Detection of Rubber Tree Powdery Mildew from Leaf Level Hyperspectral Data Using Continuous Wavelet Transform and Machine Learning

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 1; p. 105
• Main Authors: Cheng, Xiangzhe, Feng, Yuyun, Guo, Anting, Huang, Wenjiang, Cai, Zhiying, Dong, Yingying, Guo, Jing, Qian, Binxiang, Hao, Zhuoqing, Chen, Guiliang, Liu, Yixian
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2024
• Subjects: Accuracy; Airborne microorganisms; Algorithms; Analysis; Artificial neural networks; Back propagation networks; Care and treatment; Coefficients; Continuous wavelet transform; Crop diseases; Diagnosis; Diseases and pests; energy; Feasibility studies; Genetic aspects; Growth; Hevea brasiliensis; hyperspectral reflectance; Identification; Learning algorithms; Leaves; Machine learning; Mathematical models; Methods; Natural rubber; Neural networks; Pathogens; Performance evaluation; Phenology; Powdery mildew; Powdery mildew diseases; principal component analysis; Principal components analysis; random forest; reflectance; Remote sensing; Rubber; rubber tree powdery mildew; Rubber trees; Spectroradiometers; Support vector machines; Unmanned aerial vehicles; Vegetation; wavelet; Wavelet transforms; Wheat; Brazil; China
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16010105

Powdery mildew is one of the most significant rubber tree diseases, with a substantial impact on the yield of natural rubber. This study aims to establish a detection approach that coupled continuous wavelet transform (CWT) and machine learning for the accurate assessment of powdery mildew severity in rubber trees. In this study, hyperspectral reflectance data (350–2500 nm) of healthy and powdery mildew-infected leaves were measured with a spectroradiometer in a laboratory. Subsequently, three types of wavelet features (WFs) were extracted using CWT. They were as follows: WFs dimensionally reduced by the principal component analysis (PCA) of significant wavelet energy coefficients (PCA-WFs); WFs extracted from the top 1% of the determination coefficient between wavelet energy coefficients and the powdery mildew disease class (1%R2-WFs); and all WFs at a single decomposition scale (SS-WFs). To assess the detection capability of the WFs, the three types of WFs were input into the random forest (RF), support vector machine (SVM), and back propagation neural network (BPNN), respectively. As a control, 13 optimal traditional spectral features (SFs) were extracted and combined with the same classification methods. The results revealed that the WF-based models all performed well and outperformed those based on SFs. The models constructed based on PCA-WFs had a higher accuracy and more stable performance than other models. The model combined PCA-WFs with RF exhibited the optimal performance among all models, with an overall accuracy (OA) of 92.0% and a kappa coefficient of 0.90. This study demonstrates the feasibility of combining CWT with machine learning in rubber tree powdery mildew detection.