AgriForecast: A Machine Learning Solution for Crop Yield and Fertilizer Prediction for Developing Countries

Main Article Content

Anindita A. Khade, Aditya Rangari, Sanika Gidye


In developing countries like India, agriculture is vital for the livelihoods of its massive population, yet it grapples with inefficiencies and outdated equipment. Bridging the gap between traditional farming practices and modern technological solutions is imperative to boost agricultural productivity. Leveraging advanced machine learning algorithms like Logistic Regression, Support Vector Machine, XGBOOST and Random Forest holds tremendous promise in this regard. These algorithms offer precise forecasts and insights, revolutionizing crop forecasting and yield estimation processes. While farmers traditionally relied on experience for projections, machine learning enables data-driven decision-making, facilitating optimized planting strategies and risk mitigation. Moreover, the adoption of machine learning fosters sustainable practices by enhancing resource allocation and minimizing environmental impact. Ultimately, integrating machine learning into agriculture represents a shift towards smarter and more sustainable farming practices in India. This transition is expected to unlock the agricultural sector's potential, ensuring food security and economic prosperity for farming communities.

Article Details