Geographical Information Based Crop Yield Prediction Using Machine Learning

  • R Punithavathi
  • B Kalaavathi

Abstract

Indian agriculture is facing a huge, challenging task of producing 480 Mt by the year 2050 to meet out the food grain requirement of the population. However the problems are plenty like biotic and abiotic stresses experienced by crops, soil degra- dation, erratic rainfall, climate change scenarios, emergence of new pest and disea- ses etc. Yield prediction is one of the most critical issues faced in the agricultural sector, which will help the government to device suitable planning strategies to improve the productivity and to create a good market price for the poor farmers. If application of soft computing on geographical information to improve the life of farmers, it will be useful to our nation. In this study we attempted the modern scien- ce & technology tool of machine learning and developed a model as Supervised Lear- ning Algorithm for Crop Yield Prediction (SLACYP) to predict crop yield rate. The variables considered in this model are area under cultivation (per Hectares), Rain- fall (mm), Consumption of fertilizers (MT) viz., Nitrogen(N), Phosphorous(P), Potassium(K). The model was designed and developed the algorithm using R Progra- mming to predict the popularly cultivated crops in the selected region of Tamil Nadu, India for crops like Paddy, Maize, Turmeric, Groundnut, and Sugarcane. The R2 value for all the crops are greater than 80% indicating the best fit model for the crops. Among the crops, the multiple regression equation of paddy is found to be highly significant with the R2 value of 0.95 and the lowest value was found to be with the sugarcane with the R2 value of 0.81.

Downloads

Download data is not yet available.

Author Biographies

R Punithavathi

Professor and Head, Department of Computer Science and Engineering, Vivekanandha College of Technology for Women, Tiruchengode,Namakkal, India

B Kalaavathi

Professor and Head, Department of Computer Science and Engineering, KSR Institute for Engineering and Technology, Tiruchengode, Namakkal, India

Published
2017-12-31
How to Cite
Punithavathi, R., & Kalaavathi, B. (2017). Geographical Information Based Crop Yield Prediction Using Machine Learning. Revista De La Facultad De Agronomía De La Universidad Del Zulia, 35(1), 128-138. Retrieved from https://produccioncientificaluz.org/index.php/agronomia/article/view/27264
Section
Socioeconomía