ARCHIVES

Abstract: India is an agriculture dependent country and the economic status of the country is totally and partially dependent on it. Agricultural yield is affected by organic, economic and seasonal causes. Estimating agricultural production is a very challenging task for this country with regard to the state of the population. In recent days, people growing these products and such products are very unstable in production due to sudden weather effects on the environment and lack of underground water resources. The main goal is to collect data that can be stored and analyzed to predict crop yield. Machine learning techniques are implemented for crop yield prediction. Machine learning (ML) is an essential perspective to obtain real and operational solutions to crop yield problems. From a given set of predictors, ML can predict the goal/outcome using supervised learning. To get the desired outputs, you need to generate a suitable function using a set of variables that will map the input variable to the target output. Crop yield prediction involves predicting crop yield from past historical data that includes factors such as temperature, humidity, ph, rainfall and crop name. It gives us an idea of the best predicted crop to be grown under field weather conditions. These predictions can be made using a machine learning algorithm called Random Forest. It achieves crop yield prediction with the best accuracy value. A random forest algorithm is used to obtain the best crop yield model considering the least number of models. It is very useful to predict crop yield in agriculture sector.