数字农科院2.0

A Comparative Machine Learning Study Identifies Light Gradient Boosting Machine (LightGBM) as the Optimal Model for Unveiling the Environmental Drivers of Yellowfin Tuna (Thunnus albacares) Distribution Using SHapley Additive exPlanations (SHAP) Analysis

文献类型： 外文期刊

作者： Yang, Ling;Zhou, Weifeng;Zhang, Cong;Tang, Fenghua

作者机构：

关键词： yellowfin tuna;catch per unit effort (CPUE);environmental drivers;machine learning;feature importance analysis;SHapley Additive exPlanations (SHAP);explainable machine learning;comparative analysis;Light Gradient Boosting Machine (LightGBM);ensemble learning

期刊名称： BIOLOGY-BASEL

ISSN：

年卷期： 2025 年 14 卷 11 期

页码：

收录情况： SCIE（2025版）

摘要： Simple Summary Tuna fisheries are a vital source of global protein, making it important to understand the key environmental factors that influence their distribution. This study aimed to identify which environmental conditions most affect where yellowfin tuna gather in the western and central Pacific Ocean. Using integrated fishing log data and 24 multi-source environmental variables, we applied and compared 16 machine learning regression models. The Light Gradient Boosting Machine (LightGBM) performed best and was selected to evaluate the influence of key environmental drivers. The results highlight that spatiotemporal and thermal factors are the most important predictors of tuna distribution. This research provides a reliable, data-driven framework to support sustainable fishery management, resource assessment, and operational forecasting.Abstract Fishery resources of tuna serve as a vital source of global protein. This study investigates the key environmental drivers influencing the spatial distribution of yellowfin tuna (Thunnus albacares) in the western tropical Pacific Ocean. A comprehensive dataset was constructed by linking the catch per unit effort (CPUE) from 43 Chinese longline fishing vessels (2008-2019) with 24 multi-source environmental variables. To accurately model this complex relationship, a total of 16 machine learning regression models, including advanced ensemble methods like Light Gradient Boosting Machine (LightGBM), Random Forest, and Categorical Boosting Regressor (CatBoost), were evaluated and compared using multiple performance metrics (e.g., Coefficient of Determination [R2], Root Mean Squared Error [RMSE]). The results indicated that the Light Gradient Boosting Machine (LightGBM) model achieved superior performance, demonstrating excellent nonlinear fitting capabilities and generalization ability. For robust feature interpretation, the study employed both the model's internal feature importance metrics and the SHapley Additive exPlanations (SHAP) method. Both approaches yielded highly consistent results, identifying temporal (month), spatial (longitude, latitude), and key seawater temperature indicators at intermediate depths (T450, T300, T150) as the most critical predictors. This highlights significant spatiotemporal heterogeneity in the distribution of Thunnus albacares. The analysis suggests that mid-layer ocean temperatures directly influence catch rates by governing the species' vertical and horizontal movements. In contrast, large-scale climate indices such as the Oceanic Ni & ntilde;o Index (ONI) exert indirect effects by modulating ocean thermal structures. This research confirms the dominance of spatiotemporal and thermal variables in predicting yellowfin tuna distribution and provides a reliable, data-driven framework for supporting sustainable fishery management, resource assessment, and operational forecasting.

分类号：

  • 相关文献

[1]Ensemble learning prediction of soybean yields in China based on meteorological data. Qian chuan LI,Shi wei XU,Jia yu ZHUANG,Jia jia LIU,Yi ZHOU,Ze xi ZHANG. 2023

[2]A New Safe-Level Enabled Borderline-SMOTE for Condition Recognition of Imbalanced Dataset. Chen, Chao,Shen, Wei,Yang, Chenhao,Fan, Wei,Liu, Xin,Li, Ying. 2023

[3]Application of ensemble learning to genomic selection in chinese simmental beef cattle. Liang M.,Miao J.,Wang X.,Chang T.,An B.,Duan X.,Xu L.,Gao X.,Zhang L.,Li J.,Gao H.. 2021

[4]Estimation of Maize LAI Using Ensemble Learning and UAV Multispectral Imagery under Different Water and Fertilizer Treatments. Cheng, Qian,Xu, Honggang,Fei, Shuaipeng,Li, Zongpeng,Chen, Zhen. 2022

[5]Image Classification of Wheat Rust Based on Ensemble Learning. Qian Pan,Maofang Gao,Pingbo Wu,Jingwen Yan,Mohamed A.E. AbdelRahman. 2022

[6]A Stacking Ensemble Learning Framework for Genomic Prediction. Mang Liang,Tianpeng Chang,Bingxing An,Xinghai Duan,Lili Du,Xiaoqiao Wang,Jian Miao,Lingyang Xu,Xue Gao,Lupei Zhang,Junya Li,Huijiang Gao. 2021

[7]Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance. Fei, Shuaipeng,Hassan, Muhammad Adeel,He, Zhonghu,Chen, Zhen,Shu, Meiyan,Wang, Jiankang,Li, Changchun,Xiao, Yonggui. 2021

[8]Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation. Jingyu Hu,Hao Feng,Qilei Wang,Jianing Shen,Jian Wang,Yang Liu,Haikuan Feng,Hao Yang,Wei Guo,Hongbo Qiao,Qinglin Niu,Jibo Yue. 2024

[9]Quantifying corn LAI using machine learning and UAV multispectral imaging. Cheng, Qian,Ding, Fan,Xu, Honggang,Guo, Shuzhe,Li, Zongpeng,Chen, Zhen. 2024

[10]Improving soybean yield prediction by integrating UAV nadir and cross-circling oblique imaging. Guangyao Sun,Yong Zhang,Haochong Chen,Lei Wang,Mingxue Li,Xuhong Sun,Shuaipeng Fei,Shunfu Xiao,Long Yan,Yinghui Li,Yun Xu,Lijuan Qiu,Yuntao Ma. 2024

[11]A Machine-Learning Model Based on the Fusion of Spectral and Textural Features from UAV Multi-Sensors to Analyse the Total Nitrogen Content in Winter Wheat. Zongpeng Li,Xinguo Zhou,Qian Cheng,Shuaipeng Fei,Zhen Chen. 2023

[12]Estimating Maize Crop Height and Aboveground Biomass Using Multi-Source Unmanned Aerial Vehicle Remote Sensing and Optuna-Optimized Ensemble Learning Algorithms. Li, Yafeng,Li, Changchun,Cheng, Qian,Duan, Fuyi,Zhai, Weiguang,Li, Zongpeng,Mao, Bohan,Ding, Fan,Kuang, Xiaohui,Chen, Zhen. 2024

[13]Maize biomass estimation by integrating spectral, structural, and textural features from unmanned aerial vehicle data. Lin Meng,Bo Ming,Yuan Liu,Chenwei Nie,Liang Fang,Lili Zhou,Jiangfeng Xin,Beibei Xue,Zhongyu Liang,Huirong Guo,Dameng Yin,Xiuliang Jin. 2025

[14]Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning. Junlong Li,Quan Feng,Junqi Yang,Jianhua Zhang,Sen Yang. 2025

[15]The Bayesian mixture expert recognition model for tobacco leaf curing stages based on feature fusion. Panzhen Zhao,Shijiang Duan,Songfeng Wang,Aihua Wang,Lingfeng Meng,Zhicheng Wang,Yingpeng Dai. 2025

[16]Comparative Transcriptome Analysis Of Tucps I.n Gossypium Hirsutum Ligon-Lintless-1 M utant And Their Proposed Functions In Cotton Fiber Development. Salih, Haron,Salih, Haron,Salih, Haron,Mustafa, Nada S.,Du, Xiongming,He, Shoupu,Gong, Wenfang. 2019

[17]A comparative analysis of agricultural research and extension reforms in China and India. Babu, Suresh Chandra,Huang, Jikun,Venkatesh, P.,Zhang, Yumei. 2015

[18]Comparison of transcriptomes undergoing waterlogging at the seedling stage between tolerant and sensitive varieties of Brassica napus L.. Zou Xi-ling,Zeng Liu,Lu Guang-yuan,Cheng yong,Xu Jin-song,Zhang Xue-kun. 2015

[19]A collection of 10,096 indica rice full-length cDNAs reveals highly expressed sequence divergence between Oryza sativa indica and japonica subspecies. Liu, Xiaohui,Lu, Tingting,Yu, Shuliang,Li, Ying,Huang, Yuchen,Huang, Tao,Zhang, Lei,Zhu, Jingjie,Zhao, Qiang,Fan, Danlin,Mu, Jie,Shangguan, Yingying,Feng, Qi,Guan, Jianping,Ying, Kai,Zhang, Yu,Lin, Zhixin,Sun, Zongxiu,Qian, Qian,Lu, Yuping,Han, Bin.

[20]FTIR Analysis of Burkholderia seminalis from Apricot, Water and Rice Rhizosphere. Fang, Y.,Fang, Y.,Li, B.,Wang, Y. L.,Sun, G. C.,Guo, L. B..

作者其他论文 更多>>