Climate-Smart Crop Recommendation System Using Random Forest Algorithm

Abstract

Abstract

Climate change has significantly impacted agricultural production since it has altered soil conditions, temperature ranges, and rainfall patterns. In order to help farmers choose the best crops for shifting climate circumstances, this project suggests a Climate-Smart Crop Recommendation System that makes use of artificial intelligence and data analytics. Temperature, precipitation, humidity, soil nutrients (N, P, and K), pH, and other environmental factors are among the historical and current data that the system analyzes. The Random Forest machine learning technique is used to analyze patterns and forecast suitable crops. Model performance and prediction reliability are enhanced by feature engineering and methodical data pretreatment. With an overall accuracy of 90% on the test dataset, the Random Forest model showed excellent generalization and predictive power. Through encouraging effective resource use and lowering the chance of crop failure, the suggested strategy promotes sustainable agriculture. The technology improves food security, resilience, and agricultural output in climate-sensitive areas by offering smart, data-driven crop recommendations.