A plant-by-plant-level cotton root rot identification method based on UAV remote sensing

Authors: WANG, TIANYI - Texas A&M University; THOMASSON, ALEX - Texas A&M University; ISAKEIT, THOMAS - Texas A&M University; Yang, Chenghai

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/10/2020
Publication Date: 11/12/2020
Citation: Wang, T., Thomasson, A., Isakeit, T., Yang, C. 2020. A plant-by-plant-level cotton root rot identification method based on UAV remote sensing. Remote Sensing. 12:2453. https://doi.org/10.3390/rs12152453.
DOI: https://doi.org/10.3390/rs12152453

Interpretive Summary: Cotton root rot is a destructive cotton disease that mainly affects the crop in Texas. Flutriafol fungicide applied at or soon after planting has been proven effective. Aerial imagery has been used for mapping cotton root rot infestations, but high-resolution imagery from unmanned aerial vehicles (UAVs) has made plant-by-plant root rot classification possible. In this study, a classification algorithm was developed to delineate root rot-infested areas at approximately the single-plant level. Multispectral image data collected with a UAV were used to test the algorithm. Results showed that the single-plant level classification achieved better overall accuracy than traditional classification methods with accuracy as high as 96%. The results from this study indicate that UAV-based imagery can not only detect cotton root rot, but also has the potential for providing detailed information for fungicide application to individual plants.

Technical Abstract: Cotton root rot (CRR), caused by the fungus Phymatotrichopsis omnivora, is a destructive cotton disease that mainly affects the crop in Texas. Flutriafol fungicide applied at or soon after planting has been proven effective at protecting cotton plants from being infected by CRR. Previous research has indicated that CRR will reoccur in the same regions of a field as in past years. CRR-infected plants can be detected with aerial remote sensing (RS). As unmanned aerial vehicles (UAVs) have been introduced into agricultural RS, the spatial resolution of farm images has increased significantly, making plant-by-plant (PBP) CRR classification possible. An unsupervised classification algorithm, PBP, based on the Superpixel concept, was developed to delineate CRR-infested areas at roughly the single-plant level. Five-band multispectral data were collected with a UAV to test these methods. The results indicated that the single-plant level classification achieved overall accuracy as high as 95.94%. Compared to regional classifications, PBP classification performed better in overall accuracy, kappa coefficient, errors of commission, and errors of omission. The single-plant fungicide application was also effective in preventing CRR.