ارزیابی و بهکارگیری روشهای کریجینگ و شبکه عصبی مصنوعی در پیشبینی تراز آب زیرزمینی (مطالعه موردی: دشت رودان)
محورهای موضوعی : علوم آب
وحید سهرابی
1
*
,
محمدابراهیم عفیفی
2
,
کامران واحدی
3
,
احسان مرادی
4
1 - دکترای جغرافیا و برنامهریزی شهری، واحد لارستان، دانشگاه آزاد اسلامی، لارستان، ایران
2 - دانشیار گروه جغرافیا، واحد لارستان، دانشگاه آزاد اسلامی، لارستان، ایران
3 - مربی گروه عمران، واحد میناب، دانشگاه آزاد اسلامی، میناب، ایران
4 - دانشجوی دکترای جغرافیا و برنامهریزی شهری، واحد لارستان، دانشگاه آزاد اسلامی، لارستان، ایران؛
کلید واژه: آب زیرزمینی, مدلهای کریجینگ, شبکههای عصبی, رودان,
چکیده مقاله :
با افزایش جمعیت و افزایش نیاز انسان به آب طی هفتاد سال گذشته مصرف آب 6 برابر شده است. . امروزه كمبود آب و هجوم به سـفرههـاي آب زيرزمينـي، زنـدگي بشـر را بـا تهديد روبرو ساخته و نياز فزاينده به آب، از بين رفتن منابع طبيعي و توسعه بيابانها، بشر را به سوي بحران جهاني آب سوق مي دهـد. وقوع خشكسالیهای متوالی در دهه اخیر لزوم برنامه ریزي صحیح و همه جانبه جهت مقابله با مسئله کم آبی را افزایش داده است. هدف اصلی پژوهش مدلسازی مکانی - زمانی تراز آب زیرزمینی دشت رودان طی سالهای 1385 الی 1401 است با تهیه نقشه تراز آب زیرزمینی در سالهای مورد نظر و بررسی قرار دادن آنها به شناسایی و تحلیل الگوی مکانی و زمانی تراز آب زیر زمینی دشت رودان و تحلیل حساسیت و ارزیابی قابلیت اعتماد نتایج روشهای پیشنهادی دست پیدا میکنیم.روش کار از نوع کاربردی و رویکرد حاکم بر آن توصیفی-تحلیلی می باشد که در این پژوهش از اطلاعات چاههای مشاهدهای مربوط به سالهای 1385 تا 1401 به عنوان نمونه معلوم استفاده گردید و با استفاده از تکنیک های زمین آمار و شبکه عصبی مدل های درون یابی اجرا و تغییرات به صورت زمانی و مکانی در سطح دشت رودان مورد کنکاش قرار گرفت. نتایج این تحقیق نشان می دهد روش کریجینگ بهتر از روش RBF توانسته است تا تراز آب زیر زمینی بین سالهای 1385 تا 1401 را مدل سازی کند. باید این نکته را در نظر داشت که در این منطقه مدل کریجینگ بهتر بوده است.
With population growth and the increasing human demand for water, water consumption has multiplied sixfold over the past seventy years. Today, water scarcity and the overexploitation of groundwater resources have posed serious threats to human life. The growing demand for water, the destruction of natural resources, and the expansion of deserts are driving humanity toward a global water crisis. The occurrence of consecutive droughts in recent decades has further highlighted the need for comprehensive and strategic planning to address water scarcity.
The main objective of this study is the spatio-temporal modeling of groundwater levels in the Rudan Plain from 2006 to 2022. By preparing groundwater level maps for the mentioned years and examining them, the spatial and temporal patterns of groundwater level changes in the Rudan Plain are identified and analyzed. Furthermore, the study evaluates the sensitivity and reliability of the proposed methods.
This is an applied study with a descriptive-analytical approach. Observation well data from 2006 to 2022 were used as known samples. Using geostatistical techniques and artificial neural networks, interpolation models were implemented and groundwater level changes were examined both spatially and temporally across the Rudan Plain.
The results of this research indicate that the kriging method outperformed the RBF (Radial Basis Function) method in modeling groundwater levels from 2006 to 2022. It should be noted that in this particular region, the kriging model proved to be more effective
Abdul Aziz, O. and Burn, D. 2003. Trends andvariabilityinthe hydrological regime of the Mackenzie River Basin. Journal of Hydrology.319:282-294
Affandi, A. and Watanabe, K., 2007. Daily groundwater level fluctuation forecasting using soft computing Es-timation of Reference Evapotranspiration from Pan Evaporation in a Semi-Arid Environment. Irrigation Sci-ence, Available in www.Springer.com.
Ahmadizadeh, M., Maroufi, p. 2017, application of Bayesian analysis and particle filter in rainfall-runoff models and uncertainty analysis, Journal of Water and Soil Protection Research, Volume 24, Number 1, p. 251. (In Persian) . https://doi.org/10.22069/jwfst.2017.12108.2663
Bierkens, M., 1998. Modeling water table fluctuations by means of a stochastic differential equation. Water Resources Reserch,34(10), pp.2485-2499.
Boroujerdi, A., Feridouni, M., 2015, Simulation of underground water level using support vector models and its comparison with fuzzy neural models and neural wavelet (case study of Shiraz Plain), Water Engineering Conference and Exhibition. (In Persian) https://civilica.com/doc/407797/
Connor KM, Davidson JR, Churchill LE, Sherweed A, Foa EB. Psychometric properties of the Social Phobia Inventory (SPIN). The British Journal of Psychiatry 2012; 176:379-386.
Fakher, A. (2000) Application of physical models in teaching engineering courses, Iranian Engineer-ing Educational Journal, Volume 2, Number 6, pp. 39-72. (In Persian)https://doi.org/10.22047/ijee.2000.2014
Feridouni, M., Khojand, M. (2014), Application of geostatistical model (Kriging) and its integration with neural fuzzy inference system in underground water level zoning (case study: Shiraz plain), 2nd National Conference on Water, Man and Earth. (In Persian) https://cpro.ir/product/586034/
Ghorbani, M.A., R. Khatibi, M. Hasanpour kashani and O. Kisi. 2019. Comparison of three artificial intelli-gence techniques for discharge routing. Journal of Hydrology, 4. (In Persian) https://doi.org /10.22034/hydro.2024.60223.1310
Hossein Sarzabi, A., Esmaili, K. (2013), Investigation and Quantitative Modeling of Groundwater (Case Study: Neishapur Plain), Irrigation Engineering Sciences (Agriculture Scientific Journal), Volume 36, Number 4, Winter 92. (In Persian) https://doi.org/20.1001.1.25885952.1392.36.4.8.5
Hosseini Someh, M., A. Roshani and A. Zebah. 2020. Modeling of groundwater level changes based on meth-ods based on artificial intelligence (Case study of Zaveh Torbat Heydariyeh plain). Water-shed Management,Period 11,Number 21: 223-235. (In Persian) https://doi.org/10.52547/jwmr.11.21.223
Kazemi, T., Fadeli, M., Farzin, M., 2015, assessment and analysis of peak flow with different return periods for Bashar River using HEC-HMS model, Iranian Water Resources Research Quarterly, Volume: 17, Number 4, March 1400 , page 50-69. (In Persian) https://doi.org/20.1001.1.17352347.1400.17.4.3.0
Meshaikhi, S., Ebrahimi, K., Modaresi, F., Iraqhinejad, S. (2022), integrated management of Minab basin water resources using modified sustainability index, Iranian Journal of Irrigation and Water Engineering, Year 12, Number 47, Spring 2022. (In Persian) https://profdoc.um.ac.ir/paper-abstract-1082166.html#tabs-2
Mir Arabi, A., Nakhai, M., 2017, prediction of underground water level fluctuations in Birjand Plain using ar-tificial neural network, 12th conference of Geological Society of Iran. (In Persian) file:///C:/Users/sohra/Downloads/50013890101-1.pdf
Moghadisi, M., Mardian, M., Parsa, M. (2021) Comparison and evaluation of smart models and geostatistics in order to analyze the spatial changes of groundwater quality (Dasht Kamijan), watershed management research journal, volume: 12, number 24, pages 54 -64. (In Persian) https://doi.org/10.52547/jwmr.12.24.54
Mubaraki, M. Feridouni, M., 2015. Simulation of underground water level using the combination of wavelet, neural fuzzy models and its comparison with the neural fuzzy model, international conference on new research achievements in civil engineering and urban architecture. (In Persian) https://isnac.ir/XYCC-ACCBA
Nayak, P., Satyaji Rao, Y.R. and Sudheer, K.P., 2001. Groundwater Level Forecasting in a Shallow Aquifer Using Artificial Neural Network Approach. Water Resources Management,20, pp.77-90.
Rajaei, T., Zainivand, A., 2014, Modeling the underground water level using the hybrid wavelet-artificial neural network model (case study: Sharifabad plain), Reist Civil and Environmental Engineering Journal, Volume 44.4, Number 77, March 2013. Page 51-63. (In Persian) SID. https://sid.ir/paper/102298/fa
Ramezani Charmehineh, A. and M. Zounematkermani. 2017. Investigating the efficiency of support vector regression, multilayer perceptron neural network and multivariable linear regression methods to predict the level of underground water (case study: Shahrekord Plain). Watershed Management Research Journal, Volume 8, Number 15, pp. 1-12 . (In Persian) https://doi.org/10.29252/jwmr.8.15.1
Shirzaei, S (2019), a review of variable selection meth-ods in regression models with time series errors, master's thesis, Shahrood University of Technology. (In Persian)
Yazidi, A., Davari, K., Alizadeh, A., Kahraman, B., and Haqati Moghadam, S.A. (2007). Prediction of water level using artificial neural networks (case study: Neyshabur Plain). Iranian Journal of Irrigation and Drainage, 1(2), 59-71. (In Persian)