Multi-temporal UAV multispectral phenotyping and machine learning for modeling cotton defoliation dynamics across diverse accessions
- 1Key Laboratory of Genetic Improvement and Efficient Production of Specialty Crops in Arid Areas of Southern Xinjiang, College of Agronomy, Tarim University, Alar, Xinjiang, 843300, China
- 2State Key Laboratory of Herbage Improvement and Grassland Agro-ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou, 730000, China
- 3State Key Laboratory of Cotton Bio-breeding and Integrated Utilization, Institute of Cotton Research of Chinese Academy of Agricultural Sciences, Anyang, Henan, 455000, China
Abstract
Cotton defoliation is critical for efficient mechanical harvesting, yet its temporal progression across diverse germplasm remains difficult to quantify at high throughput. This study developed a multi-temporal unmanned aerial vehicle (UAV)-based machine-learning framework to characterize post-treatment defoliation dynamics across 419 cotton accessions. Multispectral imagery acquired before and after defoliant application was used to derive spectral and texture features, and an Entropy Weight Method (EWM)-based strategy was used for feature ranking and selection. Multiple regression algorithms were evaluated using accession-grouped cross-validation. Spectral indices provided substantially stronger predictive information than texture features, while relative changes from the pre-treatment baseline further improved model performance. Temporal encoding provided a modest but complementary contribution. Among the evaluated algorithms, Random Forest achieved the best overall performance, with an R² of 0.73 and an RMSE of 10.69%. Accession-level trajectory analysis subsequently identified four post-treatment defoliation patterns, with variation primarily reflected in the magnitude and rate of defoliation progression. These results demonstrate the potential of multi-temporal UAV phenotyping for scalable characterization of cotton defoliation dynamics and provide a practical basis for germplasm evaluation and mechanized harvest management.
Related
- Winter wheat yield prediction using temporal fusion of multispectral imagery and LiDAR point clouds acquired from a ground-based phenotyping platform
- Temporal and species-dependent variation in foliar monoterpene compositions of conifers under spruce budworm defoliation
- Large-scale phenotyping and multi-trait selection identify low-methane Napier grass (Cenchrus purpureus) accessions under contrasting environmental conditions
- Multispectral UAV dataset for multi-temporal mangrove monitoring in the Cirebon Coastal Area, Indonesia (2025-2026).
- Rice multi-variety yield prediction using multi-temporal fusion of thermal infrared and multispectral UAV data based on random Forest feature selection
BibTeX
@article{li2026multitemporal,
title = {{Multi-temporal UAV multispectral phenotyping and machine learning for modeling cotton defoliation dynamics across diverse accessions}},
author = {Mingze Li and Qisheng Feng and Xiaofei Li and Guoping Wang and Mingwei Du and Sumei Wan and Hongqiang Dong and Mengyan Ren and Zuoren Yang and Lu Feng and Guodong Chen},
journal = {Plant phenomics (Washington, D.C.)},
year = {2026},
month = oct,
doi = {10.1016/j.plaphe.2026.100295},
url = {https://europepmc.org/article/PMC/PMC13718646},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multi-temporal UAV multispectral phenotyping and machine learning for modeling cotton defoliation dynamics across diverse accessions
AU - Mingze Li
AU - Qisheng Feng
AU - Xiaofei Li
AU - Guoping Wang
AU - Mingwei Du
AU - Sumei Wan
AU - Hongqiang Dong
AU - Mengyan Ren
AU - Zuoren Yang
AU - Lu Feng
AU - Guodong Chen
PY - 2026
DA - 2026/10/13
JO - Plant phenomics (Washington, D.C.)
DO - 10.1016/j.plaphe.2026.100295
UR - https://europepmc.org/article/PMC/PMC13718646
AB - Cotton defoliation is critical for efficient mechanical harvesting, yet its temporal progression across diverse germplasm remains difficult to quantify at high throughput. This study developed a multi-temporal unmanned aerial vehicle (UAV)-based machine-learning framework to characterize post-treatment defoliation dynamics across 419 cotton accessions. Multispectral imagery acquired before and after defoliant application was used to derive spectral and texture features, and an Entropy Weight Method (EWM)-based strategy was used for feature ranking and selection. Multiple regression algorithms were evaluated using accession-grouped cross-validation. Spectral indices provided substantially stronger predictive information than texture features, while relative changes from the pre-treatment baseline further improved model performance. Temporal encoding provided a modest but complementary contribution. Among the evaluated algorithms, Random Forest achieved the best overall performance, with an R² of 0.73 and an RMSE of 10.69%. Accession-level trajectory analysis subsequently identified four post-treatment defoliation patterns, with variation primarily reflected in the magnitude and rate of defoliation progression. These results demonstrate the potential of multi-temporal UAV phenotyping for scalable characterization of cotton defoliation dynamics and provide a practical basis for germplasm evaluation and mechanized harvest management.
SN - 2643-6515
ER -