Catch Per Unit Effort Research Articles

Unveiling the population structure and breeding patterns of Petrolisthes boscii (Audouin, 1826) a common intertidal inhabitant of Shivrajpur, Saurashtra Coast, Gujarat

The present study focused on investigating the population structure and breeding biology of a species of Porcellanid crab, Petrolisthes boscii (Audouin, 1826). Evaluating the population ecology of the species is essential considering its crucial role in ecological functions including the nutrition cycle and its potential vulnerability to environmental stressors. The samples were collected over a period of 12 consecutive months (from March 2019 to February 2020) in an area of 500 m2 during low tide, utilizing the catch-per-unit-effort (CPUE) method when the water receded. The collected specimens (859 individuals) were categorized into males (407 individuals), non-ovigerous females (452 individuals), and ovigerous females (303 individuals). The assessment of fecundity was conducted by measuring the egg characteristics, including the total number, size, and weight of the eggs, as well as the carapace width of the ovigerous females. There was an evident difference in size, with males (8.60 ± 2.76) being significantly larger compared to females (8.39 ± 2.46) (p < 0.001). The overall and monthly sex ratios were female-biased (1:1.17). Moreover, the size frequency distribution revealed a bimodal distribution in male as well as female individuals. Ovigerous females occurred in all the months, which shows that the species breeds continuously throughout the year, with peaks in the months of March to May and August to October. There was a significant positive relationship observed among the size of ovigerous females and their total number of eggs (130.39 ± 83.31), egg mass weight (150 ± 110 mg). The study may provide baseline information for future studies on the impacts of a continuously altering environment and the consequences of increasing anthropogenic pressure on coastal areas.

Length‐Based Assessment of Hovsgol Grayling (Thymallus nigrescens), Lenok (Brachymystax lenok), and Burbot (Lota lota) Population Status in Lake Hovsgol, Mongolia

ABSTRACTDespite the global importance of inland fisheries, data available for stock assessment is often limited. Data‐limited methods that use length composition data offer a potential approach to assessing more inland fisheries. We assessed the population status of three fish species in Lake Hovsgol, Mongolia through length‐based spawning potential ratio (LBSPR) analysis and evaluation of trends in eight length‐based indicators of population status, catch‐per‐unit‐effort (CPUE), and body size. Hovsgol grayling (Thymallus nigrescens) were not yet overfished, but CPUE and body size declined due to targeting of large, mature fish. Lenok (Brachymystax lenok) were experiencing overfishing, especially of small, immature fish, which contributed to size–structure truncation. The burbot (Lota lota) population was healthy according to most indicators, but the lack of local life history information exacerbated already large uncertainties. Continued monitoring and improved coordination among fishers, managers, and scientists will be critical to enhancing the sustainability of these fisheries.

Mathematical approaches to fisheries quota management: ensuring sustainable practices in U.S. commercial fishing

Fisheries quota management plays a critical role in ensuring the sustainability of commercial fishing practices, particularly in the United States, where overfishing and resource depletion pose significant challenges to marine ecosystems. This review explores the mathematical approaches utilized to manage fisheries quotas effectively and sustainably. The paper examines key mathematical models, including population dynamics, bioeconomic models, game theory, and Catch-per-Unit-Effort (CPUE) models, highlighting their role in maintaining fish stock levels and regulating fishing activities. Through case studies from U.S. fisheries, such as the New England groundfish and Alaska pollock fisheries, the review assesses the effectiveness of these models in real-world applications. Additionally, it explores how advances in technology, such as satellite tracking, big data, and artificial intelligence, are enhancing the accuracy and adaptability of fisheries management models. The review concludes with insights into future directions for mathematical approaches in fisheries management, emphasizing the need for continuous innovation to support sustainable commercial fishing practices. By integrating advanced mathematical techniques and data-driven models, this paper aims to provide a pathway for policymakers and fisheries managers to achieve long-term sustainability in U.S. commercial fisheries.

Regional Factors Affecting Smallmouth Bass and Largemouth Bass Recruitment in Midwestern USA Reservoirs

ABSTRACTRegional factors correlated with recruitment of black bass (largemouth bass; Micropterus nigricans and smallmouth bass; Micropterus dolomieu), two important fishes, are rarely studied, despite the importance of recruitment variation in influencing fish populations. We sought to identify factors that drove variation in age‐0 and age‐1 black bass abundance. Age‐0 or age‐1 black bass catch per unit effort (CPUE) in reservoirs in Kansas and Illinois, USA, was positively correlated with local short‐term (i.e., mean April precipitation) environmental variables. In contrast, age‐0 or age‐1 black bass CPUE was generally negatively correlated with long‐term environmental variables and river regulation metrics (i.e., reservoir elevation) in the Mississippi and Missouri river reservoirs. Our findings highlight that consideration of spatiotemporal scale is important when managing black bass populations.

Prediction on Yellowfin Tuna (Thunnus albacares) Fishing Ground in Waters Near the Marshall Islands Based on SMOTETomek‐RF

ABSTRACTThis study monitored 37 longliners fishing in waters near the Marshall Islands from 2020 to 2022 by Liancheng Overseas Fishery (Shenzhen) Co., Ltd.'s operation management system. This study developed nine predictive models on the relationship between catch per unit effort (CPUE) data for yellowfin tuna (Thunnus albacares) and the environmental data. The environmental data integrate 48 variables, including eddy kinetic energy, chlorophyll a concentration, sea surface height, and additional measures of vertical oceanic conditions, alongside spatiotemporal parameters (year, month, day, longitude, and latitude). This study employed four spatial resolutions (0.25° × 0.25°, 0.5° × 0.5°, 1° × 1°, and 2° × 2°) to develop nine predictive models: KNN, RF, GBDT, CART, LightGBM, XGBoost, CatBoost, AdaBoost, and Stacking (RF, KNN, GBDT, and LR). These models, with a daily time resolution, were trained using 75% of the data and tested with the remaining 25%. The optimal spatial resolution and model were determined through a comprehensive comparison of model evaluation metrics across these spatial resolutions. The SMOTETomek algorithm was then applied to resample 75% of the data at the optimal spatial resolution, forming a new training dataset. This dataset was used to refine the model, subsequently tested with the remaining 25% of the data. Results indicated that (1) the optimal spatial resolution is 0.25° × 0.25° and the optimal model is RF; (2) the SMOTETomek algorithm enhances the model's predictive performance; and (3) the developed SMK‐RF model, exhibiting Acc and AUC values of 76.73% and 82.47%, respectively, accurately predicts the central fishing grounds for yellowfin tuna, consisting closely with actual fishing activity.

Comparison of catch efficiency of wire mesh fish traps operated along the coast of Thoothukudi, South-east coast of India

Aim: The study designs and fabricates traps with diverse wire mesh colors and shapes for field experiments. It also collects detailed catch data to assess their catch efficiency and determine the most effective design. Methodology: Experimental fish traps were fabricated utilizing four distinct colors (Light green, Dark green, White and Orange) and three different shapes (rectangle, square and circle). Fishing trials were conducted in selected fishing villages of Thereshpuram, with the traps operated fortnightly from June 2022 to May 2023. The catch rate per trip (CPUE) was calculated using the Total catch (in numbers) divided by the Unit Effort (White, 1987). An economic analysis of trap fishery was also performed based on gross revenue and total cost (Geetha et al., 2014). Results: The traps' overall catch per unit effort (CPUE) was recorded at 0.48Nos hr-1. Siganus canaliculatus emerged as the dominant species among the fishes trapped, constituting 16% of the total catch. Regarding trap color, the highest CPUE was observed with traps of dark green color (0.63 Nos hr-1), followed by light green (0.51 Nos hr-1), white (0.49 Nos hr-1) and orange (0.38 Nos hr-1). Economically, the performance of the trap fishery was evaluated using indicators such as operating cost/year, fixed cost, gross revenue and profit cost ratio. The success of the trap fishery was further emphasized by a benefit-cost ratio (BCR) of 3.50. Interpretation: Dark green-colored, square-shaped traps show promise in significantly enhancing fishermen's profits due to their higher catch per unit effort (CPUE) compared to other colors. Moreover, dark green traps may offer ecological advantages by blending into natural surroundings. This study highlights their potential and provides practical insights for fishermen to make informed gear choices, considering factors like color and shape. Key words: BCR, Color, CPUE, Shape, Trap

Testing best practices in small scale fisheries management: Evidence from a collaborative intervention in two marine protected areas of the central Mediterranean Sea

Adopting best practices (BPs) in small scale fisheries (SSF) is generally acknowledged to enhance ecological and social conditions, improving SSF management overall. Yet studies that empirically assess the effects of BPs on social-ecological outcomes (e.g., fishers' catches, revenues, and level of support towards management measures) remain limited. This study aimed to assess the effects of adopting BPs on catch per unit of effort (CPUE), revenue per unit of effort (RPUE) and small-scale fishers' perceptions in two Marine Protected Areas (MPAs) in Campania, Italy (Santa Maria di Castellabate (CAS-MPA) and Regno di Nettuno (NET-MPA)). Two BPs were implemented and tested in the two MPAs: i) five selective gears with three different mesh/hook sizes and ii) a participatory approach to increase dialogue between fishers and managers. The results from 36 surveys with small scale fishers and 158 SSF operations monitored using photo-sampling and image analysis techniques (between 2020 and 2022) are presented. Analyses of landings showed that significant differences in CPUE and RPUE between mesh/hook sizes were found in a limited number of cases (i.e., combination of fishing gears used in the 2 MPAs). Significant but divergent effects were found on CPUE in the two MPAs for gillnet used to target amberjack (GNA) only. RPUE was significantly higher in the NET-MPA when adopting the largest mesh size for GNA and the largest hook size for bottom longlines (BLL). When analyzing perceptions, fishers generally reported that the BPs adopted had a positive impact on their revenues, improved their relationship with MPA managers and increased their support for the MPA. In addition, eight stakeholder focus groups were held which helped investigators better understand the context, feedback the data gathered from the research and open up dialogue between the relevant stakeholders. The study concluded that increasing mesh/hook sizes, within the range tested here, does not negatively impact fishers’ revenues, while likely improving the status of target populations. Moreover, increasing dialogue between fishers and decision-makers can generate more positive perceptions towards the MPA and improve mutual understanding, helping to reconcile biodiversity conservation with human wellbeing for SSF.

Characterization of the Operability, Catch, and Fishing Effort of a Hake Trawling Vessel in Peru

In this study, the operational characteristics of the industrial hake fishing vessel "Santa Monica II" were characterized for the years 2020 and 2021, focusing on its catch production and fishing effort. A total of 234 trips and 1087 hauls were analyzed, considering a working depth of 100 fathoms on the continental shelf. Fishing effort was assessed based on years, seasonal periods, and months, allowing for a comparison of its productivity with 33 other vessels in the industrial fleet. The results revealed that the vessel caught 18% of the total catch of the industrial fleet in 2020 and 17% in 2021. Subarea A was the most frequented in 2020, with 66 trips, while in 2021, Subarea B led with 78 trips. The Catch per Unit Effort (CPUE) was 6.24 tons per hour and 8.99 tons per haul in 2020, and increased to 8.20 tons per hour and 10.75 tons per haul in 2021, highlighting its performance. Additionally, a significant concentration of hake resources was observed in the upper part of the continental slope during the study years.

Kernel density estimation of egg attachment areas aids in revealing spatiotemporal changes in Chinese sturgeon spawning grounds

Identifying precise egg attachment areas and tracking trends of spawning magnitude (total amount of spawned eggs) are critical for accurate habitat assessment and effective conservation efforts, especially for lithophilic spawning fishes. However, accurate measurement of spawning conditions across both spatial and temporal dimensions poses significant challenges. We conducted a fourteen-year field study below the Gezhouba Dam, the main spawning ground for the Chinese sturgeon, using Kernel Density Estimation (KDE) method and Catch per Unit of Effort (CPUE) to refine knowledge on egg attachment areas relative to previous assessments. In addition, our analysis documented shifts in spawning locations within these four areas over the past fourteen years, revealing a worrying trend of decreasing spawning magnitude. This approach not only enabled the incorporation of the density distribution of eggs into the assessment of spawning magnitude trends, but also underscored the potential of the KDE as a framework for identifying egg attachment areas and estimating spawning magnitude trends. Our results provide valuable insights into spawning degradation of Chinese sturgeon and inform conservation strategies to protect their fragile spawning grounds.

Marine recreational fishery trends in total catch, catch per unit effort, and release rates in Delaware during 1981–2021

AbstractThe impact of recreational fisheries on marine ecosystems is often overshadowed by commercial fisheries, although recreational fishing harvest can be substantial, especially for species that are either overfished or experiencing overfishing. Delaware is a small coastal state with ~1,000,000 residents and nearly 272,000 resident and non‐resident anglers. We used publicly available data for Delaware's recreational fisheries during 1981–2021 to determine the nine most caught fish species and to evaluate trends in total numbers caught, harvested, released, and catch per unit effort (CPUE). The top nine most frequently captured fish by recreational anglers were Summer Flounder (Paralichthys dentatus), Atlantic Croaker (Micropogonias undulatus), Bluefish (Pomatomus saltatrix), Black Sea Bass (Centropristis striata), Weakfish (Cynoscion regalis), White Perch (Morone americana), Tautog (Tautoga onitis), Striped Bass (Morone saxatilis), and Spot (Leiostomus xanthurus). The proportion of fish released increased through time for all nine species, suggesting that the recreational fishery in Delaware is transitioning from a harvest‐oriented to a catch‐and‐release‐oriented fishery. Observations of higher release rates in recreational fisheries of Delaware are consistent with the findings elsewhere in the world for freshwater and marine systems.

Construction and Comparison of Machine-Learning Forecast Models of Albacore Thunnus alalunga Fishing Grounds in the South Pacific Ocean

The traditional methods for predicting the distribution of albacore (Thunnus alalunga) fishing grounds have low performance and accuracy. Uneven sampling can result in unreasonable evaluation indicators. To address these issues, three methods, equi-frequency, K-means clustering algorithm, and 1-R split, were applied to discretize the catch per unit effort (CPUE) of albacore in the South Pacific from 2016 to 2021 and partition the fishing grounds into abundance levels. Eight machine learning models were used to predict the fishing grounds. In addition to the traditional evaluation index based on confusion matrix, top-k index was also used to evaluate the accuracy of fishery abundance predictions. The results showed that (1) When sampling is unbalanced, the reported accuracy does not fully represent the actual performance of the model in predicting the abundance of albacore in the fishing ground. F1 value can be used as the index of the model effect and stability. (2) In binary classification, the quartile stacking algorithm has the best stacking performance, with F1 0.89. (3) The top-1 prediction accuracy of three-category fishery forecasting is the highest at 0.74, and the top-1 prediction accuracy of five-category fishery forecasting is the highest at 0.54. (4) The top-k accuracy of classification of fisheries with multiple abundance using K-means is significantly better than that of equal frequency discretization (p < 0.001). The top-k evaluation index was used to predict the fishing grounds of albacore across multiple abundance levels for the first time in this study, which is significant for pioneering a new method for this application and which provides a demonstration of the development of artificial intelligence techniques for fisheries in the future.

Dwarf Seahorse (Hippocampus zosterae) Density, Distribution, and Habitat Use in Texas

Seagrass beds are composed of foundation species, providing essential nursery grounds, feeding areas, and refuge for various marine life. Several species of fish and invertebrates utilize seagrasses as essential habitat. The Dwarf Seahorse (Hippocampus zosterae) is an understudied species in Texas, and little is known about its density, distribution, and habitat associations in this area of their range. Physicochemical water parameters, nekton community data, habitat data, and Dwarf Seahorse catch data were collected at 80 sites in Texas. The highest catch per unit effort (CPUE) of the target species was in Aransas Bay (0.038/m2). There was a positive relationship between the presence and percent cover of turtle grass (Thalassia testudinum) and the presence and CPUE of Dwarf Seahorses. Dwarf Seahorses were detected more often and at a higher CPUE in locations with a higher seagrass community diversity and richness. The nekton community at sites where Dwarf Seahorses were detected was also more abundant, diverse, and species rich. This is the first comprehensive study of the distribution of the Dwarf Seahorse along the Texas coast. Dwarf Seahorses were generally found in higher abundances in association with mature, stable, and diverse seagrass beds. Recommended conservation strategy to protect Dwarf Seahorses should prioritize the protection of established and mature seagrass beds. Continued directed monitoring of this species is recommended to better understand their distribution and population status.

Estimating common whelk (Buccinum undatum) abundance using baited remote underwater video (BRUV)

Abstract Baited static gear fisheries targeting benthic invertebrates have expanded at a global scale. While improvements have been made in the monitoring and management of these fisheries, reliable survey methods for stock assessments of many key species are lacking. In this study we examine the viability of a baited remote underwater video (BRUV) system for obtaining abundance indices for a data-limited stock (common whelk, Buccinum undatum), and compare this method to catch per unit effort (CPUE) from commercial fishing. BRUVs capable of collecting 15 hours of timelapse footage were deployed on pot strings in two distinct whelk fishing sites, with replication over a spring-neap tidal cycle. Three potential BRUV metrics—the maximum (MaxN) and mean (MeanN) abundance and time of first arrival (T1)—were calculated for each deployment, and significant linear relationships were identified between MaxN, MeanN, and CPUE across sites. Temporal variability in BRUV indices driven by tidal dynamics was minimal, although results suggest high current speeds may reduce abundance estimates, and a potential method for predicting density on the seabed using arrival rates is also demonstrated. BRUVs are a valuable tool in developing stock assessment surveys for static gear fisheries.

Using vessel surveillance data to estimate spatiotemporal patterns in the short mackerel purse-seine fishery: Implications for time–area closure management in Thai waters

Mapping fishing effort and fish abundance across management areas is required to adjust and enforce time–area management measures. Seasonal closures are imposed in Thai waters to mitigate the overexploitation of short mackerel (Rastrelliger brachysoma), one of Southeast Asia’s most economically important pelagic species. This study applied machine learning to fishing vessel surveillance data to estimate spatiotemporal distributions of fishing effort and fish abundance in the Gulf of Thailand (GOT) and the Andaman Sea (ADS) to provide reliable and near real-time information to support seasonal closures. Data collected between 2018 and 2020 from Thai purse seiners targeting short mackerel included VMS data, fishing trip records, and landing information. Spatiotemporal patterns in fishing effort and catch per unit effort (CPUE) were then visualized in relation to the closures in different statistical management zones. The results show that fishing effort in the ADS increased in 2020 from 2018 and 2019, and peaked in 2019 in the GOT. No significant spatiotemporal trend in the distribution of CPUE was identified over the 3 years. Notably, the results reveal spatiotemporal adjustments to fishing effort and CPUE following the implementation of seasonal closures. This study is the first to present a practical approach to using vessel surveillance data to examine seasonal patterns in fishing effort and estimated fish distribution in Thai waters. The findings improve our understanding of fishing effort in response to area closures. The information generated here supports the time–area management of an intensively exploited migratory fish species, given timely and accurate information.

Species diversity and catch per unit effort (CPUE) of Portunidae in Batubara, North Sumatera, Indonesia

Abstract Crabs from the family of Portunidae are distributed widely in Indonesian waters, including the blue swimming crabs which has been exploited as a target species to meet the export demand and economic needs 3 of the capture fisheries sector. Crab catches from Portunidae family makes a major contribution to marine fisheries production in Batubara Regency, North Sumatra, Indonesia. The purpose of this study was to analyze the species diversity and catch per unit effort (CPUE) of crabs of Portunidae family in January–March 2023 in Tanjung Tiram Waters, Batu Bara Regency, North Sumatra, Indonesia. The fishing area was located right across the Malacca Strait, which is congested with international shipping traffic. Data were obtained through observations and community interview. Catch per unit effort (CPUE) of crabs was analyzed. The results showed about five species of crab from the Portunidae family were caught, including Portunus pelagicus, Scylla serrata, Charybdis feriata, Charybdis affinis, and Charybdis natator. The avearga CPUE value of target species Portunus pelagicus was 8,8 kg/trip.

Catch and characteristics of Decapterus sp. fishing areas in The Southern Waters of East Java - Bali

Abstract One of the essential potential resources of small pelagic fish to the livelihood of fishermen is Decapterus sp. The purpose of this study was to examine the catch and features of the Decapterus sp fishing region in Indian Ocean waters from East Java to Bali. The fisheries data for Decapterus sp during 2019 - 2021 were provided by Ministry of Maritime Affairs and Fisheries, Republic of Indonesia. The chl-a, and SST data were downloaded from Copernicus Marine Environment Monitoring Service (https://marine.copernicus.eu/). The fisheries and environmental data were then grouped by season. The results showed that the highest catch per unit efforts (CPUE) value occurred during transition 2 season with value of 2.89 followed by west season with value of 2.65. The smallest value of CPUE occurred during transition 1 (1.98). In general, most of Decapterus sp were caught in SST range between 27 – 29°C and chl-a range between 0.1 – 0.3 mg/m3. These results can be used as a basis for management of Decapterus sp especially in southern waters of East Java - Bali.

Temporal-Spatial Influences on Atlantic Bluefin Tuna CPUE in Recreational Fishery in the Aegean Sea: A Generalized Additive Model Approach

The Thunnus thynnus, a sought-after fish in recreational fishing, demands sustainable management due to its migratory nature. However, the lack of data on the impact of recreational fishing hampers understanding. This study aims to address this gap using Catch Per Unit Effort (CPUE) data from fishing contests on the Urla Peninsula (2016-2022). Findings revealed a yearly influence on CPUE, with the mean at 5.56±0.49 Kg·day-1. The peak was in 2018 with 13.98 Kg·day-1. Individual catches ranged from 305 to 10.45 Kg. 'Catch' was 21 times more prevalent than 'Catch and Release.' More catches occurred in the southern area, possibly due to tuna fattening cages. The study showed a yearly influence, but the dataset is insufficient to fully understand the environmental variables' impact. Despite the limitations, the potential of this data as a future benchmark for recreational fishing efforts is significant.

Towards sustainable exploitation of European pilchard (Sardina pilchardus) stocks off West African waters

European pilchard (Sardina pilchardus), herein referred to as “sardine” or “European sardine”, is the most productive and economically important small pelagic fish in the Northwest African waters. Thus far, very little is known about its stock status in the West African region despite the rapid decadal increase in its catch production. The present study provides avenues vital to improving guidance for sustainable species management. In this region, sardine is divided administratively into three stocks (northern: stock N, central: stock A + B, and southern: stock C). Thus, the present study used two Surplus Production Models (SPM) to evaluate sardine's stock status. Sardine's catch and scientific survey biomass data obtained from FAO-CECAF's (Fishery Committee for the Eastern Central Atlantic (CECAF)) latest reports were used in this analysis to fit the SPMs and investigate the effectiveness of the available catch-per-unit-effort (CPUE) trends in setting the total allowable catch (TAC) for sustaining the different sardine stocks in the region. Results from the SPMs indicate that the sardine stock in the north is fished at optimum levels. Meanwhile, the SPMs output based on the scientific survey biomass indices indicated a healthy state for the central and southern sardine stocks. Similarly, the fishery CPUE indices for the central and southern stocks showed similar biomass trends compared to the survey biomass index, indicating healthy stock status. Therefore, in cases where survey biomass index data is unavailable to run stock assessments, this study suggests that sardine fishery CPUEs could be used in SPMs to monitor biomass trends over time and may also provide stock status proxies. Additionally, with rapid climate and other environmental changes, sardine stocks must be regularly monitored with consistent and comparable scientific methodologies and updated fisheries time series data.

A Study on the Impact of Environmental Factors on Chub Mackerel Scomber japonicus Fishing Grounds Based on a Linear Mixed Model

Chub mackerel (Scomber japonicus) is a commercially important fish species which are widely distributed in the North Pacific. Based on the fishery data from China’s high-sea light-purse seine fishing from 2014 to 2020 and the marine environment factors, a mixed linear model considering the actual spatiotemporal stratification of the catch per unit effort (CPUE) was established to analyze the fixed and random effects of marine environmental factors on the CPUE of chub mackerel and to investigate the relationship between the abundance of chub mackerel resources in the Northwest Pacific and two marine environmental factors: sea surface temperature (SST) and chlorophyll-a concentration (CHL). The results showed that SST had a significant fixed effect on the CPUE. In contrast, the natural logarithm of chlorophyll (logCHL) had no fixed effect on the CPUE. Based on the monthly analysis, random fluctuations were observed in the impact of logCHL on the CPUE. LogCHL and CPUE show a positive correlation during spawning and wintering periods and a negative correlation during the feeding period. The study showed that when fishery sampling data exhibit spatiotemporal stratification, linear mixed models can effectively incorporate both the fixed and random effects of environmental factors on the CPUE of chub mackerel. Linear mixed models can play an important role in analyzing the fluctuations in resource abundance and the mechanisms governing the formation of fishing grounds for chub mackerel in the Northwest Pacific.

Structured neural networks for CPUE standardization: A case study of the blue endeavour prawn in Australia's Northern Prawn Fishery

We performed a study on standardizing the catch per unit effort (CPUE) for blue endeavour prawns (Metapenaeus endeavouri) caught in the Northern Prawn Fishery (NPF), one of Australia’s largest and most valuable prawn fisheries. Blue endeavour prawns constitute a significant proportion of the total NPF catches. However, there have been very limited studies on their population dynamics. This study assessed the effectiveness of Artificial Neural Networks (ANNs) for CPUE standardization, with a focus on blue endeavour prawns as a case study. Our approach involved developing new ANN models for CPUE standardization with two key ideas: using an architecture inspired by the catch equation to mitigate overfitting; and using the Tweedie distribution to manage uncertainties and zero counts in the catch data. Specifically, we grouped variables into three distinct modules based on the catch equation, with each representing catchability, fishing effort, and fish density, respectively. Parameter estimation for our ANNs was achieved by maximizing the likelihood using a coordinate descent approach, which alternates between optimizing the Tweedie distribution parameters (power and dispersion) and the standard neural net parameters. We conducted a comprehensive comparison among ANNs, generalized linear models, and generalized additive models. The findings suggest that customizing ANN structure improves model fitting and effectively mitigates the risk of overfitting. It also reveals a promising path for the application of neural networks in CPUE standardization.