Machine Learning, Neural Networks, and Computer Vision in Addressing Railroad Accidents, Railroad Tracks, and Railway Safety: An Artificial Intelligence Review
Source abstract
Abstract
Ensuring robust railway safety is paramount for efficient and reliable transportation systems, a challenge increasingly addressed through advancements in artificial intelligence (AI). This review paper comprehensively explores the burgeoning role of AI in enhancing the safety of railway operations, focusing on key contributions from machine learning, neural networks, and computer vision. We synthesize current research that leverages these sophisticated AI methodologies to mitigate risks associated with railroad accidents and optimize railroad tracks management. The scope of this review encompasses diverse applications, including real-time monitoring of track conditions, predictive maintenance for infrastructure components, automated defect detection, and intelligent systems for obstacle and intrusion detection. Furthermore, it delves into the use of AI in assessing human factors, improving signaling systems, and analyzing accident/incident reports for proactive risk management. By examining the integration of advanced analytical techniques into various facets of railway operations, this paper highlights how AI is transforming traditional safety paradigms, paving the way for more resilient, efficient, and secure railway networks worldwide.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Railway Engineering and Dynamics · Railway Systems and Energy Efficiency · Occupational Health and Safety Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Automotive Engineering and Transport, Kielce University of Technology, 7 Tysiąclecia Państwa Polskiego Ave., 25-314 Kielce, Poland
Department of Information Systems, Kielce University of Technology, 7 Tysiąclecia Państwa Polskiego Ave., 25-314 Kielce, Poland
References (100+)
Show source-provided references
1. A Literature Review of Artificial Intelligence Applications in Railway Systems10.1016/j.trc.2022.103679 ↗
2. A Review of Computer Vision for Railways10.1109/TITS.2025.3552011 ↗
3. Helmi, W., Bridgelall, R., and Askarzadeh, T. (2024). Remote Sensing and Machine Learning for Safer Railways: A Review. Appl. Sci., 14.10.3390/app14093573 ↗
4. Liao, Y., Han, L., Wang, H., and Zhang, H. (2022). Prediction Models for Railway Track Geometry Degradation Using Machine Learning Methods: A Review. Sensors, 22.10.3390/s22197275 ↗
5. Automated Rail Surface Crack Analytics Using Deep Data-Driven Models and Transfer Learning10.1016/j.scs.2021.102898 ↗
6. Choi, J.-Y., and Han, J.-M. (2024). Deep Learning (Fast R-CNN)-Based Evaluation of Rail Surface Defects. Appl. Sci., 14.10.3390/app14051874 ↗
7. Bai, T., Gao, J., Yang, J., and Yao, D. (2021). A Study on Railway Surface Defects Detection Based on Machine Vision. Entropy, 23.10.3390/e23111437 ↗
8. Li, X., Wang, Q., Yang, X., Wang, K., and Zhang, H. (2023). Track Fastener Defect Detection Model Based on Improved YOLOv5s. Sensors, 23.10.3390/s23146457 ↗
9. Hu, J., Qiao, P., Lv, H., Yang, L., Ouyang, A., He, Y., and Liu, Y. (2022). High Speed Railway Fastener Defect Detection by Using Improved YoLoX-Nano Model. Sensors, 22.10.3390/s22218399 ↗
10. Ding, K., Luo, J., Huang, H., Hart, J.M., Qamhia, I.I.A., and Tutumluer, E. (2024). Augmented Dataset for Vision-Based Analysis of Railroad Ballast via Multi-Dimensional Data Synthesis. Algorithms, 17.10.3390/a17080367 ↗
11. A LiDAR Based Obstacle Detection Framework for Railway10.1051/epjconf/202430500027 ↗
12. Influence of Selected Design Parameters of the Composite-Foam Cover Rail on the Course of the TB11 Crash Test of a Road Safety Barrier Forming a Horizontal Concave Arc
13. Łodygowski, K. (2017). Fuelling Compression Ignition Engine by Mineral Diesel Fuel Mixture with Synthetic Hydrocarbons. Arch. Automot. Eng. Arch. Motoryz., 75.10.14669/AM.VOL.75.ART6 ↗
14. Inspection of Railway Catenary Systems Using Machine Learning with Domain Knowledge Integration10.1038/s41598-025-15289-x ↗
15. Tan, P., Cui, Z., Lv, W., Li, X., Ding, J., Huang, C., Ma, J., and Fang, Y. (2022). Pantograph Detection Algorithm with Complex Background and External Disturbances. Sensors, 22.10.3390/s22218425 ↗
16. Railway Accident Prediction Strategy Based on Ensemble Learning10.1016/j.aap.2022.106817 ↗
17. Railroad Accident Analysis by Machine Learning and Natural Language Processing
18. Yürekli, Y., Özarpa, C., and Avcı, İ. (2025). Real-Time Railway Hazard Detection Using Distributed Acoustic Sensing and Hybrid Ensemble Learning. Sensors, 25.10.3390/s25133992 ↗
19. Min, Y., Wang, Z., Liu, Y., and Wang, Z. (2023). FS-RSDD: Few-Shot Rail Surface Defect Detection with Prototype Learning. Sensors, 23.10.3390/s23187894 ↗
20. Natural Disaster Warning System for Safe Operation of a High-Speed Railway10.1093/tse/tdab019 ↗
21. A Reliability Assessment Approach for Slab Track Structure Based on Vehicle-Track Dynamics and Surrogate Model
22. Estimating the Occurrence of Broken Rails in Commuter Railroads with Machine Learning Algorithms10.1177/09544097241280848 ↗
23. Automated Machine Learning Techniques in Prognostics of Railway Track Defects
24. Application of Intelligence System: ANN and ANFIS for Enhanced Slope Stability Analysis
25. Machine Learning-Based Approach for Railway Switch and Crossing System Diagnosis
26. Development of a Machine Learning Based Automated Model to Predict the Load-Bearing Capacity of Circular Hollow Section Brace Members Having Accidental Joint Eccentricity10.1016/j.istruc.2024.107882 ↗
27. Real-Time Assessment for Running Safety of High-Speed Railway Based on Physical Models and Deep Neural Networks10.1016/j.istruc.2025.108466 ↗
28. Wu, C., Lu, X., Wang, Y., and Pang, T. (2025). Prediction of Railway Track Irregularity Based on TCN-BiLSTMs-Attention Model. Proceedings of the 3rd International Conference on Signal Processing, Computer Networks and Communications, SPCNC, Association for Computing Machinery, Inc.10.1145/3712335.3712416 ↗
29. Estimation of Railway Track Longitudinal Irregularity Using Vehicle Response with Information Compression and Bayesian Deep Learning10.1111/mice.12802 ↗
30. A Multimodal TransTCN Fusion Network Embedding Prior Knowledge for Predicting Seismic Responses in High-Speed Railways Considering Pier Height10.1016/j.engstruct.2025.120225 ↗
31. Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks10.1109/TNNLS.2016.2551940 ↗
32. Alsahli, A., Zarembski, A.M., and Attoh-Okine, N. (2020). Predicting Track Geometry Defect Probability Based on Tie Condition Using Pattern Recognition Technique. Proceedings of the ASME International Mechanical Engineering Congress and Exposition, American Society of Mechanical Engineers (ASME).10.1115/1.0003834V ↗
33. Rail Track Monitoring Using AI and Machine Learning
34. Heterogeneous Graph Attention Network for Rail Fastener Looseness Detection Using Distributed Acoustic Sensing and Accelerometer Data Fusion10.1016/j.autcon.2025.106051 ↗
35. Intelligent Detection of Loose Fasteners in Railway Tracks Using Distributed Acoustic Sensing and Machine Learning10.1016/j.engappai.2024.108684 ↗
36. A Method for Train Tracking Based on Distributed Acoustic Sensing
37. An AIoT System for Real-Time Monitoring and Forecasting of Railway Temperature10.1007/s13349-024-00851-4 ↗
38. Estimation of Wheel-Rail Friction Coefficient Using Deep CNN on Axlebox Accelerations10.1016/j.ymssp.2025.112756 ↗
39. Identification of Rail Surface Defects Based on One-Shot Learning
40. MemFormer: A Memory Based Unified Model for Anomaly Detection on Metro Railway Tracks10.1016/j.eswa.2023.121509 ↗
41. Research on Fault Prediction of High-Speed Train Auxiliary Power Supply System Based on LSTM
42. Application of Neural Networks for the Prediction of Railway Bearing Failures10.1177/09544097221084419 ↗
43. Estimating Track Geometry Irregularities from In-Service Train Accelerations Using Deep Learning10.1016/j.autcon.2025.106114 ↗
44. Leveraging Deep Reinforcement Learning for Reducing Longitudinal Train Forces in Railway Systems
45. Development of a Deep Neural Network-Based Life Accident Evaluation Model for Weather-Related Railway Accidents10.1007/s12205-024-0042-7 ↗
46. Wang, Y., and Zhang, Z. (2021). Exploring Multi-Layer Convolutional Neural Networks for Railway Safety Text Classification. Proceedings of the IEEE International Conference on Progress in Informatics and Computing, PIC, Institute of Electrical and Electronics Engineers Inc.10.1109/PIC53636.2021.9687014 ↗
47. Using Text Mining to Establish Knowledge Graph from Accident/Incident Reports in Risk Assessment10.1016/j.eswa.2022.117991 ↗
48. Shabbir, M.N.S.K., Wang, C., Liang, X., and Adajar, E. (2022). A Novel Regression Model-Based Toolbox for Induced Voltage Prediction on Rail Tracks Due to AC Electromagnetic Interference of Adjacent Power Lines. Proceedings of the IEEE Industry Applications Society Annual Meeting (IAS), Institute of Electrical and Electronics Engineers Inc.10.1109/IAS54023.2022.9939715 ↗
49. The Modelling Recorded Faults in Railways and Prediction
50. Cloud-Based Anomaly Detection for Broken Rail Track Using LSTM Autoencoders and Cross-Modal Audio Analysis
51. Prediction of Tram Track Gauge Deviation Using Artificial Neural Network and Support Vector Regression10.1080/14488353.2019.1616357 ↗
52. Review of Data Analytics for Condition Monitoring of Railway Track Geometry10.1109/TITS.2022.3214121 ↗
53. Detection of Rail Line Track and Human Beings Near the Track to Avoid Accidents
54. Yanwei, J., and Yu, D. (2021). Research on Railway Obstacle Detection Method Based on Radar. Proceedings of the International Symposium on Mechatronics and Industrial Informatics, ISMII, Institute of Electrical and Electronics Engineers Inc.10.1109/ISMII52409.2021.00054 ↗
55. Fayyaz, M.A.B., and Johnson, C. (2020). Object Detection at Level Crossing Using Deep Learning. Micromachines, 11.10.3390/mi11121055 ↗
56. Real-Time Object Detection Technology in Railway Operations10.33430/V28N3THIE-2020-0028 ↗
57. Zhang, T., Chen, Y., Qu, J., and Bai, R. (2024). Research on Obstacle Detection Method for Rail Transportation Under Low-Light Condition Based on Infrared Image. Proceedings of the 2024 4th International Conference on Artificial Intelligence, Automation and High Performance Computing, Association for Computing Machinery.10.1145/3690931.3690934 ↗
58. A Forward Train Detection Method Based on Convolutional Neural Network
59. Moving Camera Background-Subtraction for Obstacle Detection on Railway Tracks10.1109/ICIP.2016.7533104 ↗
60. Railway Intrusion Detection Based on Machine Vision: A Survey, Challenges, and Perspectives10.1109/TITS.2024.3412170 ↗
61. A Novel Prevention Conceptual Development of Implementing the Safety Mechanisms in Indian Railways to Prevent Accidents
62. Efficient Dual-Stream Fusion Network for Real-Time Railway Scene Understanding10.1109/TITS.2024.3377187 ↗
63. Efficient Railway Track Region Segmentation Algorithm Based on Lightweight Neural Network and Cross-Fusion Decoder10.1016/j.autcon.2023.105069 ↗
64. Khrueakhrai, S., and Srinonchat, J. (2023). Railway Track Detection Based on SegNet Deep Learning. Proceedings of the IEEE Region 10 Annual International Conference, Proceedings TENCON, Institute of Electrical and Electronics Engineers Inc.10.1109/TENCON58879.2023.10322378 ↗
65. Deep Multitask Learning for Railway Track Inspection10.1109/TITS.2016.2568758 ↗
66. Ji, A., Thee, Q.Y., Woo, W.L., and Wong, E. (2023). Experimental Investigations of a Convolutional Neural Network Model for Detecting Railway Track Anomalies. Proceedings of the IECON Proceedings, IEEE Computer Society.10.1109/IECON51785.2023.10312404 ↗
67. A Stable Lightweight and Adaptive Feature Enhanced Convolution Neural Network for Efficient Railway Transit Object Detection10.1109/TITS.2022.3156267 ↗
68. Wang, Y., Wang, T., Yang, Z., Ren, S., Gouliu, X., and Gao, J. (2023). Deep Convolutional Neural Networks for Rail Surface Defect Perception. Proceedings of the International Conference on Image Processing, Computer Vision and Machine Learning, ICICML, Institute of Electrical and Electronics Engineers Inc.10.1109/ICICML60161.2023.10424775 ↗
69. Development of Track Component Health Indices Using Image-Based Railway Track Inspection Data10.1177/09544097231224825 ↗
70. Use of Deep Convolutional Neural Networks and Change Detection Technology for Railway Track Inspections10.1177/09544097221093486 ↗
71. Defect Classification of Railway Fasteners Using Image Preprocessing and a Lightweight Convolutional Neural Network10.55730/1300-0632.3817 ↗
72. A Rail Fastener Defect Detection Algorithm Based on Improved YOLOv510.1177/09544097241234380 ↗
73. Automated Status Inspection of Fastening Bolts on Freight Trains Using a Machine Vision Approach10.1177/0954409715619603 ↗
74. Wheel Defect Detection with Machine Learning10.1109/TITS.2017.2720721 ↗
75. RAG-PaDiM: Residual Attention Guided PaDiM for Defects Segmentation in Railway Tracks10.1007/s42835-022-01346-2 ↗
76. Uncertainty Inspired Domain Adaptation Network for Rail Surface Defect Segmentation10.1016/j.engappai.2024.108860 ↗
77. Advanced Deep Learning-Based Hybrid Rail Extraction Algorithm Leveraging LiDAR Technology10.1061/JITSE4.ISENG-2457 ↗
78. Luo, H., Cai, L., and Li, C. (2023). Rail Surface Defect Detection Based on An Improved YOLOv5s. Appl. Sci., 13.10.3390/app13127330 ↗
79. Rail Surface Defect Detection Based on MobileViTv2 and Eddy Current
80. Real-Time Railroad Track Components Inspection Based on the Improved YOLOv4 Framework10.1016/j.autcon.2021.103596 ↗
81. Novel Conditional Tabular Generative Adversarial Network Based Image Augmentation for Railway Track Fault Detection10.7717/peerj-cs.2898 ↗
82. Adaptive Fault Diagnosis Model for High-Speed Railway Turnout Using Deep Convolutional Neural Networks10.1504/IJSN.2023.134134 ↗
83. Serna, A.A., Yu, X., and Saniie, J. (2024). AI-Based Security Surveillance and Hazard Detection for Train Platform Safety. Proceedings of the IEEE International Conference on Electro Information Technology, IEEE Computer Society.10.1109/eIT60633.2024.10609931 ↗
84. Rethinking Reliability Engineering Using Machine Vision Systems10.1177/0954409714565500 ↗
85. Wang, Y., Yang, Z., Ren, S., Gouliu, X., Gao, J., and Wang, T. (2023). DDRSNet-Rail Surface Defects Classification Based on Depthwise-Dilated Convolution. Proceedings of the International Conference on Image Processing, Computer Vision and Machine Learning, ICICML, Institute of Electrical and Electronics Engineers Inc.10.1109/ICICML60161.2023.10424928 ↗
86. Autonomous Rail Surface Defect Identification Based on an Improved One-Stage Object Detection Algorithm10.1061/JPCFEV.CFENG-4816 ↗
87. Application of Neural Networks for Recognizing Rail Structural Elements in Magnetic and Eddy Current Defectograms10.3103/S0146411619070137 ↗
88. A Novel Toolbox for Induced Voltage Prediction on Rail Tracks Due to AC Electromagnetic Interference Between Railway and Nearby Power Lines10.1109/TIA.2023.3234935 ↗
89. Design and Application of Real-Time Monitoring System for Service Status of Continuously Welded Turnout on the High-Speed Railway Bridge
90. MSRConvNet: Classification of Railway Track Defects Using Multi-Scale Residual Convolutional Neural Network10.1016/j.engappai.2023.105965 ↗
91. Sansiñena, A., Rodríguez-Arana, B., and Arrizabalaga, S. (2025). A Systematic Review of Acceleration-Based Estimation of Railway Track Quality. Veh. Syst. Dyn., 1–28.10.1080/00423114.2025.2483972 ↗
92. Symmetry-Driven Unsupervised Abnormal Object Detection for Railway Inspection10.1109/TII.2023.3246995 ↗
93. Enhancing Railway Transportation Safety with Proactive Maintenance Strategies Incorporating Machine Learning10.1504/IJSNET.2024.140382 ↗
94. Hadj-Mabrouk, H. (2017). Contribution of Artificial Intelligence to the Assessment of Rail Safety. Proceedings of the Institution of Mechanical Engineers-Stephenson Conference: Research for Railways, Institution of Mechanical Engineers.
95. Contribution of Learning CHARADE System of Rules for the Prevention of Rail Accidents
96. Parkinson, H.J., Bamford, G., and Kandola, B. (2016). The Development of an Enhanced Bowtie Railway Safety Assessment Tool Using a Big Data Analytics Approach. Proceedings of the International Conference on Railway Engineering, Institution of Engineering and Technology.10.1049/cp.2016.0510 ↗
97. Lloyd-Roberts, B., James, P., Edwards, M., Robinson, S., and Werner, T. (2023). Improving Railway Safety: Human-in-the-Loop Invariant Finding. Proceedings of the Conference on Human Factors in Computing Systems, Association for Computing Machinery.10.1145/3544549.3573853 ↗
98. van Gulijk, C., Haugen, S., Barros, A., Vinnem, J.E., and Kongsvik, T. (2018). A Computer Leaning Approach to Obtain Safety Information from Multi-Lingual Accident Reports. Proceedings of the Safety and Reliability–Safe Societies in a Changing World, CRC Press/Balkema.
99. Afzalan, M., Jazizadeh, F., and Ahmadian, M. (2019). A Machine Learning Approach for Track Condition Assessment through Repeated Historical Data Analytics. Proceedings of the Joint Rail Conference, JRC, American Society of Mechanical Engineers (ASME).10.1115/JRC2019-1272 ↗
100. Classification-Learning-Based Framework for Predicting Railway Track Irregularities10.1177/0954409714552818 ↗