{"url":"/dataset/pemsd4","name":"PeMSD4","full_name":null,"description_markdown":"The dataset refers to the traffic speed data in San Francisco Bay Area, containing 307 sensors on 29 roads. The time span of the dataset is January-February in 2018. It is a popular benchmark for traffic forecasting.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Traffic Prediction","url":"/task/traffic-prediction","datasets_with_task":"/datasets/task/traffic-prediction"}],"languages":[],"variants":["PeMSD4"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/traffic-prediction-on-pemsd4","task":"Traffic Prediction","dataset_variant":"PeMSD4","rows":13,"metrics":["12 steps MAE","12 steps MAPE","12 steps RMSE"],"first_row_in_archive_order":{"model":"Hierarchical-Attention-LSTM (HierAttnLSTM)","paper":"/paper/big-data-application-for-network-level-travel","metrics":{"12 steps MAE":"9.168","12 steps RMSE":"22.844"},"code_links":[{"title":"TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM","url":"https://github.com/TeRyZh/Network-Level-Travel-Prediction-Hierarchical-Attention-LSTM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/fastersts-a-faster-spatio-temporal","title":"FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting","date":"2025-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pdg2seq-periodic-dynamic-graph-to-sequence","title":"PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction","date":"2024-12-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pattern-matching-dynamic-memory-network-for-1","title":"Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction","date":"2024-08-12","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-novel-hybrid-time-varying-graph-neural","title":"A novel hybrid time-varying graph neural network for traffic flow forecasting","date":"2024-01-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-decoupled-masked-pre-training","title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","date":"2023-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/when-spatio-temporal-meet-wavelets","title":"When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks","date":"2023-07-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-decomposition-dynamic-graph-convolutional","title":"A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting","date":"2023-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-rough-differential-equations-for","title":"Graph Neural Rough Differential Equations for Traffic Forecasting","date":"2023-03-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":6,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pdformer-propagation-delay-aware-dynamic-long","title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","date":"2023-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hagcn-network-decentralization-attention","title":"HAGCN : Network Decentralization Attention Based Heterogeneity-Aware Spatiotemporal Graph Convolution Network for Traffic Signal Forecasting","date":"2022-09-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/big-data-application-for-network-level-travel","title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","date":"2022-01-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-controlled-differential","title":"Graph Neural Controlled Differential Equations for Traffic Forecasting","date":"2021-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":28,"samples_ran":14,"samples_unverified":14,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}