Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186742,
        author = {Tanmay Yambal and Shreyas Vichale and Ayush Jadhav and Syed Ameen Ali and Neha Nandurkar},
        title = {Survey On Ai Powered Early Detection of Plant Disease},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {1769-1773},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186742},
        abstract = {Global food security and sustainable farming practices are continuously jeopardized by recurrent outbreaks of pests and crop diseases. Conventional methods for identifying these issues, relying primarily on expert visual inspections, are fundamentally slow, resource-intensive, and too expensive for widespread, large-scale deployment. Deep Learning (DL) has recently materialized as a revolutionary solution, facilitating the automated, image-based diagnosis of crop health with notable accuracy. This review will showcase key advancements in applying DL to plant disease and pest detection, specifically synthesizing literature published since 2021. It documents the progression from earlier machine learning strategies that necessitated manual feature engineering to sophisticated modern deep architectures, such as Convolutional Neural Networks (CNNs). The subsequent discussion investigates crucial elements for optimizing performance, including the strategic use of transfer learning, the leveraging of pre-trained models, and the essential role of diverse and augmented datasets. Furthermore, the paper executes a comparative assessment of major DL frameworks, judging their precision, operational efficiency, and trustworthiness in practical agricultural settings. The final section offers conclusions on ongoing challenges and suggests future research pathways to sharpen the utility of deep learning within precision agriculture.},
        keywords = {Advanced deep learning techniques, traditional machine learning methods, CNN-based image recognition, agricultural image processing, crop disease detection, neural network modeling, and transfer learning strategies.},
        month = {November},
        }