AI-Driven Intrusion Detection System for Smart Agriculture in Remote and Disaster-Prone Areas

Abstract

Smart agriculture integrates Internet of Things devices, sensors, and wireless communication technologies to enhance crop productivity and support sustainable farming practices. In India, climate change has significantly affected major crops, resulting in highly unpredictable yields over recent decades. Accurate prediction of crop yield before harvest is therefore essential for effective planning and efficient resource management. This study proposes an Artificial Intelligence driven Intrusion Detection System designed to secure smart agriculture networks while enabling intelligent crop yield prediction. The proposed framework combines agricultural data collected through Internet of Things technologies with machine learning techniques. A Random Forest algorithm is employed to predict crop yield with high accuracy. An interactive web based platform is developed to provide a user friendly interface for farmers and other stakeholders. Standard benchmark datasets such as the Network Security Laboratory Knowledge Discovery and Data Mining dataset are used to train and validate the Intrusion Detection System module. The system continuously monitors Internet of Things network traffic to detect potential cyber threats, thereby ensuring data integrity and reliable system operation. The integrated framework enhances network security and decision making capabilities, supports efficient resource allocation and farm planning, improves overall agricultural productivity, and strengthens cybersecurity in smart farming environments. The proposed approach promotes sustainable and data driven agriculture.