An evaluation of semi‐automated methods for collecting ecosystem‐level data in temperate marine systems

Abstract

Historically, marine ecologists have lacked efficient tools that are capable of capturing detailed species distribution data over large areas. Emerging technologies such as high‐resolution imaging and associated machine‐learning image‐scoring software are providing new tools to map species over large areas in the ocean. Here, we combine a novel diver propulsion vehicle (DPV) imaging system with free‐to‐use machine‐learning software to semi‐automatically generate dense and widespread abundance records of a habitat‐forming algae over ~5,000 m2 of temperate reef. We employ replicable spatial techniques to test the effectiveness of traditional diver‐based sampling, and better understand the distribution and spatial arrangement of one key algal species. We found that the effectiveness of a traditional survey depended on the level of spatial structuring, and generally 10–20 transects (50 × 1 m) were required to obtain reliable results. This represents 2–20 times greater replication than have been collected in previous studies. Furthermore, we demonstrate the usefulness of fine‐resolution distribution modeling for understanding patterns in canopy algae cover at multiple spatial scales, and discuss applications to other marine habitats. Our analyses demonstrate that semi‐automated methods of data gathering and processing provide more accurate results than traditional methods for describing habitat structure at seascape scales, and therefore represent vastly improved techniques for understanding and managing marine seascapes.

Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs

“…Such an approach would improve data quality -by increasing representativeness of data or by increasing precision and therefore statistical power. The greatest potential gains might come from fully-automated image analysis combined with use of autonomous platform technologies to increase the amount and scale of image acquisition (Griffin et al, 2017;Manderson et al, 2017).…”

The Aichi Biodiversity Targets: achievements for marine conservation and priorities beyond 2020

“…The development and increasingly widespread use of innovative technologies and informatics has allowed for non-invasive and low-cost methods for long-term, continuous measurements of biodiversity. These technologies include automated monitoring systems such as passive and active acoustic monitoring ( Buscaino et al, 2016 ; McWilliam et al, 2017 ; Monczak et al, 2017 ; Egerton et al, 2018 ), autonomous underwater vehicles ( Griffin et al, 2017 ; Ferrari et al, 2016 , 2018 ), and high-resolution models of critical habitats for biodiversity (e.g., Allen Coral Atlas , structure-from-motion and benthic imagery models) ( Asaad et al, 2019 ; Friedman et al, 2012 ; Burns et al, 2015 ; Ismail, Huvenne & Masson, 2015 ; González-Rivero et al, 2017 ).…”

Peer Review #3 of "The Aichi Biodiversity Targets: achievements for marine conservation and priorities beyond 2020 (v0.1)"

“…The development and increasingly widespread use of innovative technologies and informatics has allowed for non-invasive and low-cost methods for long-term, continuous measurements of biodiversity. These technologies include automated monitoring systems such as passive and active acoustic monitoring (Buscaino et al, 2016;McWilliam et al, 2017;Monczak et al, 2017;Egerton et al, 2018), autonomous underwater vehicles (Griffin et al, 2017;Ferrari et al, 2016;Ferrari et al, 2018), and highresolution models of critical habitats for biodiversity (e.g., Allen Coral Atlas https://allencoralatlas.org/, structure-from-motion and benthic imagery models) (Asaad et al, 2019;Friedman et al, 2012;Burns et al, 2015;Ismail et al, 2015;González-Rivero et al, 2017).…”