Home / Current Issue / Paper 1707760
Soil Quality Analyzer and Crop Recommendation System Using Machine Learning Algorithms for Optimizing Agricultural Productivity and Sustainability
Subject area: Science,Engineering and Technology · Area of research: Machine Learning , Deep Learning
Abstract
Agriculture is crucial to India's economy, employing about 48% of the population, yet traditional farming methods and soil depletion pose challenges to crop yield. This project aims to assist farmers by analyzing soil and pH data using machine learning to recommend suitable crops and fertilizers, addressing the lack of precision agriculture. By leveraging categorization strategies, the system enhances crop and fertilizer recommendations, aiding novice farmers. Additionally, it introduces a computer-aided disease recognition model to combat crop losses due to unidentified plant diseases, replacing time-consuming manual inspections with accurate, automated detection. The integration of modern technology in farming not only increases productivity but also optimizes resource utilization, minimizes wastage, and supports sustainable agricultural practices. This approach empowers farmers with data-driven insights, ensuring better decision-making and improved profitability in the long run.
Keywords
ML-Machine Learning, NEHA- National E-Health Authority, PCA-Principal Compound Analysis.
References
[1] Joyce G. Latimer, Extension Specialist, Greenhouse Crops; Virginia Tech, "The Basics of Fertilizer Calculations for Greenhouse Crops", Virginia Polytechnic Institute and State University, 2015.
[2] Chuan-Sheng Zhou, Software College, Shenyang Normal University, Shenyang, Liaoning, and Li-Hua Niu, College of Basic Medicine, Medical University, He Fei, China, "Research on Component-Based Online Shopping System Design", International Conference on Computational Aspects of Social Networks, 2010.
[3] M.L. Vitosh, Extension Specialist, Crop and Soil Sciences, "N-PK Fertilizers", Michigan State University Extension, Reprint July 1996.
[4] Agricultural Department, "Soil Test Information | Recommended Fertilizers – Soil Health Card", February 2015.
[5] E.W. Wilde, R.L. Brigmon, C.J. Berry, D.J. Altman, J. Rossabi, B.B. Looney, and S.P. Harris, "D-Area Drip Irrigation Phytoremediation Project: SRTC Final Report", WSRCTR Journal, January 2013.
[6] S. Praveena Katharine, R. Santhi, S. Maragatham, R. Natesan, V. Ravikumar, and Pradip Dey, Department of Soil Science and Agricultural Chemistry, Tamil Nadu Agricultural University, Coimbatore, India; Agricultural Engineering College and Research Institute, Kumulur, Tamil Nadu, India; Indian Institute of Soil Science, Bhopal, Madhya Pradesh, India, "Soil Test Based Fertilizer Prescriptions Through Inductive Cum Targeted Yield Model for Transgenic Cotton on Inceptisol", Volume 6, Issue 5 (Nov. - Dec. 2013).
[7] Lloyd Murdock, Extension Soils Specialist, "Evaluating Fertilizer Recommendations", IOSR Journal of Agriculture and Veterinary Science (IOSR-JAVS), December 2011.
[8] Nilkamal More, Assistant Professor, Department of Information Technology, K.J. Somaiya College of Engineering, Mumbai-07, "Recommendation of Books Using Improved Apriori Algorithm", International Journal for Innovative Research in Science.
How to cite this paper
@article{1707760,
author = {Kavipreetha R, Kavinashri V, Nithisha N, Kalaiarasan T},
title = {Soil Quality Analyzer and Crop Recommendation System Using Machine Learning Algorithms for Optimizing Agricultural Productivity and Sustainability},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {10},
pages = {142-148},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1707760.pdf},
abstract = {Agriculture is crucial to India's economy, employing about 48% of the population, yet traditional farming methods and soil depletion pose challenges to crop yield. This project aims to assist farmers by analyzing soil and pH data using machine learning to recommend suitable crops and fertilizers, addressing the lack of precision agriculture. By leveraging categorization strategies, the system enhances crop and fertilizer recommendations, aiding novice farmers. Additionally, it introduces a computer-aided disease recognition model to combat crop losses due to unidentified plant diseases, replacing time-consuming manual inspections with accurate, automated detection. The integration of modern technology in farming not only increases productivity but also optimizes resource utilization, minimizes wastage, and supports sustainable agricultural practices. This approach empowers farmers with data-driven insights, ensuring better decision-making and improved profitability in the long run.},
keywords = {ML-Machine Learning, NEHA- National E-Health Authority, PCA-Principal Compound Analysis.},
month = {April},
}