Abstract :

Effective Fertilizer Management Is A Critical Component In Modern Agriculture, Directly Influencing Crop Productivity, Soil Health, And Environmental Sustainability. Traditional Fertilizer Recommendation Practices Are Often Based On Generalized Guidelines Or Farmer Experience, Which May Lead To Inefficient Nutrient Utilization, Increased Cultivation Costs, And Long-term Ecological Imbalance. In Many Cases, Improper Fertilizer Application Results In Nutrient Depletion Or Excessive Chemical Usage, Negatively Impacting Both Yield And Soil Fertility. To Address These Limitations, This Study Proposes A Machine Learning–based Smart Fertilizer Recommendation System That Utilizes Soil Nutrient Parameters And Crop-specific Data To Generate Accurate And Data-driven Fertilizer Suggestions. The System Incorporates Key Agricultural Attributes Such As Nitrogen (N), Phosphorus (P), Potassium (K), Soil PH, Rainfall, Temperature, And Crop Type To Train Predictive Models. A Structured Preprocessing Pipeline Is Employed, Including Data Cleaning, Normalization, And Encoding, To Enhance Model Efficiency And Reliability. Multiple Supervised Learning Algorithms Were Evaluated, Including Decision Tree, Naive Bayes, K-Nearest Neighbors (KNN), And Random Forest. Among These, The Random Forest Classifier Demonstrated Superior Predictive Performance Due To Its Ability To Handle Complex, Non-linear Relationships And Reduce Overfitting Through Ensemble Learning. Experimental Results Indicate That The Model Achieves High Accuracy And Robustness Across Multiple Evaluation Metrics. The Proposed System Offers A Cost-effective, Scalable, And Efficient Solution By Eliminating The Dependency On Hardware Sensors And Expensive Soil Testing Infrastructure. By Enabling Precise And Timely Fertilizer Recommendations, The Framework Supports Sustainable Agricultural Practices, Improves Crop Yield, And Empowers Farmers With Intelligent Decision-making Tools.

Published:

14-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

574-581

Section:

Articles

License:

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

How to Cite