Location: Aerial Application Technology Research
Title: Identification of cotton root rot by multifeature selection from Sentinel-2 images using random forestAuthor
LI, XINGRONG - Chinese Academy Of Sciences | |
Yang, Chenghai | |
HUANG, WENJIANG - Chinese Academy Of Sciences | |
TANG, JIA - Chinese Academy Of Sciences | |
TIAN, YANQIN - Chinese Academy Of Sciences | |
ZHANG, QING - Chinese Academy Of Sciences |
Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal Publication Acceptance Date: 12/21/2020 Publication Date: 12/23/2020 Citation: Li, X., Yang, C., Huang, W., Tang, J., Tian, Y., Zhang, Q. 2020. Identification of cotton root rot by multifeature selection from Sentinel-2 images using random forest. Remote Sensing. 12:3504. https://doi.org/10.3390/rs12213504. DOI: https://doi.org/10.3390/rs12213504 Interpretive Summary: Accurate identification of cotton root rot-infested areas within fields is critical for cotton growers to effectively control the disease. In this study, no-cost Sentinel-2 satellite images were used to explore the feasibility of creating classification maps and prescription maps for site-specific fungicide application. Eight cotton fields with different levels of root rot were selected, and advanced classification and modeling techniques were used for image classification and prescription map creation. Accuracy assessment showed that the prescription maps derived from Sentinel-2 imagery were accurate and practical compared with those based on airborne imagery. These results confirmed that it is feasible to identify cotton root rot and create prescription maps using no-cost Sentinel-2 imagery and appropriate imaging processing techniques. Technical Abstract: Cotton root rot is a destructive cotton disease and significantly affects cotton quality and yield, and accurate identification of its distribution within fields is critical for cotton growers to control the disease effectively. In this study, Sentinel-2 images were used to explore the feasibility of creating classification maps and prescription maps for site-specific fungicide application. Eight cotton fields with different levels of root rot were selected and random forest (RF) was used to identify the optimal spectral indices and texture features of the Sentinel-2 images. Five optimal spectral indices (plant senescence reflectance index (PSRI), normalized difference vegetation index (NDVI), normalized difference water index (NDWI1), moisture stressed index (MSI), and renormalized difference vegetation index (RDVI)) and seven optimal texture features (Contrast 1, Dissimilarity 1, Entory 2, Mean 1, Variance 1, Homogeneity 1, and Second moment 2) were identified. Three binary logistic regression (BLR) models, including a spectral model, a texture model, and a spectral-texture model, were constructed for cotton root rot classification and prescription map creation. The results were compared with classification maps and prescription maps based on airborne imagery. Accuracy assessment showed that the accuracies of the classification maps for the spectral, texture and spectral-texture models were 92.95%, 84.81%, and 91.98%, respectively, and the accuracies of the prescription maps for the three respective models were 90.83%, 87.14%, and 91.40%. These results confirmed that it was feasible to identify cotton root rot and create prescription maps using different features of Sentinel-2 imagery. The addition of texture features had little effect on the overall accuracy, but it could improve the ability to identify root rot areas. The producer’s accuracy (PA) for infested cotton in the classification maps for the texture model and the spectral-texture model was 2.82% and 1.07% higher, respectively, than that of the spectral model, and the PA for treatment zones in the prescription maps for the two respective models was 9.6% and 8.22% higher than that of the spectral model. Results based on the eight cotton fields showed that the spectral model was appropriate for the cotton fields with relatively severe infestation and the spectral-texture model was more appropriate for the cotton fields with low or moderate infestation. |