Cargando…

Study of various machine learning approaches for Sentinel-2 derived bathymetry

In recent years precise and up-to-date information regarding seabed depth has become more and more important for companies and institutions that operate on coastlines. While direct, in-situ measurements are performed regularly, they are expensive, time-consuming and impractical to be performed in sh...

Descripción completa

Detalles Bibliográficos
Autores principales: Chybicki, Andrzej, Sosnowski, Paweł, Kulawiak, Marek, Bieliński, Tomasz, Korlub, Waldemar, Łubniewski, Zbigniew, Kempa, Magdalena, Parzuchowski, Jarosław
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10503737/
https://www.ncbi.nlm.nih.gov/pubmed/37713403
http://dx.doi.org/10.1371/journal.pone.0291595
_version_ 1785106584359141376
author Chybicki, Andrzej
Sosnowski, Paweł
Kulawiak, Marek
Bieliński, Tomasz
Korlub, Waldemar
Łubniewski, Zbigniew
Kempa, Magdalena
Parzuchowski, Jarosław
author_facet Chybicki, Andrzej
Sosnowski, Paweł
Kulawiak, Marek
Bieliński, Tomasz
Korlub, Waldemar
Łubniewski, Zbigniew
Kempa, Magdalena
Parzuchowski, Jarosław
author_sort Chybicki, Andrzej
collection PubMed
description In recent years precise and up-to-date information regarding seabed depth has become more and more important for companies and institutions that operate on coastlines. While direct, in-situ measurements are performed regularly, they are expensive, time-consuming and impractical to be performed in short time intervals. At the same time, an ever-increasing amount of satellite imaging data becomes available. With these images, it became possible to develop bathymetry estimation algorithms that can predict seabed depth and utilize them systematically. Since there are a number of theoretical approaches, physical models, and empirical techniques to use satellite observations in order to estimate depth in the coastal zone, the presented article compares the performance and precision of the most common one to modern machine learning algorithms. More specifically, the models based on shallow neural networks, decision trees and Random Forest algorithms have been proposed, investigated and confronted with the performance of pure analytical models. The particular proposed machine learning models differ also in a set of satellite data bands used as an input as well as in applying or not geographical weighting in the learning process. The obtained results point towards the best performance of the regression tree algorithm that incorporated as inputs information about data localization, raw reflectance data from four satellite data bands and a quotient of logarithms of B2 and B3 bands. The study for the paper was performed in relatively optically difficult and spatially variant conditions of the south Baltic coastline starting at Szczecin, Poland on the west (53°26’17’’ N, 14°32’32’’ E) to Hel peninsula (54°43’04,3774’’ N 18°37’56,9175’’ E). The reference bathymetry data was acquired from Polish Marine Administration. It was obtained through profile probing with single-beam sonar or direct in-situ probing.
format Online
Article
Text
id pubmed-10503737
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-105037372023-09-16 Study of various machine learning approaches for Sentinel-2 derived bathymetry Chybicki, Andrzej Sosnowski, Paweł Kulawiak, Marek Bieliński, Tomasz Korlub, Waldemar Łubniewski, Zbigniew Kempa, Magdalena Parzuchowski, Jarosław PLoS One Research Article In recent years precise and up-to-date information regarding seabed depth has become more and more important for companies and institutions that operate on coastlines. While direct, in-situ measurements are performed regularly, they are expensive, time-consuming and impractical to be performed in short time intervals. At the same time, an ever-increasing amount of satellite imaging data becomes available. With these images, it became possible to develop bathymetry estimation algorithms that can predict seabed depth and utilize them systematically. Since there are a number of theoretical approaches, physical models, and empirical techniques to use satellite observations in order to estimate depth in the coastal zone, the presented article compares the performance and precision of the most common one to modern machine learning algorithms. More specifically, the models based on shallow neural networks, decision trees and Random Forest algorithms have been proposed, investigated and confronted with the performance of pure analytical models. The particular proposed machine learning models differ also in a set of satellite data bands used as an input as well as in applying or not geographical weighting in the learning process. The obtained results point towards the best performance of the regression tree algorithm that incorporated as inputs information about data localization, raw reflectance data from four satellite data bands and a quotient of logarithms of B2 and B3 bands. The study for the paper was performed in relatively optically difficult and spatially variant conditions of the south Baltic coastline starting at Szczecin, Poland on the west (53°26’17’’ N, 14°32’32’’ E) to Hel peninsula (54°43’04,3774’’ N 18°37’56,9175’’ E). The reference bathymetry data was acquired from Polish Marine Administration. It was obtained through profile probing with single-beam sonar or direct in-situ probing. Public Library of Science 2023-09-15 /pmc/articles/PMC10503737/ /pubmed/37713403 http://dx.doi.org/10.1371/journal.pone.0291595 Text en © 2023 Chybicki et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Chybicki, Andrzej
Sosnowski, Paweł
Kulawiak, Marek
Bieliński, Tomasz
Korlub, Waldemar
Łubniewski, Zbigniew
Kempa, Magdalena
Parzuchowski, Jarosław
Study of various machine learning approaches for Sentinel-2 derived bathymetry
title Study of various machine learning approaches for Sentinel-2 derived bathymetry
title_full Study of various machine learning approaches for Sentinel-2 derived bathymetry
title_fullStr Study of various machine learning approaches for Sentinel-2 derived bathymetry
title_full_unstemmed Study of various machine learning approaches for Sentinel-2 derived bathymetry
title_short Study of various machine learning approaches for Sentinel-2 derived bathymetry
title_sort study of various machine learning approaches for sentinel-2 derived bathymetry
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10503737/
https://www.ncbi.nlm.nih.gov/pubmed/37713403
http://dx.doi.org/10.1371/journal.pone.0291595
work_keys_str_mv AT chybickiandrzej studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT sosnowskipaweł studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT kulawiakmarek studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT bielinskitomasz studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT korlubwaldemar studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT łubniewskizbigniew studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT kempamagdalena studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry
AT parzuchowskijarosław studyofvariousmachinelearningapproachesforsentinel2derivedbathymetry