Detecting cotton Verticillium wilt within and across multiple fields with Sentinel-2 imagery and machine learning
- Publisher:
- WILEY
- Publication Type:
- Journal Article
- Citation:
- AGRONOMY JOURNAL, 2026, 118, (4)
- Issue Date:
- 2026-07-10
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Abstract Verticillium wilt, caused by Verticillium dahliae , poses a major threat to cotton production worldwide. This study presents a framework for predicting Verticillium wilt incidence across multiple cotton fields by combining Sentinel‐2 imagery, preseason inoculum, and weather variables with machine learning models. Three machine‐learning models: random forest, support vector machine, and extreme gradient boosting were evaluated using data from seven commercial cotton fields in northern New South Wales, Australia. Model performance was assessed under two validation schemes: fivefold cross‐validation to assess within‐field interpolation performance and leave‐one‐field‐out validation to evaluate extrapolation across fields. Random forest achieved the highest accuracy (mean overall accuracy = 0.63, mean weighted F1 = 0.64 for interpolation; mean overall accuracy = 0.58, mean weighted F1 = 0.56 for extrapolation) when all data sources were combined. Model interpretability was assessed using Shapley additive explanations, which identified preseason inoculum, near‐infrared and red‐edge bands are the most influential predictors. Results highlight the advantage of integrating multisource data for disease prediction and the importance of rigorous validation to avoid overestimation of model performance—something that is commonly overlooked in published disease studies. The approach offers a scalable, nondestructive framework for operational monitoring of Verticillium wilt in cotton.
Plain Language Summary Verticillium wilt is a soil‐borne disease that damages cotton plants by blocking the flow of water and nutrients, causing leaf yellowing, wilting, and major yield losses. Reliable large‐scale prediction of this disease is important for supporting farm management decisions. This study tested whether combining satellite imagery, soil pathogen levels measured before planting, and weather data could improve the prediction of Verticillium wilt in cotton fields. Three machine‐learning models were applied to data from seven commercial cotton fields, and their performance was evaluated both within known fields and across new fields. Results showed that prediction accuracy was highest when all three data sources were used together, with a mean weighted F1 score of 0.64. The study also showed that commonly reported validation approaches can lead to inflated accuracy estimates. Overall, the proposed framework provides a scalable, nondestructive approach for operational monitoring of Verticillium wilt in cotton.
Please use this identifier to cite or link to this item: