Predictive Analysis of Plant Macronutrient Consumption Pattern Using Machine Learning

This study incorporates many machine learning (ML) methods to predict and analyze the nutrient intake as it explores the macronutrient consumption patterns of different plants in few different states of India. Important macronutrient factors for a wide variety of plant species were recorded using data gathered from a variety of agricultural online sources. Creating precise prediction models to improve nutrition management strategies was the main goal. K-Nearest Neighbors (KNN), Naive Bayes, and Support Vector Classification (SVC) were the three machine learning techniques used. Based on how well these algorithms predicted intake of macronutrients, their performance was assessed. The outcomes showed that, at 95.87%, Naive Bayes had the best accuracy, followed by KNN at 89.65% and SVC at 83.85%. Our results demonstrate that Naive Bayes is the best appropriate machine learning approach for this dataset analysis and show its promise for efficient nutrition prediction. Finally, by promoting sustainable farming practices, this research helps optimise nutrient management systems