Farming Futures: Machine Learning Models for Crop Yield Prediction

India's economy depends heavily on agriculture, and choosing the right crops is essential to reducing losses. Crop yield is influenced by factors such as soil conditions and weather patterns. A rational assessment of many aspects is included in data analysis, which is essential for researching agricultural output. Pre-season crop mapping, which is crucial for early warningson agricultural supply networks and output, is one way that machine learning algorithms support agricultural surveillance and the food industry. gathered and examined datasets that combined meteorological and soil data. Pre-season crop-type maps were analyzed and recommended using machine learning techniques, such as XG Boost, Decision Tree, Linear Regression, Bagging Regressor, and Random Forest, based on historical data. Crop forecast was based on the same parameters that were taken into account during computation. Among the evaluated machine learning algorithms, Random Forest achieved the highest accuracy of 0.986572, closely followed by Bagging Regressor with an accuracy of 0.986569. Machine learning-based pre-season crop mapping reduces trade tensions and dangers by providing early warnings on agricultural supply networks. This approach improves agricultural surveillance, assisting farmers and other stakeholders in the food industry in making well-informed decisions.