Machine Learning Models using Paprika Leaf Growth Forecast Based on Environmental and Energy Data
AUTHORS
Saravanakumar Venkatesan,Department of Information and Communication Engineering, Sunchon National University, South Korea
Jonghyun Lim,Department of Information and Communication Engineering, Sunchon National University, South Korea
Changsun Shin,Department of Information and Communication Engineering, Sunchon National University, South Korea
Yongyun Cho* ,Department of Information and Communication Engineering, Sunchon National University, South Korea
ABSTRACT
Paprika (Capsicum annuum L) is an extremely popular and widespread plant species in South Korea. The purpose of this paper is to develop the prediction method for Paprika growth and compare the leaf count of two areas of paprika (R1 and R2 mean Row planting) through investigation of the Greenhouse with the different environmental factors influencing its growth. The objectives of this paper are the following: (1) to use Machine Learning (ML) approach for crop growth prediction in greenhouse agriculture; (2) to research on the correlativity among different weather factors like input temperature, output temperature, wind speed, dew point, CO2, and humidity are connected to Paprika growth at the field level; and (3) to test growth data using the predictive machine-learning models Support Vector Machine (SVM), generic Random Forest (RF), Gradient Boosting Machines (GBM) and eXtreme Gradient Boosting (XGB). Compared to the principal component regression the machine learning models show the best skills in predicting Paprika growths. The Support Vector Machine method is used to provide the best performance in predicting Paprika growth. While measurements of one production period can predict crop development with sensible requirements, we need more attempts to allow this approach in several fields in the region.
KEYWORDS
Paprika leaf, Environmental, Correlation, Linear regression and machine learning
REFERENCES
[1] M. H. Aminifard, et al., “Growth and yield characteristics of paprika pepper (Capsicum annum L.) in response to plant density,” Asian Journal of Plant Sciences, vol.9, no.5, pp.276, (2010)
[2] H. Kirnak, et al., “Paprika pepper yield and quality as affected by different irrigation levels,” Tarim Bilimleri Dergisi – Journal of Agricultural Sciences, vol.22, pp.77-88, (2016)
[3] S. Venkatesan, S. Sivamani, M. B. Lee, J. W. Park, C. Shin, and Y. Cho, “A comparative study of forecasting strawberry production based on random forest and support vector machine,” Information Technology Convergence Engineering Journal in Korea, vol.9, pp45-52, (2019)
[4] M. L. Maskey, T. B. Pathak, and S. K. Dara, “Weather-based strawberry yield forecasts at field scale using statistical and machine learning models,” Atmosphere, vol.10, pp.378, (2019)
[5] F. B. Peña and I. Z. de Polanía, ‘Growth of three-color hybrids of sweet paprika under greenhouse conditions,” Agronomía Colombiana, vol.33, no.2, pp.139-146, (2015)
[6] S. Venkatesan, “A prediction of nutrition water for strawberry production using linear regression,” International Journal of Advanced Smart Convergence, vol.9, no.1, pp.132-140, (2020)
[7] R. Muhammad Fikri and M. Hwang, “Electric vehicle waiting time prediction with openCV and support Vector regression,” Asia-pacific Journal of Convergent Research Interchange, vol.6, no.10, pp.137-146, (2020)
[8] A. Hamrani, A. Akbarzadeh, and C. A. Madramootoo, “Machine learning for predicting greenhouse gas emissions from agricultural soils,” Science of The Total Environment, vol.741, pp.140338, (2020)
[9] P. B. Lohiya and G. R. Bamnote, “A machine learning model for the growth of agriculture industry,” IOSR Journal of Engineering, vol.10, pp.2278-8719, (2020)
[10] Z. Ceylan, “Assessment of agricultural energy consumption of Turkey by MLR and Bayesian optimized SVR and GPR models,” Journal of Forecasting, Sep., vol.39, no.6, pp944-56, (2020)