AI-Powered Intrusion Detection Framework For Smart Agriculture In Remote And Disaster-Prone Areas

Abstract

Smart agriculture utilizes IoT devices, sensors, and wireless communication to enhance crop yield and promote sustainable farming methods. In India, the impacts of climate change have notably influenced key crops, leading to inconsistent yields over the past few decades. Precise crop yield forecasting prior to harvest is crucial for effective planning and resource allocation. This study introduces an AI powered Intrusion Detection System aimed at securing smart agriculture networks while facilitating intelligent crop yield forecasting. The system integrates IoT based agricultural data with machine learning approaches. A Random Forest algorithm is utilized to predict crop yields with a high level of accuracy. An interactive web platform has been created to offer an easy to use experience for farmers and stakeholders. Standard datasets such as NSL KDD are employed to train and assess the IDS module. The IDS continuously monitors the IoT network. The proposed system improves overall agricultural productivity while strengthening cybersecurity in smart farming environments. The approach promotes sustainable agriculture based on data driven decision making.