@Article{phyton.2025.066286,
AUTHOR = {Kaihao Shi, Lin Yuan, Qimeng Yu, Zhongting Shen, Yingtan Yu, Chenwei Nie, Xingjian Zhou, Jingcheng Zhang},
TITLE = {Detection of Rice Bacterial Leaf Blight Using Hyperspectral Technology and Continuous Wavelet Analysis},
JOURNAL = {Phyton-International Journal of Experimental Botany},
VOLUME = {94},
YEAR = {2025},
NUMBER = {7},
PAGES = {2033--2054},
URL = {http://www.techscience.com/phyton/v94n7/63217},
ISSN = {1851-5657},
ABSTRACT = {Plant diseases are a major threat that can severely impact the production of agriculture and forestry. This can lead to the disruption of ecosystem functions and health. With its ability to capture continuous narrow-band spectra, hyperspectral technology has become a crucial tool to monitor crop diseases using remote sensing. However, existing continuous wavelet analysis (CWA) methods suffer from feature redundancy issues, while the continuous wavelet projection algorithm (CWPA), an optimization approach for feature selection, has not been fully validated to monitor plant diseases. This study utilized rice bacterial leaf blight (BLB) as an example by evaluating the performance of four wavelet basis functions—Gaussian2, Mexican hat, Meyer, and Morlet—within the CWA and CWPA frameworks. Additionally, the classification models were constructed using the k-nearest neighbors (KNN), random forest (RF), and Naïve Bayes (NB) algorithms. The results showed the following: (1) Compared to traditional CWA, CWPA significantly reduced the number of required features. Under the CWPA framework, almost all the model combinations achieved maximum classification accuracy with only one feature. In contrast, the CWA framework required three to seven features. (2) The choice of wavelet basis functions markedly affected the performance of the model. Of the four functions tested, the Meyer wavelet demonstrated the best overall performance in both the CWPA and CWA frameworks. (3) Under the CWPA framework, the Meyer-KNN and Meyer-NB combinations achieved the highest overall accuracy of 93.75% using just one feature. In contrast, under the CWA framework, the CWA-RF combination achieved comparable accuracy (93.75%) but required six features. This study verified the technical advantages of CWPA for monitoring crop diseases, identified an optimal wavelet basis function selection scheme, and provided reliable technical support to precisely monitor BLB in rice (<i>Oryza sativa</i>). Moreover, the proposed methodological framework offers a scalable approach for the early diagnosis and assessment of plant stress, which can contribute to improved accuracy and timeliness when plant stress is monitored.},
DOI = {10.32604/phyton.2025.066286}
}