“…Traditional machine learning models, such as support vector machines (SVM), decision trees, K-means, and random forests, require manual feature design specific to different disease types, making them susceptible to environmental factors and lacking generalization capabilities ( Bhavsar et al., 2022 ; Zou et al., 2020 ; Steven, 2021 ; Yu et al., 2021 ; Bao et al., 2022 ; Prabu et al., 2022 ). Conversely, deep learning, particularly in object detection, exhibits potential in crop disease identification ( Krisnandi et al., 2019 ; Ayan et al., 2020 ; Jiang et al., 2020 ; Tetila et al., 2020 ; Xiong et al., 2020 ; Hu et al., 2021b ).…”