Machine Learning-Driven Identification of Key Environmental Factors Influencing Fiber Yield and Quality Traits in Upland Cotton
文献类型： 外文期刊
作者： Souaibou, Mohamadou 1 ; Yan, Haoliang 1 ; Dai, Panhong 3 ; Pan, Jingtao 1 ; Li, Yang 1 ; Shi, Yuzhen 1 ; Gong, Wankui 1 ; Shang, Haihong 1 ; Gong, Juwu 1 ; Yuan, Youlu 1 ;
作者机构： 1.Chinese Acad Agr Sci, Inst Cotton Res, State Key Lab Cotton Biobreeding & Integrated Util, Anyang 455000, Peoples R China
2.Zhengzhou Univ, Sch Agr Sci, State Key Lab Cotton Biobreeding & Integrated Util, Zhengzhou Res Base, Zhengzhou 450001, Peoples R China
3.Anyang Inst Technol, Coll Comp Sci & Informat Engn, Anyang 455000, Peoples R China
4.Kashi Acad Adv Agr Sci, Kashi 844000, Peoples R China
关键词： cotton; machine learning; genotype environment interaction; SHAP interpretation; environmental factors
期刊名称：PLANTS-BASEL （ 影响因子：4.1； 五年影响因子：4.5 ）
ISSN： 2223-7747
年卷期： 2025 年 14 卷 13 期
页码：
收录情况： SCI
摘要： Understanding the influence of environmental factors on cotton performance is crucial for enhancing yield and fiber quality in the context of climate change. This study investigates genotype-by-environment (GxE) interactions in cotton, using data from 250 recombinant inbred lines (CCRI70 RILs) cultivated across 14 diverse environments in China's major cotton cultivation areas. Our findings reveal that environmental effects predominantly influenced yield-related traits (boll weight, lint percentage, and the seed index), contributing to 34.7% to 55.7% of their variance. In contrast fiber quality traits showed lower environmental sensitivity (12.3-27.0%), with notable phenotypic plasticity observed in the boll weight, lint percentage, and fiber micronaire. Employing six machine learning models, Random Forest demonstrated superior predictive ability (R2 = 0.40-0.72; predictive Pearson correlation = 0.63-0.86). Through SHAP-based interpretation and sliding-window regression, we identified key environmental drivers primarily active during mid-to-late growth stages. This approach effectively reduced the number of influential input variables to just 0.1-2.4% of the original dataset, spanning 2-9 critical time windows per trait. Incorporating these identified drivers significantly improved cross-environment predictions, enhancing Random Forest accuracy by 0.02-0.15. These results underscore the strong potential of machine learning to uncover critical temporal environmental factors underlying GxE interactions and to substantially improve predictive modeling in cotton breeding programs, ultimately contributing to more resilient and productive cotton cultivation.
- 相关文献
作者其他论文 更多>>
-
Enhancing genetic transformation efficiency in cucurbit crops through AtGRF5 overexpression: Mechanistic insights and applications
作者：Li, Yang;Wang, Naonao;Feng, Jing;Liu, Yue;Wang, Huihui;Deng, Shijun;Dong, Wenjing;Liu, Xiaofeng;Lv, Bingsheng;Xu, Kuipeng;Zhang, Huimin;Zhang, Zhonghua;Chai, Sen;Sun, Jinjing
关键词：auxin; cucurbit crops; genetic transformation; GRF; regeneration; scRNA-Seq
-
Deciphering the flavor constituents, microbiota and physicochemical properties of Yancaigao, a traditional sour rice paste from Southwest China
作者：Gao, Jinxiao;Li, Yang;Zhang, Yue;Shan, Yimeng;Wang, Aixia;Zhang, Xiya;Wang, Fengzhong;Tong, Li-Tao;Gao, Jinxiao;Luo, Tingting;Tong, Li-Tao
关键词：Sour rice paste; Lactic fermentation; Organic acids; Volatiles; Bacterial community
-
A comprehensive review of starch-based technology for encapsulation of flavor: From methods, materials, and release mechanism to applications
作者：Shan, Yimeng;Li, Jiaxin;Nie, Mengzi;Li, Dezhi;Zhang, Yue;Li, Yang;Wang, Lili;Liu, Liya;Wang, Fengzhong;Tong, Li-Tao;Tong, Li-Tao
关键词：Encapsulation techniques; Flavor; Starch-based materials; Inclusion complex; Release mechanisms; Industry applications
-
Numerical Simulation Analysis and Research on Drag Reduction and Stability Enhancement Effect of Head Swing Based on Biomimetic Flexible Variants
作者：Qi, Debo;Li, Yang;Yang, Baisheng;Wu, Zhengyang;Li, Bo;Niu, Shichao
关键词：head swing; drag reduction; biomimetic flexible variants; radial drag; numerical simulation
-
The PAP Gene Family in Cotton: Impact of Genome-Wide Identification on Fiber Secondary Wall Synthesis
作者：Sun, Cong;Li, Weijie;Qi, Ruiqiang;Liu, Yangming;Wang, Xiaoyu;Gong, Juwu;Gong, Wankui;Pan, Jingtao;Li, Yang;Shi, Yuzhen;Yan, Haoliang;Shang, Haihong;Yuan, Youlu;Wang, Xiaoyu;Shang, Haihong
关键词：cotton; purple acid phosphatase (PAP); cotton fiber; expression analysis
-
Coenzyme Q GhCoQ9 enhanced the salt resistance by preserving the homeostasis of mitochondrial in upland cotton
作者：Xu, Nan;Zhong, Yike;Chen, Zhuona;Zhang, Doudou;Han, Xu;Wei, Renhui;Wang, Panpan;Li, Xinru;Gong, Juwu;Li, Yang;Yan, Haoliang;Yuan, Youlu;Shang, Haihong;Xu, Nan;Zhong, Yike;Zhang, Yuanming;Yuan, Youlu;Shang, Haihong;Chen, Zhuona;Zhang, Doudou;Han, Xu;Wang, Panpan;Li, Xinru;Zhao, Yanpeng;Li, Gangling;Yang, Zheng;Yuan, Youlu;Shang, Haihong;Gao, Xu
关键词：Cotton; CoQ; GhCoQ9; Salt stress; Ultrastructure
-
Genome-Wide Identification and Classification of Arabinogalactan Proteins Gene Family in Gossypium Species and GhAGP50 Increases Numbers of Epidermal Hairs in Arabidopsis
作者：Wei, Renhui;Guo, Ziru;Yan, Haoliang;Pan, Jingtao;Liu, Aiying;Gong, Wankui;Ge, Qun;Gong, Juwu;Yuan, Youlu;Shang, Haihong;Yang, Zheng;Zhao, Yanpeng;Azhar, Muhammad Tehseen;Zhang, Yamin;Li, Gangling;Yuan, Youlu;Shang, Haihong;Azhar, Muhammad Tehseen
关键词：cotton; arabinogalactan protein; gene regulation; functional characterization
