PERM REGION NATURAL RESOURCE POTENTIAL FORECASTING USING MACHINE LEARNING MODELS
DOI:
https://doi.org/10.14529/ctcr210411Keywords:
machine learning, quality metrics, regression analysis, natural resource potential, Perm regionAbstract
In the article we consider a complex indicator of region natural resource potential modeling and forecasting quality improvement using different machine learning models. Problem under consideration importance is determined by the fact that the models traditionally used for these purposes demonstrate either low quality, or high configuration and parameters evaluation difficulty. The aim of the study is determination of machine learning models that provide the optimal values of various modeling quality metrics. Materials and methods. For this study purposes we considered the multiple linear regression, decision tree, random forest, gradient boosting and multilayer perceptron models. We used the determination coefficient R2, the root mean square error of modeling RMSE, the average absolute error of modeling MAE, and the relative error of prediction for 1 and 2 time intervals as quality metrics. This study is based on data of the complex indicator of the Perm Region natural resource potential and the system of its determining factors in the time interval from 2001 to 2018. We evaluate models and calculate quality metrics using Pandas and Scikit-learn Python libraries in Jupiter Notebook environment. Results. According to our research the classical multiple linear regression model demonstrates the worst results for all quality metrics under consideration. The decision tree model demonstrates determination coefficient maximum value and minimum root mean square error and mean absolute error. Minimum relative forecasting error for 2017 is provided by the gradient boosting model, for 2018 – by the multilayer perceptron model. Conclusion. Our study allows us to affirm that nonlinear machine learning models for the task of region natural resource potential modeling and forecasting demonstrate better approximating and predictive properties compared to multiple linear regression and thus can be used to improve the quality of natural resource management.References
Samus, T. Assessing the natural resource use and the resource efficiency potential of the Deser¬tec concept / T. Samus, B. Lang // Solar Energy. – 2013. – Vol. 87. – Р. 176–183.
Березовский, П.В. Экономическая оценка вторичных минеральных ресурсов: моногр. / П.В. Березовский. – СПбГГИ им. Г.В. Плеханова, 2009. – 161 с.
Соколова, Н.В. Природно-ресурсный потенциал территории: содержание понятия, методы оценки / Н.В. Соколова // Вестник Ленинградского университета. – 1988. – № 3. – С. 125–130.
Xie, X. Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land / X. Xie, T. Wu, M. Zhu
et al. // Ecological Indicators. – 2021. – Vol. 120, 106925.
Ракаева, Т.Г. Регрессионно-дифференциальная модель динамики горной промышленности Пермского края / Т.Г. Ракаева, В.Ф. Беккер // Системный анализ в науке и образовании. – 2019. – № 2. – С. 45–51.
Biswas, M.H. Mathematical Modeling Applied to Sustainable Management of Marine Resources / M.H. Biswas, M.R. Hossain, M.K. Mondal // Procedia Engineering. – 2017. – Vol. 194. – Р. 337–344.
Красильников, П.А. Геоинформационное обеспечение экономической оценки природно-ресурсного потенциала территорий Пермского края / П.А. Красильников // Экономика региона. – 2009. – № 1. – С. 143–151.
Kumar, N. Applications of Remote Sensing and GIS in Natural Resource Management / N. Kumar, S.S. Yamaс, A. Velmurugan // Journal of the Andaman Science Association. – 2015. – Vol. 20 (1). – Р. 1–6.
Multi-criteria decision support for geothermal resources exploration based on remote sensing, GIS and geophysical techniques along the Gulf of Suez coastal area, Egypt / S. Abuzied, M. Kaiser, E. Shendi, M. Abdel-Fattah // Geothermics. – 2020. – Vol. 88, 101893.
Akhter, R. Precision agriculture using IoT data analytics and machine learning / R. Akhter, S.A. Sofi // Journal of King Saud University – Computer and Information Sciences. – 2021, 101016.
Modeling groundwater potential using novel GIS-based machine-learning ensemble techniques / A. Arabameri, S.C. Pal, F. Rezaie et al. // Journal of Hydrology: Regional Studies. – 2021. – Vol. 36, 100848.
Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area / M. Mohajane, R. Costache, F. Karimi et al. // Ecological Indicators. – 2021. – Vol. 129, 107869.
Machine learning for large-scale crop yield forecasting / D. Paudel, H. Boogaard, A. de Wit et al. // Agricultural Systems. – 2021. – Vol. 187, 103016.
Classical and machine learning modeling of crude oil production in Nigeria: Identification of an eminent model for application / C.P. Obite, A. Chukwu., D.C. Bartholomew et al. // Energy Reports. – 2021. – Vol. 7. – P. 3497–3505.
Сиротина, Н.А. Применение конечно-разностных моделей для краткосрочного прогнозирования природно-ресурсного потенциала Пермского края / Н.А. Сиротина, А.В. Копотева,
А.В. Затонский // Вестник ЮУрГУ. Серия «Компьютерные технологии, управление, радиоэлектроника». – 2021. – Т. 21, № 2. – С. 154–166. DOI: 10.14529/ctcr210215
Wu, X. Top 10 algorithms in data mining / X. Wu, V. Kumar, Quinlan R. et al. // Knowledge and Information Systems. – 2008. – Vol. 14. – Р. 1–37.
Biau, G. Analysis of a Random Forests Model / G. Biau // Journal of Machine Learning Research. – 2012. – Vol. 13. – P. 1063–1095.
Natekin, A. Gradient Boosting Machines, A Tutorial / A. Natekin, A. Knoll // Frontiers in neurorobotics. – 2013. – Vol. 7. – P. 21.
Multilayer perceptron and neural networks / P. Marius, V. Balas, L. Perescu-Popescu, N. Mas¬torakis // WSEAS Transactions on Circuits and Systems. – 2009. – Vol. 8. – Р. 579–588.
Сиротина, Н.А. Оценка вклада горнодобывающей отрасли в природно-ресурсный потенциал региона / Н.А. Сиротина, А.В. Копотева, А.В. Затонский // Горный информационно-аналитический бюллетень (научно-технический журнал). – 2020. – № 8. – С. 163–178. DOI: 10.25018/0236-1493-2020-8-0-163-178
