Identification of Cotton Fields Using Sentinel-2 Satellite Imagery for Boll Weevil Eradication

Early identification of cotton fields is important for the boll weevil eradication program in Texas. Remote sensing has long been used for crop identification, but limited work has been reported on identification of cotton fields when cotton plants are small. Our previous work demonstrated that high-resolution airborne imagery was effective for this purpose, but large numbers of images taken along multiple flight lines are needed to cover large geographic regions. As 10-m Sentinel-2 satellite imagery is available for free and has large area coverage, we evaluated this type of imagery for identifying cotton fields before cotton plants start to bloom in this study. Two cloud-free Sentinel-2 scenes acquired on June 11 and July 11, 2019 were selected to identify cotton fields over an 8 km by 12 km cropping area. The images were classified into different crops and cover types using multiple supervised classification techniques. Accuracy assessment results showed that Sentinel-2 imagery in conjunction with maximum likelihood and support vector machine classifiers was feasible and effective for distinguishing cotton from other crops. The methodologies presented in this study will be useful for boll weevil eradication program managers to quickly and efficiently identify cotton fields at relatively early growth stages.