Cotton root rot, caused by the soilborne fungus Phymatotrichopsis omnivore, is a severe soilborne disease that has affected cotton production for over a century. Recent research has shown that a commercial fungicide, flutriafol, has potential for the control of this disease. To effectively and economically control this disease, it is necessary to identify infected areas within the field so that variable rate technology can be used to apply fungicide only to the infected areas. The objective of this study was to use airborne imagery to monitor cotton root rot infection in cotton before and after fungicide treatment to the soil. A 105-ha irrigated cotton field with a historically consistent spatial pattern of infection was selected for this study. Airborne multispectral imagery with visible and near-infrared wavebands was taken from the field in 2001 and 2011 with natural root rot infection and again in 2013 with uniform flutriafol treatment at planting. The imagery was rectified and then classified into infected and noninfected zones using two unsupervised classification methods (one based on multispectral imagery and the other based on the normalized difference vegetation index) and three supervised classification techniques (minimum distance, maximum likelihood, and spectral angle mapper). All five methods provided similar classification results and were equally effective and accurate for detection of cotton root rot-infected areas. The classification results showed that the fungicide treatment reduced root rot infection from approximately 17% in both 2001 and 2011 to less than 2% in 2013. Although overall spatial patterns of infection between 2001 and 2011 were similar, there were slight changes in the locations of infected areas. A change detection analysis showed that 9.0% of the field was infected in both years, while 8.0% of the field was infected only in 2001 and 8.5% only in 2011. Thus a total of 25.5% of the field was infected in either 2001 or 2011. Change detection also showed that the infection in 2013 occurred within the infected areas in either 2001 or 2011, indicating a higher rate of fungicide may be needed to more effectively control the fungus with the season. Results from this study demonstrate that airborne multispectral imagery in conjunction with unsupervised and supervised classification techniques can be a useful tool for detecting and mapping cotton root rot infection under treated and nontreated conditions. The results of this study will be useful for assessing the efficacy of fungicide treatments and for optimizing site-specific treatment plans.