An Approach for Prediction of Crop Yield Using Machine Learning and Big Data Techniques

Abstract

Agriculture is the primary source of livelihood which forms the backbone of our country. Current challenges of water shortages, uncontrolled cost due to demand-supply, and weather uncertainty necessitate farmers to be equipped with smart farming. In particular, low yield of crops due to uncertain climatic changes, poor irrigation facilities, reduction in soil fertility and traditional farming techniques need to be addressed. Machine learning is one such technique employed to predict crop yield in agriculture. Various machine learning techniques such as prediction, classification, regression and clustering are utilized to forecast crop yield. Artificial neural networks, support vector machines, linear and logistic regression, decision trees, Naïve Bayes are some of the algorithms used to implement prediction. However, the selection of the appropriate algorithm from the pool of available algorithms imposes challenge to the researchers with respect to the chosen crop. In this paper, an investigation has been performed on how various machine learning algorithms are useful in prediction of crop yield. An approach has been proposed for prediction of crop yield using machine learning techniques in big data computing paradigm.

Implementation of Machine Learning for Predicting Maize Crop Yields Using Multiple Linear Regression and Backward Elimination

“…Moreover, machine learning models outperform traditional methods for predicting maize crop yields (Palanivel & Surianarayanan, 2019).Some scholars including (Crane-Droesch, 2018; Gandhi et al, 2016;Johnson et al, 2016;Palanivel & Surianarayanan, 2019;van Klompenburg et al, 2020;Veenadhari et al, 2014) predicted crop yields using climatic parameters. However, the future work will focus on customized and automated decision support systems on the prediction of crop yield to aid decision making to complement farmers' experience is still nascent.…”

“…Also, the crops used by the authors were their local subsistence crops whereas the maize crops used in this study are the main subsistence crop grown in Eswatini. The use of machine learning has also been applied in the United States of America to create statistical models for forecasting crop yield productions (Cai et al, 2017;Forkuor et al, 2017;Palanivel & Surianarayanan, 2019); however, this was in the context of a developed country with the resources available to keep the soil well managed, as well as the regular use of remote sensing. In India, a system created by Liakos et al, (2018) applied multi-linear regression and machine learning to predict the yields of several different crops ranging from barley, beans, carrots, as well as other local crops through the implementation of an Android and web application and sought to find the most profitable crop for the farmer.…”

Remote sensing-based estimation of rice yields using various models: A critical review

“…Machine learning, a class of empirical modeling, provided new approaches to reliably estimate rice yields along with other types of crops (Palanivel and Surianarayanan 2019). Neural networks used with radar backscatter from RADARSAT-1 and yield measurements as inputs achieved an accuracy of 94% (Chen and Mcnairn 2006).…”

Comparative Study for Classification Algorithms Performance in Crop Yields Prediction Systems

“…The average of absolute deviations between the target and predicted values are calculated as the Mean Absolute Error (MAE) [56,57]. The computation of MAE is shown in (2).…”