pith. sign in

arxiv: 2509.11614 · v4 · submitted 2025-09-15 · ⚛️ physics.geo-ph

Vessel Detection and Localization Using Distributed Acoustic Sensing in Submarine Optical Fiber Cables

Erick Eduardo Ramirez-Torres , Javier Macias-Guarasa , Daniel Pizarro-Perez , Javier Tejedor , Sira Elena Palazuelos-Cagigas , Pedro J. Vidal-Moreno , Sonia Martin-Lopez , Miguel Gonzalez-Herraez
show 1 more author
Roel Vanthillo
This is my paper

Pith reviewed 2026-05-18 17:09 UTC · model grok-4.3

classification ⚛️ physics.geo-ph
keywords distributed acoustic sensingvessel detectionsubmarine cablesmaritime surveillancemachine learningacoustic localizationDASinfrastructure protection
0
0 comments X

The pith

Distributed acoustic sensing on submarine cables detects vessels with over 90% F1-score and 141 m average distance error.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper shows how existing submarine optical fiber cables can be turned into large acoustic sensor arrays for monitoring ship traffic in real time. Distributed acoustic sensing captures vibrations along the cable, and machine learning models then identify vessels and estimate their distance without needing weather clearance, daylight, or vessels to broadcast their positions via AIS. The authors test the full pipeline over ten continuous days across varied ship types and sea conditions, reporting an F1-score above 90% for detection and a mean localization error of 141 meters. A sympathetic reader would care because this approach could protect the global network of undersea cables that carry most internet traffic and energy links from accidental damage or sabotage using infrastructure already laid on the seafloor. The work also releases the complete evaluation dataset to let others test and refine the method.

Core claim

By repurposing submarine telecommunication cables as large-scale acoustic sensor arrays through distributed acoustic sensing and processing the signals with advanced machine learning models, the approach detects vessels with an overall F1-score exceeding 90% and estimates vessel distance with a mean average error of 141 m. The results come from continuous operation over a ten-day period that includes diverse ship and operational conditions and represent one of the largest-scale real-world validations of this technique to date.

What carries the argument

Distributed Acoustic Sensing (DAS) on submarine optical fiber cables, combined with machine learning models that classify acoustic events and regress distance from the cable.

If this is right

  • Existing submarine cables can supply continuous real-time vessel monitoring that works regardless of weather or lighting.
  • The method functions without any cooperation from the vessels themselves.
  • Ten-day real-world results support using DAS for operational protection of critical underwater infrastructure against damage or sabotage.
  • Releasing the full dataset allows other researchers to develop and compare improved detection and localization algorithms.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • A network of multiple monitored cables could track vessel routes over wider ocean regions rather than single-point detection.
  • The same acoustic data stream might be repurposed to flag non-vessel events such as underwater construction or seismic activity.
  • Merging DAS outputs with satellite or radar feeds could produce hybrid surveillance that compensates for the limits of any single modality.

Load-bearing premise

The acoustic signatures produced by vessels remain sufficiently distinct from background noise and other maritime sources across the full range of sea states and ship types encountered during the ten-day period.

What would settle it

A new recording period that includes high sea states or vessel types absent from the original ten-day set and yields an F1-score below 80% or a mean distance error above 300 m would show the claimed performance does not generalize.

Figures

Figures reproduced from arXiv: 2509.11614 by Daniel Pizarro-Perez, Erick Eduardo Ramirez-Torres, Javier Macias-Guarasa, Javier Tejedor, Miguel Gonzalez-Herraez, Pedro J. Vidal-Moreno, Roel Vanthillo, Sira Elena Palazuelos-Cagigas, Sonia Martin-Lopez.

Figure 1
Figure 1. Figure 1: General location and bathymetry (cable location has been displaced for security considerations). [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: AIS data update rate histogram for the used dataset. [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: AIS vessel speed histogram for the used dataset. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Comparison of bathymetry sources in the cable under study. [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Class instance distribution for different distance thresholds. [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Proposed System Architecture (with reference to the corresponding paper section in relevant modules). [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Long term averaged strain power spectrum plots for strain measurements under different environmental conditions (expressed in dBs). [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: (a) Raw strain signal sensed at 15.4 km in the time interval of the red dashed square in [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Summary of frame processing strategies to exploit spatial and temporal redundancy in the feature space, and majority voting in the output results. [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Baseline F1-scores as a function of distance threshold (T[500,1000,1500,2000,3000,5000]_V1_S10_ACH), by varying the number of sensors used (NS = {10, 25, 50, 100, 250}): (a) F G 1 , (b) F C0 1 , (c) F C1 1 . the same way, the vertical axis range has been modified to facilitate the visualization. Considering the results shown so far, it would seem that the classification task for the 500 m distance thresho… view at source ↗
Figure 11
Figure 11. Figure 11: Baseline F1-scores as a function of distance threshold (T[500,1000,1500]_V1_S1_ACH) by varying the number of sensors used (10, 25, 50, 100 and 250): (a) F G 1 , (b) F C0 1 , (c) F C1 1 [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: F1-scores for 1000 m distance threshold as a function of: (a) temporal context duration (SC = {10, 30, 50} seconds long, T1000_V1_- S[10,30,50]_ACH), (b) 10 s temporal context with majority window length (VC = {1, 3, 5} windows, T1000_V[1,3,5]_S10_ACH), (c) 50 s temporal context with majority window length (VC = {1, 3, 5} windows, T1000_V[1,3,5]_S50_ACH) [PITH_FULL_IMAGE:figures/full_fig_p012_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Global F1-score as a function of the averaging type [PITH_FULL_IMAGE:figures/full_fig_p012_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Classification task: Performance comparison between the best [PITH_FULL_IMAGE:figures/full_fig_p012_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Baseline MAE and rMAE scores (T[500,1000,1500,2000,3000,5000]_V1_S10_ACH): (a) Distance estimation MAE as a function of distance thresholds, (b) Relative MAE as a function of distance thresholds, (c) Distance estimation MAE as a function of the number of sensors used [PITH_FULL_IMAGE:figures/full_fig_p013_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Distance estimation MAE for the 1000 m distance threshold as a function of (a) temporal context duration (SC = {10, 30, 50} seconds long, T1000_V1_S[10,30,50]_ACH), (b) 10 s temporal context with majority window length (VC = {1, 3, 5} windows, T1000_V[1,3,5]_S10_ACH), (c) 50 s temporal context with majority window length (VC = {1, 3, 5} windows, T1000_V[1,3,5]_S50_ACH) [PITH_FULL_IMAGE:figures/full_fig_p… view at source ↗
Figure 17
Figure 17. Figure 17: Distance estimation MAE for the 1000 m distance threshold, 50 seconds time span, 5 majority voting windows, evaluating spatial averaging (ACH) vs. spatial+temporal averaging (ACI) (T1000_V5_S50_A[CH,TI] [PITH_FULL_IMAGE:figures/full_fig_p013_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Regression task: Performance comparison between the best XGBoost [PITH_FULL_IMAGE:figures/full_fig_p013_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Comparison of SRP beamforming and ML regression methods. (a) SRP map for a case where both methods perform well, particularly as the vessel [PITH_FULL_IMAGE:figures/full_fig_p014_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Distribution of absolute distance errors by (a) vessel size range, (b) vessel type (indicating also the average length (avg.len.) for the group type). [PITH_FULL_IMAGE:figures/full_fig_p014_20.png] view at source ↗
read the original abstract

Submarine cables play a critical role in global internet connectivity, energy transmission, and communication but remain vulnerable to accidental damage and sabotage. Recent incidents in the Baltic Sea highlighted the need for enhanced monitoring to protect this vital infrastructure. Traditional vessel detection methods, such as synthetic aperture radar, video surveillance, and multispectral satellite imagery, face limitations in real-time processing, adverse weather conditions, and coverage range. This paper explores Distributed Acoustic Sensing (DAS) as an alternative by repurposing submarine telecommunication cables as large-scale acoustic sensor arrays. DAS offers continuous real-time monitoring, operates independently of cooperative systems like the "Automatic Identification System" (AIS), being largely unaffected by lighting or weather conditions. However, existing research on DAS for vessel tracking is limited in scale and lacks validation under real-world conditions. To address these gaps, a general and systematic methodology is presented for vessel detection and distance estimation using DAS. Advanced machine learning models are applied to improve detection and localization accuracy in dynamic maritime environments. The approach is evaluated over a continuous ten-day period, covering diverse ship and operational conditions, representing one of the largest-scale DAS-based vessel monitoring studies to date, and for which we release the full evaluation dataset. Results demonstrate DAS as a practical tool for maritime surveillance, with an overall F1-score of over 90% in vessel detection, and a mean average error of 141 m for vessel distance estimation, bridging the gap between experimental research and real-world deployment.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The manuscript presents a methodology for vessel detection and localization by repurposing submarine optical fiber cables as Distributed Acoustic Sensing (DAS) arrays. It applies advanced machine learning models to real-world DAS data collected continuously over a ten-day period spanning diverse ship types and operational conditions, reports an overall F1-score exceeding 90% for detection and a mean average error of 141 m for distance estimation, and releases the full evaluation dataset.

Significance. If the performance metrics prove robust under the full range of encountered conditions, the work would establish DAS as a viable, weather-independent tool for real-time maritime surveillance of critical infrastructure. The scale of the field deployment and public release of the dataset are clear strengths that could enable reproducibility and follow-on studies.

major comments (1)
  1. [Evaluation] Evaluation section: The abstract and results claim that the ten-day dataset covers diverse ship and operational conditions sufficient to demonstrate real-world applicability, yet no quantitative breakdown of sea-state distribution, ship-type frequency counts, or separate performance metrics on high-background-noise subsets is provided. This information is load-bearing for the generalization of the reported F1-score and 141 m MAE.
minor comments (1)
  1. [Abstract] Abstract: reporting the F1-score only as 'over 90%' rather than the exact value reduces precision and makes direct comparison with prior work more difficult.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive assessment of the work's significance and for the detailed comment on the evaluation. We agree that quantitative breakdowns of dataset composition are important for supporting claims of real-world applicability and generalization. We address the comment below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: The abstract and results claim that the ten-day dataset covers diverse ship and operational conditions sufficient to demonstrate real-world applicability, yet no quantitative breakdown of sea-state distribution, ship-type frequency counts, or separate performance metrics on high-background-noise subsets is provided. This information is load-bearing for the generalization of the reported F1-score and 141 m MAE.

    Authors: We agree that the current manuscript lacks explicit quantitative breakdowns, which limits the ability to fully assess generalization. In the revised version, we will expand the Evaluation section to include: (i) a summary of sea-state conditions over the 10-day period (e.g., significant wave height distribution from nearby buoy or reanalysis data), (ii) frequency counts of ship types (cargo, tanker, passenger, fishing, etc.) derived from AIS cross-referencing, and (iii) stratified performance metrics (F1-score and distance MAE) on high-background-noise subsets identified by elevated acoustic energy or concurrent meteorological conditions. These additions will be presented in a new table or figure with accompanying text, directly addressing the load-bearing nature of the overall metrics. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical ML evaluation on held-out real data

full rationale

The paper reports direct experimental results from applying machine learning models to Distributed Acoustic Sensing data collected over a continuous ten-day period on real submarine cables. Central performance claims (F1 > 90 %, MAE 141 m) are obtained via evaluation on held-out periods within the collected dataset rather than any derivation, parameter fitting presented as prediction, or self-referential definition. The methodology is described as general and systematic with the full evaluation dataset released, rendering the results self-contained and externally verifiable without reduction to the paper's own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The work rests on standard domain assumptions about DAS signal formation and ML generalization rather than new free parameters or invented physical entities.

axioms (2)
  • domain assumption Vessel-generated acoustic signals produce detectable and classifiable perturbations in the optical phase of light propagating in the submarine fiber.
    Invoked when repurposing the cable as a distributed acoustic array.
  • domain assumption Machine-learning models trained on DAS data can maintain high detection and localization accuracy across varying sea states and vessel types without requiring per-deployment retraining.
    Underlies the reported F1-score and distance error on the ten-day test set.

pith-pipeline@v0.9.0 · 5841 in / 1425 out tokens · 39291 ms · 2026-05-18T17:09:29.641408+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages

  1. [1]

    Finland-Germany submarine cable damaged again in Baltic Sea in possible sabotage act,

    Y . Zoria, “Finland-Germany submarine cable damaged again in Baltic Sea in possible sabotage act,” Online, accessed march 2025, 2025

    work page 2025

  2. [2]

    Undersea cables cut or damaged, leading European nations to

    CBS News, “Undersea cables cut or damaged, leading European nations to ...” Online, accessed june 2025, 2024

    work page 2025

  3. [3]

    Seabed Cable Damaged in Latest Baltic CUI Incident,

    Naval News, “Seabed Cable Damaged in Latest Baltic CUI Incident,” Online, accessed june 2025, 2024

    work page 2025

  4. [4]

    Joint Communication: Strengthen Security and Resilience of Submarine Cables,

    European Commission, “Joint Communication: Strengthen Security and Resilience of Submarine Cables,” Online, accessed june 2025, 2025

    work page 2025

  5. [5]

    A Moving Ship Detection and Tracking Method Based on Optical Remote Sensing Images from the Geostationary Satellite,

    W. Yu, H. You, P. Lv, Y . Hu, and B. Han, “A Moving Ship Detection and Tracking Method Based on Optical Remote Sensing Images from the Geostationary Satellite,”Sensors, vol. 21, no. 22, p. 7547, 2021

    work page 2021

  6. [6]

    Vessel Detection and Tracking Method Based on Video Surveillance,

    N. Wawrzyniak, T. Hyla, and A. Popik, “Vessel Detection and Tracking Method Based on Video Surveillance,”Sensors, vol. 19, no. 23, p. 5230, 2019

    work page 2019

  7. [7]

    Ship Detection in Multispectral Satellite Images Under Complex Environment,

    X. Xie, B. Li, and X. Wei, “Ship Detection in Multispectral Satellite Images Under Complex Environment,”Remote Sensing, vol. 12, no. 5, p. 792, 2020

    work page 2020

  8. [8]

    Photonic seismology: A new decade of distributed acoustic sensing in geophysics from 2012 to 2023,

    F. Cheng, “Photonic seismology: A new decade of distributed acoustic sensing in geophysics from 2012 to 2023,”Surveys in Geophysics, vol. 45, no. 4, pp. 1205–1243, 2024

    work page 2012

  9. [9]

    Sensing whales, storms, ships and earthquakes using an Arctic fibre optic cable,

    M. Landrø, L. Bouffaut, H. J. Kriesell, J. R. Potter, R. A. Rørstadbotnen, K. Taweesintananon, S. E. Johansen, J. K. Brenne, A. Haukanes, O. Schjelderup, and F. Storvik, “Sensing whales, storms, ships and earthquakes using an Arctic fibre optic cable,”Scientific Reports, vol. 12, no. 1, 2022

    work page 2022

  10. [10]

    Ship noise characterization for marine traffic monitoring using dis- tributed acoustic sensing,

    L. Thiem, S. Wienecke, K. Taweesintananon, M. Vaupel, and M. Landrø, “Ship noise characterization for marine traffic monitoring using dis- tributed acoustic sensing,” in2023 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters. IEEE, Oct. 2023, pp. 334–339

    work page 2023

  11. [11]

    Toward Detecting Ship Char- acteristics and Movements using DAS and Machine Learning,

    J. Malaprade, R. Hunt, and G. Lees, “Toward Detecting Ship Char- acteristics and Movements using DAS and Machine Learning,” in Proceedings of the 10th International Conference on Insulated Power Cables (Jicable’19), Versailles, France, June 2019

    work page 2019

  12. [12]

    Underwater Noise Characteristics of Small Ships,

    S. Malinowski and I. Gloza, “Underwater Noise Characteristics of Small Ships,”Acta Acustica united with Acustica, vol. 88, pp. 718–721, 2002

    work page 2002

  13. [13]

    Design and evaluation of real-time data storage and signal processing in a long-range distributed acoustic sensing (das) using cloud-based services,

    A. Nur and Y . Muanenda, “Design and evaluation of real-time data storage and signal processing in a long-range distributed acoustic sensing (das) using cloud-based services,”Sensors, vol. 24, no. 18, 2024

    work page 2024

  14. [14]

    DASSA: Parallel DAS data storage and analysis for subsurface event detection,

    B. Dong, V . R. Tribaldos, X. Xing, S. Byna, J. Ajo-Franklin, and K. Wu, “DASSA: Parallel DAS data storage and analysis for subsurface event detection,” in2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 2020, pp. 254–263

    work page 2020

  15. [15]

    Preliminary assessment of ship detection and trajectory evaluation using distributed acoustic sensing on an optical fiber telecom cable,

    D. Rivet, B. de Cacqueray, A. Sladen, A. Roques, and G. Calbris, “Preliminary assessment of ship detection and trajectory evaluation using distributed acoustic sensing on an optical fiber telecom cable,”The Journal of the Acoustical Society of America, vol. 149, no. 4, pp. 2615– 2627, 2021

    work page 2021

  16. [16]

    Application of machine learning to microseismic event detection in distributed acoustic sensing data,

    A. L. Stork, A. F. Baird, S. A. Horne, G. Naldrett, S. Lapins, J.- M. Kendall, J. Wookey, J. P. Verdon, A. Clarke, and A. Williams, “Application of machine learning to microseismic event detection in distributed acoustic sensing data,”GEOPHYSICS, vol. 85, no. 5, p. KS149–KS160, 2020. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 16

    work page 2020

  17. [17]

    Source detection and tracking for underwater distributed acoustic sens- ing,

    K. T. Drylerakis, M. Belal, R. Mestre, T. J. Norman, and C. Evers, “Source detection and tracking for underwater distributed acoustic sens- ing,” in2024 32nd European Signal Processing Conference (EUSIPCO), 2024, pp. 1292–1296

    work page 2024

  18. [18]

    Application of machine learning for signal recognition in distributed fibre optic acoustic sensing technology,

    Y . Zhan, L. Liu, and K. Li, “Application of machine learning for signal recognition in distributed fibre optic acoustic sensing technology,”IET Optoelectronics, vol. 18, no. 4, pp. 81–95, 2024

    work page 2024

  19. [19]

    Photonic Integrated Sensing and Communication System Harnessing Submarine Fiber Optic Cables for Coastal Event Monitoring,

    S. Chen, K. Zhu, J. Han, Q. Sui, and Z. Li, “Photonic Integrated Sensing and Communication System Harnessing Submarine Fiber Optic Cables for Coastal Event Monitoring,”IEEE Communications Magazine, vol. 60, no. 12, pp. 110–116, 2022

    work page 2022

  20. [20]

    New advances in fiber optic technology for environmental monitoring, safety, and risk management applica- tions,

    S. Wienecke and J. K. Brenne, “New advances in fiber optic technology for environmental monitoring, safety, and risk management applica- tions,” in2023 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters, 2023, pp. 316–321

    work page 2023

  21. [21]

    Acoustic Technology for Mar- itime Surveillance: Insights from Experimental Exercises,

    A. R. Dias, N. P. Santos, and V . Lobo, “Acoustic Technology for Mar- itime Surveillance: Insights from Experimental Exercises,” inOCEANS 2024 - Singapore, 2024, pp. 1–7

    work page 2024

  22. [22]

    Distributed acoustic sensing for detecting near surface hydroacoustic signals,

    A. S. Douglass, S. Abadi, and B. P. Lipovsky, “Distributed acoustic sensing for detecting near surface hydroacoustic signals,”JASA Express Letters, vol. 3, no. 6, p. 066005, 2023

    work page 2023

  23. [23]

    Leveraging Distributed Acoustic Sensing for monitoring vessels using submarine fiber-optic cables,

    B. Paap, V . Vandeweijer, J.-D. van Wees, and D. Kraaijpoel, “Leveraging Distributed Acoustic Sensing for monitoring vessels using submarine fiber-optic cables,”Applied Ocean Research, vol. 154, p. 104422, 2025

    work page 2025

  24. [24]

    Tracking Moving Ships Using Distributed Acoustic Sensing Data,

    J. Shao, Y . Wang, Y . Zhang, X. Zhang, and C. Zhang, “Tracking Moving Ships Using Distributed Acoustic Sensing Data,”IEEE Geoscience and Remote Sensing Letters, vol. 22, pp. 1–5, 2025

    work page 2025

  25. [25]

    DAShip: A Large-Scale Annotated Dataset for Ship Detection Using Distributed Acoustic Sensing Technique,

    W. Huang, S. Chen, Y . Wu, R. Li, T. Li, Y . Huang, X. Cao, and Z. Li, “DAShip: A Large-Scale Annotated Dataset for Ship Detection Using Distributed Acoustic Sensing Technique,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 4093–4107, 2025

    work page 2025

  26. [26]

    Estimates of Source Spectra of Ships from Long Term Recordings in the Baltic Sea,

    I. Karasalo, M. ¨Ostberg, P. Sigray, J.-P. Jalkanen, L. Johansson, M. Liefvendahl, and R. Bensow, “Estimates of Source Spectra of Ships from Long Term Recordings in the Baltic Sea,”Frontiers in Marine Science, vol. 4, p. 164, 2017

    work page 2017

  27. [27]

    Distributed Acoustic Sensing Turns Fiber-Optic Cables into Sensitive Seismic Antennas,

    Z. Zhan, “Distributed Acoustic Sensing Turns Fiber-Optic Cables into Sensitive Seismic Antennas,”Seismological Research Letters, vol. 91, no. 1, pp. 1–15, 2020

    work page 2020

  28. [28]

    On the sensitivity of distributed acoustic sensing,

    H. Gabai and A. Eyal, “On the sensitivity of distributed acoustic sensing,”Optics letters, vol. 41, no. 24, pp. 5648–5651, 2016

    work page 2016

  29. [29]

    Optical pulse compression re- flectometry: proposal and proof-of-concept experiment,

    W. Zou, S. Yang, X. Long, and J. Chen, “Optical pulse compression re- flectometry: proposal and proof-of-concept experiment,”Optics Express, vol. 23, no. 1, p. 512, 2015

    work page 2015

  30. [30]

    Real-time phase-recording DAS in 171 km low-loss fiber,

    O. H. Waagaard, E. Rønnekleiv, A. Haukanes, F. Stabo-Eeg, D. Thingbø, S. Forbord, S. E. Aasen, and J. K. Brenne, “Real-time phase-recording DAS in 171 km low-loss fiber,” inOptical Fiber Sensors Conference 2020 Special Edition, ser. OFS. Optica Publishing Group, 2021, p. T2A.3

    work page 2020

  31. [31]

    Enhancing fibre-optic distributed acoustic sensing capabilities with blind near-field array signal processing,

    F. Mu ˜noz and M. A. Soto, “Enhancing fibre-optic distributed acoustic sensing capabilities with blind near-field array signal processing,”Nature Communications, vol. 13, no. 1, p. 4019, 2022

    work page 2022

  32. [32]

    Distributed Acoustic Sensing for Submarine Cable Protection,

    O. Brenne, S. Besanger, and P. Travers, “Distributed Acoustic Sensing for Submarine Cable Protection,” inSubOptic 2019 Conference Proceedings, New Orleans, USA, 2019. [Online]. Available: https: //suboptic.org

    work page 2019

  33. [33]

    OptoDAS interrogator,

    Alcatel Submarine Networks, “OptoDAS interrogator,” Online, accessed march 2025

    work page 2025

  34. [34]

    The promises and perils of Automatic Identification System data,

    T. Emmens, C. Amrit, A. Abdi, and M. Ghosh, “The promises and perils of Automatic Identification System data,”Expert Systems with Applications, vol. 178, p. 114975, 2021

    work page 2021

  35. [35]

    Automatic Identi- fication System (AIS): Data Reliability and Human Error Implications,

    A. Harati-Mokhtari, A. Wall, P. Brooks, and J. Wang, “Automatic Identi- fication System (AIS): Data Reliability and Human Error Implications,” Journal of Navigation, vol. 60, no. 3, p. 373–389, 2007

    work page 2007

  36. [36]

    Technical Characteristics for an Automatic Identification System Using Time Division Multiple Access in the VHF Maritime Mobile Band (Recommendation ITU-R M.1371-5),

    International Telecommunication Union, “Technical Characteristics for an Automatic Identification System Using Time Division Multiple Access in the VHF Maritime Mobile Band (Recommendation ITU-R M.1371-5),” International Telecommunication Union, Geneva, Switzer- land, Technical Report, 2014

    work page 2014

  37. [37]

    Improved kinematic interpolation for AIS trajectory reconstruction,

    S. Guo, J. Mou, L. Chen, and P. Chen, “Improved kinematic interpolation for AIS trajectory reconstruction,”Ocean Engineering, vol. 234, p. 109256, 2021

    work page 2021

  38. [38]

    Distributed sensing of earthquakes and ocean-solid Earth interactions on seafloor telecom cables,

    A. Sladen, D. Rivet, J. P. Ampuero, L. De Barros, Y . Hello, G. Calbris, and P. Lamare, “Distributed sensing of earthquakes and ocean-solid Earth interactions on seafloor telecom cables,”Nature communications, vol. 10, no. 1, p. 5777, 2019

    work page 2019

  39. [39]

    Identification of two vibration regimes of underwater fibre optic cables by distributed acoustic sensing,

    D. Mata Flores, E. D. Mercerat, J. P. Ampuero, D. Rivet, and A. Sladen, “Identification of two vibration regimes of underwater fibre optic cables by distributed acoustic sensing,”Geophysical Journal International, vol. 234, no. 2, pp. 1389–1400, 2023

    work page 2023

  40. [40]

    EMODnet Digital Bathymetry (DTM 2024),

    EMODnet Bathymetry Consortium, “EMODnet Digital Bathymetry (DTM 2024),” 2024. [Online]. Available: https://dx.doi.org/10.12770/ cf51df64-56f9-4a99-b1aa-36b8d7b743a1

    work page 2024

  41. [41]

    Marlinks-NS DAS: Dataset for Vessel Detection and Distance Estimation Using Distributed Acoustic Sensing in Submarine Cables,

    E. E. Ramirez-Torres, J. Macias-Guarasa, D. Pizarro-Perez, J. Tejedor, S. E. Palazuelos-Cagigas, P. J. Vidal-Moreno, S. Martin-Lopez, M. Gonzalez-Herraez, and R. Vanthillo, “Marlinks-NS DAS: Dataset for Vessel Detection and Distance Estimation Using Distributed Acoustic Sensing in Submarine Cables,” To be published in 2025. [Online]. Available: https://do...

    work page doi:10.5281/zenodo.15611778 2025

  42. [42]

    Long-range sound propagation in the central region of the Baltic Sea,

    R. Vadov, “Long-range sound propagation in the central region of the Baltic Sea,”Acoustical Physics, vol. 47, no. 2, pp. 150–159, 2001

    work page 2001

  43. [43]

    Precise and low-complexity method for underwater Doppler estimation based on acoustic frequency comb waveforms,

    J. Li, Z. Qian, D. Hong, and J. Zhai, “Precise and low-complexity method for underwater Doppler estimation based on acoustic frequency comb waveforms,”Frontiers in Marine Science, vol. 11, p. 1365095, 2024

    work page 2024

  44. [44]

    On the Detection Capabilities of Underwater Distributed Acoustic Sensing,

    I. Lior, A. Sladen, D. Rivet, J. Ampuero, Y . Hello, C. Becerril, H. F. Martins, P. Lamare, C. Jestin, S. Tsagkli, and C. Markou, “On the Detection Capabilities of Underwater Distributed Acoustic Sensing,” Journal of Geophysical Research: Solid Earth, vol. 126, no. 3, p. e2020JB020925, 2021

    work page 2021

  45. [45]

    Toward prevention of pipeline integrity threats using a smart fiber-optic surveillance system,

    J. Tejedor, H. F. Martins, D. Piote, J. Macias-Guarasa, J. Pastor- Graells, S. Martin-Lopez, P. C. Guill ´en, F. De Smet, W. Postvoll, and M. Gonzalez-Herraez, “Toward prevention of pipeline integrity threats using a smart fiber-optic surveillance system,”Journal of Lightwave Technology, vol. 34, no. 19, pp. 4445–4453, 2016

    work page 2016

  46. [46]

    A. H. Hartog,An introduction to distributed optical fibre sensors. CRC press, 2017

    work page 2017

  47. [47]

    XGBoost: A Scalable Tree Boosting System,

    T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” inProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ser. KDD ’16. New York, NY , USA: Association for Computing Machinery, 2016, p. 785–794

    work page 2016

  48. [48]

    Machine learning methods for pipeline surveillance systems based on distributed acoustic sensing: A review,

    J. Tejedor, J. Macias-Guarasa, H. F. Martins, J. Pastor-Graells, P. Corred- era, and S. Martin-Lopez, “Machine learning methods for pipeline surveillance systems based on distributed acoustic sensing: A review,” Applied Sciences, vol. 7, no. 8, p. 841, 2017

    work page 2017

  49. [49]

    The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances,

    A. Bagnall, J. Lines, A. Bostrom, J. Large, and E. Keogh, “The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances,”Data mining and knowledge discovery, vol. 31, pp. 606–660, 2017

    work page 2017

  50. [50]

    A contextual GMM-HMM smart fiber optic surveillance system for pipeline integrity threat detection,

    J. Tejedor, J. Macias-Guarasa, H. F. Martins, S. Martin-Lopez, and M. Gonzalez-Herraez, “A contextual GMM-HMM smart fiber optic surveillance system for pipeline integrity threat detection,”Journal of Lightwave Technology, vol. 37, no. 18, pp. 4514–4522, 2019

    work page 2019

  51. [51]

    A real scale application of a novel set of spatial and similarity features for detection and classification of natural seismic sources from distributed acoustic sensing data,

    C. Huynh, C. Hibert, C. Jestin, J.-P. Malet, and V . Lanticq, “A real scale application of a novel set of spatial and similarity features for detection and classification of natural seismic sources from distributed acoustic sensing data,”Geophysical Journal International, vol. 240, no. 1, pp. 462–482, 2025

    work page 2025

  52. [52]

    Reliable Accuracy Estimates from k- Fold Cross Validation,

    T.-T. Wong and P.-Y . Yeh, “Reliable Accuracy Estimates from k- Fold Cross Validation,”IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 8, pp. 1586–1594, 2020

    work page 2020

  53. [53]

    Efron and R

    B. Efron and R. J. Tibshirani,An Introduction to the Bootstrap. Boca Raton, FL: Chapman & Hall/CRC, 1994

    work page 1994

  54. [54]

    Confidence Interval Estimation for Machine Learning Models in Fore- casting Infectious Diseases,

    T. Goo, K. Han, H. Song, J. Park, Z. Liu, J. Oh, S. A. Jose, and T. Park, “Confidence Interval Estimation for Machine Learning Models in Fore- casting Infectious Diseases,” in2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2024, pp. 5914–5919

    work page 2024

  55. [55]

    Estimation of Prediction Intervals for Performance Assessment of Building Using Machine Learning,

    K. Shabbir, M. Umair, S.-H. Sim, U. Ali, and M. Noureldin, “Estimation of Prediction Intervals for Performance Assessment of Building Using Machine Learning,”Sensors, vol. 24, no. 13, p. 4218, 2024

    work page 2024

  56. [56]

    Array signal processing on distributed acoustic sensing data: Directivity effects in slowness space,

    S. P. N ¨asholm, K. Iranpour, A. Wuestefeld, B. D. Dando, A. F. Baird, and V . Oye, “Array signal processing on distributed acoustic sensing data: Directivity effects in slowness space,”Journal of Geophysical Research: Solid Earth, vol. 127, no. 2, p. e2021JB023587, 2022

    work page 2022

  57. [57]

    Robust local- ization in reverberant rooms,

    J. H. DiBiase, H. F. Silverman, and M. S. Brandstein, “Robust local- ization in reverberant rooms,” inMicrophone arrays: signal processing techniques and applications. Springer, 2001, pp. 157–180

    work page 2001

  58. [58]

    DAS data for submarine cable detection,

    Q. Wang, “DAS data for submarine cable detection,” 2025. [Online]. Available: https://dx.doi.org/10.21227/1308-8605

    work page doi:10.21227/1308-8605 2025

  59. [59]

    Real-time processing of distributed acoustic sensing data for earthquake monitoring operations,

    E. Biondi, G. Tepp, E. Yu, J. K. Saunders, V . Yartsev, M. Black, M. Watkins, A. Bhaskaran, R. Bhadha, Z. Zhanet al., “Real-time processing of distributed acoustic sensing data for earthquake monitoring operations,”arXiv preprint arXiv:2505.24077, 2025

    work page arXiv 2025