|THOMASSON, ALEX - Texas A&M University
|WANG, TIANYI - Texas A&M University
|WANG, XIWEI - Texas A&M University
|COLLETT, RYAN - Texas A&M University
|NICHOLS, ROBERT - Cotton, Inc
Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 9/9/2018
Publication Date: 10/15/2018
Citation: Thomasson, A., Wang, T., Wang, X., Collett, R., Yang, C., Nichols, R. 2018. Disease detection and mitigation in a cotton crop with UAV remote sensing. Proceedings of SPIE. 1066404L.
Interpretive Summary: Cotton root rot can devastate a cotton crop by infecting the roots and destroying large numbers of cotton plants. Topguard Terra fungicide has proven effective at protecting cotton plants from the disease. However, the fungicide is expensive, so it is desirable to treat only the portions of the field susceptible to the disease. In this study, an image mosaic created from high resolution images captured by an unmanned aircraft system was used to create a prescription map for site-specific fungicide application in a cotton field. Results showed that the classification map from the mosaic was able to identify infected plants at the single-plant level. Thus it is conceivable that precision application of the fungicide during planting could be done at the level of a single seed.
Technical Abstract: In many fields in the southwestern U.S. and Mexico, a soil-borne fungus (Phymatotrichopsis omnivorum) causes a disease called cotton root rot (CRR) that can devastate a cotton crop by infecting the roots and destroying large numbers of cotton plants. In the last few years a fungicide treatment including the chemical, flutriafol, has proven effective at protecting cotton plants from CRR infection. However, the fungicide is expensive, and growers desire to minimize input costs and environmental risks, so it is desirable to treat only the portions of the field susceptible to CRR infection. Remote sensing with high-resolution satellites and manned aircraft has enabled delineation of the full extent of the disease late in the growing season. Recently, classified images have been used effectively to create prescription maps for variable-rate application of fungicide when planting a cotton crop in subsequent years. In 2015 a UAV was used to create a high-resolution image mosaic of a CRR-infected field at Thrall, Texas. The mosaic was classified into healthy and CRR-infected small zones, and a prescription map was created from the mosaic for variable-rate fungicide application during planting in 2017. The method proved as effective as uniform application across the field would have been. Furthermore, image-analysis techniques were developed that enable classification of image mosaics at approximately the single-plant level. Thus in the future it is conceivable that precision application of flutriafol during planting to prevent cotton root rot could be done at the level of a single seed.