Bigeye tuna fishing ground analysis using oceanographic features in Eastern Indian Ocean off Southern Java

Dewi, Amanda Kusuma; Gaol, Jonson Lumban; Siregar, Vincentius P.; Atmadipoera, Agus S.

doi:10.1088/1755-1315/429/1/012043

Cited by 4 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final environmental factors used in our best model included T0, T50, T100, T300, T500, S100, S200, S400, D0, D50, D100, D200, D500, chl-a, WS, EKE, and MLD. The environmental factors were This is inconsistent with some literatures that mentioned the bigeye tuna preference habitat at depth of 150-250 m (Bigelow et al, 2002;Dewi et al, 2020). This may be related to water characteristics in our study area.…”

Section: Analysis Of the Environmental Factorscontrasting

confidence: 98%

See 1 more Smart Citation

Comparison of machine learning models within different spatial resolutions for predicting the bigeye tuna fishing grounds in tropical waters of the Atlantic Ocean

Song

Zhang

et al. 2023

Fisheries Oceanography

View full text Add to dashboard Cite

To understand the effects of the machine learning models and the spatial resolutions on the prediction accuracy of bigeye tuna (Thunnus obesus) fishing grounds, logbook data of 13 Chinese longliners operating in the high seas of the Atlantic Ocean from 2016 to 2019 were collected. The environmental factors were selected based on the correlation analysis of calculation of catch per unit effort (CPUE) and the marine vertical environmental factors. Five machine learning models: random forest, gradient‐boosting decision tree, K‐nearest neighbor, logistic regression and stacking ensemble learning (STK) within four spatial resolutions of .5° × .5°, 1° × 1°, 2° × 2° and 5° × 5° grids were constructed and compared. Results showed that (1) the prediction performance of STK model was the best, with the highest scores of the four evaluation indexes, accuracy (Acc), precision (P), recall (R), and F1‐score (F1), and the highest correct prediction rate for predicting “high CPUE fishing ground”; (2) models within the spatial resolution of 1° × 1° grids predicted the better results compared with .5° × .5°, 2° × 2° and 5° × 5° grids; (3) the vertical environmental factors selected based on the correlation analysis could be used as reliable predictors in the models. Results suggested that using STK within 1° × 1° grids could improve the generalization performance and prediction accuracy for predicting the bigeye tuna fishing grounds in the Atlantic Ocean.

show abstract

Section: Analysis Of the Environmental Factorscontrasting

confidence: 98%

“…In this study, we found that temperatures at the depth of 150 m have little correlation with CPUE. This is inconsistent with some literatures that mentioned the bigeye tuna preference habitat at depth of 150–250 m (Bigelow et al, 2002; Dewi et al, 2020). This may be related to water characteristics in our study area.…”

Section: Discussioncontrasting

confidence: 79%

Comparison of machine learning models within different spatial resolutions for predicting the bigeye tuna fishing grounds in tropical waters of the Atlantic Ocean

Song

Zhang

et al. 2023

Fisheries Oceanography

View full text Add to dashboard Cite

show abstract

“…Based on the results of fishermen's interviews, bigeye tuna is only caught during the full moon. This can be reinforced by the statement (Dewi et al 2020) [5] that tuna, which are predators that are positive phototaxis, need light to find food, therefore at night, the tuna will rise to the surface 0-100m to look for food. Thus, during the full moon, the light entering the waters will be brighter than the crescent moon.…”

Section: Resultsmentioning

confidence: 99%

Potential big eye tuna (Thunnus obesus) fishing zone in western Sumatra Sea, Indonesia based on Sub-surface Temperature

Sari,

Hartoko,

Fitri

2024

IJMRGE

View full text Add to dashboard Cite

Tuna is a large pelagic fish that has high economic value, so knowledge of the potential bigeye tuna fishing zone is needed to facilitate fishermen in conducting tuna fishing operations. This study was conducted using bigeye tuna catch logbook data from 2022-2023 obtained from Bungus Fishing Port, Padang, Indonesia. Sub-surface temperature data was obtained from global modeling data conducted by CMEMS at depths of 77m, 100m, and 130m. The results of potential bigeye tuna fishing zones in the Western Waters of Sumatra, Indonesia based on sub-surface temperature using the ECDF method found that in the east season, bigeye tuna has an optimum temperature in the range of 26.9-30OC at 77m depth, while the west season has an optimum temperature in the range of 15.7-27.6OC at 109m depth. The algorithm used in spatial modeling of potential bigeye tuna fishing zones in the east season is y = -0.0134x2 + 0.7688x - 10.968 and the west season is y = -0.0031x2 + 0.1332x - 1.3354.

show abstract

“…Although many researchers have focused on South Java upwelling, studies o f upwelling comparisons in the shelf area, particularly by analyzing the upwelling index based on Chl-a, wind, and SST, have not yet been conducted. Dewi et al (2020) used only UISST to investigate the South Java upwelling characteristics during ENSO. Naulita et al (2020) analyzed the South Java Upwelling Index based on wind and SST in the region between 106 and 114˚E.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of the Three Upwelling Indices in the South Java Sea Shelf

Budiman¹,

Bengen²,

Nurjaya³

et al. 2022

CMUJNS

View full text Add to dashboard Cite

Upwelling plays a crucial role in driving cross-shelf circulation between the continental shelf and boundary currents. It is well known that upwelling results in the exchange of heat, nutrients, fish larvae, and other properties. It controls primary productivity, which promotes higher trophic levels and fisheries. Upwelling can be identified by at least three physical variables: wind, sea surface temperature (SST), and chlorophyll-a (Chl-a). The intensity of upwelling can then be calculated using the Upwelling Index (UI), which is based on these three variables. Wind-based UI (UIET), SST-based UI (UISST), and Chl-a-based UI (UICHL) were calculated using satellite-derived and reanalysis data from 2002 to 2017. Those three UIs were analyzed spatially and temporarily to determine the differences in upwelling strength and duration. The most appropriate UI for explaining the South Java upwelling system in our domain was determined through the correlation analysis. The monthly mean climatology of all UI (UIET, UISST, and UICHL) reveals the seasonal variation, which is high during the southeast (SE) monsoon. The strongest correlation between UISST and Chl-a with the smallest lag times suggested that South Java upwelling in our domain can be identified better using SST-based UI (UISST) than through the Ekman mass transport-based UIET, particularly in the east, relevant to the earlier study. Keywords: Chlorophyll-a, Upwelling Indexes, South Java Upwelling

show abstract

Bigeye tuna fishing ground analysis using oceanographic features in Eastern Indian Ocean off Southern Java

Cited by 4 publications

References 18 publications

Comparison of machine learning models within different spatial resolutions for predicting the bigeye tuna fishing grounds in tropical waters of the Atlantic Ocean

Comparison of machine learning models within different spatial resolutions for predicting the bigeye tuna fishing grounds in tropical waters of the Atlantic Ocean

Potential big eye tuna (Thunnus obesus) fishing zone in western Sumatra Sea, Indonesia based on Sub-surface Temperature

A Comparison of the Three Upwelling Indices in the South Java Sea Shelf

Contact Info

Product

Resources

About