The skipjack tuna fishery in the west-central Pacific Ocean: applying neural networks to detect habitat preferences

Wang, Jintao; Chen, Xinjun; Staples, Kevin W.; Chen, Yong

doi:10.1007/s12562-017-1161-6

Cited by 16 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the validity and advancement of the proposed model in the model validation experiment, we used traditional models [10][11][12][13][21][22][23][24][25] and basic network models to carry out comparison experiments on same datasets. The comparison experiment models include Linear Regression Model (LR), Bayesian Regression Model (BR), Support Vector Regression Model (SVR), Regression Tree Model (RT), Random Forest Model (RF), Back Propagation Neural Network (BPNN), Convolution Neural Network (CNN), Long Short-Term Memory Network (LSTM), and a sequence model (CNN-LSTM-BPNN).…”

Section: Results' Comparative Analysis Of Model Validation Experimentsmentioning

confidence: 99%

Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Han¹,

Guo²,

Ma³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Accurate habitat prediction is important to improve fishing efficiency. Most of the current habitat-prediction studies use the single-source datasets and the sequence model based on single-source datasets, which, to a certain extent, limits the further improvement of prediction accuracy. In this paper, we propose a habitat-prediction method based on the multi-source heterogeneous remote-sensing data fusion, using product-level remote-sensing data and L1B-level original remote-sensing data. We designed a heterogeneous data feature extraction model based on a Convolution Neural Network (CNN) and Long and Short-Term Memory network (LSTM), and we designed a decision-fusion model based on multi-source heterogeneous data feature extraction. In the habitat prediction for the Northwest Pacific Saury, the mean R2 of the model reaches 0.9901 and the RMSE decreases to 0.01588 in the model validation experiment. It is significantly better than the results of other models, with the single datasets as input. Moreover, the model performs well in the generalization experiment because we limited the prediction error to less than 8%. Compared with the single-source sequence network model in the existing literature, the proposed method in this paper solves the problem of ineffective fusion caused by the differences in the structure and size of heterogeneous data through multilevel feature fusion and decision fusion, and it deeply explores the features of remote-sensing fishery data with different data structures and sizes. It can effectively improve the accuracy of fishery prediction, proving the feasibility and advancement of using multi-source remote-sensing data for habitat prediction. It also provides new methods and ideas for future research in the field of habitat prediction.

show abstract

Section: Results' Comparative Analysis Of Model Validation Experimentsmentioning

confidence: 99%

Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Han¹,

Guo²,

Ma³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The authors found several significant relationships, amongst others between tuna hotspots and phytoplankton bloom. Similarly, Wang et al (2018) sought to detect skipjack tuna environmental habitat preferences in the west‐central Pacific Ocean with the help of classical feedforward neural networks. A novel SOM analysis would provide clues for environmental conditions of candidate conservation areas and could draw upon previous findings for validation (see Table 1 in Lopez et al, 2017).…”

Section: Discussionmentioning

confidence: 99%

“…Similarly, Wang et al (2018) Forecasting near-future hotspots with oceanographic models, possible with SOMs using functions for supervised networks (Melssen et al, 2006), would allow the short-term planning of restrictive measures. With climate change, tuna habitat distribution limits are already spreading poleward at an overall estimated rate of about 6 kilometres per decade, varying by hemisphere and species (Erauskin-Extramiana et al, 2019).…”

Section: Perspectivesmentioning

confidence: 99%

Multi‐species hotspots detection using self‐organizing maps: Simulation and application to purse seine tuna fisheries management

et al. 2022

View full text Add to dashboard Cite

1. To fulfil fisheries management objectives that often include implementing the precautionary and ecosystem-based approaches, multispecies fisheries data need to be analysed. Amongst the different methods dealing with these multidimensional data, self-organizing maps (SOMs) remain rarely used, although they are highly flexible in data input and offer visualization possibilities particularly suited to summarize complex datasets.2. Here, we propose to combine SOMs with a clustering approach to break down data complexity and produce simple geographic maps showing catch hotspots, which can indicate sensitive zones in terms of fishery management. To promote this approach, we tested it first on simulated datasets and then on the openaccess ICCAT commercial catch database of the tropical tuna fisheries of the Atlantic Ocean. We aimed to detect drifting fish aggregating devices (dFADs) catch hotspots of juveniles of two tuna species, bigeye and yellowfin tunas and of the silky shark, a commonly bycaught vulnerable shark species, in tropical tuna purse seine fisheries. Simulations on datasets increasing in complexity (in number, geographic and duration extent of the hotspots and number of species in the analysis) informed us about the method's sensitivity and limits.3. Our findings showed that, in the context of multi-specific fisheries, the detection of the hotspot is dependent on a certain level of catch within the hotspot and that adding species to the analysis tended to mask small and short-duration hotspots. Applied to tropical tuna fisheries' data, the method confirmed the empirical knowledge on which first time-area closures were based and provided scientifical support. 4. All in all, the visual support provided by the method, its interpretability and its potential transferability to other fisheries' systems constitute its main strengths and imply a possible implementation in management decisions; specifically, as a tool to reach agreement between stakeholders in the definition of regulated areas for protecting juveniles of tunas and vulnerable associated species to dFAD practices.

show abstract

“…Therefore, it is necessary to be aware of the oceanographic conditions that are preferred by specific fish species. Several previous studies have revealed that the optimal combination of oceanographic factors can be a way to predict fish habitat (Chen et al 2009;Mugo et al 2010;Yen et al 2017;Zainuddin et al 2017;Wang et al 2018), although it may not be the only determining factor of skipjack tuna fishing location (Mugo et al 2010). Therefore, in this study, we combine primary data (fishing points, number of catches, and SST) and secondary data (SST and PP satellite imagery data) and compile them in the PHI model.…”

Section: Discussionmentioning

confidence: 99%

“…The distribution and migration pattern of skipjack tuna is extensive because it is a fast swimmer with long-distance highways ranging from archipelagic waters to ocean waters (Matsumoto et al 1984;Hall and Roman 2013;Hidayat et al 2019;Venegas et al 2019). Skipjack tuna migrate in schooling because they look for waters rich in food, looking for places to spawn, and changes in several aquatic environmental factors (Mugo et al 2010;Wang et al 2018). Skipjack tuna is found in warmer and shallower waters than other types of tuna (Hall and Roman 2013;Grande et al 2016;Hermida et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Mapping potential fishing zones for skipjack tuna in the southern Makassar Strait, Indonesia, using Pelagic Habitat Index (PHI)

et al. 2021

View full text Add to dashboard Cite

Abstract. Putri ARS, Zainuddin M, Musbir, Mustapha MA, Hidayat R. 2021. Mapping potential fishing zones for skipjack tuna in the southern Makassar Strait, Indonesia, using Pelagic Habitat Index (PHI). Biodiversitas 22: 3037-3045. Southern Makassar Strait is one of the potential fishing grounds for skipjack tuna in the Indonesian waters. Oceanographic factors become the primary factors that limit the distribution and abundance of fish. The study aimed to identify the relationship between fish distribution with sea surface temperature (SST) and primary productivity (PP) and map out the potential fishing grounds of skipjack tuna in the southern Makassar Strait. It used pelagic habitat index (PHI) analysis, which is strengthened by the results of correlation analysis in the form of generalized additive models (GAM) and Empirical cumulative distribution function (ECDF) analysis. The results showed that the distribution of skipjack tuna was significantly associated with the preferred range of SST 29-30.5°C and PP 350-400 mg C/m2/day. The potential fishing zone is well established near the coast to offshore of Barru and Polman waters (3°-6°S and 117°-119°E), with the peak season in May and October. The spatial pattern of potential fishing grounds for skipjack fishing is associated with hotspots (oceanographic preference), leading to increased feeding opportunities. This study suggests that the spatial pattern of high potential fishing zones could improve fishing, management, and conservation strategies along the southern Makassar Strait.

show abstract

The skipjack tuna fishery in the west-central Pacific Ocean: applying neural networks to detect habitat preferences

Cited by 16 publications

References 32 publications

Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Multi‐species hotspots detection using self‐organizing maps: Simulation and application to purse seine tuna fisheries management

Mapping potential fishing zones for skipjack tuna in the southern Makassar Strait, Indonesia, using Pelagic Habitat Index (PHI)

Contact Info

Product

Resources

About