Exploring Machine Learning Techniques for Disease Detection in Plant Life: A Comprehensive Survey of Literature
Abstract: This paper conducts a comprehensive survey of the literature focusing on the application of machine learning (ML) techniques for disease detection in plant life. Plant diseases pose significant threats to agricultural productivity and food security, prompting the exploration of ML-driven solutions. The review encompasses the impact of various pathogens on crops, limitations of traditional detection methods, and the role of ML in augmenting disease identification. Examining ML methodologies reveals a spectrum of techniques, including supervised, unsupervised, and deep learning approaches. Decision trees, support vector machines, and convolutional neural networks (CNNs) stand out for their efficiency in classifying diseases based on plant images. However, challenges persist, such as data scarcity, labeling inconsistencies, and model interpretability across diverse environmental conditions. This survey concludes by advocating for future research directions. Recommendations include dataset augmentation, advancements in interpretability methods, and exploration of transfer learning strategies. The integration of ML with IoT, remote sensing, and hyperspectral imaging presents opportunities for real-time disease monitoring, paving the way for enhanced disease management and agricultural sustainability.
Keywords: Machine Learning, Decision trees, Support Vector Machines, Convolutional Neural Networks, Disease Detection in Plant Life
How to Cite?: Mala Singh, Vinay Saxena, "Exploring Machine Learning Techniques for Disease Detection in Plant Life: A Comprehensive Survey of Literature", Volume 15 Issue 7, July 2026, International Journal of Science and Research (IJSR), Pages: 2422-2427, https://www.ijsr.net/getabstract.php?paperid=SR26725002927, DOI: https://dx.doi.org/10.21275/SR26725002927