Cost‐effective seafloor habitat mapping using a portable speedy sea scanner and deep‐learning‐based segmentation: A sea trial at Pujada Bay, Philippines

Terayama, Kei; Mizuno, Katsunori; Tabeta, Shigeru; Sakamoto, Shingo; Sugimoto, Yu; Sugimoto, Kenichi; Fukami, Hironobu; Sakagami, Masa–aki; Jimenez, Lea A.

doi:10.1111/2041-210x.13744

Cited by 8 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seagrass species found in the area include Cymodocea rotundata, Cymodocea serrulata, Enhalus acoroides, Halodule pinifolia, Halodule univervis, Halophila minor, Halophila ovalis, Syringodium isoetifolium and T. hemprichii. Seagrass species T. hemprichii and C. rotundata are predominant in the current study site (De Troch et al 2008;Jimenez 2016;Terayama et al 2022).). This study was established in a pre-selected seagrass bed of T. hemprichii to better understand the ecology of this vital ecosystem in a controlled manner in Guang-guang mangrove sanctuary, which is part of a Marine Protected Area (MPA) in Davao .…”

Section: Description Of the Study Areamentioning

confidence: 84%

Effects of fish herbivory on seagrass meadows of Guang-guang, Mati City, Philippines

2023

View full text Add to dashboard Cite

This study provides information on the effects of fish grazing on a seagrass bed that was dominated by Thalassia hemprichii in Guang-guang, Dahican, Mati City, Davao Oriental, Philippines. We tested the assumption that herbivore exclusion keeps the growth of seagrass shoots up to a minimum length. Fish visual census was used to count the abundance of fish in the area during high tide at a distance of 5 m away from the treatment cages with a 15 m transect length. Among all species, Siganus fuscescens was the most abundant (499) followed by S. guttatus (153), while Thalassoma jansenii was the less abundant (13). The result of the weekly fish count in the seagrass bed showed highly significant variations in the number and census of species present in the area (df = 11, MS = 2.88, F = 30.10, p < 0.001). Analysis of shoot length measurement in treatment cages also exhibited highly significant differences throughout the sampling period (df = 11, MS = 726.71, F = 1,633.10, p < 0.001). Comparison between initial and final shoot counts also showed significant differences, with a higher shoot count in the full cage (X2 = 8, df = 2, p = 0.018; FC > PC > OP). This study raises clear evidence to support the assumption that herbivore exclusion positively influences the growth of T. hemprichii in this area.

show abstract

Section: Description Of the Study Areamentioning

confidence: 84%

Effects of fish herbivory on seagrass meadows of Guang-guang, Mati City, Philippines

2023

View full text Add to dashboard Cite

show abstract

“…As human activity increases alongside the expression of climate change, localized modifications to the seafloor become cumulatively significant, resulting in permanent changes to an already modified seabed that can alter ecosystem processes supporting major ecosystem services [10][11][12]. For the most part, information on changes in benthic community structure and functioning has been obtained either through ex situ experimentation [13], with in situ observations taken from above the seafloor [14][15][16][17], or with destructive sampling devices (grabs, cores, anchor dredges, etc.) [18] that remove species from their three-dimensional habitat.…”

Section: Introductionmentioning

confidence: 99%

Combining three-dimensional acoustic coring and a convolutional neural network to quantify species contributions to benthic ecosystems

Mizuno,

Terayama,

Ishida

et al. 2024

R. Soc. Open Sci.

Self Cite

View full text Add to dashboard Cite

The seafloor is inhabited by a large number of benthic invertebrates, and their importance in mediating carbon mineralization and biogeochemical cycles is recognized. However, the majority of fauna live below the sediment surface, so most means of survey rely on destructive sampling methods that are limited to documenting species presence rather than event driven activity and functionally important aspects of species behaviour. We have developed and tested a laboratory-based three-dimensional acoustic coring system that is capable of non-invasively visualizing the presence and activity of invertebrates within the sediment matrix. Here, we present reconstructed three-dimensional acoustic images of the sediment profile, with strong backscatter revealing the presence and position of individual benthic organisms. These data were used to train a three-dimensional convolutional neural network model and, using a combination of data augmentation and data correction techniques, we were able to identify individual species with an 88% accuracy. Combining three-dimensional acoustic coring with deep learning forms an effective and non-invasive means of providing detailed mechanistic information of in situ species–sediment interactions, opening new opportunities to quantify species-specific contributions to ecosystems.

show abstract

“…Convolutional neural network‐based prediction has been used for accurate and high‐speed processing of underwater sonar images for the navigation and positioning of underwater remotely operated vehicles (Kim & Yu, 2016; Zhang et al, 2022). However, previous surveys on applying CNNs to benthic organisms in underwater environments mainly used high‐resolution optical images of the sea floor, rather than underwater sonar images (Mizuno et al, 2019; Mizuno et al, 2020; Li et al, 2021; Terayama et al, 2022). Compared with high‐resolution optical images, underwater sonar images present more challenges in achieving large‐scale surveys of benthic organisms in turbid waters, particularly in aspects such as image mosaic and data labeling (Bučas et al, 2016; Mizuno et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Survey of freshwater mussels using high‐resolution acoustic imaging sonar and deep learning‐based object detection in Lake Izunuma, Japan

Zhao,

Mizuno,

Tabeta

et al. 2023

Aquatic Conservation

Self Cite

View full text Add to dashboard Cite

The use of traditional in situ methods for underwater surveys to map freshwater mussel habitats is limited by challenges such as water transparency, depth and high labour demands. In this study, adaptive resolution imaging sonar (ARIS) was applied to monitor mussel distribution and abundance. In contrast to conventional quadrat surveys, this acoustic survey is non‐invasive and enables direct observation of mussels to allow their survival status to be determined in turbid water. ARIS produces high‐quality acoustic images that facilitate the creation of a distribution map for broader‐scale monitoring, especially if paired with deep learning methods such as the YOLOv4 algorithm for automatic mussel detection and classification. ARIS was successfully applied to surveying over 2000 m2 of Lake Izunuma in Miyagi, Japan. In one site, a high mussel abundance of ~0.6 individuals/m2 was detected, while other sites had low densities. The detection model achieved a mean average precision of 0.97. The survey results were used to generate a distribution map of living mussels. This study illustrates the feasibility of using an acoustic video camera with an open‐source deep learning algorithm to monitor mussels and other benthos in turbid water.

show abstract

Cost‐effective seafloor habitat mapping using a portable speedy sea scanner and deep‐learning‐based segmentation: A sea trial at Pujada Bay, Philippines

Abstract: Various methods have been developed for monitoring benthic marine habitats, such as coral reefs and seagrass meadows. In general, field transects, which are simple and relatively inexpensive, have been the most widely used methods (

Cited by 8 publications

References 24 publications

Effects of fish herbivory on seagrass meadows of Guang-guang, Mati City, Philippines

Effects of fish herbivory on seagrass meadows of Guang-guang, Mati City, Philippines

Combining three-dimensional acoustic coring and a convolutional neural network to quantify species contributions to benthic ecosystems

Survey of freshwater mussels using high‐resolution acoustic imaging sonar and deep learning‐based object detection in Lake Izunuma, Japan

Contact Info

Product

Resources

About