بررسی تغییرات تراز سفرۀ آب زیرزمینی با استفاده از الگوریتم فیلتر ذره مبتنی بر جذب داده ماهواره‌ای (محدودۀ خراسان جنوبی)

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد آب و سازه ‏های هیدرولیکی، گروه مهندسی عمران، دانشکدۀ مهندسی، دانشگاه بیرجند، بیرجند

2 استادیار، گروه مهندسی عمران، دانشکدۀ مهندسی، دانشگاه بیرجند، بیرجند

3 دانشیار، گروه مهندسی عمران، دانشکدۀ مهندسی، دانشگاه بیرجند، بیرجند

10.22059/ije.2023.355554.1714

چکیده

در دهه‏های گذشته به دلیل برداشت بی‏رویه از منابع آب زیرزمینی، کاهش بارندگی‏ها و افزایش دمای هوا، سطح آب‏های زیرزمینی به‌شدت کاهش پیدا کرده است. بر اساس پژوهش‏های قبلی، کشور ایران از ۱۳۰ میلیارد مترمکعب منابع آب زیرزمینی برخوردار بوده؛ اما منابع آب تجدیدشونده در ۲۰ سال گذشته به ۱۱۰ میلیارد مترمکعب و در شش سال گذشته به کمتر از ۱۰۰ میلیارد مترمکعب کاهش یافته است. بنابراین مسئلۀ تغییرات سطح آب زیرزمینی و پیش‏بینی این تغییرات از اهمیت ویژه‏ای برخوردار است. در این پژوهش سعی بر آن شد تا مدلی توسعه داده شود که با استفاده از الگوریتم جذب داده به پیش‏بینی این تغییرات بپردازد. علاوه بر این، یک مدل یادگیری عمیق نیز به‏ عنوان مدل رقیب توسعه داده شد تا نتایج حاصل از مدل پیشنهادی با آن مورد مقایسه قرار گیرند. استان خراسان جنوبی به‏ عنوان مطالعۀ موردی برای مدل‏سازی انتخاب شد. مقایسۀ بین مدل پیشنهادی و رقیب نشان داد ‌مدل پیشنهادی توانایی بسیار زیادی در پیش‏بینی داشته و دقت آن حدود دقت مدل رقیب است. براساس این ارزیابی، برای مدل پیشنهادی و مدل رقیب، ضریب تبیین ( ) به‌ترتیب برابر 91/0 و 95/0 و ریشۀ میانگین مربعات خطا (RMSE) به‌ترتیب برابر 18/0 و 20/0 به دست آمدند. همچنین ارائۀ‏ صریح روابط و پارامترهای مدل در کنار ارائۀ‏ عدم قطعیت‏ها و یک بازۀ‏ اطمینان‏پذیری، از سایر مزایای مدل پیشنهادی است که می‏تواند آیندۀ گسترده‏ای را برای الگوریتم‏های جذب داده فراهم آورد. البته مدل‏های یادگیری ماشین و یادگیری عمیق که امروزه کاربرد گسترده‎‏‏ای دارند، چنین مزایایی را ارائه نمی‏کنند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Investigation of groundwater level changes using particle filtering algorithm based on satellite data absorption (case study: Khorasan Jonoubi)

نویسندگان [English]

  • Omid Hajisamiei 1
  • Mahdi Mollazadeh 2
  • Mohammad Akbari 3
1 MSc candidate of water and hydraulic structures, Department of Civil Engineering, University of Birjand, Birjand, Iran
2 Assistant Professor, Department of Civil Engineering, University of Birjand, Birjand, Iran
3 Associate Professor, Department of Civil Engineering, University of Birjand, Birjand, Iran
چکیده [English]

In the past decades, due to excessive extraction of underground water resources, decrease in rainfall and increase in air temperature, the level of underground water has decreased drastically. According to previous researches, Iran has 130 billion cubic meters of underground water resources; but in the last 20 and six years, renewable water resources have decreased to 110 and less than 100 billion cubic meters, respectively. Therefore, the issue of underground water level changes and the prediction it, is of particular importance. Therefore, in this research, a model was developed to predict these changes using the data absorption algorithm. In addition, a deep learning model was also developed as a competing model to compare the results of the proposed model with it. South Khorasan province was selected as a case study for modeling. The comparison between the proposed model and the competing model showed that the proposed model has a very high prediction ability and its accuracy is close to the accuracy of the competitor model. Based on this evaluation, for the proposed model and the competing model, (R2) was equal to 0.91 and 0.95, and the root mean square error (RMSE) was equal to 0.18 and 0.20, respectively. Also, explicit presentation of equations and parameters of the model along with providing uncertainties and a confidence interval are other advantages of proposed model that can provide a wide future for data absorption algorithms. Meanwhile, machine learning and deep learning models, that are widely used today, do not provide such benefits.

کلیدواژه‌ها [English]

  • Groundwater Level
  • Particle Filter Algorithm
  • GRACE Satellite
  • Deep Learning
  • Satellite Data
  • Faramarzifard A. Investigation of changes in the groundwater level (case study: Silakhor plain, Lorestan province). Master's thesis, Department of Water Engineering, Faculty of Agriculture, Urmia University, 2013 [Persian].

 

  • Azimi M. Assessing the accuracy of GRACE satellite data in estimating changes in underground water resources in the six main watersheds of the country. Master's Thesis, Faculty of Engineering, Isfahan University, 2018 [Persian].
  • Joodaki G. Earth mass change tracking using GRACE satellite gravity data. Norwegian University of Science and Technology, Trondheim, 2014.
  • Asghari Moghadam A, Nadiri A, Noorani V. Temporal and spatial prediction of underground water level using a combined time series-geostatistics model. 26th Earth Sciences Meeting, Tehran (Ministry of Industries and Mines, Organization of Geology and Mineral Exploration of Iran); 2016 [Perisan].
  • Strassberg G, Scanlon B, Chambers D. Evaluation of groundwater storage monitoring with the GRACE satellite: Case study of the High Plains aquifer, central United States. Water Resources Research. 2009; 45(5): 1-10.
  • Longuevergne L, Scanlon B, Wilson C. GRACE Hydrological estimates for small basins: Evaluating processing approaches on the High Plains aquifer, USA. Water Resources Research. 2010; 46(11): 1-15.
  • Joodaki G, Nahavandchi H. Mass balance and mass loss acceleration of the 80 Greenland ice sheet (2002–2011) from GRACE gravity data. Geodetic Science. 2012; 156-161.
  • Ferreira V, Gong Z, He X, Zhang Y. Estimating total discharge in the Yangtze river basin using satellite-based observations. Remote Sensing. 2013; 5: 3415-3430.
  • Lee S, Seo JY, Lee SK. Validation of terrestrial water storage change estimates using hydrologic simulation. Journal of Water Resources and Ocean Science. 2014; 3(1): 5-9.
  • Ashrafzade A, Judaki G, Sharifi M. Iran's groundwater resources assessment using data from the GRACE satellite gravity survey. Journal of Research Science and Technology Mapping. 2015; 5(4): 73-84.
  • Chen J, Famiglietti JS, Scanlon BR, Rodell M. Groundwater storage changes: present status from GRACE observations. Surveys in Geophysics Journal. 2016; 37: 397-417.
  • Sun Y, Riva R, Ditmer P. Optimizing estimates of annual variations and trends in geocenter motion and J2 from a combination of GRACE data and geophysical models. Geophysical research letters. 2016; 121(11): 8352-8370.
  • Yin W, Hu L, Jiao JJ. Evaluation of groundwater storage variations in northern China using GRACE data. Geofluids; 2017.
  • Khaki M, Awange J, Forootan E, Kuhn M. Understanding the association between climate variability and the Nile's water level fluctuations and water storage changes during 1992-2016. Science of the Total Environment. 2018; 645: 1509-1521.
  • Frappart F, Ramilien G. Monitoring groundwater storage changes using the gravity recovery and climate experiment (GRACE) satellite mission: A review. Remote Sensing. 2018; 10(6): 1-25.
  • Singh AK, Tripathi JN, Kotlia BS, Singh KK. Monitoring groundwater fluctuations over India during Indian Summer Monsoon (ISM) and Northeast monsoon using GRACE satellite: Impact on agriculture. Quaternery International. 2019; 507: 342-351.
  • Su Y, Gou B, Zhou Z, Zhong Y, Min L. Spatio-temporal variations in groundwater revealed by GRACE and its driving factors in the Huang-Huai-Hai plain, China. Journal of Sensors. 2020; 20(922): 1-17.
  • Arast M, Ranjbar A. Mousavi H. Abdollahi K.H. Jonarbakhsh A. Relationship between groundwater level variations using grace satellite dataand rainfall. Proceeding of the institution of civil engineering-water management. 2020; 173(4): 1-10.
  • Chanu CS, Munagapati H, Tiwari VM, Kumar A, Elango L. Use of grace time-series data for estimating groundwater storage at small scale. Journal of earth system science. 2020; 129(15): 1-19.
  • HafezParast M. Monitoring of groundwater level changes using Grace and GLDAS satellites in Kermanshah Province. Journal of Irrigation and water engineering. 2022; 12(4): 234-257.
  • Faraji Z, Kaviani A, Ashrafzadeh A. Evaluation of GRACE satellite data in estimation of groundwater level changes in Qazvin province. Journal of Ecohydrology. 2016; 4(2): 463-476 [Persian].
  • Mohtashmi A, Hashemi Monfared A, Azizian G, Akbarpour A. Using particle filter for accurate estimation of steady water load boundary conditions in open aquifer. Amirkabir Civil Engineering Journal. 2021; 53(12): 1-6 [Persian].
  • Kazemi A. Using the wavelet and Gaussian filter method to estimate the annual changes of groundwater in Iran using GRACE gravimetric satellites. Master's thesis, Faculty of Civil Engineering, Shahrood University of Technology; 2017 [Persian].
  • Abbaszadeh P, Moradkhani H, Daescu DN. The Quest for Model uncertainty quantification: A hybrid ensemble and variational data sssimilation framework. Water Resource Researchs. 2019; 55: 2407–2431.
  • Verstegen JA, Karssenberg D, Hilst F, Faaij A. Identifying a land use change cellular automaton by Bayesian data assimilation. Environmental modelling and software. 2014; 53: 121-136.

 

  • Banerjee P, Karpenko O, Udpa L, Haq M, Deng Y. Prediction of impact-damage growth in GFRP plates using particle filtering algorithm. Composite Structures. 2018;194:527-536.
  • Daroogheh N, Meskin N, Khorasani K. A novel particle filter parameter prediction scheme for failure prognosis. In: 2014 American Control Conference. Portland; 2014.
  • Jalilehvand M, Alizadeh H, Mojaradi DB. A novel approach for modelling crop land use change and identifying its spatial drivers in an agricultural system. Available at SSRN: https://ssrn.com/abstract=4081770; 2022.