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

Abstract

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 km2 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/m2 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/m2) 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.

Protected yet unmanaged: insights into the ecological status of conservation priority stony reefs in Belgian waters based on the integrative use of remote sensing technologies

“…In the current Belgian MSP (MSP; 2020-2026) it is designated as a search zone for biodiversity protection as well as a prospecting area for marine aggregate extraction. Here, SNHS biotopes (namely, geogenic reefs similar to those observed in the German Exclusive Economic Zone (EEZ) in Michaelis et al, 2019a, b) have been first observed in 2018 (OD Nature, 2018;Montereale Gavazzi et al, 2021;Montereale Gavazzi et al, 2022) and yearly followed up since.…”

“…Post-processing of underwater imagery follows the methodology described in Montereale Gavazzi et al (2021) and involves the following steps: 1) video sequencing into image stills every 10 s, 2) selection of annotatable image stills, 3) editing and enhancing imagery where needed, 4) annotation (identifying and enumerating benthic taxa), 5) georeferencing (where needed) and 6) collation of metadata. For each video transect, frames were extracted every 10 s using VLC media player (https://www.…”

“…Over the past decade, advancements in underwater photography, particularly still imagery, has revolutionised the study of SNHS biotopes (Michaelis et al, 2019a, b;van der Reijden et al, 2019;Becker et al, 2020;Montereale Gavazzi et al, 2021;Romoth et al, 2023). This technology allows for the observation of micro-scale (1 mm 2 -1 cm 2 ) features and processes at ecologically relevant spatial scales, while also ground truthing hydroacoustic remote sensing data.…”

“…Our findings will support legal enforcement and environmental conservation and mainstream the stewardship of SNHS biotopes. The investigation focuses on two key offshore study sites: an MPA under the EU HD ("Vlaamse Banken"), and a recently discovered biodiversity hotspot (Montereale Gavazzi et al, 2021) situated underneath the busiest shipping lane in the world, currently being proposed as an MPA in the framework of the new Belgian MSP.…”

Seafloor Habitat Mapping by Combining Multiple Features From Optic and Acoustic Data: A Case Study From Ganquan Island, South China Sea

“…The acoustic signal has minimal attenuation in water, making acoustic transmission the most appropriate mechanism for transmitting information through the water column [9], [10]. Shipboard multibeam echo sounder (MBES) is rapidly becoming the most common acoustic survey tool of choice [11], [12], mainly because it allows the collection of continuous bathymetric information. High-resolution and high-precision bathymetric information is of key importance in characterizing substrate types.…”