{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T17:53:40Z","timestamp":1791309220339,"version":"4.3.1"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20330"],"award-info":[{"award-number":["U24A20330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Program of Jiangsu Province","award":["SJCX24_2191"],"award-info":[{"award-number":["SJCX24_2191"]}]},{"name":"Innovation Program of Jiangsu Province","award":["SJCX24_2189"],"award-info":[{"award-number":["SJCX24_2189"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Short\u2011term metro passenger flow forecasting\u2014predicting station\u2011level inflow and outflow volumes is challenging, mainly due to the complexity of multimodal spatial couplings and the difficulty of modeling long\u2011range temporal dependencies while retaining local variations. Therefore, this paper proposes an Integrated Spatio-Temporal LSTM (IST-LSTM). IST-LSTM adopts a dual-branch architecture in which a diffusion branch explicitly models OD-driven propagation and a convergence branch captures structural aggregation among stations; these branches are coupled through a Diffusion and Convergence Graph (DCG) that fuses structural links, inter-station distances, and behavior-driven OD diffusion into a unified spatial representation. To strengthen temporal representation, we refine the LSTM gating mechanism by integrating a Swin Transformer module, enabling the model to better represent long-range dependencies while retaining sensitivity to local, fine-grained temporal patterns. To evaluate model generalization under dense and heterogeneous urban conditions, we construct the NJMetro dataset from Nanjing AFC smart-card transaction data, which reflects inner-ring high-density travel dynamics and pronounced spatio-temporal heterogeneity; this dataset is used alongside the public HZMetro dataset. IST-LSTM reduces RMSE by 9.19% on NJMetro relative to GCN-SBULSTM and achieves an average MAE improvement of 9.62% over Graph WaveNet on HZMetro and 8.68% versus LSTM on NJMetro. On HZMetro, it also achieves competitive RMSE performance relative to PB-GRU, with notable advantages at 15- and 30-minute horizons. Overall, the results indicate that the proposed design more effectively captures the coupled spatial and temporal mechanisms underlying metro passenger flow.<\/jats:p>","DOI":"10.1371\/journal.pone.0359409","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T17:26:13Z","timestamp":1791307573000},"page":"e0359409","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Short-term metro passenger flow forecasting via decoupled spatio-temporal modeling with a diffusion-convergence graph and Swin-Enhanced LSTM"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1339-8698","authenticated-orcid":true,"given":"Yixin","family":"Feng","sequence":"first","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-4511","authenticated-orcid":true,"given":"Shangbing","family":"Gao","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anming","family":"Bai","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guxue","family":"Gao","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahuan","family":"Ren","sequence":"additional","affiliation":[{"name":"Huaiyin Institute of Technology","place":["Huaian, Jiangsu, China"],"department":["Department of Computer and Software Engineering"]},{"name":"Trusted Firmware and Intelligent Software Laboratory","place":["Huaian, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"issue":"4","key":"pone.0359409.ref001","first-page":"141","article-title":"Characteristics of stampede accidents in subway stations and risk governance: an investigation of 15 typical accidents since 2008","volume":"4","author":"RS Wang","year":"2016","journal-title":"J Renmin Univ China"},{"key":"pone.0359409.ref002","doi-asserted-by":"crossref","first-page":"103651","DOI":"10.1016\/j.tust.2020.103651","article-title":"A case study of development and utilization of urban underground space in Shenzhen and the Guangdong-Hong Kong-Macao Greater Bay Area","volume":"107","author":"H Xie","year":"2021","journal-title":"Tunn Undergr Sp Tech"},{"key":"pone.0359409.ref003","doi-asserted-by":"crossref","first-page":"105373","DOI":"10.1016\/j.tust.2023.105373","article-title":"Metro systems: construction, operation and impacts","volume":"143","author":"D Lin","year":"2024","journal-title":"Tunn Undergr Sp Tech"},{"issue":"1","key":"pone.0359409.ref004","doi-asserted-by":"crossref","DOI":"10.1007\/s40747-024-01693-9","article-title":"Transforming traffic accident investigations: a virtual-real-fusion framework for intelligent 3D traffic accident reconstruction","volume":"11","author":"Y Chen","year":"2024","journal-title":"Complex Intell Syst"},{"key":"pone.0359409.ref005","doi-asserted-by":"crossref","first-page":"104838","DOI":"10.1016\/j.trc.2024.104838","article-title":"Roadside LiDAR placement for cooperative traffic detection by a novel chance constrained stochastic simulation optimization approach","volume":"167","author":"Y Chen","year":"2024","journal-title":"Transp Res Part C: Emerg Technol"},{"key":"pone.0359409.ref006","first-page":"336","author":"X Tian","year":"2024","journal-title":"FMSYS: Fine-grained passenger flow monitoring in a large-scale metro system based on AFC smart card data. PAKDD; 2024. Singapore: Springer Nature Singapore"},{"key":"pone.0359409.ref007","doi-asserted-by":"crossref","first-page":"7176","DOI":"10.1109\/ACCESS.2019.2890819","article-title":"A Data-Driven-Based Wavelet Support Vector Approach for Passenger Flow Forecasting of the Metropolitan Hub","volume":"7","author":"M Tang","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0359409.ref008","doi-asserted-by":"crossref","unstructured":"Ren Z, Gu H, Ren Z. Predicting Passenger Flow in Hangzhou Metro Stations\u2014Using a Time Series ARIMA Model based on Desensitized Data. In: Proceedings of the 7th International Conference on Cyber Security and Information Engineering. 2022. p. 465\u201370.","DOI":"10.1145\/3558819.3565127"},{"key":"pone.0359409.ref009","doi-asserted-by":"crossref","first-page":"120937","DOI":"10.1109\/ACCESS.2019.2937114","article-title":"Short-Term Passenger Flow Prediction in Urban Public Transport: Kalman Filtering Combined K-Nearest Neighbor Approach","volume":"7","author":"S Liang","year":"2019","journal-title":"IEEE Access"},{"issue":"8","key":"pone.0359409.ref010","first-page":"3681","article-title":"Deep learning for spatio-temporal data mining: A survey","volume":"34","author":"a Zeghina","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"pone.0359409.ref011","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s41019-020-00151-z","article-title":"A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation","volume":"6","author":"H Yuan","year":"2021","journal-title":"Data Sci Eng"},{"key":"pone.0359409.ref012","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"J Zhou","year":"2020","journal-title":"AI Open"},{"key":"pone.0359409.ref013","article-title":"Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875","author":"B Yu","year":"2017"},{"key":"pone.0359409.ref014","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926","author":"Y Li","year":"2017"},{"key":"pone.0359409.ref015","article-title":"Graph WaveNet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121","author":"Z Wu","year":"2019"},{"key":"pone.0359409.ref016","doi-asserted-by":"crossref","first-page":"114691","DOI":"10.1016\/j.engappai.2026.114691","article-title":"Spatial-channel collaborative multi-scale graph interaction deep transfer learning for unsupervised rotating machinery fault diagnosis","volume":"176","author":"X Wang","year":"2026","journal-title":"Eng Appl Artif Intell"},{"issue":"01","key":"pone.0359409.ref017","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1609\/aaai.v33i01.3301922","article-title":"Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting","volume":"33","author":"S Guo","year":"2019","journal-title":"AAAI"},{"key":"pone.0359409.ref018","doi-asserted-by":"crossref","first-page":"128842","DOI":"10.1016\/j.physa.2023.128842","article-title":"Knowledge fusion enhanced graph neural network for traffic flow prediction","volume":"623","author":"S Wang","year":"2023","journal-title":"Physica A Stat Mech Appl"},{"issue":"12","key":"pone.0359409.ref019","doi-asserted-by":"crossref","first-page":"21526","DOI":"10.1109\/TITS.2025.3613178","article-title":"Diffusion Models for Intelligent Transportation Systems: A Survey","volume":"26","author":"M Peng","year":"2025","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"17","key":"pone.0359409.ref020","doi-asserted-by":"crossref","first-page":"15008","DOI":"10.1609\/aaai.v35i17.17761","article-title":"Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network","volume":"35","author":"X Zhang","year":"2021","journal-title":"AAAI"},{"issue":"4","key":"pone.0359409.ref021","doi-asserted-by":"crossref","first-page":"4365","DOI":"10.1609\/aaai.v37i4.25556","article-title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","volume":"37","author":"J Jiang","year":"2023","journal-title":"AAAI"},{"issue":"5","key":"pone.0359409.ref022","article-title":"T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks","volume":"20","author":"A Ji","year":"2025","journal-title":"PLoS One"},{"issue":"1","key":"pone.0359409.ref023","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s10489-025-07056-2","article-title":"Spatiotemporal decoupling-gated transformer: modeling high-dimensional coupling for traffic flow prediction","volume":"56","author":"G Wang","year":"2026","journal-title":"Appl Intell"},{"key":"pone.0359409.ref024","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. p. 9992\u201310002.","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"pone.0359409.ref025","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: a comprehensive review","volume":"6","author":"S Zhang","year":"2019","journal-title":"Comput Soc Netw"},{"key":"pone.0359409.ref026","doi-asserted-by":"crossref","first-page":"108496","DOI":"10.1016\/j.engappai.2024.108496","article-title":"Optimized single-image super-resolution reconstruction: a multimodal approach based on reversible guidance and cyclical knowledge distillation","volume":"133","author":"JK Yan","year":"2024","journal-title":"Eng Appl Artif Intell"},{"issue":"7","key":"pone.0359409.ref027","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures","volume":"31","author":"Y Yu","year":"2019","journal-title":"Neural Comput"},{"key":"pone.0359409.ref028","article-title":"Attention is all you need","author":"A Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0359409.ref029","doi-asserted-by":"crossref","first-page":"102674","DOI":"10.1016\/j.trc.2020.102674","article-title":"Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values","volume":"118","author":"Z Cui","year":"2020","journal-title":"Transp Res Part C: Emerg Technol"},{"issue":"4","key":"pone.0359409.ref030","doi-asserted-by":"crossref","first-page":"3377","DOI":"10.1109\/TITS.2020.3036057","article-title":"Physical-Virtual Collaboration Modeling for Intra- and Inter-Station Metro Ridership Prediction","volume":"23","author":"L Liu","year":"2022","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"7","key":"pone.0359409.ref031","doi-asserted-by":"crossref","first-page":"6950","DOI":"10.1109\/TITS.2021.3065404","article-title":"A Graph Convolutional Stacked Bidirectional Unidirectional-LSTM Neural Network for Metro Ridership Prediction","volume":"23","author":"P Chen","year":"2022","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0359409.ref032","doi-asserted-by":"crossref","unstructured":"Gao F, Wang Z, Liu Z. Parallel multi-graph convolution network for metro passenger volume prediction. In: 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA). IEEE; 2021. p. 1\u201310.","DOI":"10.1109\/DSAA53316.2021.9564196"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T17:26:21Z","timestamp":1791307581000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359409"}},"subtitle":[],"editor":[{"given":"Gen","family":"Li","sequence":"first","affiliation":[{"name":"Nanjing Forestry University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":32,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359409","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]}}}