Fertilizers Recommendation System for Disease Prediction Using Machine Learning

Abstract

India is the world's largest agrarian economy, with arable land accounting for 54% of the total land area. Agriculture accounts for more than half of the world's gross domestic output (GDP). It has been established that increasing agricultural productivity has a significant impact on poverty reduction. A variety of factors can influence the number of harvest able crops growing in a given location. These three major groups of components (climate, soil fertility, topography, water quality, and so on) are made up of biological, technical, and environmental aspects. soil infertility caused by over-fertilization, as well as an Access concern and a lack of understanding about contemporary farming practices is two of the many factors that contribute to low agricultural productivity. The main purpose of this research project is to develop a machine learning-based recommendation system to increase agricultural productivity.In this work, sophisticated models were devised and developed to estimate crop yield, recommend fertilizer, and identify plant sickness. The XG Boost model estimates an optimal crop based on regional soil nutrients and rainfall. Rough Forest [RF] A model was used to propose fertilizers and provide ideas for improving soil fertility based on the nutrients present in the soil. The plant sickness is recognized using the NB Classifier and the Support Vector Machine [SVM], which also provides therapy. When compared to existing approaches, the proposed model provides a high degree of accuracy. Furthermore, the farmer is advised in this article to increase crop yield by entering input where the model provides 99% accurate crop recommendations.