Related Experiment Video
Updated: Jan 10, 2026
07:09
Integrating Visual Psychophysical Assays within a Y-Maze to Isolate the Role that Visual Features Play in Navigational Decisions
Published on: May 2, 2019
6.5K
A Comparative Machine Learning Study Identifies Light Gradient Boosting Machine (LightGBM) as the Optimal Model for
Ling Yang1,2, Weifeng Zhou1, Cong Zhang3
1East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, China.
Biology
|November 27, 2025
Summary
This study reveals that ocean temperature and location are key factors in yellowfin tuna distribution in the western Pacific. Machine learning models accurately predict tuna movements, aiding sustainable fishery management.
Area of Science:
- Fisheries Science
- Marine Ecology
- Data Science
Background:
- Tuna fisheries are crucial for global protein supply.
- Understanding yellowfin tuna (Thunnus albacares) distribution is vital for sustainable management.
- Environmental factors significantly influence marine species' spatial distribution.
Purpose of the Study:
- To identify key environmental drivers of yellowfin tuna distribution in the western tropical Pacific.
- To compare the performance of various machine learning models in predicting tuna spatial distribution.
- To provide a data-driven framework for sustainable yellowfin tuna fishery management.
Main Methods:
- Compiled a dataset linking catch per unit effort (CPUE) from Chinese longline vessels (2008-2019) with 24 environmental variables.
- Evaluated 16 machine learning regression models, including Light Gradient Boosting Machine (LightGBM), Random Forest, and CatBoost.
- Utilized SHapley Additive exPlanations (SHAP) for robust feature interpretation alongside internal model importance metrics.
Main Results:
- The Light Gradient Boosting Machine (LightGBM) model demonstrated superior performance in predicting yellowfin tuna distribution.
- Consistent results from internal feature importance and SHAP identified temporal (month), spatial (longitude, latitude), and intermediate seawater temperatures (T450, T300, T150) as critical predictors.
- Ocean temperatures at intermediate depths were found to directly influence tuna catch rates by affecting species movements.
Conclusions:
- Spatiotemporal and thermal variables are dominant factors in predicting yellowfin tuna distribution.
- Mid-layer ocean temperatures directly impact yellowfin tuna catch rates through movement.
- Large-scale climate indices indirectly affect tuna distribution by modulating ocean thermal structures.
- The study provides a reliable framework for sustainable fishery management and operational forecasting.
Keywords:
Light Gradient Boosting Machine (LightGBM)SHapley Additive exPlanations (SHAP)catch per unit effort (CPUE)comparative analysisensemble learningenvironmental driversexplainable machine learningfeature importance analysismachine learningyellowfin tunaMore Related Videos
Related Concept Videos
01:11Testing a Claim about Mean: Known Population SD
3.2K
A complete procedure of testing the hypothesis about a population mean is explained here.
Estimating a population mean requires the samples to be distributed normally. The data should be collected from the randomly selected samples having no sampling bias. The sample size needed to be higher than 30, and most importantly, the population standard deviation should be already known.
In most realistic situations, the population standard deviation is often unknown, but in rare circumstances, when it...
Estimating a population mean requires the samples to be distributed normally. The data should be collected from the randomly selected samples having no sampling bias. The sample size needed to be higher than 30, and most importantly, the population standard deviation should be already known.
In most realistic situations, the population standard deviation is often unknown, but in rare circumstances, when it...
3.2K
02:16Light Acquisition
9.3K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.3K