Copyright © 2026 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{177145,
        author = {Punam Anna Navale and Yashwant Sudhakar Ingle},
        title = {AI-Based Pest and Disease Detection in Crops},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {64-69},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177145},
        abstract = {The increasing global demand for food necessitates enhanced crop productivity, which is critically hindered by plant diseases and pest infestations. Conventional detection methods are predominantly manual, time-consuming, and ineffective for large-scale agricultural monitoring. This paper presents an integrated, AI-based approach for automated detection of crop diseases and pests using deep learning techniques. For disease identification, a custom Convolutional Neural Network (CNN) is trained on the disease detection dataset to classify potato leaf conditions into three categories: early blight, late blight, and healthy. The model incorporates data augmentation and image preprocessing to enhance generalization, achieving a test accuracy of 96.3%.
For pest detection, a transfer learning framework utilizing the MobileNet architecture is employed. The model is fine-tuned on a dataset comprising nine pest classes and is optimized using advanced image augmentation techniques. The resulting classifier demonstrates a test accuracy of 96.22%, indicating high reliability and scalability in field conditions. The proposed dual-model framework offers a non-invasive, high-throughput solution for real-time monitoring of crop health. This work contributes to the development of intelligent precision agriculture systems by supporting early detection, timely intervention, and informed decision-making.},
        keywords = {Convolutional Neural Network (CNN), MobileNet, crop disease detection, pest classification, deep learning, image processing, smart farming, precision agriculture.},
        month = {April},
        }