A Machine Learning-Powered Framework for Predictive Soil Analysis and Smart Fertilizer Recommendation

View at publisher Summarise with VIRAT
Authors: Venkatesh Kumar S, V. Muthu Krishnan , Sujitha M, Sai Shanmuga Raja, Saravanan Elumalai
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In contemporary agriculture, optimizing soil health anddelivering precise fertilizer guidance are indispensable to enhancing crop yield, sustainability, and resource efficiency. This paperpresents AGROMIND, an intelligent Machine Learning-Powered Framework for Predictive Soil Analysis and Smart FertilizerRecommendation, designed to transform conventional soil management practices. The framework employs machine learningalgorithms to evaluate key soil parameters including pH, nitrogen (N), phosphorus (P), potassium (K), moisture, and temperature.Based on these parameters, the system carries out two primary functions: it evaluates soil quality to suggest necessary correctivemeasures through targeted fertilizer usage, and it identifies the most appropriate fertilizer type for specific regional soil conditions. By training predictive models on varied soil datasets, the system delivers accurate, data-driven fertilizer guidance that encourages sustainablefarming. The solution is deployed via the Django web framework,providing farmers and agricultural specialists an accessible andintuitive interface for enhanced soil management and cropproduction decision-making. Keywords—soil health analysis; machine learning; fertilizerrecommendation; soil salinity prediction; soil parameter classification; sustainable agriculture; Django web deployment; supervised learning algorithms

Fields of Study & Subjects

Smart Agriculture and AI Agricultural Science and Fertilization Plant Growth and Agriculture Techniques

Publication details

Journal / source
International Scientific Journal of Engineering and Management
Volume
05
Issue
03
Pages
1–9
Publication date
22 March 2026
Language
EN