Ocean Systems Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Deep neural network based seafloor sediment mapping using bathymetric features of MBES multifrequency

  • Khomsin (Department of Ocean Engineering, ITS Surabaya) ;
  • Mukhtasor (Department of Ocean Engineering, ITS Surabaya) ;
  • Suntoyo (Department of Ocean Engineering, ITS Surabaya) ;
  • Danar Guruh Pratomo (Department of Geomatics Engineering, ITS Surabaya)
  • Received : 2023.10.20
  • Accepted : 2023.12.15
  • Published : 2024.06.25
⟨ Previous Next ⟩

Abstract

Seafloor sediment mapping is an essential research topic in shallow coastal waters, especially in port development, benthic habitat mapping, and underwater communications. The seafloor sediments can be interpreted by collecting sediment samples directly in the field using a grab sampler or corer. Another method is optical, especially using underwater cameras and videos. Both methods each have weaknesses in terms of area coverage (mechanic) and accurate positioning (optic). The latest technology used to overcome it is the acoustic method (echosounder) with Global Navigation Satellite System (GNSS) Real Time Kinematic (RTK) positioning. Therefore, in this study will propose the classification of seafloor sediments in coastal waters using acoustic method that is Multibeam Echosounder (MBES) multi-frequency with five frequency (200 kHz, 250 kHz, 300 kHz, 350 kHz, and 400 kHz). In this study, the deep neural network (DNN) used the bathymetric multi frequency, bathymetric difference inters frequencies, and bathymetric features from 5 (five) frequencies as input layer and 4 (four) sediment types in 74 (seventy-four) sample sediment as output layer to make a seafloor sediment map. Results of sediment mapping using the DNN method show an overall accuracy of 71.6% (significant) and a kappa coefficient of 0.59 (moderate). The distribution of seafloor sediment in the study area is mainly silt (41.6%), followed by clayey sand (36.6%), sandy silt (14.2%), and silty sand (7.5%).

Keywords

Acknowledgement

We thank our colleagues from PT. APBS provided insight and expertise that greatly assisted the research related to the R2Sonic2020 multi-frequency MBES survey and Eiva Corporation, which has licensed the Navi Edit JobPlanner and Navi Model Producer software to the geomatics engineering department. Not to forget, we also thank PT. GJT has allowed GJT waters as a survey area.

References

  1. Agarap, A.F.M. (2019), "Deep Learning using Rectified Linear Units (ReLU)", arXiv:1803.08375v2. [cs.NE]
  2. Arif, T.M. (2020), Introduction to Deep Learning for Engineers: Using Python and Google Cloud Platform. (Synthesis Lectures on Mechanical Engineering). Morgan & Claypool, Vol. 5.
  3. Brown, C.J., Beaudoin, J., Brissette, M. and Gazzola, V. (2017), "Setting the Stage for Multispectral Acoustic Backscatter Research" WHITE PAPER. R2Sonic.
  4. Brown, C.J., Beaudoin, J., Brissette, M. and Gazzola, V. (2019), "Multispectral multibeam echo sounder backscatter as a tool for improved seafloor characterization", Geosciences, 9(3), 126 MDPI. https://doi.org/10.3390/geosciences9030126.
  5. Cohen, J. (1960), "A coefficient of agreement for nominal scales", Educational and Physicological Measurement, 20(1). 37-46. https://doi.org/10.1177/001316446002000104.
  6. Congalton, R.G. (1991), "A review of assessing the accuracy of classifications of remotely sensed data", Remote Sens. Environ., 37, 35-46. https://doi.org/10.1016/0034-4257(91)90048-B.
  7. Feldens, P., Schulze, I., Papenmeier, S., Schonke, M. and Schneider von Deimling, J. (2018), "Improved interpretation of marine sedimentary environments using multi-frequency multibeam backscatter data", Geosciences, 8(6), 214. https://doi.org/10.3390/geosciences8060214.
  8. Fonseca, L. and Calder, B. (2005), "Geocoder: an efficient backscatter map constructor", Proceedings of the U.S. Hydrographic Conference, San Diego.
  9. Foody, M.G. (2002), "Status of land classification accuracy", Remote Sens. Environ., 80(1). 185-201. https://doi.org/10.1016/S0034-4257(01)00295-4.
  10. Gaida, T.C., Ali, T.A.T., Snellen, M., Simkooei, A.A., van Dijk, T.A.G.P. and Simons, D.G. (2018), "A multispectral bayesian classification method for increased acoustic discrimination of seabed sediments using multi-frequency multibeam backscatter data", Geosciences, 8, 455. MDPI. https://doi.org/10.3390/geosciences8120455.
  11. Hell, B. (2011), "Mapping bathymetry: From measurement to applications", Doctoral thesis in Marine Geoscience. Department of Geological Sciences Stockholm University, Stockholm Sweden.
  12. Hoy, S. and Kissinger, K. (2010), "Multibeam calibration: Conducting a patch test NOAA ship Okeanos explorer", OER Interns
  13. IHO (2005), Manual on Hydrography Publication M-13 1st Ed., Monaco: International Hydrographic Bureau
  14. Janowski, L., Tegowski, J. and Nowak, J. (2018), "Seafloor mapping based on multibeam echosounder bathymetry and backscatter data using Object-Based Image Analysis: A case study from the Rewal site, the Southern Baltic", Int. J. Oceanography Hydrobiol., 47(3). https://doi.org/10.1515/ohs-2018-0024.
  15. Ji, X., Yang, B. and Tang, Q. (2020), "Seabed sediment classification using multibeam backscatter data based on the selecting optimal random forest model", Appl. Acoust., 167, 107387. https://doi.org/10.1016/j.apacoust.2020.107387.
  16. Kingma, D.P. and Ba, J.L. (2015), Adam: A Method for Stochastic Optimization. ICLR. arXiv:1412.6980v9 [cs.LG].
  17. Kobryn, H.T., Beckley, L.E. and Wouters, K. (2022), "Bathymetry derivatives and habitat data from hyperspectral imagery establish a high-resolution baseline for managing the Ningaloo Reef, Western Australia", Remote Sens., 14, 1827. https://doi.org/10.3390/rs14081827.
  18. Landis, R.J. and Koch, G.G. (1977), "The measurement of observer agreement for categorial data", Biometrics, 33(1), 159- 174. https://doi.org/10.2307/2529310.
  19. Lamarche, G. and Lurton, X. (2018), "Recommendations for improved and coherent acquisition and processing of backscatter data from seafloor-mapping sonars", Mar. Geophys. Res., 39, 5-22. https://doi.org/10.1007/s11001-017-9315-6.
  20. Mertikas, P. and Karantzalos, K. (2020), "Seafloor mapping from multispectral multibeam acoustic data at the European open science cloud", Int. Archiv. Photogramm. Remote Sens. Spatial Inform. Sci., 2020, XXIV ISPRS Congress (2020 edition). https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-985-2020.
  21. Nitriansyah, R. and Cahyono, B.K. (2022), "Seabed classification using multibeam echosounder measurement data", IOP Conf. Ser.: Earth Environ. Sci., 1039 012045. https://doi.org/10.1088/1755-1315/1039/1/012045.
  22. NOAA (1997), Nautical Chart User's Manual. U.S. Department of Commerce National Oceanic and Atmospheric Administration (NOAA) National Ocean Service. United State of America.
  23. Ntouskos, V., Mertikas, P., Mallios, A. and Karantzalos, K. (2023), "Seabed classification from multispectral multibeam data", IEEE J. Oceanic Eng., 48(3), https://doi.org/10.1109/JOE.2023.3267795.
  24. Penrose, J.D., Siwabessy, P.J.W., Gavrilov, A., Parnum, I., Hamilton, L.J., Bickers, A., Brooke, B., Ryan, D.A., and Kennedy, P. (2005), Acoustic Techniques for Seabed Classification, Cooperative Research Centre for Coastal Zone Estuary and Waterway Management. Technical Report 32.
  25. Pratomo, D.G. (2021), "The development of seafloor sediment mapping methods: The opportunity application in the coastal waters", IOP Conf. Ser.: Earth Environ. Sci., 731, 012039. https://doi.org/10.1088/1755-1315/731/1/012039.
  26. Pratomo, D.G., Khomsin, Cahyadi, M.N., Akbar, K. and Aprilia, E. (2018), "Analysis of seafloor sediment Distribution using Multibeam Backscatter Data", MATEC Web of Conferences, 177, 01026. https://doi.org/10.1051/matecconf/201817701026.
  27. R2Sonic (2020), Multibeam Echosounder Specifications. 5307 Industrial Oaks Blvd. Suite 120. Austin, Texas 78735, USA.
  28. Story, M. and Congalton, R.G. (1986), "Accuracy assessment: A user's perspective", Photogramm. Eng. Remote Sens., 52, 397-399.
  29. Van Zuidam, R.A. (1973), Guide to Geomorphologic-Aerial Photographic Interpretation and Mapping, International Institute for Geo-Information Science and Earth Observation, ITC. Enschede, Netherland.
  30. Wan, J., Qin, Z., Cui, X., Yang, F., Yasir, M., Ma, B. and Liu, X. (2022), "MBES seabed sediment classification based on a decision fusion method using deep learning model", Remote Sens., 14, 3708. https://doi.org/10.3390/rs14153708.
  31. Xu, W., Cheng, H., Zheng, S. and Hu, H. (2021), "Predicted mapping of seabed sediments based on MBES backscatter and bathymetric data: A case study in Joseph Bonaparte Gulf, Australia, using random forest decision tree", J. Mar. Sci. Eng., 9, 947. https://doi.org/10.3390/jmse9090947.
  32. Zakariya, R., Abdullah, M.A., Hasan, R.C. and Khalil, I. (2018), "The use of backscatter classification and bathymetry derivatives from multibeam data for seabed sediment characterization", (Ed., Ochsner, A.), Eng. Appl. New Mater. Tech., 85. https://doi.org/10.1007/978-3-319-72697-7_47
  33. Zhang, Q., Zhao, J., Li, S. and Zhang, H. (2022), "Seabed sediment classification using spatial statistical characteristics", J. Mar. Sci. Eng., 10, 691. https://doi.org/10.3390/jmse10050691.
  34. Zheng, H.B., Yan, P., Chen, J. and Wang, Y.L. (2013), "Seabed sediment classification in the northern South China sea using inversion method", Appl. Ocean Res., 39, 131-136. https://doi.org/10.1016/j.apor.2012.11.002.