Agricultural Production Optimization through Predictive Modelling

This study presents an agricultural production optimization model to support farmers in selecting appropriate crops for varied climatic and soil conditions.Built on machine-learning algorithms like logistic regression, SVM, k-NN, random forest, and gradient boosting, the model achieves a peak accuracy of 99.54% with the random forest classifier.A significant contribution of this research is a fertilizer recommendation system, which compares soil nutrient levels with the crop's average nutrient needs, guiding fertilizer application to bridge nutrient gaps.This approach aids in efficient fertilization and improved crop growth.Integrating predictive analytics into daily farm operations enhances crop yield, promotes sustainable practices, and boosts agricultural productivity.