Analysis of agricultural crop yield prediction using statistical techniques of machine learning. (2021)

• Record Type: Journal Article
• Authors: Pant, Janmejay; Pant, R.P.; Kumar Singh, Manoj; Pratap Singh, Devesh; Pant, Himanshu
• Is Part Of: Materials today. Volume 46:Part 20(2021)
• Page Start: 10922
• Page End: 10926
• Publication Date: 2021
• Subjects: Machine learning -- Yield prediction -- Agriculture -- Accuracy -- Feature selection -- Correlation; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2021.01.948
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: Agriculture plays a crucial role in Indian economy. Crop yield is main component of food security as human population is increasing in a drastic way. One of the most important problems of agriculture is crop yield prediction. Agriculture yield depends on the various factors such as weather situation (rain, humidity, temperature etc.), information about pesticides. Apart from these factors exact information about the crop yield history is an essential concept for making predictions and controlling agriculture risk. Earlier yield prediction was performed by considering the farmer's experience on a particular field and crop. In this study machine learning is used to predict four popular yields which are mostly cultivated all over India. Once the crop yield is site specifically predicted, the inputs such as fertilizers could be applied variably according to the expected crop and soil needs. In our study we use Machine Learning approaches to develop a trained model to identify the patterns among data and it is used for crop prediction. In this study the prediction of four most cultivated yields in India is considered by applying machine learning. These crops include: Maize, Potatoes, Rice (Paddy) and wheat.