An Efficient Crop Yield Prediction Using Machine Learning

Abstract

In normal, agriculture plays a vital role in the Indian economy and agriculture is the spine of India. In India most of the occupation is agriculture. Farmers always try to cultivate the same type of crop using regular methodologies (not technical methods), Farmers don’t have awareness about the technical methods to avoid losses in cultivation. They are mostly using chemicals to solve that problem to the crop and taking suggestions from the public. There are more technical methods that are implemented but not used properly to get a high crop yield. But now a day crop yield gets decreased due to environmental effects (temperature, rain) which affect crop production and lead to loss. So, there is a necessity to know the crop yield before cultivation. This project – Will allow us to predict crops based on climatic conditions and soil conditions, which would help us to know the crop yield earlier of harvesting. It would be more helpful for farmers and also in business to take solid decisions before investing the capital. Machine learning is one such advanced technique deployed to predict crop yield in agriculture. Here, the machine learning algorithm is mostly used to predict crop yield to get more accurate predictions in that Random Forest. By analyzing the issues that affect crop yield is that climatic factors such as average temperature, average humidity, average rainfall, and route map for a selected crop for particular features with date specification. This methodology to design and development of crop prediction and crop yield prediction using different machine learning techniques are used such as K-Near Neighbor, Decision Tree, Random Forest Classifier helps to increase yield and subsequent profit of agricultural production. Some of the features like algorithm verification and check, crop prediction using some parameters, crop analysis, and guide for yield. The project aims to provide an easy way to predict the yield by using various environment parameters accurately and efficiently.