.png)
.png)
.png)
Email this article 
Use of machine learning techniques for modeling of snow depth
https://doi.org/10.15356/2076-6734-2017-1-34-44
Abstract
Snow exerts significant regulating effect on the land hydrological cycle since it controls intensity of heat and water exchange between the soil-vegetative cover and the atmosphere. Estimating of a spring flood runoff or a rain-flood on mountainous rivers requires understanding of the snow cover dynamics on a watershed. In our work, solving a problem of the snow cover depth modeling is based on both available databases of hydro-meteorological observations and easily accessible scientific software that allows complete reproduction of investigation results and further development of this theme by scientific community. In this research we used the daily observational data on the snow cover and surface meteorological parameters, obtained at three stations situated in different geographical regions: Col de Porte (France), Sodankyla (Finland), and Snoquamie Pass (USA).
Statistical modeling of the snow cover depth is based on a complex of freely distributed the present-day machine learning models: Decision Trees, Adaptive Boosting, Gradient Boosting. It is demonstrated that use of combination of modern machine learning methods with available meteorological data provides the good accuracy of the snow cover modeling. The best results of snow cover depth modeling for every investigated site were obtained by the ensemble method of gradient boosting above decision trees – this model reproduces well both, the periods of snow cover accumulation and its melting. The purposeful character of learning process for models of the gradient boosting type, their ensemble character, and use of combined redundancy of a test sample in learning procedure makes this type of models a good and sustainable research tool. The results obtained can be used for estimating the snow cover characteristics for river basins where hydro-meteorological information is absent or insufficient.
About the Author
G. V. AyzelRussian Federation
Moscow
References
1. Brun E., Durand Y., Martin E., Braun L. Snow modelling as an efficient tool to simulate snow cover evolution at different spatial scales. IAHS Publications-Series of Proceedings and Reports-Intern Assoc Hydrological Sciences. 1994, 223: 163–176.
2. Gusev E.M., Nasonova O.N., Dzhogan L.Y., Ayzel G.V. Simulating the formation of river runoff and snow cover in the northern West Siberia. Water Resources. 2015, 42 (4): 460–467. doi: 10.1134/S0097807815040065.
3. Gelfan A.N., Moreido V.M. Dynamic-stochastic modeling of snow cover formation on the European territory of Russia. Led i Sneg. Ice and Snow. 2014, 54 (2): 44–52. doi: 10.15356/2076-6734-2014-2-44-52 [In Russian].
4. Singh P., Spitzbart G., Hübl H., Weinmeister H.W. Hydrological response of snowpack under rain-on-snow events: a field study. Journ. of Hydrology. 1997, 202 (1): 1–20. doi: 10.1016/S0022-1694(97)00004-8.
5. SNiP 2.01.07-85. Nagruzki i vozdeystviya. Load and Force. Moscow, 1996: 82 p. [In Russian].
6. Borzenkova A.V., Shmakin A.B. Changes in the snow cover thickness and of daily snowfall intensity affecting the highways cleaning expenses in russian cities. Led i Sneg. Ice and Snow. 2012, 52 (2): 59–70. doi: 10.15356/2076-6734-2012-2-59-70 [In Russian].
7. Armstrong R.L., Brun E. Snow and Climate. Physical Processes, Surface Energy Exchange and Modeling. Cambridge: Cambridge Univ. Press, 2008: 222 p.
8. Sokratov V.S., Shmakin A.B. Numerical modeling of snow cover on Hooker Island (Franz Josef Land archipelago). Led i Sneg. Ice and Snow. 2013, 53 (3): 55–62. doi: 10.15356/2076-6734-2013-3-55-62 [In Russian].
9. Anderson E.A. National Weather Service river forecast system: Snow accumulation and ablation model. US Department of Commerce, National Oceanic and Atmospheric Administration, National Weather Service, 1973 (17): 217 p.
10. Etchevers P., Martin E., Brown R., Fierz C., Lejeune Y., Bazile E., Boone A., Dai Y.J., Essery R., Fernandez A.,Gusev Y., Jordan R., Koren V., Kowalczyk E., Nasonova O., Pyles R.D., Schlosser A., Shmakin A.B., Smirnova T.G., Strasser U., Verseghy D., Yamazaki T., Yang Z.L. Validation of the energy budget of an alpine snowpack simulated by several snow models (SnowMIP project). Annals of Glaciology. 2004, 38 (1): 150–158. doi: 10.3189/172756404781814825.
11. Henderson-Sellers A., Pitman A.J., Love P.K., Irannejad P., Chen T.H. The project for intercomparison of land surface parameterization schemes (PILPS): Phases 2 and 3. Bulletin of the American Meteorological Society. 1995, 76 (4): 489–503. doi: 10.1175/1520-0477(1995)076<0489:TPFIOL>2.0.CO;2.
12. Gusev E.M., Nasonova O.N., Dzhogan L.Y. Physically based modeling of many-year dynamics of daily streamflow and snow water equivalent in the Lena R. basin. Water Resources. 2016, 43 (1): 21–32. doi: 10.1134/S0097807816010085.
13. Ayzel G.V. Runoff calculations for ungauged basins: potential of hydrological model and artifitial neural networks use. Inzhenernye izyskaniya. Engineering Research. 2014, 7: 60–66. [In Russian].
14. Elder K., Michaelsen J., Dozier J. Small basin modeling of snow water equivalence using binary regression tree methods. IAHS Publications-Series of Proceedings and Reports-Intern Assoc Hydrological Sciences. 1995, 228: 129–140.
15. Gharaei-Manesh S., Fathzadeh A., Taghizadeh-Mehrjardi R. Comparison of artificial neural network and decision tree models in estimating spatial distribution of snow depth in a semi-arid region of Iran. Cold Regions Science and Technology. 2016, 122: 26–35. doi: 10.1016/j.coldregions.2015.11.004.
16. Balk B., Elder K. Combining binary decision tree and geostatistical methods to estimate snow distribution in a mountain watershed. Water Resources Research. 2000, 36 (1): 13–26. doi: 10.1029/1999WR900251.
17. Volchek A.A., Kostyuk D.A., Petrov D.O. Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory. Led i Sneg. Ice and Snow. 2016, 56 (1): 43–51. doi: 10.15356/2076-67342016-1-43-51 [In Russian].
18. Internet source: Buitinck L., Louppe G., Blondel M., Pedregosa F., Mueller A., Grisel O., Niculae V., Prettenhofer P., Gramfort A., Grobler J., Layton R., VanderPlas J., Joly A., Holt B., Varoquaux G. API design for machine learning software: experiences from the scikitlearn project // arXiv preprint. 2013. http://arxiv.org/abs/1309.0238.
19. Internet source: Morin S., Lejeune Y., Lesaffre B., Panel JM., Poncet D., David P., Sudul M. A 18-years long (1993-2011) snow and meteorological dataset from a mid-altitude mountain site (Col de Porte, France, 1325 altitude). 2012. https://doi.pangaea.de/10.1594/PANGAEA.774249.
20. Internet source: Arctic research centre of Finnish Meteorological Institute: observations on Sodankyla station (Finland). http://litdb.fmi.fi/index.php.
21. Wayand N.E., Massmann A., Butler C., Keenan E., Stimberis J., Lundquist J.D. A meteorological and snow observational data set from Snoqualmie Pass (921 m), Washington Cascades, USA. Water Resources Research. 2015, 51 (12): 10092–10103. doi: 10.1002/2015WR017773.
22. Breiman L., Friedman J., Stone C.J., Olshen R.A. Classification and regression trees. CRC press, 1984: 360 p.
23. Hastie T., Tibshirani R., Friedman J., Franklin J. The elements of statistical learning: data mining, inference and prediction. Springler, 2005: 758 p.
24. Freund Y., Schapire R.E. A decision-theoretic generalization of on-line learning and an application to boosting. Journ. of computer and system sciences. 1997, 55 (1): 119–139. doi: 10.1007/3-540-59119-2_166.
25. Schapire R.E., Freund Y. Boosting: Foundations and algorithms. MIT press, 2012: 528 p.
26. Friedman J.H. Greedy function approximation: a gradient boosting machine. Annals of Statistics. 2001, 29 (5): 1189–1232.
27. Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. Intern. Joint Conf. on Artificial Intelligence (Ijcai). 1995, 14 (2): 1137–1145.
28. Jonas T., Marty C., Magnusson J. Estimating the snow water equivalent from snow depth measurements in the Swiss Alps. Journ. of Hydrology. 2009, 378 (1): 161–167. doi: 10.1016/j.jhydrol.2009.09.021.
29. Hinkler J., Pedersen S.B., Rasch M., Hansen B.U. Automatic snow cover monitoring at high temporal and spatial resolution, using images taken by a standard digital camera. Intern. Journ. of Remote Sensing. 2002, 23 (21): 4669–4682. doi: 10.1080/01431160110113881.
30. Muller C.L., Chapman L., Johnston S., Kidd C., Illingworth S., Foody G., Overeem A., Leigh R.R. Crowdsourcing for climate and atmospheric sciences: current status and future potential. Intern. Journ. of Climatology. 2015, 35 (11): 3185–3203. doi: 10.1002/joc.4210.
Supplementary files
For citation: Ayzel G.V. Use of machine learning techniques for modeling of snow depth. Ice and Snow. 2017;57(1):34-44. https://doi.org/10.15356/2076-6734-2017-1-34-44
Refbacks
- There are currently no refbacks.
ISSN 2076-6734 (Print)
ISSN 2412-3765 (Online)