Crop predicting system using supervised machine learning approach based on region and season

• Main Authors: Rajendran, Sasikumar, Karthik, K., Rajavarman, R., Aarthirai, P., Faya, S. Esthar, Gayathri, M., Karthika, S.
• Format: Conference Proceeding
• Language: English
• Subjects: Agriculture; Algorithms; Crops; Farmers; Gardening; Geographical locations; Guidance systems; Hand tools; Harvesting; Machine learning; Model accuracy; Planting; Seasons; Soil properties; Soils; Supervised learning
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0173107

Agriculture is one of the leading fields in the world and that is the pillar of an India. In that traditional method with or without non-scientific methods of those farmers can be delegated or decided on that best-suited crop in the land. In the farming, country is having a serious issue nearly with 58 percent. Nowadays, in this world agriculture is being placed in poor condition. Correct crops based on that soil guidelines, planting seasons and environmental position. Despites, farmers are quitting their agriculture and moved towards that city or urban areas. Manufacturing of that crops were doing that variations and impact of temperature through this uncertainty. Nowadays, agriculture is one of the challenges for the farmers. Crops can be produced well or not is based only on the season and soil properties etc. The enhancement of producing the crops depends on an agricultural factors or land. To solve difficulty in crop cultivation, so we introduced that crop guidance system. In this model, we are introducing that prior for planting and assisting with the cultivators for overcoming those issues, so we started our research is purely based on that season, soil and geographical location. By continuing, this framework fluctuates the monetary misfortunes saw by the cultivators and unfavorable harvesting gave that details on an irregular characteristic for those relent. Then the reasonable for which season to harvested the crops. Here we were used machine learning algorithm for that predefined dataset. In this model, we attained accuracy is higher than comparing to the existing system.