AI-Enabled Intelligent System for Automatic Detection and Classification of Plant Diseases Towards Precision Agriculture
Open Access
- 8 December 2025
- journal article
- research article
- Published by MDPI AG in Informatics
- Vol. 12 (4) , 138
Abstract
Technology-driven agriculture, or precision agriculture (PA), is indispensable in the contemporary world due to its advantages and the availability of technological innovations. Particularly, early disease detection in agricultural crops helps the farming community ensure crop health, reduce expenditure, and increase crop yield. Governments have mainly used current systems for agricultural statistics and strategic decision-making, but there is still a critical need for farmers to have access to cost-effective, user-friendly solutions that can be used by them regardless of their educational level. In this study, we used four apple leaf diseases (leaf spot, mosaic, rust and brown spot) from the PlantVillage dataset to develop an Automated Agricultural Crop Disease Identification System (AACDIS), a deep learning framework for identifying and categorizing crop diseases. This framework makes use of deep convolutional neural networks (CNNs) and includes three CNN models created specifically for this application. AACDIS achieves significant performance improvements by combining cascade inception and drawing inspiration from the well-known AlexNet design, making it a potent tool for managing agricultural diseases. AACDIS also has Region of Interest (ROI) awareness, a crucial component that improves the efficiency and precision of illness identification. This feature guarantees that the system can quickly and accurately identify illness-related areas inside images, enabling faster and more accurate disease diagnosis. Experimental findings show a test accuracy of 99.491%, which is better than many state-of-the-art deep learning models. This empirical study reveals the potential benefits of the proposed system for early identification of diseases. This research triggers further investigation to realize full-fledged precision agriculture and smart agriculture.Keywords
This publication has 58 references indexed in Scilit:
- Smart Agriculture Framework for Automated Detection of Leaf Blast Disease in Paddy Crop Using Colour Slicing and GLCM Features based Random Forest ApproachWireless Personal Communications, 2023
- Smart greenhouses as the path towards precision agriculture in the food-energy and water nexus: case study of QatarEnvironment Systems and Decisions, 2022
- A novel deep learning method for detection and classification of plant diseasesComplex & Intelligent Systems, 2021
- Automated Plant Leaf Disease Detection and Classification Using Fuzzy Based Function NetworkWireless Personal Communications, 2021
- Crop disease monitoring and recognizing system by soft computing and image processing modelsMultimedia Tools and Applications, 2020
- An effective automatic system deployed in agricultural Internet of Things using Multi-Context Fusion Network towards crop disease recognition in the wildApplied Soft Computing, 2020
- Internet of Things in arable farming: Implementation, applications, challenges and potentialBiosystems Engineering, 2020
- IoT based Smart Farming : Feature subset selection for optimized high-dimensional data using improved GA based approach for ELMComputers and Electronics in Agriculture, 2019
- Towards a Smart Farming Platform: From IoT-Based Crop Sensing to Data Analytics2018
- Intelligent Communication and Computational Technologies2018