Abstract :

Accurate Crop Selection Is Essential For Improving Agricultural Productivity And Ensuring Sustainable Resource Utilization. Conventional Crop Planning Methods Often Rely On Experiential Judgment Rather Than Systematic Analysis Of Soil And Environmental Conditions, Which Can Lead To Inefficient Input Usage And Reduced Yields. Our Approach Treats Crop Selection As A Classification Challenge Where Soil Nutrient Profiles And Climatic Variables Serve As The Primary Predictors. We Scrutinized The Performance Of Several Widely Used Models, From Basic Decision Trees To High-performance Gradient-boosted Machines, To See How Well They Could Map These Inputs To Specific Crop Suitability. To Guard Against Overfitting And Ensure The Model Generalizes Well To New Regions, We Applied A Combination Of Standard Hold-out Validation And Iterative Cross-validation Techniques. Experimental Results Demonstrate That XGBoost Achieves Superior Predictive Performance And Generalization Capability, Attaining An Accuracy Of Approximately 99% On The Test Dataset. To Enhance Interpretability, SHAP (SHapley Additive ExPlanations) Was Applied To Analyze Feature Contributions. The Explainability Analysis Indicates That Climatic Factors, Particularly Humidity And Rainfall, Exert The Highest Influence On Crop Classification Decisions. The Proposed Framework Provides A Reliable And Interpretable Decision-support Tool For Data-driven Crop Planning. By Combining High Predictive Accuracy With Model Transparency, The System Contributes Toward Intelligent Agricultural Management And Sustainable Farming Practices.

Published:

10-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

332-340

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite