{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T16:32:09Z","timestamp":1787157129365,"version":"build-2736575974"},"reference-count":45,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Decision-Making Advisory Committee of Shanxi Provincial People\u2019s Government","award":["SXFZJZZS2601"],"award-info":[{"award-number":["SXFZJZZS2601"]}]},{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of China","award":["ZDJ2025-11"],"award-info":[{"award-number":["ZDJ2025-11"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reliable traffic speed forecasting depends on trustworthy historical road-sensor observations, yet deployed sensors may exhibit missing values, outages, noise, calibration drift, and stuck readings. Existing forecasting models are commonly evaluated on cleaned inputs, whereas conventional imputation optimizes historical reconstruction rather than downstream prediction. This study presents the Sensor-Reliability-Aware Framework with Identity-Preserved Design (SRAF-ID), a prediction-oriented speed-channel repair front-end trained end to end using only future forecasting loss. The final model requires no controlled fault-location labels during training or inference. SRAF-ID constructs same-sensor temporal and mask-aware graph-neighborhood candidates, combines them through learned two-way softmax fusion, and preserves node-identity and temporal-context features. On raw-time-disjoint 70%\/10%\/20% splits of the Metropolitan Los Angeles (METR-LA) and California Performance Measurement System Bay Area (PEMS-BAY) datasets, ten-seed matched stress tests cover six window-level controlled perturbations. SRAF-ID reduces faulty-average mean absolute error from 5.12 to 4.82 on METR-LA and from 1.99 to 1.94 on PEMS-BAY, corresponding to relative reductions of 5.7% and 2.4%, respectively. It achieves a lower mean MAE in all 12 dataset-fault comparisons and a lower faulty-average MAE in all ten seeds on both datasets; the clean-input MAE also decreases. Checkpoint-only tests retain positive all-sensor and affected-sensor mean gains in all eight localized dataset-condition pairs, whereas unseen 0.75-standard-deviation global drift produces small adverse means with paired intervals crossing zero. The evidence therefore supports fault-label-free robustness under the defined stress protocols while leaving field-recorded event continuity and fault frequency for external validation.<\/jats:p>","DOI":"10.3390\/s26165263","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T16:12:58Z","timestamp":1787155978000},"page":"5263","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SRAF-ID: A Sensor-Reliability-Aware Framework for Robust Traffic Speed Forecasting Under Missing and Faulty Sensor Observations"],"prefix":"10.3390","volume":"26","author":[{"given":"Peng","family":"Lu","sequence":"first","affiliation":[{"name":"School of Emergency Management Science and Engineering, University of Chinese Academy of Sciences, Beijing 100049, China"},{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of the People\u2019s Republic of China, Beijing 100085, China"},{"name":"Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daming","family":"Wu","sequence":"additional","affiliation":[{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of the People\u2019s Republic of China, Beijing 100085, China"},{"name":"Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaofei","family":"Lan","sequence":"additional","affiliation":[{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of the People\u2019s Republic of China, Beijing 100085, China"},{"name":"Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beinan","family":"Guo","sequence":"additional","affiliation":[{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of the People\u2019s Republic of China, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiao","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Natural Hazards, Ministry of Emergency Management of the People\u2019s Republic of China, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref_1","unstructured":"California Department of Transportation District 03 Mobility Performance Report: 2025 Q2."},{"key":"ref_2","unstructured":"Klein, L.A., Mills, M.K., and Gibson, D.R.P. (2026, July 30). Traffic Detector Handbook: Third Edition\u2014Volume II; FHWA-HRT-06-139, Available online: https:\/\/www.fhwa.dot.gov\/publications\/research\/operations\/its\/06139\/06139.pdf."},{"key":"ref_3","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/MITS.2018.2806634","article-title":"Road Traffic Forecasting: Recent Advances and New Challenges","volume":"10","author":"Vlahogianni","year":"2018","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_4","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1109\/TKDE.2020.3001195","article-title":"A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges","volume":"34","author":"Tedjopurnomo","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_5","unstructured":"Li, Y., Yu, R., Shahabi, C., and Liu, Y. (May, January 30). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_6","doi-asserted-by":"publisher","unstructured":"Yu, B., Yin, H., and Zhu, Z. (2018, January 13\u201319). Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref_7","doi-asserted-by":"publisher","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., and Zhang, C. (2019, January 10\u201316). Graph WaveNet for Deep Spatial-Temporal Graph Modeling. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China.","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref_8","doi-asserted-by":"publisher","unstructured":"Zheng, C., Fan, X., Wang, C., and Qi, J. (2020, January 7\u201312). GMAN: A Graph Multi-Attention Network for Traffic Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i01.5477"},{"key":"ref_9","first-page":"17804","article-title":"Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting","volume":"33","author":"Bai","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","doi-asserted-by":"publisher","unstructured":"Jiang, J., Han, C., Zhao, W.X., and Wang, J. (2023, January 7\u201314). PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i4.25556"},{"key":"ref_11","doi-asserted-by":"publisher","unstructured":"Shao, Z., Zhang, Z., Wang, F., Wei, W., and Xu, Y. (2022, January 17\u201321). Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting. Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM\u201822), Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557702"},{"key":"ref_12","doi-asserted-by":"publisher","unstructured":"Liu, H., Dong, Z., Jiang, R., Deng, J., Deng, J., Chen, Q., and Song, X. (2023, January 21\u201325). Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM \u201823), Birmingham, UK.","DOI":"10.1145\/3583780.3615160"},{"key":"ref_13","doi-asserted-by":"publisher","first-page":"19252","DOI":"10.1109\/TITS.2024.3478816","article-title":"A Comprehensive Survey on Traffic Missing Data Imputation","volume":"25","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"publisher","unstructured":"Sun, T., Zhu, S., Hao, R., Sun, B., and Xie, J. (2022). Traffic Missing Data Imputation: A Selective Overview of Temporal Theories and Algorithms. Mathematics, 10.","DOI":"10.3390\/math10142544"},{"key":"ref_15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1049\/iet-its.2013.0052","article-title":"Missing Traffic Data: Comparison of Imputation Methods","volume":"8","author":"Li","year":"2014","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_16","doi-asserted-by":"publisher","unstructured":"Chang, G., and Ge, T. (2011, January 16\u201318). Comparison of Missing Data Imputation Methods for Traffic Flow. Proceedings of the 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), Changchun, China.","DOI":"10.1109\/TMEE.2011.6199284"},{"key":"ref_17","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/TITS.2009.2026312","article-title":"PPCA-Based Missing Data Imputation for Traffic Flow Volume: A Systematical Approach","volume":"10","author":"Qu","year":"2009","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.trc.2012.12.007","article-title":"A Tensor-Based Method for Missing Traffic Data Completion","volume":"28","author":"Tan","year":"2013","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_19","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.trc.2018.11.003","article-title":"A Bayesian Tensor Decomposition Approach for Spatiotemporal Traffic Data Imputation","volume":"98","author":"Chen","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_20","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.trc.2018.02.021","article-title":"On the Imputation of Missing Data for Road Traffic Forecasting: New Insights and Novel Techniques","volume":"90","author":"Olabarrieta","year":"2018","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_21","doi-asserted-by":"publisher","unstructured":"Bagabaldo, A.R.B., and Gonz\u00e1lez, M.C. (September, January 31). Predicting Traffic Flow on Faulty Traffic Detectors Using Machine Learning Techniques. Proceedings of the International Conference on Transportation and Development 2022, Seattle, WA, USA.","DOI":"10.1061\/9780784484319.019"},{"key":"ref_22","doi-asserted-by":"publisher","first-page":"14317","DOI":"10.1109\/JSEN.2020.3007809","article-title":"Sensing Data Supported Traffic Flow Prediction via Denoising Schemes and ANN: A Comparison","volume":"20","author":"Chen","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_23","doi-asserted-by":"publisher","first-page":"119619","DOI":"10.1016\/j.eswa.2023.119619","article-title":"SAITS: Self-Attention-Based Imputation for Time Series","volume":"219","author":"Du","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_24","unstructured":"Du, W. (2023, January 7). PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series. Proceedings of the KDD 2023 MiLeTS Workshop, Long Beach, CA, USA."},{"key":"ref_25","doi-asserted-by":"publisher","unstructured":"Huang, L., Li, Z., Luo, R., and Su, R. (2023). Missing Traffic Data Imputation with a Linear Generative Model Based on Probabilistic Principal Component Analysis. Sensors, 23.","DOI":"10.3390\/s23010204"},{"key":"ref_26","first-page":"6776","article-title":"BRITS: Bidirectional Recurrent Imputation for Time Series","volume":"Volume 31","author":"Cao","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_27","unstructured":"Cini, A., Marisca, I., and Alippi, C. (2022, January 25\u201329). Filling the Gaps: Multivariate Time Series Imputation by Graph Neural Networks. Proceedings of the International Conference on Learning Representations (ICLR), Virtual."},{"key":"ref_28","first-page":"24804","article-title":"CSDI: Conditional Score-Based Diffusion Models for Probabilistic Time Series Imputation","volume":"Volume 34","author":"Tashiro","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_29","unstructured":"Yoon, J., Jordon, J., and van der Schaar, M. (2018, January 10\u201315). GAIN: Missing Data Imputation Using Generative Adversarial Nets. Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_30","unstructured":"Fortuin, V., Baranchuk, D., R\u00e4tsch, G., and Mandt, S. (2020, January 3\u20135). GP-VAE: Deep Probabilistic Time Series Imputation. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Italy."},{"key":"ref_31","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1177\/03611981221130026","article-title":"Deep Multimodal Learning for Traffic Speed Estimation Combining Dedicated Short-Range Communication and Vehicle Detection System Data","volume":"2677","author":"Min","year":"2023","journal-title":"Transp. Res. Rec."},{"key":"ref_32","doi-asserted-by":"publisher","first-page":"119972","DOI":"10.1016\/j.ins.2023.119972","article-title":"Towards Real-World Traffic Prediction and Data Imputation: A Multi-Task Pretraining and Fine-Tuning Approach","volume":"657","author":"Qu","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_33","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.1109\/TITS.2022.3233890","article-title":"Traffic Prediction with Missing Data: A Multi-Task Learning Approach","volume":"24","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_34","doi-asserted-by":"publisher","unstructured":"Mei, H., Li, J., Liang, Z., Zheng, G., Shi, B., and Wei, H. (2023, January 1\u20134). Uncertainty-Aware Traffic Prediction under Missing Data. Proceedings of the 23rd IEEE International Conference on Data Mining (ICDM), Shanghai, China.","DOI":"10.1109\/ICDM58522.2023.00152"},{"key":"ref_35","doi-asserted-by":"publisher","first-page":"100192","DOI":"10.1016\/j.commtr.2025.100192","article-title":"SAFER-Predictor: Sparse Adversarial Training Framework for Robust Traffic Prediction under Missing and Noisy Data","volume":"5","author":"Liu","year":"2025","journal-title":"Commun. Transp. Res."},{"key":"ref_36","doi-asserted-by":"publisher","first-page":"7127","DOI":"10.1007\/s41060-025-00869-x","article-title":"Detection of Anomalous Vehicular Traffic and Sensor Failures Using Data Clustering Techniques","volume":"20","author":"Moretti","year":"2025","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_37","doi-asserted-by":"publisher","unstructured":"Jia, X., Qu, J., Lyu, Y., Guo, M., Zhang, J., and Guo, F. (2025). A Prediction-Based Anomaly Detection Method for Traffic Flow Data with Multi-Domain Feature Extraction. Appl. Sci., 15.","DOI":"10.3390\/app15063234"},{"key":"ref_38","doi-asserted-by":"publisher","first-page":"117319","DOI":"10.1016\/j.chaos.2025.117319","article-title":"A Novel Throttle-Based Self-Stabilizing Control Scheme Integrated into an Anisotropic Continuum Model to Mitigate Cyber-Attacks in Connected Vehicle Scenarios","volume":"201","author":"Zhai","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"ref_39","doi-asserted-by":"publisher","unstructured":"Chang, J., Yin, J., Hao, Y., and Gao, C. (2025). STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast. Sensors, 25.","DOI":"10.3390\/s25113446"},{"key":"ref_40","doi-asserted-by":"publisher","unstructured":"Zhang, L., Xu, S., Li, S., Pan, L., and Gong, S. (2025). D-MGDCN-CLSTM: A Traffic Prediction Model Based on Multi-Graph Gated Convolution and Convolutional Long-Short-Term Memory. Sensors, 25.","DOI":"10.3390\/s25020561"},{"key":"ref_41","doi-asserted-by":"publisher","unstructured":"Qian, Y., Kang, T., Zhang, S., Li, C., Wang, X., and Zhao, S. (2026). Multiscale Traffic Dynamics Representation for Forecasting via MEMD-Guided Dual-Branch Recurrent Networks. Sensors, 26.","DOI":"10.3390\/s26113369"},{"key":"ref_42","doi-asserted-by":"publisher","unstructured":"Zeng, W., Wang, K., Zhou, J., and Cheng, R. (2023). Traffic Flow Prediction Based on Hybrid Deep Learning Models Considering Missing Data and Multiple Factors. Sustainability, 15.","DOI":"10.3390\/su151411092"},{"key":"ref_43","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.neucom.2018.08.067","article-title":"LSTM-Based Traffic Flow Prediction with Missing Data","volume":"318","author":"Tian","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_44","doi-asserted-by":"publisher","first-page":"63188","DOI":"10.1109\/ACCESS.2020.2984588","article-title":"Traffic Flow Prediction with Missing Data Imputed by Tensor Completion Methods","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_45","doi-asserted-by":"publisher","unstructured":"Kwak, S. (2020). PEMS-BAY and METR-LA in CSV, Version v5, Zenodo.","DOI":"10.5281\/zenodo.5146275"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5263\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T16:13:10Z","timestamp":1787155990000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":45,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165263"],"URL":"https:\/\/doi.org\/10.3390\/s26165263","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]}}}