برآورد عمق برف به عنوان یکی از پیامدهای تغییرات آب و هوایی با استفاده از رویکرد مدل ترکیبی حداقل مربعات ماشین بردار پشتیبان و الگوریتم ژنتیک

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد آبخیزداری، دانشکده کشاورزی و منابع طبیعی، دانشگاه اردکان، ایران

2 دانشیار، دانشکده دانشکده کشاورزی و منابع طبیعی، دانشگاه اردکان، ایران

3 استادیار، دانشکده دانشکده کشاورزی و منابع طبیعی، دانشگاه اردکان، ایران

4 دانشیار، دانشکده مهندسی کامپیوتر، دانشگاه یزد، ایران

چکیده

از جمله اثرات مستقیم و مشهود تغییرات آب و هوایی، دگرش در میزان بارش برف در مناطق مختلف جغرافیایی است. این در حالی است که بارش برف در حوضه‌های کوهستانی همواره به‌عنوان مهم‌ترین منبع تأمین منابع آب در فصول خشک تلقی می‌شود. یکی از آشکارترین ویژگی‌های پوشش برف کوهستان، ناهمگنی مکانی آن می‌باشد. به‌دلیل محدودیت‌های عملی، جمع‌آوری داده‌ها به‌ویژه در مقیاس‌های وسیع، دشوار و گاهی غیرممکن بوده و استفاده از روش‌های غیرمستقیم توصیه می‌شود. در این پژوهش کارایی حداقل مربعات ماشین بردار پشتیبان در مدل‌سازی عمق برف و همچنین اثر کاهش ویژگی با مدل الگوریتم ژنتیک در منطقه کوهستانی چلگرد ایران مورد بررسی قرار گرفت. ابتدا با استفاده از روش هایپرکیوب محل ۱۰۰ نقطه مشخص و داده‌های عمق برف در نقاط موردنظر و همچنین در ۱۹۵ نقطه دیگر به‌صورت تصادفی برداشت گردید. سپس با استفاده از مدل رقومی ارتفاع ۲۵ پارامتر ژئومورفومتری استخراج گردید و همراه با شش باند تصاویر ماهواره لندست هشت و شاخص تفاوت نرمال شده برف به‌عنوان ورودی‌های مدل‌ها انتخاب گردید. در این پژوهش از الگوریتم ژنتیک برای افزایش سرعت و آماده‌سازی شبکه ماشین بردار پشتیبان که به‌عنوان یک دسته‌بندی‌کننده عمل می‌کند و همچنین انتخاب متغیرهایی که بیشترین همبستگی را با عمق برف دارند استفاده گردید. ازآنجایی‌که کاهش ویژگی‌های غیر مؤثر می‌تواند سبب افزایش دقت یادگیری شود، در این پژوهش از الگوریتم ژنتیک برای فرایند بهینه‌سازی استفاده گردید. نتایج نشان داد روش حداقل مربعات ماشین بردار پشتیبان با میزان ضریب تعیین 36/0 و جذر میانگین مربعات خطای 8/17 مدل‌سازی عمق برف را انجام داده است؛ اما الگوریتم ژنتیک با انتخاب ویژگی‌های مؤثر توانست با ضریب تعیین ۹۵/۰ و جذر میانگین مربعات خطا برابر با ۹۷/۳ سانتی‌متر و بادقت بهتری نسبت به استفاده از تمامی ویژگی‌ها تغییرات عمق برف را مدل کند.

کلیدواژه‌ها

عنوان مقاله [English]

Snow depth estimating as one of the consequences of climate change using the combined least squares model approach of support vector machine and genetic algorithm

نویسندگان [English]

  • Mostafa Asefi 1
  • Ali Fathzadeh 2
  • Ruhollah Taghizadeh-Mehrjardi, 3
  • Mohammad Ali Zare Chahooki, 4
1 Ardakan University
2 Natural Dept., Ardakan University, Ardakan, Iran
3 Ardakan University
4 Yazd University
چکیده [English]

One of the direct and evident impacts of climate change is the change in the amount of snowfall in different geographical areas. It is worth mentioning that snowfall in mountain basins is always taken into account as the most important source of water supply in dry seasons. Due to some restrictions, data collection, particularly on a large scale, is difficult and at sometimes impossible. Consequently, using indirect methods is recommended. In this study, the efficiency of least squares support vector machine in modeling the depth of snow and the impact of feature reduction with genetic algorithms model in Chelgerd , Iran was investigated. At first, with using the Hypercube model, the locations of 100 points were specified, and the data of snow depth at certain points as well as other 195 points were randomly collected. Afterwards, with using DEM,, 25 Geomorphomety parameters were extracted, and these parameters with six bands, eight Landsat satellite images and the difference index of normalized snow were chosen as the inputs of models. In this study, genetic algorithm is used to increase the speed of support vector machine which is considered as a classifier and make it ready. Also, genetic algorithm is utilized to choose the variants having the most coherence with the snow depth. Since the reduction of ineffective features can increase the accuracy of learning, genetic algorithm was used in this study for the optimization process. The results showed that the least squares method of the S.V.M with the coefficient of determination of 0.36 and the SMSE of 17.8 has modeled the snow depth. However, the genetic algorithm by selecting the effective features was able to model snow depth changes better with a determination coefficient of 0.95 and RMSE equal to 3.97 cm which is more accurate than using all features.

کلیدواژه‌ها [English]

  • Snow Depth
  • Artificial Intelligence
  • Remote Sensing
  • Hypercube
  • Chelgerd

مراجع

  1.  

    1. Balk, Benjamin, and Elder, Kelly. (2000). Combining binary decision tree and geostatistical methods to estimate snow distribution in a mountain watershed, Water Resources Research, 36(1), 13–26.
    2. Bavay, M., Grunewald, T., and Lehning, M. (2013). Response of snow cover and runoff to climate change in high Alpine catchments of Eastern Switzerland, Advances in Water Resources, 55(1), 4–16.
    3. Beniston, M., Keller, F., and Goyette, S. (2003). Snow pack in the Swiss Alps under changing climatic conditions: an empirical approach for climate impacts studies, Theoretical and Applied Climatology, 74, 19–31.
    4. Bloschl, G., Kirnbauer, R., and Gutknecht, D. (1991). Distributed Snowmelt Simulations in an Alpine Catchment: 1. Model Evalution on the Basis of Snow Cover Patterns, Water Resources Research, 27(12), 3171-3179.
    5. Carrol, S.S., and Cressie, N. (1996). A comparison of geostatistical methodologies used to estimate snow water equivalent. Water Resources Bull, 32, 267-278.
    6. Choularton, T.W., and Perry, S.J. (1986). A model of the orographic enhancement of snowfall by the seeder-feeder mechanism, Quarterly Journal of the Royal Meteorological Society, 112(472), 335–345.
    7. Cline, D.W., Bales, R.C., and Dozier, J. (1998). Estimating the spatial distribution of snow inmountain basins using remote sensing and energy balance modeling. Water Resources Research, 34(5), 1275-1285.
    8. Dadic, R., Corripio, J.G., and Burlando, P. (2008). Mass-balance estimates for Haut Glacier d’Arolla, Switzerland, from 2000 to 2006 using DEMs and distributed mass-balance modeling, Annals of Glaciology, 49, 22–26.
    9. Elder, k., Dozier, J., and Michaelsen, J. (1991). Snow accumulation and distribution in an Alpin Watershed. Water Resources Research, 27(7), 1541-1552.
    10. Elder, K., Rosenthal, R., and Davis, R.E. (1998). Estimating the spatial distribution of snow water equivalent in a mountain watershed. Hydrology Processes, 12, 1793 –1808.
    11. Erickson, T.A., Williams, M.W., and Winstral, A. (2005). Persistence of topographic controls on the spatial distribution of snow in rugged mountain, Colorado, United States, Water Resources Research, 41(04014), 1-17.
    12. Gharaei-Manesh, S., Fathzadeh, A., Taghizadeh-Mehrjardi, R. (2016). Comparison of artificial neural network and decision tree modles in estimating spatial distribution of snow depth in a semi-arid region of Iran. Cold Regions Science and Technology, 122, 26-35.
    13. Iman R.L., and Conover, W.J. (1982). A Distribution-Free Approach to Inducing Rank Correlation Among Input Variables, Communications in Statistics, Simulation and Computation 11(3), 311-334.
    14. Keung, J.W., Kitchenham, B., and Jeffery, D.R. (2008). Analogy-x: providing statistical inference to analogy-based software cost estimation, IEEE Transactions on Software Engineering, 34(4), 471–484.
    15. Lehning, M., Lowe, H., Ryser, M., and Raderschall, N. (2008). Inhomogeneous precipitation distribution and snow transport in steep terrain, Water Resources Research, 44(7).
    16. Lehning, M., Volksch, I., Gustafsson, D., Nguyen, T.A., Stahli, M., and Zappa, M. (2006). ALPINE3D: a detailed model of mountain surface processes and its application to snow hydrology, Hydrological Processes, 20(1), 2111–2128.
    17. Liston, G.E., and Elder, K. (2006). A distributed snow-evolution modeling system (SnowModel), Journal of Hydrometeorology, 7(6), 1259–1276.
    18. Litaor, M.I., Williams, M., and Seastedt, T.R. (2008). Topographic controls on snow distribution, soil moisture, and species diversity of herbaceous alpine vegetation, Niwot Ridge, Colorado, Featured in Journal of Geophysical Research: Biogeosciences, 113(11).
    19. Lundquist, J.D., and Dettinger, M.D. (2005). How snowpack heterogeneity affects diurnal streamflow timing, Water Resources Research, 41(5), 1-14.
    20. Marchand, W.D., and Killingtveit, A. (2001). Analyses of the Relation Between Spatial Snow Distribution and Terrain Characteristics, 58th Estern Snow Conference Ottawa, Ontario, Canada.
    21. McKay, G.A., and Gray, D.M. (1981). The distribution of the snow cover, in: Handbook of Snow, edited by: Gray, D. and Hale, D., Pergamon Press Canada Ltd, 153–190.
    22. McKay, M.D., Conover W.J., and Beckman, R.J. (1979). A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code, Technometrics, 21(2), 239-245.
    23. Michael, D. (1999). The simple Genetic Algorithm: Foundation and Theory. The MIT Press.
    24. Mott, R., Scipion, D., Schneebeli, M., Dawes, N., Berne, A., and Lehning, M. (2014). Orographic effects on snow deposition patterns in mountainous terrain, Journal of Geophysical Research: Atmospheres, 119, 1419-1439.
    25. Pomeroy, J.W., and Li, L. (2000). Prairie and arctic areal snow cover mass balance using a blowing snow model, Journal of Geophysical Research: Atmospheres, 105(21), 26619–26634.
    26. Pomeroy, J.W., Gray, D M., Shook, K.R., Toth, B., Essery, R.L.H., Pietroniro, A., and Hedstrom, N. (1998). An evaluation of snow accumulation and ablation processes for land surface modelling, Hydrol. Process., 12(15), 2339–2367.
    27. Saavedra, F., Kampf, S., and Sibold, J. (2018). Changes in Andes snow cover from MODIS data, 2000–2016. The Cryosphere, Vol. 12, pp. 1027-1046.
    28. Schneiderbauer, S., and Prokop, A. (2011). The atmospheric snow-transport model: SnowDrift3D, Journal of Glaciology, 57(203), 526–542.
    29. Schweizer, J., Jamieson, J.B., and Schneebeli, M. (2003). Snow avalanche formation, Reviews of Geophysics, 41(3).
    30. Seifi, A., and Riahi-Madvar, H. (2012). Input Variable Selection in expert systems based on hybrid Gamma Test-Least Square Support Vector Machine, ANFIS and ANN models. Provisional chapter. INTECH.
    31. Shaban, A., Faour, G., Khawlie, M., and Abdallah, C. (2004). Remote sensing application to estimate the volume of water in the form of snow on Mount Lebanon, Hydrological Sciences Journal, 49(4), 643-653.
    32. Sivanandam, S.N., and Deepa, S.N. (2008) Introduction to Genetic Algorithms, Springer Germany.
    33. Stewart, I. T., Cayan, D.R., and Dettinger, M.D. (2005). Changes toward earlier streamflow timing across western North America. J. Clim, Vol. 18, pp. 1136-1155.
    34. Sumathi, S., Hamsapriya, T., and Surekha, P. (2008). Evolutionary Intelligence, Springer, Indi.
    35. Suykens, J.A.K., Gestel, T.V., Brabanter, J.D., Moor, B.D., and Vandewalle, J. (2002). Least Squares Support Vector Machines. Copyright by World Scientific Publishing Co. Pie. Ltd. PP 308.
    36. Tedesco, M., Pulliainen, J., Takala, M., Hallikainen, M., and Pampaloni, P. (2004). Artificial neural network-based techniques for the retrieval of SWE and snow depth from SSM/I data. Remote Sens. Environ, 90, 76-85.
    37. Tsai, Y., Dietz, A., Oppelt, N., and Kuenzer, C. (2019). Remote sensing of snow cover using Spaceborne SAR: A review. Remote Sensing, 11, 1-44.
    38. Varade, D., Maurya, A.K., Dikshit, O., Singh, G., and Manickam, S. (2019). Snow depth in Dhundi: An estimate based on weighted bias corrected differential phase observations of dual polarimetric bi-temporal Sentinel-1 data. International Journal of Remote Sensing, 41(8), 3031-3053.

    Zhang, H., Zhang, F., Che, T., and Wang, S. (2020). Comparative evaluation of VIIRS daily snow cover product with MODIS for snow detection in China based on ground observations, Science of The Total Environment, pp.138-156

فایل ها

هم رسانی

ارجاع به این مقاله

آمار