CoChat
Sign Up
Cited by 21Seismology and Earthquake StudiesAdvanced Fiber Optic SensorsStructural Health Monitoring Techniques

The DOI matches its Crossref record.

Real-Time Railway Hazard Detection Using Distributed Acoustic Sensing and Hybrid Ensemble Learning

Open access
Yürekli, Yusuf, Özarpa, Cevat, Avcı, İsa·2025·Sensors
DOI 10.3390/s25133992PMC PMC12251868
Open this paper in CoChat — free accountOpen PDF

Abstract

Rockfalls on railways are considered a natural disaster under the topic of landslides. It is an event that varies regionally due to landforms and climate. In addition to traffic density, the Karabük–Yenice railway line also passes through mountainous areas, river crossings, and experiences heavy seasonal rainfall. These conditions necessitate the implementation of proactive measures to mitigate risks such as rockfalls, tree collapses, landslides, and other geohazards that threaten the railway line. Undetected environmental events pose a significant threat to railway operational safety. The study aims to provide early detection of environmental phenomena using vibrations emitted through fiber optic cables. This study presents a real-time hazard detection system that integrates Distributed Acoustic Sensing (DAS) with a hybrid ensemble learning model. Using fiber optic cables and the Luna OBR-4600 interrogator, the system captures environmental vibrations along a 6 km railway corridor in Karabük, Türkiye. CatBoosting, Support Vector Machine (SVM), LightGBM, Decision Tree, XGBoost, Random Forest (RF), and Gradient Boosting Classifier (GBC) algorithms were used to detect the incoming signals. However, the Voting Classifier hybrid model was developed using SVM, RF, XGBoost, and GBC algorithms. The signaling system on the railway line provides critical information for safety by detecting environmental factors. Major natural disasters such as rockfalls, tree falls, and landslides cause high-intensity vibrations due to environmental factors, and these vibrations can be detected through fiber cables. In this study, a hybrid model was developed with the Voting Classifier method to accurately detect and classify vibrations. The model leverages an ensemble of classification algorithms to accurately categorize various environmental disturbances. The system has proven its effectiveness under real-world conditions by successfully detecting environmental events such as rockfalls, landslides, and falling trees with 98% success for Precision, Recall, F1 score, and accuracy.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s25133992

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • A compromised sensor node, falsified measurement, or disrupted data stream can propagate through operational systems, affecting traffic control, rolling stock safety, and signaling integrity.

    “A compromised sensor node, falsified measurement, or disrupted data stream can propagate through operational systems, affecting traffic control, rolling stock safety, and signaling integrity [1,2,3,4].”

    From Sensor-Based Cyber Risk Management in Railway Infrastructure Under the NIS2 Directive (2025) · cites this paper as [4]

    The Introduction discusses detecting environmental hazards with fiber-optic sensors to improve railway safety, and the sensor-setup section describes data collection and transmission. Searches for compromised sensors, falsified measurements, disrupted data streams, and effects on traffic control or signaling found no passage addressing that chain of consequences. (LLM, conf=0.73)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 51

  1. Liu, 2025, Strategies for sustainable road transport: Technological innovation and organizational management through AI, Transp. Res. D Transp. Environ., 141, 104651, 10.1016/j.trd.2025.104651 · DOI
  2. Peng, 2025, Relative improvements between roads and railways and transport carbon dioxide emissions: An environmental Kuznets curve hypothesis test in China, Sustain. Futures, 9, 100520, 10.1016/j.sftr.2025.100520 · DOI
  3. Xu, 2025, Optimizing Railway Track Tamping and Geometry Fine-Tuning Allocation Using a Neural Network-Based Solver, Autom. Constr., 171, 105958, 10.1016/j.autcon.2024.105958 · DOI
  4. Liu, 2025, Effect of cyclic wetting on lateritic clay subgrade settlement and train-track dynamic response of high-speed railway, Transp. Geotech., 51, 101541, 10.1016/j.trgeo.2025.101541 · DOI
  5. Rahman, 2024, A review of distributed acoustic sensing applications for railroad condition monitoring, Mech. Syst. Signal Process, 208, 110983, 10.1016/j.ymssp.2023.110983 · DOI
  6. Rahman, 2024, Remote condition monitoring of rail tracks using distributed acoustic sensing (DAS): A deep CNN-LSTM-SW based model, Green Energy Intell. Transp., 3, 100178, 10.1016/j.geits.2024.100178 · DOI
  7. Heydari, H., Zakeri, J.A., and Noori, A.S. (2025). Material-oriented maintenance of railway track using under sleeper pad (USP). Int. J. Transp. Sci. Technol., in press. · DOI
  8. Madan, 2025, Monitoring rail track bolt loosening using fiber-optic distributed acoustic sensing, Sens. Actuators A Phys., 382, 116176, 10.1016/j.sna.2024.116176 · DOI
  9. Beirao, 2023, Combination of Fibre Optic Acoustic Sensing, IoT & Smart CCTV Data And Its Uses For The Rail Industry, Transp. Res. Procedia, 72, 2668, 10.1016/j.trpro.2023.11.806 · DOI
  10. Wagner, A., Nash, A., Michelberger, F., Grossberger, H., and Lancaster, G. (2023). The Effectiveness of Distributed Acoustic Sensing (DAS) for Broken Rail Detection. Energies, 16. · DOI
  11. Khameneh, 2025, A hybrid machine learning and simulation framework for modeling and understanding disinformation-induced disruptions in public transit systems, Reliab. Eng. Syst. Saf., 255, 110656, 10.1016/j.ress.2024.110656 · DOI
  12. Guzzetti, 2002, STONE: A computer program for the three-dimensional simulation of rock-falls, Comput. Geosci., 28, 1079, 10.1016/S0098-3004(02)00025-0 · DOI
  13. Espinosa, 2018, Advanced monitoring of rail breakage in double-track railway lines by means of PCA techniques, Appl Soft Comput, 63, 1, 10.1016/j.asoc.2017.11.009 · DOI
  14. 2020, Analysis and prediction of railway accident risks using machine learning, AIMS Electron. Electr. Eng., 4, 19, 10.3934/ElectrEng.2020.1.19 · DOI
  15. Vivanco, 2024, Importance of geotechnical diagnosis in railway management: A review, Transp. Eng., 18, 100293, 10.1016/j.treng.2024.100293 · DOI
  16. Varol, 2023, Three-Dimensional Probabilistic and Empirical Evaluation of Rockfalls: The Case of Kayseri–Soğanlı Settlement, J. Geol. Eng., 47, 1
  17. Nasery, 2020, Investigation of Integrated Solutions in Rock Rehabilitation Works: A Case Study from Trabzon Kaymaklı, Uludağ Univ. J. Fac. Eng., 25, 539, 10.17482/uumfd.680226 · DOI
  18. Coruk, 2025, Determining Energy Capacity and Site Selection Criteria for Flexible Rockfall Barriers Against Rockfall Risks, Nat. Disasters Environ. J., 11, 135
  19. Yurteri, 2024, Flood Risk Analysis in GIS Environment Using Analytic Hierarchy Process (AHP): The Case of Karabük Province, J. Eng. Sci. Des., 12, 298
  20. Arslan, 2020, Artificial Intelligence and Its Applications in Education, West. Anatol. J. Educ. Sci., 11, 71
  21. Singil, 2022, Artificial Intelligence and Human Rights, Public Priv. Int. Law Bull., 42, 121, 10.26650/ppil.2022.42.1.970856 · DOI
  22. Cao, 2024, Efficient On-Demand Design of Fiber Optic Vibration Sensor With a Symmetric Bidirectional Neural Network, IEEE Sens. J., 24, 14279, 10.1109/JSEN.2024.3377197 · DOI
  23. Atalay, 2017, Artificial Intelligence and Machine Learning Applications in Big Data Analysis, Mehmet Akif Ersoy Üniversitesi Sos. Bilim. Enstitüsü Derg., 9, 155, 10.20875/makusobed.309727 · DOI
  24. Aburakhia, S., Shami, A., and Karagiannidis, G.K. (2024). On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach. arXiv. · DOI
  25. Yao, X., Liu, Z., Zhang, Y., Tao, Z., Liang, P., and Zhao, J. (2024). Effect of regionalized structures on rock fracture process. Sci. Rep., 14. · DOI
  26. Zhou, 2025, Enhancing debris flow warning via machine learning feature reduction and model selection, ESS Open Arch., 130, e2024JF008094
  27. Sarkar, 2025, Landslide susceptibility assessment for the Darjeeling Toy Train route: A GIS and machine learning approach, Stoch. Environ. Res. Risk Assess., 39, 613, 10.1007/s00477-024-02885-y · DOI
  28. Chang, C.-C., Huang, K.-H., Lau, T.-K., Huang, C.-F., and Wang, C.-H. (2025). Using deep learning model integration to build a smart railway traffic safety monitoring system. Sci. Rep., 15. · DOI
  29. Tang, 2025, An EDCC-EMD analysis-based network for DAS VSP data denoising in frequency domain, Pet. Sci., 22, 1929, 10.1016/j.petsci.2025.03.006 · DOI
  30. Kang, 2024, Automatic Monitoring of Rock-Slope Failures Using Distributed Acoustic Sensing and Semi-Supervised Learning, Geophys. Res. Lett., 51, e2024GL110672, 10.1029/2024GL110672 · DOI
  31. Wang, 2025, Enhancing traffic monitoring with noise-robust distributed acoustic sensing and deep learning, J. Appl. Geophy., 233, 105616, 10.1016/j.jappgeo.2024.105616 · DOI
  32. Li, 2020, Fiber distributed acoustic sensing using convolutional long short-term memory network: A field test on high-speed railway intrusion detection, Opt. Express, 28, 2925, 10.1364/OE.28.002925 · DOI
  33. Cao, 2024, High-Temperature Fiber-Optic Vibration Sensor Based on an Atomic Frequency Standard, ACS Photonics, 11, 3713, 10.1021/acsphotonics.4c00885 · DOI
  34. Aela, 2024, Vision-based monitoring of railway superstructure: A review, Constr. Build. Mater., 442, 137385, 10.1016/j.conbuildmat.2024.137385 · DOI
  35. Xu, 2025, An innovative method integrating two deep learning networks and hyperparameter optimization for identifying fiber optic temperature measurements in earth-rock dams, Adv. Eng. Softw., 199, 103802, 10.1016/j.advengsoft.2024.103802 · DOI
  36. Poyyamozhi, 2024, Enhancing railway track maintenance with real-time ultrasonic and moisture sensing: Proactive and zone-specific management strategies, Results Eng., 24, 103472, 10.1016/j.rineng.2024.103472 · DOI
  37. Mishra, 2022, Real time implementation of fiber Bragg grating sensor in monitoring flat wheel detection for railways, Eng. Fail. Anal., 138, 106376, 10.1016/j.engfailanal.2022.106376 · DOI
  38. Ramos, 2024, Machine Learning Models for Predicting Permanent Deformation in Railway Tracks, Transp. Geotech., 47, 101289, 10.1016/j.trgeo.2024.101289 · DOI
  39. Dai, 2022, Acceleration-Guided Acoustic Signal Denoising Framework Based on Learnable Wavelet Transform Applied to Slab Track Condition Monitoring, IEEE Sens. J., 22, 24140, 10.1109/JSEN.2022.3218182 · DOI
  40. Elgendy, 2025, Utilizing Voting Classifiers for Enhanced Analysis and Diagnosis of Cardiac Conditions, Results Eng., 26, 104636, 10.1016/j.rineng.2025.104636 · DOI
  41. Bhagat, 2022, Application of logistic regression, CART and random forest techniques in prediction of blast-induced slope failure during reconstruction of railway rock-cut slopes, Eng. Fail. Anal., 137, 106230, 10.1016/j.engfailanal.2022.106230 · DOI
  42. Ahmed, 2025, Enhancing Internet of Things security using performance gradient boosting for network intrusion detection systems, Alex. Eng. J., 116, 472, 10.1016/j.aej.2024.12.106 · DOI
  43. Alqarni, 2025, A Support Vector Machine (SVM) Model for Privacy Recommending Data Processing Model (PRDPM) in Internet of Vehicles, Comput. Mater. Contin., 82, 389
  44. Bilali, 2025, A novel hybrid modeling approach based on empirical methods, PSO, XGBoost, and multiple GCMs for forecasting long-term reference evapotranspiration in a data scarce-area, Comput. Electron. Agric., 232, 110106, 10.1016/j.compag.2025.110106 · DOI
  45. Rajathi, 2025, Hybrid Learning Model for intrusion detection system: A combination of parametric and non-parametric classifiers, Alex. Eng. J., 112, 384, 10.1016/j.aej.2024.10.101 · DOI
  46. Khan, 2023, An optimized ensemble prediction model using AutoML based on soft voting classifier for network intrusion detection, J. Netw. Comput. Appl., 212, 103560, 10.1016/j.jnca.2022.103560 · DOI
  47. Zhang, 2015, The use of ROC and AUC in the validation of objective image fusion evaluation metrics, Signal Process., 115, 38, 10.1016/j.sigpro.2015.03.007 · DOI
  48. Koca, 2023, Cybersecurity attack detection model, using machine learning techniques, Acta Polytech. Hung., 20, 29, 10.12700/APH.20.7.2023.7.2 · DOI
  49. Avcı, İ., and Koca, M. (2023). Predicting DDoS Attacks Using Machine Learning Algorithms in Building Management Systems. Electronics, 12. · DOI
  50. Avcı, İ., and Koca, M. (2024). A Novel Security Risk Analysis Using the AHP Method in Smart Railway Systems. Appl. Sci., 14. · DOI
  51. Sun, 2024, Precise disturbance localization of long distance fiber interferometer vibration senor based on an improved time–frequency variation feature extraction scheme, Infrared Phys. Technol., 137, 105097, 10.1016/j.infrared.2023.105097 · DOI

Cited by

Sorted by citations

Metadata

Authors
Yürekli, Y., Özarpa, C., & Avcı, İ.
Affiliations
  • Karabük University (TR)
  • Ankara Medipol Üniversitesi (TR)
Corresponding author
Yürekli, Yusuf
ORCID
Venue
Sensors
Publisher
MDPI AG
Published
2025-06-26
Volume
25
Issue
13
Pages
3992
ISSN
1424-8220 (ISSN-L)
DOI
10.3390/s25133992
PMC
PMC12251868
OpenAlex
W4411690780
Cited by
21
References
0
Citations by year
2026: 16 · 2025: 5
FWCI
5.41
Type
journal article
Language
en
Open access
Licence
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Seismology and Earthquake Studies
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Fiber Optic Sensors
  • Physical Sciences › Engineering › Civil and Structural Engineering › Structural Health Monitoring Techniques
Keywords
distributed acoustic sensing, fiber optic vibration sensing, rockfall detection, landslide detection, geohazards, voting classifier, ensemble learning, real-time monitoring, railway safety

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review