{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:20:52Z","timestamp":1765279252537,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"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":["52072313","KYL202312-0160","24-12R"],"award-info":[{"award-number":["52072313","KYL202312-0160","24-12R"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Ministry of Transport Planning and Research Institute Open Project","award":["52072313","KYL202312-0160","24-12R"],"award-info":[{"award-number":["52072313","KYL202312-0160","24-12R"]}]},{"name":"Shanxi Provincial Department of Transportation 2024 Annual Transportation Science and Technology Research Projects","award":["52072313","KYL202312-0160","24-12R"],"award-info":[{"award-number":["52072313","KYL202312-0160","24-12R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Origin\u2013destination (OD) flows are essential for urban studies, yet their acquisition is often hampered by high costs and privacy constraints. Prevailing inference methodologies inadequately address latent spatial dependencies between non-contiguous and distant areas, which are useful for understanding modern transportation systems with expanding regional interactions. To address these challenges, this paper propose a hybrid learning model with the Global\u2013Local Graph Attention Network and XGBoost (GLGAT-XG) to infer OD flows from both global and local geographic contextual information. First, we represent the study area as an undirected weighted graph. Second, we design the GLGAT to encode spatial correlation and urban feature information into the embeddings within a multitask setup. Specifically, the GLGAT employs a graph transformer to capture global spatial correlations and a graph attention network to extract local spatial correlations followed by weighted fusion to ensure validity. Finally, OD flow inference is performed by XGBoost based on the GLGAT-generated embeddings. The experimental results of multiple real-world datasets demonstrate an 8% improvement in RMSE, 7% in MAE, and 10% in CPC over baselines. Additionally, we produce a multi-scale OD dataset in Xian, China, to further reveal spatial-scale effects. This research builds on existing OD flow inference methodologies and offers significant practical implications for urban planning and sustainable development.<\/jats:p>","DOI":"10.3390\/ijgi14050182","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T06:18:02Z","timestamp":1745475482000},"page":"182","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hybrid Learning Model of Global\u2013Local Graph Attention Network and XGBoost for Inferring Origin\u2013Destination Flows"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6058-4922","authenticated-orcid":false,"given":"Zhenyu","family":"Shan","sequence":"first","affiliation":[{"name":"Department of Transportation and Logistics, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Transportation and Logistics, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingzi","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Transportation and Logistics, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaping","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106015","DOI":"10.1016\/j.scs.2024.106015","article-title":"Predicting origin-destination flows by considering heterogeneous mobility patterns","volume":"118","author":"Zhao","year":"2025","journal-title":"Sustain. Cities Soc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.1080\/17538947.2021.1952324","article-title":"Human Mobility Data in the COVID-19 Pandemic: Characteristics, Applications, and Challenges","volume":"14","author":"Hu","year":"2021","journal-title":"Int. J. Digit. Earth"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104050","DOI":"10.1016\/j.scs.2022.104050","article-title":"Machine Learning for Spatial Analyses in Urban Areas: A Scoping Review","volume":"85","author":"Casali","year":"2022","journal-title":"Sustain. Cities Soc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2432","DOI":"10.1109\/COMST.2017.2707140","article-title":"State-of-the-Art Deep Learning: Evolving Machine Intelligence toward Tomorrow\u2019s Intelligent Network Traffic Control Systems","volume":"19","author":"Fadlullah","year":"2017","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4817","DOI":"10.1038\/s41467-019-12809-y","article-title":"Hierarchical Organization of Urban Mobility and Its Connection with City Livability","volume":"10","author":"Bassolas","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104716","DOI":"10.1016\/j.trc.2024.104716","article-title":"Distributionally robust origin\u2013destination demand estimation","volume":"165","author":"Wang","year":"2024","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12942-022-00300-9","article-title":"Reconciling Public Health Common Good and Individual Privacy: New Methods and Issues in Geoprivacy","volume":"21","author":"Kwan","year":"2022","journal-title":"Int. J. Health Geogr."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Savage, N. (2023). Synthetic Data Could Be Better than Real Data. Nature.","DOI":"10.1038\/d41586-023-01445-8"},{"key":"ref_9","first-page":"1","article-title":"Approaches for Human Mobility Data Generation: Research Progress and Trends","volume":"26","author":"Liu","year":"2024","journal-title":"J. Geo-Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"677","DOI":"10.2307\/2087063","article-title":"The P 1 p 2 D Hypothesis: On the Intercity Movement of Persons","volume":"11","author":"Zipf","year":"1946","journal-title":"Am. Sociol. Rev."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/nature10856","article-title":"A Universal Model for Mobility and Migration Patterns","volume":"484","author":"Simini","year":"2012","journal-title":"Nature"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"845","DOI":"10.2307\/2084520","article-title":"Intervening Opportunities: A Theory Relating Mobility and Distance","volume":"5","author":"Stouffer","year":"1940","journal-title":"Am. Sociol. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101354","DOI":"10.1016\/j.compenvurbsys.2019.101354","article-title":"Trip Distribution Modeling with Twitter Data","volume":"77","author":"Pourebrahim","year":"2019","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6576","DOI":"10.1038\/s41467-021-26752-4","article-title":"A Deep Gravity Model for Mobility Flows Generation","volume":"12","author":"Simini","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Robinson, C., and Dilkina, B. (2018, January 20\u201321). A Machine Learning Approach to Modeling Human Migration. Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies, Menlo Park, CA, USA.","DOI":"10.1145\/3209811.3209868"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7474","DOI":"10.1109\/TITS.2020.3003310","article-title":"Spatial Origin-Destination Flow Imputation Using Graph Convolutional Networks","volume":"22","author":"Yao","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","first-page":"808","article-title":"Learning Geo-Contextual Embeddings for Commuting Flow Prediction","volume":"34","author":"Liu","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10707-022-00467-0","article-title":"CONVGCN-RF: A Hybrid Learning Model for Commuting Flow Prediction Considering Geographical Semantics and Neighborhood Effects","volume":"27","author":"Yin","year":"2022","journal-title":"GeoInformatica"},{"key":"ref_19","first-page":"103610","article-title":"A Fusion Model of Temporal Graph Attention Network and Machine Learning for Inferring Commuting Flow from Human Activity Intensity Dynamics","volume":"126","author":"Shi","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_20","unstructured":"Klemmer, K., Safir, N.S., and Neill, D.B. (2023, January 25\u201327). Positional Encoder Graph Neural Networks for Geographic Data. Proceedings of the International Conference on Artificial Intelligence and Statistics, Virtual Conference."},{"key":"ref_21","unstructured":"Wu, Q., Zhao, W., Li, Z., Wipf, D., and Yan, J. (2022, January 10\u201316). Nodeformer: A Scalable Graph Structure Learning Transformer for Node Classification. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20140834","DOI":"10.1098\/rsif.2014.0834","article-title":"Universal Predictability of Mobility Patterns in Cities","volume":"11","author":"Yan","year":"2014","journal-title":"J. R. Soc. Interface"},{"key":"ref_23","first-page":"586","article-title":"Principle of Big Geodata Mining","volume":"74","author":"Pei","year":"2019","journal-title":"Acta Geogr. Sin."},{"key":"ref_24","first-page":"4035","article-title":"Sgformer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation","volume":"38","author":"Lv","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"121023","DOI":"10.1016\/j.physa.2019.04.259","article-title":"New Parameter-Free Mobility Model: Opportunity Priority Selection Model","volume":"526","author":"Liu","year":"2019","journal-title":"Phys. A"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2307\/143141","article-title":"A Computer Movie Simulating Urban Growth in the Detroit Region","volume":"46","author":"Tobler","year":"1970","journal-title":"Econ. Geogr."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5652","DOI":"10.1109\/JSTARS.2020.3023730","article-title":"Mapping human activity volumes through remote sensing imagery","volume":"13","author":"Xing","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_28","unstructured":"Kipf, T.N., and Welling, M. (2017, January 24\u201326). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Pan, Z., Liang, Y., Wang, W., Yu, Y., Zheng, Y., and Zhang, J. (2019, January 4\u20138). Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330884"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yin, H., Chen, H., Wo, T., Xu, J., and Zheng, K. (2019, January 4\u20138). Origin-Destination Matrix Prediction via Graph Convolution. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330877"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1287\/trsc.2022.1128","article-title":"Real-Time Forecasting of Metro Origin-Destination Matrices with High-Order Weighted Dynamic Mode Decomposition","volume":"56","author":"Cheng","year":"2022","journal-title":"Transp. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"7943","DOI":"10.1109\/TITS.2023.3266371","article-title":"Deep Learning for Metro Short-Term Origin-Destination Passenger Flow Forecasting Considering Section Capacity Utilization Ratio","volume":"24","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"121989","DOI":"10.1016\/j.eswa.2023.121989","article-title":"An Origin\u2013Destination Passenger Flow Prediction System Based on Convolutional Neural Network and Passenger Source-Based Attention Mechanism","volume":"238","author":"Lv","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., and Wu, X.-M. (2018, January 2\u20137). Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref_35","unstructured":"Alon, U., and Yahav, E. (2021, January 3\u20137). On the Bottleneck of Graph Neural Networks and Its Practical Implications. Proceedings of the International Conference on Learning Representations, Virtual Conference."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"125534","DOI":"10.1016\/j.eswa.2024.125534","article-title":"A Geographic-Semantic Context-Aware Urban Commuting Flow Prediction Model Using Graph Neural Network","volume":"261","author":"Nejadshamsi","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1109\/TKDE.2024.3523700","article-title":"The Expressive Power of Graph Neural Networks: A Survey","volume":"37","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, L., Geng, X., Ma, X., Liu, F., and Yang, Q. (2019, January 10\u201316). Cross-City Transfer Learning for Deep Spatio-Temporal Prediction. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China.","DOI":"10.24963\/ijcai.2019\/262"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Guo, J., Bai, S., Li, X., Xian, K., Liu, E., Ding, W., and Ma, X. (Comput.-Aided Civ. Infrastruct. Eng., 2025). A Universal Geography Neural Network for Mobility Flow Prediction in Planning Scenarios, Comput.-Aided Civ. Infrastruct. Eng., in press.","DOI":"10.1111\/mice.13398"},{"key":"ref_40","unstructured":"Wu, Z.H., Jain, P., Wright, M.A., Mirhoseini, A., Gonzalez, J.E., and Stoica, I. (2021, January 6\u201314). Representing Long-Range Context for Graph Neural Networks with Global Attention. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), Virtual Conference."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Cai, M., Pang, Y., and Sekimoto, Y. (2022, January 13\u201316). Spatial Attention Based Grid Representation Learning for Predicting Origin\u2013Destination Flow. Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.","DOI":"10.1109\/BigData55660.2022.10021023"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3682058","article-title":"An Interdisciplinary Survey on Origin-Destination Flows Modeling: Theory and Techniques","volume":"57","author":"Rong","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xu, C., Ge, Y., Zhang, X., and Zhou, Y. (Earth Syst. Sci. Data, 2024). A 100-M Gridded Population Dataset of China\u2019s Seventh Census Using Ensemble Learning and Geospatial Big Data, Earth Syst. Sci. Data, Submitted.","DOI":"10.5194\/essd-2023-541"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/5\/182\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:20:34Z","timestamp":1760030434000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/5\/182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["ijgi14050182"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14050182","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}