نشریه علمی - پژوهشی مرتع و آبخیزداری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری بیابان‌زدایی، گروه احیاء و مدیریت مناطق خشک و بیابانی، دانشکده منابع طبیعی و کویر شناسی، دانشگاه یزد، یزد، ایران

2 استادیار گروه احیاء و مدیریت مناطق خشک و بیابانی، دانشکده منابع طبیعی و کویر شناسی، دانشگاه یزد، یزد، ایران

3 دانشیار بخش مهندسی راه، ساختمان و محیط زیست، دانشکده مهندسی، دانشگاه شیراز، شیراز، ایران.

4 استاد بخش هوش مصنوعی، دانشکده مهندسی کامپیوتر، دانشگاه یزد، یزد، ایران.

5 استاد گروه علوم خاک، دانشکده کشاورزی، دانشگاه اژه، ازمیر، ترکیه.

10.22059/jrwm.2022.340930.1652

چکیده

هدف از پژوهش حاضر، مدل‌سازی فرونشست دشت ابرکوه با استفاده از تکنیک تداخل‌سنجی راداری و هوش مصنوعی بود. در ابتدا با استفاده از 46 تصویر راداری Sentinel-1 بین سال‌های 2014 تا 2018 و تکنیک تداخل‌سنجی راداری نقشه فرونشست منطقه تهیه شد. در ادامه جهت مدل‌سازی فرونشست، از الگوریتم شبکه عصبی مصنوعی پیش‌رونده استفاده شد. در این الگوریتم از پنج پارامتر تغییرات سطح آب زیرزمینی (2018-2014)، سطح آب زیرزمینی، ضخامت آبخوان، ضخامت لایه رس در آبخوان و همچنین ضخامت لایه رس در محدوده تغییرات سطح آب زیرزمینی (2018-2014) به عنوان ورودی مدل و مقدار فرونشست حاصل از روش تداخل‌سنجی راداری به عنوان خروجی جهت آموزش مدل به شبکه معرفی شد. ورودی‌های مدل از مجموعه داده‌های اندازه‌گیری شده 34 چاه پیزومتری و 77 لاگ حفاری موجود در آرشیو آب منطقه‌ای استان یزد بدست آمد که پس از بررسی صحت داده‌های اخذ شده وآنالیزهای اولیه، پارامترهای پنجگانه با استفاده از میانیابی به روش کریجینگ، به کل منطقه تعمیم داده شد و لایه رستری آ‌‌‌ن‌ها تهیه گردید. نتایج روش تداخل‌سنجی راداری نشان داد که فرونشست در مناطقی از شرق، شمال شرق و شمال به ترتیب با نرخ متوسط فرونشست 6، 7/2 و 6/1 سانتی‌متر در سال بیشترین مقادیر را به خود اختصاص داده است. همچنین جهت تایید صحت مدل، از معیارهای ارزیابی نظیر ناش– ساتکلیف(NS)، جذر میانگین مربعات خطا(RMSE)، میانگین خطای مطلق(MAE) و میانگین قدر مطلق خطای نسبی(MARE) استفاده گردید که به ترتیب مقادیر9524/0، 0018/0، 0012/0 و 1545/0 بدست آمد.

کلیدواژه‌ها

عنوان مقاله [English]

Modeling of land subsidence in Abarkouh plain using Synthetic aperture radar method and artificial intelligence

نویسندگان [English]

  • Zahra Khosravani 1
  • Mohammad Akhavan Ghalibaf 2
  • Maryam Dehghani 3
  • Vali Derhami 4
  • Mustafa Bolca 5

1 Ph.D. Student of Combat Desertification, Department of Arid Land and Desert Management, Faculty of Natural Resources and Desert Studies, Yazd University, Iran.

2 Assistant Professor of Arid Land and Desert Management Department, Faculty of Natural Resources and Desert Studies, Yazd University, Iran.

3 Associated Professor of Civil and Environmental Engineering Department, School of Engineering, Shiraz University, Shiraz.

4 Professor of Computer Engineering Department, Faculty of Engineering, Yazd University, Iran.

5 Professor of Soil Science Department, Faculty of Agriculture, Ege University, Izmir, Turkey.

چکیده [English]

The aim of this study was to model the subsidence of Abarkouh plain using inSAR and artificial intelligence techniques. At first, the subsidence map was prepared using the 46 Sentinel - 1 radar images (2014 – 2018) and radar interferometry techniques. Then, the Feedforward artificial neural network (ANN) algorithm was used to model the subsidence. In this algorithm, groundwater level changes (2014-2018), groundwater level, aquifer thickness, clay thickness in the aquifer and the clay thickness in the range of groundwater level changes (2014 - 2018) were introduced as input layers and the subsidence layer obtained from the radar interferometry method was introduced as an output layer to model training. These five parameters were obtained from the measured data set of 34 piezometer wells and 77 logs available in the archive of Regional Water Company of Yazd province. After initial checking of the data accuracy, the Kriging interpolation method was used to extend the five parameters to the whole region and the raster layers were prepared. The results of inSAR showed that maximum subsidence in parts of the studied area, i.e. in east, north - east and north, were 6, 2.7 and 1.6 cm/year respectively. Also, in order to verify the accuracy of the map resulting from using a neural network model, it was compared with the map with the radar imaging method. For this purpose, model evaluation criteria such as Nash-Sutcliffe (NS), RMSE,,MAE)and MARE were used, which 0.9524, 0.0018, 0.0012 and 0.1545 were obtained respectively.

کلیدواژه‌ها [English]

  • groundwater
  • fine-grained sediments
  • artificial neural network
  • Sentinel-1 radar images
  • subsidence
[1] Afifi, M. A. (2017). Assess the potential of land subsidence and its related factors (Case study: Plain Saidan Farouk Marvdasht). Quantitative Geomorphological Research, 5(3), 121- 132.
[2] Al-Halbouni, D., Holohan, E., Saberi, L., Alrshdan, H., Sawarieh, A., Closson, D., Walter, T. R. and Dahm, T. (2017). Sinkholes, subsidence and subrosion on the eastern shore of the Dead Sea as revealed by a close-range photogrammetric survey. Geomorphology, 285, 305-324.
[3] Azarakhsh, Z., Azadbakht, M. and Matkan, A. (2022). Estimation, modeling, and prediction of land subsidence using Sentinel-1 time series in Tehran-Shahriar plain: A machine learning-based investigation. Remote Sensing Applications: Society and Environment, 25,1-17.
[4] Bagheri, M., Dehghani, M., Ali Esmaeily, A. and Akbari, V. (2019). Assessment of land subsidence using interferometric synthetic aperture radar time series analysis and artificial neural network in a geospatial information system: case study of Rafsanjan Plain. Journal of Applied Remote Sensing 13(4), 21-42.
[5] Castellazzi, P., Arroyo-Domínguez, N., Martel, R., Calderhead, A. I., Normand, J. C., Gárfias, J. and Rivera, A. (2016). Land subsidence in major cities of Central Mexico: Interpreting InSAR-derived land subsidence mapping with hydrogeological data. International Journal of Applied Earth Observation and Geoinformation, 47, 102-111.
[6] Choopani, A., Dehghani, M. and Nikoo, M. R. (2020). Determining hydrogeological parameters of an aquifer in Sirjan Basin using Envisat ASAR interferometry and groundwater modelling. International Journal of Remote Sensing, 41(2), 655-682.
[7] Daniel, R., Maisons, C., Carnec, S., Le Mouelic, C., King, C. and Hosford, S.  (2003). Monitoring of slow ground deformation by ERS radar interferometry on the Vauvert salt mine (France) Comparison with ground-based measurement. Remote Sensing of Environment, 88(4), 468-478.
[8] Dehghani, M. (2014). An Enhanced Algorithm based on Radar Interferometry for Monitoring Land Subsidence Caused by Over-Exploitation of groundwater. Journal of Geospatial Information Technology 2(2), 61-73.
[9] Dehghani, M., Valadanzoej, M. J., Hooper, A., Hanssen, R. F., Entezam, I. and Saatchi, S. (2013). Hybrid conventional and persistent scatterer SAR interferometry for land subsidence monitoring in the Tehran Basin, Iran. ISPRS Journal of Photogrammetry and Remote Sensing, 79, 157-170.
[10] Dehghani, M., Valadanzoej, M. J., Entezam, I., Saatchi, S. and Shemshaki, A. (2011). Interferometric measurements of ground surface subsidence induced by overexploitation of groundwater. Journal of Applied Remote Sensing, 4(1), 56-73.
[11] Galloway, D. L., Erkens, G., Kuniansky, E. l. and Rowland, J. C. (2016). Preface: Land subsidence processes. Hydrogeology Journal, 24 (3), 547-550.
[12] Haddad, A. and Khorasani, E. (2019). Groundwater level changes effect on the subsidence in Semnan plain Scientific Quarterly Journal of Geosciences, 28(112), 181-190.
[13] Haghighatmehr, P., Valadanzouj, M. J., Tajik, R., Jabari, S., Sahebi, M. R., Eslami, R., Ganjiyan, M. and Dehghani, M. (2012). Time Series Analysis of Hashtgerd Subsidence Using Radar Interferometry and Global Positioning System. Scientific Quarterly Journal of Geosciences, 22(85), 105-114.
[14] Herrera, G., Tomas, R., Monells, D., Centolanza, G., Mallorqui, J., Vicente, F., Navarro, V., Lopez Sanchez, J., Sanabria, M., Cano, M. and Mulas, J. (2010).  Analysis of subsidence using TerraSAR-X data: Murcia case study. Engineering Geology, 116(3-4), 284-295.
[15] Karunasingha, D. S. K. (2022). Root mean square error or mean absolute error? Use their ratio as well. Information Sciences, 585, 609-629.
[16] Knoben, W. J., Freer, J. E. and Woods, R. A. (2019). Inherent benchmark or not? Comparing Nash–Sutcliffe and Kling–Gupta efficiency scores. Hydrology and Earth System Sciences, 23(10), 4323-4331.
[17] Kumar, V., Venkataramana, G. and Høgda, K. (2011). Glacier surface velocity estimation using SAR interferometry technique applying ascending and descending passes in Himalayas. International Journal of Applied Earth Observation and Geoinformation, 13(4), 545–551.
[18] Maleki, A. and Rezaee, P. (2016). Forecast locations at risk of subsidence plain Kermanshah. The Journal of Spatial Planning, 20(1), 235-251.
[19] Mokhtari, D., Ebrahimy, H. and Salmani, S. (2019). Land subsidence susceptibility modeling using random forest approach (Case study: Tasuj plane catchment). Journal of RS and GIS for Natural Resources, 10(3), 93-105.
[20] Pourab Consulting Engineers, (2012). Geology and Hydrogeology Report (Abarkouh), Regional Water Company of Yazd. 173 Pp.
[21] Pourkhosravani, M. (2014). Geoduality Theory. Geography and Environmental Planning, 25(1), 25-36.
[22] Reich, N. G., Lessler, J., Sakrejda, K., Lauer, S. A., Iamsirithaworn, S. and Cummings, D. A. (2016). Case study in evaluating time series prediction models using the relative mean absolute error. The American Statistician, 70(3), 285-292.
[23] Saffari, A., Jafari, F., and Tavakoli Sabour, S. M.  (2016). Monitoring its land subsidence and its relation to groundwater harvesting case study: Karaj Plain – Shahriar. Quantitative Geomorphological Research, 5(2), 82-93.
[24] Sousa, J.J., Ruiz, A.M., Bakon, M., Lazecky, M., Hlavacova, I., Patrício, G., Delgado, J.M. and Perissin, D., (2016). Potential of C-Band SAR interferometry for dam monitoring. Procedia Computer Science, 100, 1103–1114.
[26] Wang, W. and Lu, Y. (2018). Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. In IOP conference series: materials science and engineering, 324(1), 1-10. 
[27] Zhu, L., Gong, H., Li, X., Li, Y., Su, X. and Guo, G. (2013). Comprehensive analysis and artificial intelligent simulation of land subsidence of Beijing, China. Chinese Geographical Science, 23(2), 237-248.