Title: Evaluating unsupervised and supervised image classification methods for mapping cotton root rot Authors
Submitted to: Precision Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: August 4, 2014
Publication Date: March 9, 2015
Citation: Yang, C., Odvody, G.N., Fernandez, C.J., Landivar, J.A., Minzenmayer, R.R., Nichols, R.L. 2015. Evaluating unsupervised and supervised image classification methods for mapping cotton root rot. Precision Agriculture. 16:201-215. Interpretive Summary: To effectively and economically control cotton root rot, it is necessary to identify infected areas within fields so that site-specific technology can be used to apply fungicide only to the infected areas. Eight different image classification methods for distinguishing root rot-infected areas within cotton fields were evaluated from airborne imagery. Analysis results showed that all these methods could effectively and accurately identify root rot infection; three methods that can be relatively easily implemented without the need for complex image processing capability have been recommended for practical applications. Cotton producers and their consultants will be able use these results to develop site-specific plans that reduce treatment costs and minimize environmental impacts.
Technical Abstract: Cotton root rot, caused by the soilborne fungus Phymatotrichopsis omnivora, is one of the most destructive plant diseases occurring throughout the southwestern United States. This disease has plagued the cotton industry for over a century, but effective practices for its control are still lacking. Recent research has shown that a commercial fungicide, flutriafol, has potential for the control of cotton root rot. To effectively and economically control this disease, it is necessary to identify infected areas within fields so that site-specific technology can be used to apply fungicide only to the infected areas. The objectives of this study were to evaluate unsupervised classification applied to multispectral imagery, unsupervised classification applied to the normalized difference vegetation index (NDVI), and six supervised classification techniques, including minimum distance, Mahalanobis distance, maximum likelihood, and spectral angle mapper (SAM), neural net, and support vector machine (SVM), for mapping cotton root rot from airborne multispectral imagery. Two cotton fields with a history of root rot infection in Texas were selected for this study. Airborne imagery with blue, green, red and near-infrared bands was taken from the fields shortly before harvest when infected areas were fully expressed in 2011. The four-band images were classified into infected and noninfected zones using the eight classification methods. Classification agreement index values for infected area estimation between any two methods ranged from 0.90 to 1.00 for both fields, indicating a high degree of agreement among the eight methods. Accuracy assessment showed that all eight methods accurately identified root rot-infected areas with overall accuracy values from 94.0 to 96.5% for Field 1 and 93.0 to 95.0% for Field 2. All eight methods appear to be equally effective and accurate for detection of cotton root rot for site-specific management of this disease, though some methods such as the NDVI-based classification, minimum distance and SAM can be easily implemented without the need for complex image processing capability.