, Z., and Zhao, J. (2024). Air Quality Prediction Based on Dynamic Graph Convolutional Network with Spatiotemporal Attention Mechanism. 2024 4th International Conference on Electronic Information Engineering and Computer Science (EIECS), IEEE.","DOI":"10.1109\/EIECS63941.2024.10800509"},{"key":"ref_9","unstructured":"Feng, Y., Wang, Q., Xia, Y., Huang, J., Zhong, S., and Liang, Y. (2024). Spatio-temporal field neural networks for air quality inference. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"091004","DOI":"10.1088\/2515-7620\/ae0012","article-title":"A graph neural networks approach predicted spatiotemporal changes of ozone concentrations in the Yangtze River Delta (China)","volume":"7","author":"Lin","year":"2025","journal-title":"Environ. Res. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"107393","DOI":"10.1016\/j.rineng.2025.107393","article-title":"Air pollutant prediction by spatial-temporal information reconstruction and fusion","volume":"28","author":"Huo","year":"2025","journal-title":"Results Eng."},{"key":"ref_12","unstructured":"Li, Y., Yu, R., Shahabi, C., and Liu, Y. (2018). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., and Zhu, Z. (2017). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., and Chang, C. (2019). Graph WaveNet for Deep Spatial-Temporal Graph Modeling. IJCAI\u201919: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), AAAI Press.","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., and Zhang, C. (2020). Connecting the dots: Multivariate time series forecasting with graph neural networks. KDD \u201820: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/3394486.3403118"},{"key":"ref_16","first-page":"1234","article-title":"GMAN: A graph multi-attention network for traffic prediction","volume":"34","author":"Zheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_17","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_18","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"10466","DOI":"10.1109\/TPAMI.2024.3443141","article-title":"A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection","volume":"46","author":"Jin","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","first-page":"24804","article-title":"CSDI: Conditional Score-Based Diffusion Models for Probabilistic Time Series Imputation","volume":"34","author":"Tashiro","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, Y., Zhang, G., Wang, Y., Liu, J., and Li, G. (2023). PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation. 2023 IEEE 39th International Conference on Data Engineering (ICDE), IEEE.","DOI":"10.1109\/ICDE55515.2023.00150"},{"key":"ref_22","unstructured":"Zhang, S., Wang, S., Tan, X., Liu, R., Zhang, J., and Wang, J. (2023). Sasdim: Self-adaptive noise scaling diffusion model for spatial time series imputation. arXiv."},{"key":"ref_23","first-page":"12255","article-title":"RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data Imputation","volume":"39","author":"Liu","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"He, W., Lin, R., Shen, L., and Kwok, J. (2025, January 16\u201322). Filling the Missings: Spatiotemporal Data Imputation by Conditional Diffusion. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2025\/320"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1145\/3783986","article-title":"A survey on diffusion models for time series and spatio-temporal data","volume":"58","author":"Yang","year":"2026","journal-title":"ACM Comput. Surv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., and Van Gool, L. (2022). Repaint: Inpainting using denoising diffusion probabilistic models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref_27","first-page":"8432","article-title":"Realistic noise synthesis with diffusion models","volume":"39","author":"Wu","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_28","unstructured":"Chung, H., Kim, J., Mccann, M.T., Klasky, M.L., and Ye, J.C. (2022). Diffusion posterior sampling for general noisy inverse problems. arXiv."},{"key":"ref_29","first-page":"23593","article-title":"Denoising diffusion restoration models","volume":"35","author":"Kawar","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_30","unstructured":"Dou, Z., and Song, Y. (2024, January 7\u201311). Diffusion posterior sampling for linear inverse problem solving: A filtering perspective. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_31","unstructured":"Aali, A., Daras, G., Levac, B., Kumar, S., Dimakis, A.G., and Tamir, J.I. (2024). Ambient diffusion posterior sampling: Solving inverse problems with diffusion models trained on corrupted data. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1109\/TCI.2025.3594988","article-title":"Gaussian is all you need: A unified framework for solving inverse problems via diffusion posterior sampling","volume":"11","author":"Yismaw","year":"2025","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1137\/24M1688321","article-title":"Efficient Diffusion Posterior Sampling for Noisy Inverse Problems","volume":"18","author":"Li","year":"2025","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_34","unstructured":"Song, J., Meng, C., and Ermon, S. (2020). Denoising diffusion implicit models. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1007\/s11633-025-1562-4","article-title":"Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models","volume":"22","author":"Lu","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"ref_36","first-page":"20240329","article-title":"Conditional sampling within generative diffusion models","volume":"383","author":"Zhao","year":"2025","journal-title":"Philos. Trans. A"},{"key":"ref_37","unstructured":"Cini, A., Marisca, I., and Alippi, C. (2021). Multivariate Time Series Imputation by Graph Neural Networks. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"119580","DOI":"10.1016\/j.ins.2023.119580","article-title":"HiSTGNN: Hierarchical spatio-temporal graph neural network for weather forecasting","volume":"648","author":"Ma","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_39","first-page":"1856","article-title":"Spatiotemporal interpolation using graph neural network","volume":"113","author":"Yao","year":"2023","journal-title":"Ann. Am. Assoc. Geogr."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liu, D., Wang, J., Shang, S., and Han, P. (2022). MSDR: Multi-step dependency relation networks for spatial temporal forecasting. KDD \u201822: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/3534678.3539397"},{"key":"ref_41","first-page":"4365","article-title":"Pdformer: Propagation delay-aware dynamic long-range transformer for traffic flow prediction","volume":"37","author":"Jiang","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, D., Cao, J., Zhang, B., Zhang, Y., and Xie, L. (2024). A Novel Flexible Geographically Weighted Neural Network for High-Precision PM2.5 Mapping across the Contiguous United States. ISPRS Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13070217"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kaveh, M., Mesgari, M.S., and Kaveh, M. (2025). A Novel Evolutionary Deep Learning Approach for PM2.5 Prediction Using Remote Sensing and Spatial\u2013Temporal Data: A Case Study of Tehran. ISPRS Int. J. Geo-Inf., 14.","DOI":"10.3390\/ijgi14020042"},{"key":"ref_44","unstructured":"Yuan, Y., Han, C., Ding, J., Jin, D., and Li, Y. (2024). Urbandit: A foundation model for open-world urban spatio-temporal learning. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wen, H., Xia, Y., Jin, M., Yang, B., Salim, F., Wen, Q., Pan, S., and Cong, G. (2025). Foundation models for spatio-temporal data science: A tutorial and survey. KDD \u201825: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, Association for Computing Machinery.","DOI":"10.1145\/3711896.3736552"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Fang, Y., Miao, H., Liang, Y., Deng, L., Cui, Y., Zeng, X., Xia, Y., Zhao, Y., Pedersen, T.B., and Jensen, C.S. (2025). Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review. arXiv.","DOI":"10.1109\/TKDE.2026.3651536"},{"key":"ref_47","unstructured":"Shu, D., Li, Z., and Barati Farimani, A. (2024, January 7\u201311). Physics-Informed Diffusion Models. Proceedings of the International Conference on Learning Representations (ICLR), Vienna Austria."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhou, N., Hong, W., Wang, H., Zheng, J., Wang, Q., Song, Y., Zhang, X.P., Li, Y., and Chen, X. (2025). STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecasting. arXiv.","DOI":"10.1109\/TKDE.2026.3678084"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Delavar, M.R., Gholami, A., Shiran, G.R., Rashidi, Y., Nakhaeizadeh, G.R., Fedra, K., and Hatefi Afshar, S. (2019). A novel method for improving air pollution prediction based on machine learning approaches: A case study applied to the capital city of Tehran. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8020099"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"118438","DOI":"10.1016\/j.envres.2024.118438","article-title":"Quantifying uncertainty: Air quality forecasting based on dynamic spatial-temporal denoising diffusion probabilistic model","volume":"249","author":"Chen","year":"2024","journal-title":"Environ. Res."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1175\/MWR2904.1","article-title":"Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation","volume":"133","author":"Gneiting","year":"2005","journal-title":"Mon. Weather Rev."},{"key":"ref_52","first-page":"49234","article-title":"On calibrating diffusion probabilistic models","volume":"36","author":"Pang","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_53","unstructured":"Cao, W., Wang, D., Li, J., Zhou, H., Li, L., and Li, Y. (2018, January 2\u20138). BRITS: Bidirectional Recurrent Imputation for Time Series. Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, QC, Canada."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/4\/171\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:17:44Z","timestamp":1776313064000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/4\/171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,14]]},"references-count":53,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["ijgi15040171"],"URL":"https:\/\/doi.org\/10.3390\/ijgi15040171","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,14]]}}}