Predictive Modeling of Nonlinear Non-Stationary Processes in Crop Production Using Tools of SAS Enterprise Miner

Authors

DOI:

https://doi.org/10.20535/1810-0546.2017.1.87423

Keywords:

Non-stationary processes, Regressive model, Agricultural crop yield, Prediction, Decision support systems, SAS Enterprise Miner

Abstract

Blackground. The issue of providing the increase of production of main agricultural crops inUkraine under conditions of environmental management requires the use of modern scientific approaches. The complexity of solving this problem lies in the lack of practical experience of applying modern information-analytical systems, where different methods for analysis and modeling of nonlinear non-stationary processes in crop production would be implemented simultaneously. The proposed methodology has the advantage of using the tools of SAS Enterprise Miner – software where a wide range of techniques are implemented, that should be used for predictive modeling of main agricultural crops according to the performed research.

Objective. The goal of the study is in application of the integrated methods of analysis and predictive modeling of non-stationary processes for agricultural crop yield prediction using SAS Enterprise Miner tools.

Methods. To solve the problems stated the following approaches were used: systems analysis, regression analysis, gradient boosting, probabilistic modeling and decision trees. The methodology for developing of crop yield prediction under influence of various groups of factors was offered, and the possibility of their use in decision support systems in agriculture was substantiated.

Results. Based on the analysis of the works of domestic and foreign scientists it was proposed to improve methodology of development of yield prediction of main agricultural crops using integrated analysis methods, which were implemented in the system of SAS Enterprise Miner. The analysis of the obtained results was performed.

Conclusions. Winter wheat and corn yield prediction was performed for the Forest-Steppe Zone using the developed methodic. Different methods of construction of models for prediction of the non-stationary processes were applied; the choice of the worthiest one was reasonably proved. Advanced information technologies, including SAS Enterprise Miner, were used for automatization the process of selecting the optimal model for investigated crop yield prediction.

Author Biographies

Petro Bidyuk, Institute for Applied System Analysis, Igor Sikorsky Kyiv Polytechnic Institute

Doctor of engineering, professor at the Department of Mathematical Methods of System Analysis

Oleksandr Terentiev, Institute for Applied System Analysis, Igor Sikorsky Kyiv Polytechnic Institute

PhD, research fellow at the Scientific Research Department 

Tetyana Prosyankina-Zharova, Pavlo Tychina Uman State Pedagogical University

PhD, lecturer at the Department of Informatics and Information-Communication Technology

 

Vladyslav Efendiev, Pavlo Tychina Uman State Pedagogical University

PhD, lecturer at the Department of Informatics and Information-Communication Technology

References

O.V. Sobkevich et al., Resource Potential of Agrarian Sphere: Problems and Tasks of Effective Use. Kyiv, Ukraine: NISS, 2013 (in Ukrainian).

National Paradigm of Sustainable Development of Ukraine, B. Paton, Ed. Kyiv, Ukraine: Institute of Environmental Economics and Sustainable Development, 2016 (in Ukrainian).

The Official Website “Ukraine-NATO. Program NATO “Science for Peace and Security” [Online]. Available: http://ukraine-nato.mfa.gov.ua/ua/about-nato/science-for-peace

The Official Website of the Group on Earth Observations [Online]. Available: https://www.earthobservations.org/geoss.php

Program-Technic Complex Control Agro [Online]. Available: http://control.ua/index.php/reseniya/selskoe-khozyajstvo/control-agro

N.N. Kussul et al., “Regression models for assessing crop yields according to the MODIS”, Sovremennye Problemy Distancionnogo Zondirovanija Zemli iz Kosmosa, vol. 9, no. 1, pp. 95–107, 2012 (in Ukrainian).

Outer Space in the Service of Agrarian [Online]. Available: http://www.agroprofi.com.ua/statti/1115-kosmichnij-prostir-na-sluzhbi-agrarija.html

The Official Website of SAS [Online]. Available: http://www.sas.com

The Official Website of State Statistics Service of Ukraine [Online]. Available: http://www.ukrstat.gov.ua/

S.О. Dovgiy et аl., Environmental Monitoring Using Satellite Images of Satellite NOAA. Kyiv, Ukraine: Ponomarenko EV, 2013 (in Ukrainian).

S.O. Dovgiy et al., Decision Support Systems Based on Statistical and Probabilistic Methods. Kyiv, Ukraine: Logos, 2014 (in Ukrainian).

P.I. Bidyuk el al., Applied Statistics. Vinnytsya, Ukraine: PP TD Edelweiss & Co, 2013 (in Ukrainian).

О. Тrofymchuk et al. “Probabilistic and statistical uncertainties in the Decision Support Systems”, Visnyk NU “L'vivs'ka Politekhnika”, no. 826, pp. 237–248, 2015 (in Ukrainian).

E. Bradley et al., “Least angle regression”, The Annals of Statistics, vol. 32, no. 2, pp. 407–499, 2004. Available: http://projecteuclid.org/euclid.aos/1083178935. doi:10.1214/009053604000000067

H. Abdi, “Partial least square regression (PLS regression)”, Encyclopedia for Research Methods for the Social Sciences, pp. 792–795, 2003. Available: https://www.utdallas.edu/~herve/Abdi-PLS-pretty.pdf. doi: 10.1002/wics.051

J.H. Friedman “Greedy function approximation: a gradient boosting machine”, The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001. Available: http://www.jstor.org/stable/2699986

P.I. Bidyuk and N.V. Kuznetzova. “The basic stages of building and examples of using Bayesian Networks”, Systemni Doslidzhennya ta Informatsiyni Tekhnolohiyi, no. 4, pp. 26–39, 2007 (in Ukrainian).

L. Breiman et al., Classification and Regression Trees.Florida: CRC Press, 2000.

Website of BayesFusion, LLC [Online]. Available: http://www.bayesfusion.com/genie-modeler

Published

2017-03-01

Issue

Section

Art