Supervised Machine Learning Algorithms Used In The Detection Of Rice Blast Disease

Abstract

Agriculture serves as a vital component of the global economy, particularly in developing nations like India. It stands as the primary livelihood source for a majority of the rural population in India and makes a significant contribution to the country’s Gross Domestic Product (GDP).As per the World Bank, agriculture constitutes approximately 17% of India’s GDP and engages over 50% of the nation’s workforce. However, the agriculture sector faces setbacks, notably from insect infestations that can considerably impact crop production. The absence of a systematic scientific approach to manage these infestations often results in substantial crop losses for farmers, complicating the task of safeguarding crops from insect attacks. The application of Artificial Intelligence (AI) holds immense promise in effectively addressing the challenges of insect management and enhancing crop production. Machine Learning (ML) techniques, in par- ticular, can empower farmers in safeguarding their crops from insect-related threats. Rice blast disease, caused by Pyricularia oryzae, a fungus, is one of the most significant and widespread diseases affecting rice plants. This disease can infect rice plants at various growth stages and affect different aerial parts, including leaves, neck, and nodes. This paper aims to present a comprehensive overview of the applicability of supervised machine learning algorithms in the detection of rice blast disease.