{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T23:56:10Z","timestamp":1775519770019,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"\u2018Pioneer\u2019 and \u2018Leading Goose\u2019 R&amp;D Program of Zhejiang Province","award":["2024C01180"],"award-info":[{"award-number":["2024C01180"]}]},{"name":"\u2018Pioneer\u2019 and \u2018Leading Goose\u2019 R&amp;D Program of Zhejiang Province","award":["2024J129"],"award-info":[{"award-number":["2024J129"]}]},{"name":"\u2018Pioneer\u2019 and \u2018Leading Goose\u2019 R&amp;D Program of Zhejiang Province","award":["D21013"],"award-info":[{"award-number":["D21013"]}]},{"name":"\u2018Pioneer\u2019 and \u2018Leading Goose\u2019 R&amp;D Program of Zhejiang Province","award":["52272334"],"award-info":[{"award-number":["52272334"]}]},{"name":"Ningbo Natural Science Foundation","award":["2024C01180"],"award-info":[{"award-number":["2024C01180"]}]},{"name":"Ningbo Natural Science Foundation","award":["2024J129"],"award-info":[{"award-number":["2024J129"]}]},{"name":"Ningbo Natural Science Foundation","award":["D21013"],"award-info":[{"award-number":["D21013"]}]},{"name":"Ningbo Natural Science Foundation","award":["52272334"],"award-info":[{"award-number":["52272334"]}]},{"name":"National \u201c111\u201d Centre on Safety and Intelligent Operation of Sea Bridge","award":["2024C01180"],"award-info":[{"award-number":["2024C01180"]}]},{"name":"National \u201c111\u201d Centre on Safety and Intelligent Operation of Sea Bridge","award":["2024J129"],"award-info":[{"award-number":["2024J129"]}]},{"name":"National \u201c111\u201d Centre on Safety and Intelligent Operation of Sea Bridge","award":["D21013"],"award-info":[{"award-number":["D21013"]}]},{"name":"National \u201c111\u201d Centre on Safety and Intelligent Operation of Sea Bridge","award":["52272334"],"award-info":[{"award-number":["52272334"]}]},{"name":"National Natural Science Foundation of China","award":["2024C01180"],"award-info":[{"award-number":["2024C01180"]}]},{"name":"National Natural Science Foundation of China","award":["2024J129"],"award-info":[{"award-number":["2024J129"]}]},{"name":"National Natural Science Foundation of China","award":["D21013"],"award-info":[{"award-number":["D21013"]}]},{"name":"National Natural Science Foundation of China","award":["52272334"],"award-info":[{"award-number":["52272334"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Currently, the short-term accurate prediction of multi-region taxi pick-up demand often adopts methods that integrate graph neural networks with temporal modeling. However, most models focus solely on node features during the learning process, neglecting or simplifying edge features. This study adopts a hybrid prediction framework, Edge-GATv2-LSTM, which integrates an edge-aware attention-based graph neural network (Edge-GATv2) with a temporal modeling component (LSTM). The framework not only models spatial interactions among regions via GATv2 and temporal evolution via LSTM but also incorporates edge features into the attention computation structure, jointly representing them with node features. This enables the model to perceive both node attributes and the strength of inter-regional relationships during attention weight calculation. Experiments are conducted based on real-world taxi order data from Ningbo City, and the results demonstrate that the adopted Edge-GATv2-LSTM model exhibits favorable performance in terms of pick-up demand prediction accuracy. Specifically, the model achieves the lowest RMSE and MAE of 3.85 and 2.86, respectively, outperforming all baseline methods and confirming its effectiveness in capturing spatiotemporal demand patterns. This research can provide decision-making support for taxi drivers, platform operators, and traffic management departments\u2014for example, by offering a reference basis for optimizing taxi pick-up route planning when vehicles are unoccupied.<\/jats:p>","DOI":"10.3390\/systems13080681","type":"journal-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T14:32:36Z","timestamp":1754922756000},"page":"681","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Region Taxi Pick-Up Demand Prediction Based on Edge-GATv2-LSTM"],"prefix":"10.3390","volume":"13","author":[{"given":"Jiawen","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinliang","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengjun","family":"Zheng","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2020\/8846955","article-title":"Taxi demand prediction based on a combination forecasting model in hotspots","volume":"2020","author":"Liu","year":"2020","journal-title":"J. Adv. Transp."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"104413","DOI":"10.1016\/j.tra.2025.104413","article-title":"Spatial transferability of machine learning based models for ride-hailing demand prediction","volume":"193","author":"Roy","year":"2025","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103508","DOI":"10.1016\/j.trc.2021.103508","article-title":"The impact of ride-hail surge factors on taxi bookings","volume":"136","author":"Agarwal","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1177\/03611981221144279","article-title":"Will the order be canceled? Order cancellation probability prediction based on deep residual model","volume":"2677","author":"Sun","year":"2023","journal-title":"Transp. Res. Rec."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102821","DOI":"10.1016\/j.trb.2023.102821","article-title":"A dynamic multi-region MFD model for ride-sourcing with ridesplitting","volume":"177","author":"Beojone","year":"2023","journal-title":"Transp. Res. Part B Methodol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"12300","DOI":"10.1109\/TITS.2025.3558274","article-title":"Ride-Hailing Service Pattern Recognition and Demand Prediction: A Reinforcement Ensemble Learning with Fuzzy C-Means Clustering Approach","volume":"26","author":"Jin","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102951","DOI":"10.1016\/j.trc.2020.102951","article-title":"Multi-community passenger demand prediction at region level based on spatio-temporal graph convolutional network","volume":"124","author":"Tang","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5704","DOI":"10.1109\/TITS.2021.3056415","article-title":"A multi-task matrix factorized graph neural network for co-prediction of zone-based and OD-based ride-hailing demand","volume":"23","author":"Feng","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103063","DOI":"10.1016\/j.trc.2021.103063","article-title":"Joint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach","volume":"127","author":"Ke","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_10","first-page":"4617","article-title":"Coupled layer-wise graph convolution for transportation demand prediction","volume":"35","author":"Ye","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3875","DOI":"10.1109\/TITS.2019.2915525","article-title":"Contextualized spatial\u2013temporal network for taxi origin-destination demand prediction","volume":"20","author":"Liu","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1109\/TITS.2023.3312224","article-title":"Coupling makes better: An intertwined neural network for taxi and ridesourcing demand co-prediction","volume":"25","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"103709","DOI":"10.1016\/j.trc.2022.103709","article-title":"H-ConvLSTM-based bagging learning approach for ride-hailing demand prediction considering imbalance problems and sparse uncertainty","volume":"140","author":"Chen","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102665","DOI":"10.1016\/j.trc.2020.102665","article-title":"Urban ride-hailing demand prediction with multiple spatio-temporal information fusion network","volume":"117","author":"Jin","year":"2020","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chen, Z. (2020). Multi-Source Information Based Short-Term Taxi Pick-Up Demand Prediction Using Deep-Learning Approaches. [Master\u2019s Thesis, Northeastern University].","DOI":"10.1088\/1742-6596\/2033\/1\/012167"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1177\/03611981241248160","article-title":"Short-Term Origin-Destination Demand Prediction Based on Spatiotemporal Encoder-Decoder Network with a Residual Feature Extractor","volume":"2678","author":"Zhong","year":"2024","journal-title":"Transp. Res. Rec."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/TITS.2022.3216016","article-title":"Exploring the impact of spatiotemporal granularity on the demand prediction of dynamic ride-hailing","volume":"24","author":"Liu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1080\/19427867.2023.2283949","article-title":"GNN-based passenger request prediction","volume":"16","author":"Makhdomi","year":"2024","journal-title":"Transp. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102851","DOI":"10.1016\/j.trc.2020.102851","article-title":"DNEAT: A novel dynamic node-edge attention network for origin-destination demand prediction","volume":"122","author":"Zhang","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112582","DOI":"10.1016\/j.asoc.2024.112582","article-title":"A multi-gated deep graph network with attention mechanisms for taxi demand prediction","volume":"169","author":"Guo","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_21","first-page":"1","article-title":"Passenger mobility prediction via representation learning for dynamic directed and weighted graphs","volume":"13","author":"Wang","year":"2021","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/03611981241287192","article-title":"Efficient Multi-Step Prediction Model That Considers the Influence of Spatial and Temporal Factors on Ride-Hailing Demand","volume":"2679","author":"Ai","year":"2024","journal-title":"Transportation Research Record"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mi, C., Cheng, S., and Lu, F. (2022). Predicting Taxi-Calling Demands Using Multi-Feature and Residual Attention Graph Convolutional Long Short-Term Memory Networks. ISPRS Int. J. Geo-Inf., 11.","DOI":"10.3390\/ijgi11030185"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1080\/19427867.2023.2175420","article-title":"Hybrid deep learning models for short-term demand forecasting of online car-hailing considering multiple factors","volume":"16","author":"Li","year":"2024","journal-title":"Transp. Lett."},{"key":"ref_25","unstructured":"Brody, S., Alon, U., and Yahav, E. (2021). How attentive are graph attention networks?. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, T., and Liu, Y. (2024). GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration. AI, 5.","DOI":"10.20944\/preprints202411.2244.v1"},{"key":"ref_27","unstructured":"Chen, J., and Chen, H. (2021). Edge-featured graph attention network. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"22950","DOI":"10.1109\/JIOT.2024.3381002","article-title":"Dyedgegat: Dynamic edge via graph attention for early fault detection in iiot systems","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_29","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_30","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.1109\/TKDE.2025.3539680","article-title":"Spatio-Temporal Multivariate Probabilistic Modeling for Traffic Prediction","volume":"37","author":"An","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_32","first-page":"7526","article-title":"STP-TrellisNets+: Spatial-temporal parallel TrellisNets for multi-step metro station passenger flow prediction","volume":"35","author":"Ou","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"130323","DOI":"10.1016\/j.physa.2024.130323","article-title":"Environment reconstruction and trajectory planning for automated vehicles driving through signal intersection","volume":"660","author":"Zong","year":"2025","journal-title":"Phys. A Stat. Mech. Its Appl."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/681\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:24:54Z","timestamp":1760034294000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,11]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["systems13080681"],"URL":"https:\/\/doi.org\/10.3390\/systems13080681","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,11]]}}}