{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:38:55Z","timestamp":1773002335472,"version":"3.50.1"},"reference-count":77,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":314,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Traffic accident prediction serves as a cornerstone of intelligent transportation systems, enabling proactive city\u2010wide control strategies and public safety interventions. Effective models must capture the evolving spatiotemporal propagation of risk while addressing heterogeneous data distributions across urban regions. Current approaches face significant limitations: fixed graph topologies fail to represent nonstationary accident patterns, while uniform task weighting leads to optimization bias toward data\u2010rich areas, ultimately constraining adaptability in adjacency construction and multihop spatial reasoning. To address these challenges, we propose a dynamic multidiffusion graph network with multitask learning (DiffG\u2010MTL) for city\u2010scale accident prediction. Specifically, a dynamic diffusion adjacency generation (DDAG) module constructs time\u2010varying, diffusion\u2010based adjacency matrices through multiple propagation pathways. A multiscale graph structure learning (MGSL) module captures multihop spatial relationships and temporal cues, while effectively highlighting anomalous traffic behaviors. To alleviate regional data imbalance, we introduce a dynamic multitask learning objective that adaptively redistributes learning focus using recall\u2010aware weighting and task\u2010level normalization. Comprehensive evaluations on six widely used datasets demonstrate that DiffG\u2010MTL consistently outperforms state\u2010of\u2010the\u2010art baselines across multiple evaluation metrics. Additional experiments validate its robustness and effectiveness in modeling complex spatiotemporal accident patterns.<\/jats:p>","DOI":"10.1155\/int\/8995422","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T05:29:48Z","timestamp":1762925388000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiffG\u2010MTL: A Dynamic Multidiffusion Graph Network for Multitask Traffic Accident Prediction"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-5532","authenticated-orcid":false,"given":"Nana","family":"Bu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9920-7751","authenticated-orcid":false,"given":"Zongtao","family":"Duan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3836-0147","authenticated-orcid":false,"given":"Wen","family":"Dang","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"e_1_2_13_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_2_13_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467430"},{"key":"e_1_2_13_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3199160"},{"key":"e_1_2_13_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/for.2975"},{"key":"e_1_2_13_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.021"},{"key":"e_1_2_13_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3155613"},{"key":"e_1_2_13_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104258"},{"key":"e_1_2_13_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102786"},{"key":"e_1_2_13_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.129356"},{"key":"e_1_2_13_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16104"},{"key":"e_1_2_13_11_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi10070485"},{"key":"e_1_2_13_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120333"},{"key":"e_1_2_13_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.168"},{"key":"e_1_2_13_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-025-02363-z"},{"key":"e_1_2_13_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3564564"},{"key":"e_1_2_13_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3055258"},{"key":"e_1_2_13_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3250962"},{"key":"e_1_2_13_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122449"},{"key":"e_1_2_13_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539397"},{"key":"e_1_2_13_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117275"},{"key":"e_1_2_13_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_2_13_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3284156"},{"key":"e_1_2_13_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3275543"},{"key":"e_1_2_13_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121101"},{"key":"e_1_2_13_25_2","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2021.2006607"},{"key":"e_1_2_13_26_2","article-title":"Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control","author":"Wu L.","year":"2021","journal-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management"},{"key":"e_1_2_13_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3349565"},{"key":"e_1_2_13_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112381"},{"key":"e_1_2_13_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3358747"},{"key":"e_1_2_13_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.057"},{"key":"e_1_2_13_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557702"},{"key":"e_1_2_13_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3452106"},{"key":"e_1_2_13_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3343452"},{"key":"e_1_2_13_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2023.07.005"},{"key":"e_1_2_13_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3299557"},{"key":"e_1_2_13_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3283611"},{"key":"e_1_2_13_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066551"},{"key":"e_1_2_13_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3308938"},{"key":"e_1_2_13_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.090"},{"key":"e_1_2_13_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3234444"},{"key":"e_1_2_13_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104120"},{"key":"e_1_2_13_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amar.2021.100204"},{"key":"e_1_2_13_43_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020303"},{"key":"e_1_2_13_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3397716"},{"key":"e_1_2_13_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2997352"},{"key":"e_1_2_13_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104798"},{"key":"e_1_2_13_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3250424"},{"key":"e_1_2_13_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3340182"},{"key":"e_1_2_13_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3039836"},{"key":"e_1_2_13_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.02.031"},{"key":"e_1_2_13_51_2","doi-asserted-by":"crossref","unstructured":"FangY. QinY. LuoH.et al. When spatio-temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks 2023 IEEE 39th International Conference on Data Engineering (ICDE) April 2023 517\u2013529 https:\/\/doi.org\/10.1109\/icde55515.2023.00046.","DOI":"10.1109\/ICDE55515.2023.00046"},{"key":"e_1_2_13_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103659"},{"key":"e_1_2_13_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119056"},{"key":"e_1_2_13_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3354802"},{"key":"e_1_2_13_55_2","doi-asserted-by":"publisher","DOI":"10.3390\/math11112528"},{"key":"e_1_2_13_56_2","unstructured":"FangY. LiangY. HuiB.et al. Efficient large-scale Traffic Forecasting with Transformers: a Spatial Data Management Perspective 2024."},{"key":"e_1_2_13_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3233890"},{"key":"e_1_2_13_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3411638"},{"key":"e_1_2_13_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104428"},{"key":"e_1_2_13_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219922"},{"key":"e_1_2_13_61_2","article-title":"Tap: a Comprehensive Data Repository for Traffic Accident Prediction in Road Networks","author":"Huang B.","year":"2020","journal-title":"Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems"},{"key":"e_1_2_13_62_2","article-title":"Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis","volume":"36","author":"Nippani A.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_13_63_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20587"},{"key":"e_1_2_13_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16542"},{"key":"e_1_2_13_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3102983"},{"key":"e_1_2_13_66_2","doi-asserted-by":"crossref","unstructured":"WangZ. ZhuangD. LiY.et al. St-gin: an Uncertainty Quantification Approach in Traffic Data Imputation with spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC) April 2023 1454\u20131459 https:\/\/doi.org\/10.1109\/itsc57777.2023.10422526.","DOI":"10.1109\/ITSC57777.2023.10422526"},{"key":"e_1_2_13_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3056502"},{"key":"e_1_2_13_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3135621"},{"key":"e_1_2_13_69_2","article-title":"Urban Traffic Accident Risk Prediction Revisited: Regionality, Proximity, Similarity and Sparsity","author":"Chen M.","year":"2022","journal-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"},{"key":"e_1_2_13_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111787"},{"key":"e_1_2_13_71_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102122"},{"key":"e_1_2_13_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3208952"},{"key":"e_1_2_13_73_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108990"},{"key":"e_1_2_13_74_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.107"},{"key":"e_1_2_13_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3279929"},{"key":"e_1_2_13_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3312261"},{"key":"e_1_2_13_77_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109530"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8995422","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/8995422","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8995422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:13:17Z","timestamp":1772993597000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/8995422"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":77,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/8995422"],"URL":"https:\/\/doi.org\/10.1155\/int\/8995422","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-02-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8995422"}}