Methodological Issues of Using the Randomized Machine Learning for Forecasting the Dynamics of Thermokarst Arctic Lakes
DOI:
https://doi.org/10.14529/ctcr190401Keywords:
machine learning, entropy-randomized approach, randomized model, forecasting, spatio-temporal dynamics, permafrost, thermokarst lakes, satellite images, meteorological data reanalysis, climate change, global warmingAbstract
The analysis of the state of the problems of modeling the spatio-temporal dynamics of the lake fields under the conditions of modern climate changes is carried out. It is shown that the analytical methods used in studying the dynamics of thermokarst processes in individual lakes are not suitable for studying the spatiotemporal changes in the fields of thermokarst lakes. The geo-simulation modeling method proposed for studying the dynamics of fields of thermokarst lakes does not provide sufficient forecasting accuracy. The problems of applying a new approach to the prediction of the spatio-temporal dynamics of fields under the conditions of modern climatic changes based on methods and algorithms of entropy-randomized machine learning are considered. The experimental results of remote studies of the dynamics of fields of thermokarst lakes in the Arctic permafrost zone of Western Siberia were obtained using satellite images for the period of several decades starting in 1973. Climatic data for the same period were obtained by reanalysis based on the well-known ERA-40, ERA-Interim systems and APHRODITE JMA. An array of experimental data has been compiled on changes in lake areas, average annual temperature and annual precipitation in the permafrost zone of Western Siberia over the period of research. Regression analysis of geocryological and climatic data showed that the reduction in the area of lakes can be explained mainly by an increase in surface temperature and a change in precipitation. The structure of a randomized forecast model for the dynamics of fields of thermokarst lakes is determined taking into account parameters reflecting changes in lake areas, average annual temperature and precipitation level. The features of using experimental data in the framework of an entropy-randomized approach to forecasting the spatio-temporal dynamics of fields of thermokarst lakes under the conditions of modern climate changes are considered.References
Опыт и результаты дистанционного исследования озер криолитозоны Западной Сибири по космическим снимкам различного разрешения за 50-летний период / Ю.М. Полищук, А.Н. Богданов, Н.А. Брыксина и др. // Современные проблемы дистанционного зондирования Земли из космоса. – 2017. – Т. 14. – № 6. – С. 42–55. DOI: 10.21046/2070-7401-2017-14-6-42-55
Minor contribution of small thaw ponds to the pools of carbon and methane in the inland waters of the permafrost - affected part of the Western Siberian lowland / Y.M. Polishchuk, A.N. Bogdanov, I.N. Muratov et al. // Environmental Research Letters. – 2018. – Vol. 13. – P. 1–16. DOI: 10.1088/1748-9326/aab046
Hydrological Changes: Historical Analysis, Contemporary Status, and Future Projections / A.I. Shiklomanov, R.B. Lammers, D.P. Lettermaier et al. // Regional Environmental Changes in Siberia and Their Global Consequences / Eds. P.Ya. Groisman and G. Gutman. – Dordrecht; Heidelberg; NewYork; London: Springer, 2013. – P. 111–154. DOI: 10.1007/978-94-007-4569-8_4
Effect of permafrost thawing on the organic carbon and metal speciation in thermokarst lakes of Western Siberia / O.S. Pokrovsky, L.S. Shirokova, S.N. Kirpotin et al. // Biogeosciences. – 2011. – Vol. 8. – P. 565–583. DOI: 10.5194/bg-8-565-2011
Кравцова, В.И. Изменение размеров термокарстовых озер в различных районах России за последние 30 лет / В.И. Кравцова, А.Г. Быстрова // Криосфера Земли. – 2009. – Т. 13, № 2. – С. 16–26.
Kirpotin, S. Abrupt changes of thermokarst lakes in Western Siberia: impacts of climatic warming on permafrost melting / S. Kirpotin, Y. Polishchuk, N. Bryksina // International Journal of Environmental Studies. – 2009. – Vol. 66. – No. 4. – P. 423–431. 10.1080/00207230902758287
Riordan, B. Shrinking ponds in subarctic Alaska based on 1950–2002 remotely sensed images / B. Riordan, D. Verbyla, A.D. McGuire // J. Geophys. Res. – 2006. – Vol. 111. – G04002. DOI: 10.1029/2005JG000150
Zuidhoff, F.S. Changes in palsa distribution in relation to climate change in Laivadalen, Northern Sweden, especially 1960-1997 / F.S. Zuidhoff, E. Kolstrup // Permafrost and Periglacial Processes. – 2000. – Vol. 11. – P. 55–69. DOI: 10.1002/(SICI)1099-1530(200001/03)11:1<55::AIDPPP338>3.0.CO;2-T
Полищук, В.Ю. Геоимитационное моделирование полей термокарстовых озер в зонах мерзлоты / В.Ю. Полищук, Ю.М. Полищук. – Ханты-Мансийск: УИП ЮГУ, 2013. – 129 с.
Викторов, А.С. Основные проблемы математической морфологии ландшафтов / А.С. Викторов. – М.: Наука, 2006. – 252 с.
Polishchuk, Y. Forecast of thermokarst lakes dynamics in permafrost based on geo-simulation modeling and remote sensing data / Y. Polishchuk, V. Polishchuk // Proc. of Conf. “Mathematical and Information Technologies MIT-2016” (Vrnjacka Banja, Serbia – Budva, Montenegro, Aug. 28 – Sept. 5, 2016) / Eds. Yu. Shokin, H. Miloshevich and D. Esipov. Published on CEUR-Workshop Proceedings. – 2017. – Vol. 1839. – P. 393–405. – http://ceur-ws.org/Vol-1839.
Polishchuk, V.Y. Modeling of thermokarst lake dynamics in West-Siberian permafrost. Chapter 6 / V.Y. Polishchuk, Y.M. Polishchuk // Permafrost: Distribution, Composition and Impacts on Infrastructure and Ecosystems / Ed. by O. Pokrovsky. – New York: Nova Science Publishers, 2014. – P. 205–234.
Попков, Ю.С. Рандомизированное машинное обучение при ограниченных объемах данных / Ю.С. Попков, А.Ю. Попков, Ю.А. Дубнов. – М.: ЛЕНАНД. – 320 с.
Полищук, Ю.М. Методические вопросы построения обобщенных гистограмм распределения площадей озер в зоне мерзлоты на основе космических снимков среднего и высокого разрешения / Ю.М. Полищук, А.Н. Богданов, И.Н. Муратов // Современные проблемы дистанционного зондирования Земли из космоса. – 2016. – Т. 13, № 6. – С. 224–232. DOI: 10.21046/2070-7401-2016-13-6-224-232
Size distribution, surface coverage, water, carbon, and metal storage of thermokarst lakes in the permafrost zone of the Western Siberia lowland / Y.M. Polishchuk, A.N. Bogdanov, V.Y. Polishchuk et al. // Water. – 2017. – Vol. 9, iss. 3. – 18 p. DOI: 10.3390/w9030228
A Canopus-V imagery-based study of the size-distribution of small lakes in the discontinuous permafrost zone of the Western Siberia / Y.M. Polishchuk, A.N. Bogdanov, I.N. Muratov, V.Y. Polishchuk // Kriosfera Zemli. – 2017. – Vol. 21. – No. 2. – P. 80–87.
Lehner, B. Development and validation of a global database of lakes, reservoirs and wetlands / B. Lehner, P. Doll // J. Hydrol. – 2004. – Vol. 296. – P. 1–22. DOI: 10.1016/j.jhydrol.2004.03.028
Downing, J.A. The global abundance and size distribution of lakes, ponds, and impoundments / J.A. Downing, Y.T. Prairie // Limnol. Oceanogr. – 2006. – Vol. 51. – P. 2388–2397. DOI: 10.4319/lo.2006.51.5.2388
A global inventory of lakes based on high resolution satellite imagery / C. Verpoorter, T. Kutser, D.A. Seekel, L.J. Tranvik // Geophys. Res. Lett. – 2014. – Vol. 41. – P. 1–7. DOI: 10.1002/2014GL060641
