With global food security under increasing threats from population expansion and climatic uncertainty, innovative techniques are key to revolutionizing agriculture. The current project employs the Random Forest method to make sound predictions of rice crop yields and environmental conditions under which rice can grow based on a historical record of agricultural and the environmental data from 1986 to2017. There are two primary objectives in this study. The first is to forecast rice yield, from cultivated area and production statistics, to assist in planning and resource allocation. The second is to forecast the soil nutrient levels Nitrogen, Phosphorus, Potassium, and pH and analyze environmental factors like humidity, rain, rainfall, and temperature that play a significant role in crop growth and soil health. Overall, the Random Forest model performed well across a range of evaluation metrics, demonstrating a clear ability to capture sophisticated relationships s within the data. In both instances, by setting target yield levels identifying the best soil and climate conditions, this research has the potential to offer relatively straightforward-to-implement data-based advice for maximizing agricultural yield, enabling farmers to cope with the pressures of an evolving environment. The research highlights key trends, including ideal humidity, rainfall, and temperature ranges required to achieve greater yields and preserve nutrient-laden soils. Ultimately, this research merges advanced machine learning with actual agricultural needs, creating a cost-effective and sustainable means to secure food systems and adopt climate-resilient farming practices.

Random Forest rice yield prediction crop yield optimization machine learning in agriculture Precision Agriculture Climate Data Machine Learning