Smart Crop Selection: A Machine Learning-Based Decision Support System for Farmers

The paper proposes a machine learning-based decision support system for smart crop selection, leveraging predictive analytics to assist farmers in making data-driven decisions. The study evaluates multiple machine learning algorithms, including Random Forest (RF), XGBoost, Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, and Decision Tree, to determine their effectiveness in crop recommendation. The models are trained on a dataset incorporating soil nutrients (N, P, K), pH levels, rainfall, temperature, and humidity, enabling accurate classification of suitable crops for given agricultural conditions. The experimental results indicate that ensemble learning models such as Random Forest and XGBoost achieve the highest accuracy, outperforming traditional classification models. The findings highlight the potential of AI-driven crop recommendation systems in enhancing productivity, optimizing resource utilization, and reducing farming risks associated with unpredictable climate conditions. By integrating machine learning into precision agriculture, farmers can receive real-time, tailored crop recommendations, leading to improved decision-making and sustainability. This study contributes to the ongoing efforts in data-driven agriculture, emphasizing the importance of advanced computing techniques in addressing modern agricultural challenges.