Xiaojing Yang , Xiaoyan Chen , Yuxin Zhu

Modern Agriculture Research Center, Cuixi Academy of Biotechnology, Zhuji, 311800, Zhejiang, China
Author    Correspondence author
Field Crop, 2025, Vol. 8, No. 3   
Received: 02 Apr., 2025    Accepted: 13 May, 2025    Published: 04 Jun., 2025

This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Cotton, as an important economic crop, its yield and quality are directly related to the development of the textile industry and agricultural economy. This study summarizes the relationship between the main agronomic traits of cotton (such as plant height, number of bolls, fiber quality, etc.) and yield and quality, discusses the urgent need for obtaining phenotypic data in large-scale field trials, as well as the significant value of phenotypic big data in cotton breeding and precise cultivation. At the technical level, it introduces the application of computer vision and deep learning in plant phenotypic identification The role of machine learning methods in the prediction and classification of cotton traits, as well as the automation technology of multimodal data fusion and feature extraction. In terms of data processing and analysis, this study explored key technologies such as image segmentation and extraction of cotton plant structure parameters, time series data analysis and growth dynamic monitoring, and correlation analysis between phenotypes and genotypes as well as environmental factors. It also analyzed the practical application and effect of the AI-driven cotton phenotype platform by combining large-scale experimental cases in cotton-growing areas of China and the United States. This study looks forward to the current challenges and proposes future development trends, aiming to provide references and inspirations for future cotton phenomics research, intelligent breeding and smart agriculture.

Cotton; High-throughput phenotype; Artificial intelligence; Unmanned aerial vehicle remote sensing; Field experiment