Incidental capture, or bycatch, of marine species is a global conservation concern. Interactions with fishing gear can cause mortality in air-breathing marine megafauna, including sea turtles. Despite this, interactions between sea turtles and fishing gear—from a behavior standpoint—are not sufficiently documented or described in the literature. Understanding sea turtle behavior in relation to fishing gear is key to discovering how they become entangled or entrapped in gear. This information can also be used to reduce fisheries interactions. However, recording and analyzing these behaviors is difficult and time intensive. In this study, we present a machine learning-based sea turtle behavior recognition scheme. The proposed method utilizes visual object tracking and orientation estimation tasks to extract important features that are used for recognizing behaviors of interest with green turtles ( Chelonia mydas ) as the study subject. Then, these features are combined in a color-coded feature image that represents the turtle behaviors occurring in a limited time frame. These spatiotemporal feature images are used along a deep convolutional neural network model to recognize the desired behaviors, specifically evasive behaviors which we have labeled “reversal” and “U-turn.” Experimental results show that the proposed method achieves an average F1 score of 85% in recognizing the target behavior patterns. This method is intended to be a tool for discovering why sea turtles become entangled in gillnet fishing gear.
more »
« less
This content will become publicly available on December 18, 2024
Analysis of bycatch patterns in four northeastern USA trawl fisheries
Discards from commercial fisheries have been linked to detrimental effects on ecosystems and stocks of living marine resources. Understanding spatial and temporal patterns of discards may assist in devising regulatory practices and mitigation strategies and promote sustainable management policies. This study investigates data from bycatch monitoring programs using a machine learning approach. We used a gradient boosting classifier for describing catch and bycatch patterns in the U.S. Mid-Atlantic Black Seabass (Centropristis striata), Summer Flounder (Paralichthys dentatus), Scup (Stenotomus chrysops), and Longfin Squid (Doryteuthis pealeii) fisheries. We used oceanographic, biological, spatial, and fisheries data as explanatory model features. We found positive associations between target species volume and bycatch. Although we found that sea surface temperature and year were important model features, the direction of impact of those predictors was variable. From our findings, we conclude that machine learning approaches are promising in supplementing traditional methodologies, especially with the increase in data availability trends.
more » « less- Award ID(s):
- 1841112
- NSF-PAR ID:
- 10491556
- Publisher / Repository:
- Northwest Atlantic Fisheries Organization
- Date Published:
- Journal Name:
- Journal of Northwest Atlantic Fishery Science
- Volume:
- 54
- ISSN:
- 1813-1859
- Page Range / eLocation ID:
- 31 to 48
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Uncertainties about the magnitude of bycatch in poorly assessed fisheries impede effective conservation management. In northern Peru, small-scale fisheries (SSF) bycatch negatively impacts marine megafauna populations and the livelihoods of fishers which is further elevated by the under-reporting of incidents. Within the last decade, accounts of entangled humpback whales (HBW) ( Megaptera novaeangliae ) off the northern coast of Peru have increased, while Eastern Pacific leatherback turtles (LBT) ( Dermochelys coriacea ) have seen over a 90% decline in nesting populations related in large part to bycatch mortality. By leveraging the experience and knowledge of local fishers, our research objectives were to use a low-cost public participation mapping approach to provide a spatio-temporal assessment of bycatch risk for HBW and LBT off two Peruvian fishing ports. We used an open-source, geographic information systems (GIS) model, the Bycatch Risk Assessment (ByRA), as our platform. Broadly, ByRA identifies high bycatch risk areas by estimating the intersection of fishing areas (i.e., stressors) with species habitat and evaluating the exposure and consequence of possible interaction between the two. ByRA outputs provided risk maps and gear risk percentages categorized as high, medium, and low for the study area and seven subzones for HBW in the austral winter and LBT in the austral summer. Overall, the highest bycatch risk for both species was identified within gillnet fisheries near the coast. Bycatch risk for most gear types decreased with distance from the coast. When we separated the ByRA model by port, our map outputs indicate that bycatch management should be port specific, following seasonal and spatial variations for HBW, and specific fishing gear impacts for HBW and LBT. Combined with direct bycatch mitigation techniques, ByRA can be a supportive and informative tool for addressing specific bycatch threats and marine megafauna conservation goals. ByRA supports a participatory framework offering rapid visual information via risk maps and replicable methods for areas with limited resources and data on fisheries and species habitat.more » « less
-
more » « less
Abstract Conservation of migratory species exhibiting wide‐ranging and multidimensional behaviors is challenged by management efforts that only utilize horizontal movements or produce static spatial–temporal products. For the deep‐diving, critically endangered eastern Pacific leatherback turtle, tools that predict where turtles have high risks of fisheries interactions are urgently needed to prevent further population decline. We incorporated horizontal–vertical movement model results with spatial–temporal kernel density estimates and threat data (gear‐specific fishing) to develop monthly maps of spatial risk. Specifically, we applied multistate hidden Markov models to a biotelemetry data set (
n = 28 leatherback tracks, 2004–2007). Tracks with dive information were used to characterize turtle behavior as belonging to 1 of 3 states (transiting, residential with mixed diving, and residential with deep diving). Recent fishing effort data from Global Fishing Watch were integrated with predicted behaviors and monthly space‐use estimates to create maps of relative risk of turtle–fisheries interactions. Drifting (pelagic) longline fishing gear had the highest average monthly fishing effort in the study region, and risk indices showed this gear to also have the greatest potential for high‐risk interactions with turtles in a residential, deep‐diving behavioral state. Monthly relative risk surfaces for all gears and behaviors were added to South Pacific TurtleWatch (SPTW) (https://www.upwell.org/sptw ), a dynamic management tool for this leatherback population. These modifications will refine SPTW's capability to provide important predictions of potential high‐risk bycatch areas for turtles undertaking specific behaviors. Our results demonstrate how multidimensional movement data, spatial–temporal density estimates, and threat data can be used to create a unique conservation tool. These methods serve as a framework for incorporating behavior into similar tools for other aquatic, aerial, and terrestrial taxa with multidimensional movement behaviors. -
more » « less
Abstract Fishery observers are prevalent actors in the global effort to reduce discards in fisheries, but there remains considerable uncertainty about how effective they are. We analyzed high-resolution logbook records of individual hauls (
n = 127 415) across five-and-a-half-years (2012–2018) for all of Greenland’s large-scale fisheries to determine if onboard fishery observers influence the mandatory reporting of discards. To do so, we used exact matching to compare reported discards for observed and unobserved hauls (each time a catch is recorded), thus controlling for systematic differences between monitored and unmonitored practices. After adjusting for variables that represent species caught, gear, vessel, owner, year, license, and location, we found that skippers systematically underreport discards when no observers are on board. Systematic underreporting was most pronounced in less valuable fisheries, in contrast to theoretical arguments in previous studies. The differences between reported discards from observed and unobserved fishing leads us to assume that onboard observers encourage more faithful logbook records. Thus, onboard observers play a vital role in improving information on the environmental impact of fishing and in turn, make a key contribution to sustainable fisheries management. -
more » « less
Abstract The Eastern Pacific leatherback turtle population (
Dermochelys coriacea ) has declined precipitously in recent years. One of the major causes is bycatch from coastal and pelagic fisheries. Fisheries observations are often underutilized, despite strong potential for this data to affect policy. In this study, we created a spatiotemporal species distribution model that synthesizes fisheries observations with remotely sensed environmental data. The model will be developed into a dynamic management tool for the Eastern Pacific leatherback population. We obtained leatherback observation data from multiple fisheries that have operated in the Southeast Pacific (2001–2018). A dynamic Poisson point process model was applied to predict leatherback intensity (observation per unit area) as a function of dynamic environmental covariates. This model serves as a tool for application by managers and stakeholders toward the reduction of leatherback turtle bycatch and provides a modeling framework for analyzing fisheries observations from other vulnerable populations and species.
