Study of MCDM Technology for Soil Fertility Analysis

Study of MCDM Technology for Soil Fertility Analysis

Prof. Vedika Avhad
Department of Information Technology VPPCOE&VA, University of Mumbai vedikaavhad@pvppcoe.ac.in

Nimeesh Tambat
Department of Information Technology VPPCOE&VA, University of Mumbai Vu4f2021112@pvppcoe.ac.in

Suraj Tambe
Department of Information Technology VPPCOE&VA, University of Mumbai  Vu4f2021036@pvppcoe.ac.in

Adesh Gaonkar
Department of Information Technology VPPCOE&VA, University of Mumbai Vu4f2021110@pvppcoe.ac.in

Sahil Gurav
Department of Information Technology VPPCOE&VA, University of Mumbai VU3T4S2021019@pvppcoe.ac.in

Abstract — Soil fertility is a critical factor in agricultural productivity and sustainable land management. Traditional methods of assessing soil health often rely on a limited set of parameters, which may not comprehensively represent the complexity of soil ecosystems. To address this limitation, our project proposes the use of Multicriteria Decision-Making (MCDM) techniques to enhance soil fertility analysis. The project incorporates multiple factors that influence soil fertility, including nutrient content, pH, organic matter, moisture, and soil structure. By employing MCDM techniques, we aim to develop a robust framework that integrates these diverse parameters to generate a comprehensive soil fertility index. This index will serve as a valuable tool for farmers, agronomists, and land management professionals, providing them with a more holistic understanding of soil health. Our approach involves a combination of data collection, parameter weighting, and decision-making algorithms. By engaging stakeholders in the agricultural sector, we ensure that the criteria and weightings reflect real-world priorities and conditions. Through a case study, we demonstrate the effectiveness of our MCDM-based method in assessing soil fertility and guiding agricultural practices. The results indicate that our MCDM approach offers a more flexible and nuanced analysis compared to traditional methods. It allows users to adjust weightings according to specific goals or regional considerations, facilitating tailored recommendations for soil improvement. The project concludes with a discussion on the broader implications for sustainable agriculture and potential areas for further research. Our project underscores the importance of adopting a multidimensional perspective in soil fertility analysis, contributing to improved agricultural productivity and sustainable land management. The MCDM technique, with its capacity to integrate complex data sets and accommodate diverse stakeholder inputs, has the potential to become a standard tool in soil health assessment.

KEY WORDS – Soil Fertility, Artificial Intelligence And Machine Learning Algorithms, Image Identification, Numpy, Pandas.