Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning

Subtidal natural hard substrates (SNHS) promote occupancy by rich benthic communities that provide irreplaceable and fundamental ecosystem functions, representing a global priority target for nature conservation and recognised in most European environmental legislation. However, scientifically valid...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Giacomo Montereale Gavazzi, Danae Athena Kapasakali, Francis Kerchof, Samuel Deleu, Steven Degraer, Vera Van Lancker
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	underwater imagery multibeam echosounder random forest subtidal natural hard substrate stone colonisation epilithic fauna Science Q
Acceso en línea:	https://doaj.org/article/7eeba4cab24d4a92baa376940c1fe3c9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7eeba4cab24d4a92baa376940c1fe3c9
record_format	dspace
spelling	oai:doaj.org-article:7eeba4cab24d4a92baa376940c1fe3c92021-11-25T18:54:42ZSubtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning10.3390/rs132246082072-4292https://doaj.org/article/7eeba4cab24d4a92baa376940c1fe3c92021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4608https://doaj.org/toc/2072-4292Subtidal natural hard substrates (SNHS) promote occupancy by rich benthic communities that provide irreplaceable and fundamental ecosystem functions, representing a global priority target for nature conservation and recognised in most European environmental legislation. However, scientifically validated methodologies for their quantitative spatial demarcation, including information on species occupancy and fine-scale environmental drivers (e.g., the effect of stone size on colonisation) are rare. This is, however, crucial information for sound ecological management. In this investigation, high-resolution (1 m) multibeam echosounder (MBES) depth and backscatter data and derivates, underwater imagery (UI) by video drop-frame, and grab sediment samples, all acquired within 32 km<sup>2</sup> of seafloor in offshore Belgian waters, were integrated to produce a random forest (RF) spatial model, predicting the continuous distribution of the seafloor areal cover/m<sup>2</sup> of the stones’ grain sizes promoting colonisation by sessile epilithic organisms. A semi-automated UI acquisition, processing, and analytical workflow was set up to quantitatively study the colonisation proportion of different grain sizes, identifying the colonisation potential to begin at stones with grain sizes Ø ≥ 2 cm. This parameter (i.e., % areal cover of stones Ø ≥ 2 cm/m<sup>2</sup>) was selected as the response variable for spatial predictive modelling. The model output is presented along with a protocol of error and uncertainty estimation. RF is confirmed as an accurate, versatile, and transferable mapping methodology, applicable to area-wide mapping of SNHS. UI is confirmed as an essential aid to acoustic seafloor classification, providing spatially representative numerical observations needed to carry out quantitative seafloor modelling of ecologically relevant parameters. This contribution sheds innovative insights into the ecologically relevant delineation of subtidal natural reef habitat, exploiting state-of-the-art underwater remote sensing and acoustic seafloor classification approaches.Giacomo Montereale GavazziDanae Athena KapasakaliFrancis KerchofSamuel DeleuSteven DegraerVera Van LanckerMDPI AGarticleunderwater imagerymultibeam echosounderrandom forestsubtidal natural hard substratestone colonisationepilithic faunaScienceQENRemote Sensing, Vol 13, Iss 4608, p 4608 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	underwater imagery multibeam echosounder random forest subtidal natural hard substrate stone colonisation epilithic fauna Science Q
spellingShingle	underwater imagery multibeam echosounder random forest subtidal natural hard substrate stone colonisation epilithic fauna Science Q Giacomo Montereale Gavazzi Danae Athena Kapasakali Francis Kerchof Samuel Deleu Steven Degraer Vera Van Lancker Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
description	Subtidal natural hard substrates (SNHS) promote occupancy by rich benthic communities that provide irreplaceable and fundamental ecosystem functions, representing a global priority target for nature conservation and recognised in most European environmental legislation. However, scientifically validated methodologies for their quantitative spatial demarcation, including information on species occupancy and fine-scale environmental drivers (e.g., the effect of stone size on colonisation) are rare. This is, however, crucial information for sound ecological management. In this investigation, high-resolution (1 m) multibeam echosounder (MBES) depth and backscatter data and derivates, underwater imagery (UI) by video drop-frame, and grab sediment samples, all acquired within 32 km<sup>2</sup> of seafloor in offshore Belgian waters, were integrated to produce a random forest (RF) spatial model, predicting the continuous distribution of the seafloor areal cover/m<sup>2</sup> of the stones’ grain sizes promoting colonisation by sessile epilithic organisms. A semi-automated UI acquisition, processing, and analytical workflow was set up to quantitatively study the colonisation proportion of different grain sizes, identifying the colonisation potential to begin at stones with grain sizes Ø ≥ 2 cm. This parameter (i.e., % areal cover of stones Ø ≥ 2 cm/m<sup>2</sup>) was selected as the response variable for spatial predictive modelling. The model output is presented along with a protocol of error and uncertainty estimation. RF is confirmed as an accurate, versatile, and transferable mapping methodology, applicable to area-wide mapping of SNHS. UI is confirmed as an essential aid to acoustic seafloor classification, providing spatially representative numerical observations needed to carry out quantitative seafloor modelling of ecologically relevant parameters. This contribution sheds innovative insights into the ecologically relevant delineation of subtidal natural reef habitat, exploiting state-of-the-art underwater remote sensing and acoustic seafloor classification approaches.
format	article
author	Giacomo Montereale Gavazzi Danae Athena Kapasakali Francis Kerchof Samuel Deleu Steven Degraer Vera Van Lancker
author_facet	Giacomo Montereale Gavazzi Danae Athena Kapasakali Francis Kerchof Samuel Deleu Steven Degraer Vera Van Lancker
author_sort	Giacomo Montereale Gavazzi
title	Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
title_short	Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
title_full	Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
title_fullStr	Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
title_full_unstemmed	Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning
title_sort	subtidal natural hard substrate quantitative habitat mapping: interlinking underwater acoustics and optical imagery with machine learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7eeba4cab24d4a92baa376940c1fe3c9
work_keys_str_mv	AT giacomomonterealegavazzi subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning AT danaeathenakapasakali subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning AT franciskerchof subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning AT samueldeleu subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning AT stevendegraer subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning AT veravanlancker subtidalnaturalhardsubstratequantitativehabitatmappinginterlinkingunderwateracousticsandopticalimagerywithmachinelearning
_version_	1718410534242484224

Subtidal Natural Hard Substrate Quantitative Habitat Mapping: Interlinking Underwater Acoustics and Optical Imagery with Machine Learning

Ejemplares similares