Classification and prediction of benthic habitat based on scientific echosounder data: application of machine learning algorithms

• Autorzy: Hamuna Baigo , Pujiyati Sri , Gaol Jonson Lumban , Hestirianoto Totok

Identyfikatory

DOI

10.35784/acs-2024-42

• Języki publikacji: EN

Abstrakty

EN

This study aims to map three main benthic habitats (coral, seagrass, and sand) in Kapota Atoll (Wakatobi, Indonesia) using a single-beam echosounder (SBES) Simrad EK15. The acoustic data were processed using Sonar5-Pro software. Eight acoustic parameters were used as input for the classification and prediction of benthic habitats, including depth (D), five acoustic parameters of the first echo (BD, BP, AttSv1, DecSv1, and AttDecSv1), and cumulative energy of the second and third echoes (AttDecSv2 and AttDecSv3). The classification and prediction process of benthic habitats uses two machine learning algorithms, Random Forest (RF) and Support Vector Machine (SVM), in XLSTAT Basic+ software. The study results show that 49 combinations of acoustic parameters produce benthic habitat maps that meet the minimum accuracy standards for benthic habitat mapping (≥60%). Using eight acoustic parameters produces a more accurate benthic habitat map than using only two main SBES parameters (DecSv1 and AttDecSv2 parameters or E1 and E2 in the RoxAnn system indicating the roughness and hardness indices). The RF and SVM algorithms produce benthic habitat maps with the highest accuracy of 79.33% and 78.67%, respectively. Each acoustic parameter has a different importance for the classification of benthic habitats, where the order of importance of each acoustic parameter in the overall classification follows the following order: AttDecSv2 > D > DecSv1 > BD > AttDecSv3 > AttSv1 > AttDecSv1 > BP. Overall, using more acoustic parameters can significantly improve the accuracy of benthic habitat maps.

Słowa kluczowe

EN

acoustic parameters; single beam echo sounder; mapping accuracy; Random Forest; Support Vector Machine

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2024
• Tom: Vol. 20, no. 4
• Strony: 100--116
• Opis fizyczny: Bibliogr. 50 poz., fig., tab.

Twórcy

autor

Hamuna Baigo

• Cenderawasih University, Faculty of Mathematics and Natural Science, Department of Marine Science and Fisheries, Indonesia

• https://orcid.org/0000-0002-0706-2496

autor

Pujiyati Sri

• IPB University, Faculty of Fisheries and Marine Sciences, Department of Marine Sciences and Technology, Indonesia

• https://orcid.org/0000-0003-4049-4589

autor

Gaol Jonson Lumban

• IPB University, Faculty of Fisheries and Marine Sciences, Department of Marine Sciences and Technology, Indonesia

• https://orcid.org/0000-0001-8908-3161

autor

Hestirianoto Totok

• IPB University, Faculty of Fisheries and Marine Sciences, Department of Marine Sciences and Technology, Indonesia

• https://orcid.org/0000-0002-1636-4525

Bibliografia

• [1] Anderson, J. T., Van Holliday, D., Kloser, R., Reid, D. G., & Simard, Y. (2008). Acoustic seabed classification: current practice and future directions. ICES Journal of Marine Science, 65(6), 1004-1011. https://doi.org/10.1093/icesjms/fsn061
• [2] Balk, H., & Lindem, T. (2015). Sonar4 and Sonar5-Pro post processing systems: operator manual version 6.0.3. University of Oslo. https://www.scribd.com/document/477760502/SonarX-Manual-v603-2014-12-30-pdf
• [3] Bartholomä, A., Capperucci, R. M., Becker, L., Coers, S. I. I., & Battershill, C. N. (2020). Hydrodynamics and hydroacoustic mapping of a benthic seafloor in a coarse grain habitat of the German Bight. Geo-Marine Letters, 40(2), 183-195. https://doi.org/10.1007/s00367-019-00599-7
• [4] Bejarano, S., Mumby, P. J., Hedley, J. D., & Sotheran, I. (2010). Combining optical and acoustic data to enhance the detection of Caribbean forereef habitats. Remote Sensing of Environment, 114(11), 2768-2778. https://doi.org/10.1016/j.rse.2010.06.012
• [5] Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
• [6] Bravo, F., & Grant, J. (2020). Benthic habitat mapping and sediment nutrient fluxes in a shallow coastal environment in Nova Scotia, Canada. Estuarine, Coastal and Shelf Science, 242, 106816. https://doi.org/10.1016/j.ecss.2020.106816
• [7] Breiman, L. (1996). Bagging predictors. Machine Learning, 24, 123-140. https://doi.org/10.1007/BF00058655
• [8] Breiman, L. (2001). Random Forests. Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
• [9] Brown, C. J., Smith, S. J., Lawton, P., & Anderson, J. T. (2011). Benthic habitat mapping: A review of progress towards improved understanding of the spatial ecology of the seafloor using acoustic techniques. Estuarine, Coastal and Shelf Science, 92(3), 502-520. https://doi.org/10.1016/j.ecss.2011.02.007
• [10] Congalton, R. G., & Green, K. (2019). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Third Edition (3rd ed.). CRC Press.
• [11] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273-297. https://doi.org/10.1007/BF00994018
• [12] Diesing, M., Green, S. L., Stephens, D., Lark, R. M., Stewart, H. A., & Dove, D. (2014). Mapping seabed sediments: Comparison of manual, geostatistical, object-based image analysis and machine learning approaches. Continental Shelf Research, 84, 107-119. https://doi.org/10.1016/j.csr.2014.05.004
• [13] Fajaryanti, R., & Kang, M. (2019). A preliminary study on seabed classification using a scientific echosounder. Journal of the Korean Society of Fisheries Technology, 55, 39-49. https://doi.org/10.3796/KSFOT.2019.55.1.039
• [14] Freitas, R., Ricardo, F., Pereira, F., Sampaio, L., Carvalho, S., Gaspar, M., Quintino, V., & Rodrigues, A. M. (2011). Benthic habitat mapping: Concerns using a combined approach (acoustic, sediment and biological data). Estuarine, Coastal and Shelf Science, 92(4), 598-606. https://doi.org/10.1016/j.ecss.2011.02.022
• [15] Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random Forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300. https:/doi.org/10.1016/j.patrec.2005.08.011
• [16] Goff, J. A., Kraft, B. J., Mayer, L. A., Schock, S. G., Sommerfield, C. K., Olson, H. C., Gulick, S. P. S., & Nordfjord, S. (2004). Seabed characterization on the New Jersey middle and outer shelf: correlatability and spatial variability of seafloor sediment properties. Marine Geology, 209(1-4), 147-172. https://doi.org/10.1016/j.margeo.2004.05.030
• [17] Green, E. P., Mumby, P. J., Edwards, A. J., & Clark, C. D. (2000). Remote sensing: handbook for tropical coastal management. UNESCO Pub.
• [18] Gumusay, M., Bakırman, T., Tüney Kızılkaya, I., & Aykut, N. (2018). A review of seagrass detection, mapping and monitoring applications using acoustic systems. European Journal of Remote Sensing, 52(1), 1-29. https://doi.org/10.1080/22797254.2018.1544838
• [19] Hamilton, L. (2001). Acoustic Seabed Classification Systems. DSTO Aeronautical and Maritime Research Laboratory.
• [20] Hamouda, A., Soliman, K., El-Gharabawy, S., & Nassar, M. (2019). Comparative study between acoustic signals and images for detecting seabed features. Egyptian Journal of Aquatic Research, 45(2), 145-151. https:/doi.org/10.1016/j.ejar.2019.03.002
• [21] Hamuna, B., Dimara, L., Pujiyati, S., & Natih, N. (2018). Correlation of substrate fraction percentage with acoustic backscattering strength from single beam echosounder detection. AACL Bioflux, 11, 1343-1351.
• [22] Hamuna, B., Pujiyati, S., Gaol, J., & Hestirianoto, T. (2023). Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery. Biodiversitas Journal of Biological Diversity, 24(7). https://doi.org/10.13057/biodiv/d240706
• [23] Hasan, R. C., Ierodiaconou, D., & Monk, J. (2012). Evaluation of four supervised learning methods for benthic habitat mapping using backscatter from multi-beam sonar. Remote Sensing, 4(11), 3427-3443. https://www.mdpi.com/2072-4292/4/11/3427
• [24] Henriques, V., Guerra, M. T., Mendes, B., Gaudêncio, M. J., & Fonseca, P. (2015). Benthic habitat mapping in a Portuguese Marine Protected Area using EUNIS: An integrated approach. Journal of Sea Research, 100, 77-90. https://doi.org/10.1016/j.seares.2014.10.007
• [25] Hilgert, S., Kiemle, L., Fuchs, S., & Wagner, A. (2016). Investigation of echo sounding parameters for the characterisation of bottom sediments in a sub-tropical reservoir. Advances in Oceanography and Limnology, 7(1). https://doi.org/10.4081/aiol.2016.5623
• [26] Huang, Z., Siwabessy, P. J., Heqin, C., & Nichol, S. (2018). Using multibeam backscatter data to investigate sediment-acoustic relationships. Journal of Geophysical Research: Oceans, 123(7), 4649-4665. https://doi.org/10.1029/2017JC013638
• [27] Lee, W. S., & Lin, C. Y. (2018). Mapping of tropical marine benthic habitat: Hydroacoustic classification of coral reefs environment using single-beam (RoxAnn™) system. Continental Shelf Research, 170, 1-10. https://doi.org/10.1016/j.csr.2018.09.012
• [28] Lumivero. (2023). XLSTAT statistical and data analysis solution. https://www.xlstat.com/en
• [29] Manik, H., Mamun, A., & Hestirianoto, T. (2014). Computation of single beam echo sounder signal for underwater objects detection and quantification. International Journal of Advanced Computer Science and Applications, 5(5). https://doi.org/10.14569/IJACSA.2014.050514
• [30] McIntyre, K., McLaren, K., & Prospere, K. (2018). Mapping shallow nearshore benthic features in a Caribbean marine-protected area: assessing the efficacy of using different data types (hydroacoustic versus satellite images) and classification techniques. International Journal of Remote Sensing, 39(4), 1117-1150. https://doi.org/10.1080/01431161.2017.1395924
• [31] McLaren, K., McIntyre, K., & Prospere, K. (2019). Using the random forest algorithm to integrate hydroacoustic data with satellite images to improve the mapping of shallow nearshore benthic features in a marine protected area in Jamaica. GIScience & Remote Sensing, 56(7), 1065-1092. https://doi.org/10.1080/15481603.2019.1613803
• [32] Misiuk, B., & Brown, C. J. (2024). Benthic habitat mapping: A review of three decades of mapping biological patterns on the seafloor. Estuarine, Coastal and Shelf Science, 296, 108599. https://doi.org/10.1016/j.ecss.2023.108599
• [33] Moszynski, M., & Hedgepeth, J. B. (2000). Using single-beam side-lobe observations of fish echoes for fish target strength and abundance estimation in shallow water. Aquatic Living Resources, 13(5), 379-383. https://doi.org/https://doi.org/10.1016/S0990-7440(00)01087-1
• [34] Nemani, S., Cote, D., Misiuk, B., Edinger, E., Mackin-McLaughlin, J., Templeton, A., Shaw, J., & Robert, K. (2022). A multi-scale feature selection approach for predicting benthic assemblages. Estuarine, Coastal and Shelf Science, 277, 108053. https:/doi.org/10.1016/j.ecss.2022.108053
• [35] Nguyen, T., Liquet, B., Mengersen, K., & Sous, D. (2021). Mapping of coral reefs with multispectral satellites: A review of recent papers. Remote Sensing, 13(21), 4470. https://doi.org/10.3390/rs13214470
• [36] Penrose, J., Siwabessy, P. J., Gavrilov, A., Parnum, I., Hamilton, L., Bickers, A., Brooke, B., Ryan, D., & Kennedy, P. (2006). Acoustic Techniques for Seabed Classification. CRC for Coastal Zone, Estuary & Waterway Management.
• [37] Pijanowski, B., & Brown, C. (2022). Grand challenges in acoustic remote sensing: Discoveries to support a better understanding of our changing planet. Frontiers in Remote Sensing, 2. https://doi.org/10.3389/frsen.2021.824848
• [38] Poulain, T., Argillier, C., Gevrey, M., & Guillard, J. (2011). Identifying lakebed nature: Is it feasible with a combination of echosounder and Sonar5-pro? Advances in Oceanography and Limnology, 2(1), 49-53. https://doi.org/10.1080/19475721.2011.565803
• [39] Pujiyati, S., Hamuna, B., Rohilah, Hisyam, M., Srimariana, E. S., & Natih, I. N. M. (2022). Distributions of environmental parameters and Plankton’s volume backscattering strength at Yos Sudarso Bay, Jayapura, Indonesia. Egyptian Journal of Aquatic Research, 48(1), 37-44. https://doi.org/https://doi.org/10.1016/j.ejar.2021.08.001
• [40] Reshitnyk, L., Costa, M., Robinson, C., & Dearden, P. (2014). Evaluation of WorldView-2 and acoustic remote sensing for mapping benthic habitats in temperate coastal Pacific waters. Remote Sensing of Environment, 153, 7-23. https://doi.org/10.1016/j.rse.2014.07.016
• [41] Riegl, B. M., & Purkis, S. J. (2005). Detection of shallow subtidal corals from IKONOS satellite and QTC View (50, 200 kHz) single-beam sonar data (Arabian Gulf; Dubai, UAE). Remote Sensing of Environment, 95(1), 96-114. https://doi.org/10.1016/j.rse.2004.11.016
• [42] Sánchez-Carnero, N., Rodríguez-Pérez, D., Llorens, S., Orenes-Salazar, V., Ortolano, A., & García-Charton, J. A. (2023). An expeditious low-cost method for the acoustic characterization of seabeds in a Mediterranean coastal protected area. Estuarine, Coastal and Shelf Science, 281, 108204. https://doi.org/10.1016/j.ecss.2022.108204
• [43] Shao, H., Kiyomoto, S., Kawauchi, Y., Kadota, T., Nakagawa, M., Yoshimura, T., Yamada, H., Acker, T., & Moore, B. (2021). Classification of various algae canopy, algae turf, and barren seafloor types using a scientific echosounder and machine learning analysis. Estuarine, Coastal and Shelf Science, 255, 107362. https://doi.org/10.1016/j.ecss.2021.107362
• [44] Sklar, E., Bushuev, E., Misiuk, B., Morissette, G., & Brown, C. (2024). Seafloor morphology and substrate mapping in the Gulf of St Lawrence, Canada, using machine learning approaches. Frontiers in Marine Science, 11. https://doi.org/10.3389/fmars.2024.1306396
• [45] Solikin, S., Manik, H., Pujiyati, S., & Susilohadi, S. (2018). Measurement of bottom backscattering strength using single-beam echosounder. Journal of Physics: Conference Series, 1075, 012036. https://doi.org/10.1088/1742-6596/1075/1/012036
• [46] Stephens, D., & Diesing, M. (2014). A comparison of supervised classification methods for the prediction of substrate type using multibeam acoustic and legacy grain-size data. PLOS ONE, 9(4), e93950. https://doi.org/10.1371/journal.pone.0093950
• [47] Vapnik, V. N. (1999). An overview of statistical learning theory. IEEE Transactions on Neural Networks, 10(5), 988-999. https://doi.org/10.1109/72.788640
• [48] Vassallo, P., Bianchi, C. N., Paoli, C., Holon, F., Navone, A., Bavestrello, G., Cattaneo Vietti, R., & Morri, C. (2018). A predictive approach to benthic marine habitat mapping: Efficacy and management implications. Marine Pollution Bulletin, 131(Part A), 218-232. https://doi.org/10.1016/j.marpolbul.2018.04.016
• [49] Wadoux, A. M. J. C., Heuvelink, G. B. M., de Bruin, S., & Brus, D. J. (2021). Spatial cross-validation is not the right way to evaluate map accuracy. Ecological Modelling, 457, 109692. https://doi.org/10.1016/j.ecolmodel.2021.109692
• [50] Wölfl, A.-C., Snaith, H., Amirebrahimi, S., Devey, C. W., Dorschel, B., Ferrini, V., Huvenne, V. A. I., Jakobsson, M., Jencks, J., Johnston, G., Lamarche, G., Mayer, L., Millar, D., Pedersen, T. H., Picard, K., Reitz, A., Schmitt, T., Visbeck, M., Weatherall, P., & Wigley, R. (2019). Seafloor mapping – The challenge of a truly global ocean bathymetry. Frontiers in Marine Science, 6. https://doi.org/10.3389/fmars.2019.00283

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).