The "Sugarcane Leaf Dataset" is a comprehensive resource for machine learning applications in disease detection and classification of sugarcane leaves. The dataset, consisting of 6748 high-resolution images, covers nine disease categories (smut, yellow leaf disease, pokkah boeng, mosale, grassy shoot, brown spot, brown rust, banded chlorosis, and sett rot), a healthy leaves category, and a dried leaves category. It is the first openly accessible collection of sugarcane leaf samples, facilitating collaboration among researchers and practitioners. The dataset's high quality and diverse nature make it valuable for developing and evaluating machine learning algorithms, including deep learning, feature extraction, and pattern recognition, to enhance the accuracy and efficiency of automated disease identification systems. The dataset's open availability encourages research on disease control strategies, improving sugarcane production and agricultural practices. The data was collected through field surveys in sugarcane-growing regions, ensuring a comprehensive representation of leaf diseases under various environmental conditions. The dataset is available through Mendeley Data, and the authors acknowledge the support of Vishwakarma University and Kasetsart University.The "Sugarcane Leaf Dataset" is a comprehensive resource for machine learning applications in disease detection and classification of sugarcane leaves. The dataset, consisting of 6748 high-resolution images, covers nine disease categories (smut, yellow leaf disease, pokkah boeng, mosale, grassy shoot, brown spot, brown rust, banded chlorosis, and sett rot), a healthy leaves category, and a dried leaves category. It is the first openly accessible collection of sugarcane leaf samples, facilitating collaboration among researchers and practitioners. The dataset's high quality and diverse nature make it valuable for developing and evaluating machine learning algorithms, including deep learning, feature extraction, and pattern recognition, to enhance the accuracy and efficiency of automated disease identification systems. The dataset's open availability encourages research on disease control strategies, improving sugarcane production and agricultural practices. The data was collected through field surveys in sugarcane-growing regions, ensuring a comprehensive representation of leaf diseases under various environmental conditions. The dataset is available through Mendeley Data, and the authors acknowledge the support of Vishwakarma University and Kasetsart University.