{"url":"/sota/traffic-prediction-on-pemsd8","task":{"name":"Traffic Prediction","url":"/task/traffic-prediction","note":null},"dataset":{"name":"PeMSD8","url":"/dataset/pemsd8"},"category":"Time Series","categories":["Time Series"],"category_note":null,"description":"**Traffic Prediction** is a task that involves forecasting traffic conditions, such as the volume of vehicles and travel time, in a specific area or along a particular road. This task is important for optimizing transportation systems and reducing traffic congestion.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [BaiduTraffic](https://github.com/JingqingZ/BaiduTraffic) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE","MAE@1h"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"12 steps MAE":"lower","12 steps MAPE":null,"12 steps RMSE":"lower","MAE@1h":"lower"}},"counts":{"rows":13,"rows_with_code":11,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Hierarchical-Attention-LSTM (HierAttnLSTM)","metrics":{"12 steps MAE":"9.215","12 steps RMSE":"22.320"},"uses_additional_data":false,"paper_date":"2022-01-15","paper":"/paper/big-data-application-for-network-level-travel","paper_url":"https://arxiv.org/abs/2201.05760v4","paper_title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","code":"https://github.com/TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"HTVGNN","metrics":{"12 steps MAE":"13.24"},"uses_additional_data":false,"paper_date":"2024-01-17","paper":"/paper/a-novel-hybrid-time-varying-graph-neural","paper_url":"https://arxiv.org/abs/2401.10155v4","paper_title":"A novel hybrid time-varying graph neural network for traffic flow forecasting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"PM-DMNet(R)","metrics":{"12 steps MAE":"13.40","12 steps MAPE":"8.87","12 steps RMSE":"23.22"},"uses_additional_data":false,"paper_date":"2024-08-12","paper":"/paper/pattern-matching-dynamic-memory-network-for-1","paper_url":"https://arxiv.org/abs/2408.07100v1","paper_title":"Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction","code":"https://github.com/wengwenchao123/PM-DMNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"STWave","metrics":{"12 steps MAE":"13.42"},"uses_additional_data":false,"paper_date":"2023-07-26","paper":"/paper/when-spatio-temporal-meet-wavelets","paper_url":"https://ieeexplore.ieee.org/document/10184591","paper_title":"When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks","code":"https://github.com/lmissher/stwave","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"STD-MAE","metrics":{"12 steps MAE":"13.44","12 steps MAPE":"8.76","12 steps RMSE":"22.47"},"uses_additional_data":true,"paper_date":"2023-12-01","paper":"/paper/spatio-temporal-decoupled-masked-pre-training","paper_url":"https://arxiv.org/abs/2312.00516v3","paper_title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","code":"https://github.com/jimmy-7664/std-mae","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":6,"model":"PM-DMNet(P)","metrics":{"12 steps MAE":"13.55","12 steps MAPE":"9.04","12 steps RMSE":"23.35"},"uses_additional_data":false,"paper_date":"2024-08-12","paper":"/paper/pattern-matching-dynamic-memory-network-for-1","paper_url":"https://arxiv.org/abs/2408.07100v1","paper_title":"Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction","code":"https://github.com/wengwenchao123/PM-DMNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"PDFormer","metrics":{"12 steps MAE":"13.58"},"uses_additional_data":false,"paper_date":"2023-01-19","paper":"/paper/pdformer-propagation-delay-aware-dynamic-long","paper_url":"https://arxiv.org/abs/2301.07945v3","paper_title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","code":"https://github.com/BUAABIGSCity/PDFormer","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"PDG2Seq","metrics":{"12 steps MAE":"13.60","12 steps MAPE":"8.99","12 steps RMSE":"23.37"},"uses_additional_data":false,"paper_date":"2024-12-05","paper":"/paper/pdg2seq-periodic-dynamic-graph-to-sequence","paper_url":"https://www.sciencedirect.com/science/article/pii/S0893608024008700?via%3Dihub","paper_title":"PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction","code":"https://github.com/wengwenchao123/PDG2Seq","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"FasterSTS","metrics":{"12 steps MAE":"13.60","MAE@1h":"13.60"},"uses_additional_data":false,"paper_date":"2025-01-01","paper":"/paper/fastersts-a-faster-spatio-temporal","paper_url":"https://arxiv.org/abs/2501.00756v1","paper_title":"FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting","code":"https://github.com/Salabh2k2/Awesome-Project-Collection/blob/main/Traffic_flow_Prediction_using_LSTM%2BFasterSTGCN.ipynb","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DDGCRN","metrics":{"12 steps MAE":"14.40"},"uses_additional_data":false,"paper_date":"2023-05-01","paper":"/paper/a-decomposition-dynamic-graph-convolutional","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0031320323003710","paper_title":"A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting","code":"https://github.com/wengwenchao123/DDGCRN","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"HAGCN","metrics":{"12 steps MAE":"14.85"},"uses_additional_data":false,"paper_date":"2022-09-05","paper":"/paper/hagcn-network-decentralization-attention","paper_url":"https://arxiv.org/abs/2209.01967v1","paper_title":"HAGCN : Network Decentralization Attention Based Heterogeneity-Aware Spatiotemporal Graph Convolution Network for Traffic Signal Forecasting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"STG-NRDE","metrics":{"12 steps MAE":"15.32","12 steps MAPE":"8.9","12 steps RMSE":"24.72"},"uses_additional_data":false,"paper_date":"2023-03-20","paper":"/paper/graph-neural-rough-differential-equations-for","paper_url":"https://arxiv.org/abs/2303.10909v2","paper_title":"Graph Neural Rough Differential Equations for Traffic Forecasting","code":"https://github.com/jeongwhanchoi/STG-NCDE","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":11,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"STG-NCDE","metrics":{"12 steps MAE":"15.45","12 steps MAPE":"9.92","12 steps RMSE":"24.81"},"uses_additional_data":false,"paper_date":"2021-12-07","paper":"/paper/graph-neural-controlled-differential","paper_url":"https://arxiv.org/abs/2112.03558v1","paper_title":"Graph Neural Controlled Differential Equations for Traffic Forecasting","code":"https://github.com/jeongwhanchoi/STG-NCDE","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":14,"n_samples":28,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":14,"n_samples":28,"n_pointer_only_licence":3,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}