Depth estimation of Salt Domes using gravity data through General Regression Neural Networks, case study: Mors Salt dome Denmark

Authors

Abstract

In this paper an intelligent method through General Regression Neural Networks (GRNN) is presented to estimate the depth of salt domes from gravity data. Neural networks are as a good tool for automatic interpretation of geophysical data especially for depth estimation of gravity anomalies. The gravity signal is a nonlinear function of depth and density and the geometrical parameters of the buried body. One of the common modern tools for non-linear systems identifications is neural networks. The parallel processing and the ability of the network to learn from training data is a good motivation to use them for interpretation of gravity data. Salt domes are as a target of the gravity explorations in oil exploration because in the most cases in Middle East, America and some parts of the Europe like Denmark they are as a good locations for oil traps and diapers. The non-simple structure of the salt domes is noticeable. Almost in most of the available methods of salt dome modeling for depth estimation they are considered simply to simple geometrical bodies like sphere or cylinder.These simplifications cause to no adaption to the real nature of salt domes. The salt domes modeling in this paper is not followed these simplifications and the near to real shape of salt dome bodies is modeled through Grav2dc software. Different possibilities for the salt dome model are considered: salt dome with oil, salt dome with oil and salt water, salt dome with gas and oil, salt dome with none of the gas oil or salt water. For all the mentioned salt dome models both the Grav2dc software and surfer are used to calculate the gravity effect of the body and then the related feature are extracted. To train the general regression neural network the range of the salt dome depth(s) are selected regard to available geological prior information. For example if the possible range of the salt dome is regard to the geological properties and/or well log data between 2 to 4 kilometers the GRNN is trained with models of salt dome with depths from 1 to 4 kilometer. In this way, first the gravity effect of several salt dome models with different depths were calculated via forward modeling and the GRNN was trained with this set of data. The GRNN architecture was modified regard to Root Mean Square Error of the GRNN network and modifications were followed and repeated until achieving the network with acceptable Root Mean Square Error (RMSE) for the training process. To test the GRNN the synthetic gravity data of salt dome with two different level of noise 5% as low noise, and 10% as high noise were applied to the designed GRNN and the related depth was estimated. Totally the results showed good ability of GRNN for depth estimation of salt domes. Finally, to test the GRNN for real data the GRNN was tested for gravity data over Mors Salt dome in Denmark. Mors salt dome is a gravity field for oil exploration and is also an interesting case study for a lot of the geophysics researchers and geoscientists. The results for real data also proved the ability of the general regression neural network for estimating the depth of salt domes with low root mean square error.

Keywords

Main Subjects

References

  1.  1. اسماعیل‌زاده آ.، ضیاییم.، دولتی اردجانی ف.، 1389. بررسی مناطق احتمالی نفوذ گنبد نمکی در تاقدیس دهنو با استفاده از تلفیق لایه‌های گرانی‌سنجی و مغناطیس سنجی به روش حاصل‌ضرب فازی، چهاردهمین کنفرانس ژئوفیزیک ایران، تهران.

    2.آقاجانی، ح. مرادزاده، ع. هوالین زنگ. 1389. برآورد موقعیت افقی و ژرفای بی هنجاری‌های گرانی به کمک گرادیان کل بهنجارشده، فصلنامه علوم زمین، سال نوزدهم، 76، 169 – 176

    3. آقاجانی، ح. 1388. بررسی قابلیت روش گرادیان کل نرمال داده‌های گرانی در تعیین پتانسیل هیدروکربوری تله‌های نفتی، رساله دکتری.

    4. پیشدادیان، م.، دولتی ارده جانی، ف.، فتحیان پور، ن.، خالو کاکائی ر.،1389. مقایسه روش هندسه فرکتال با روش‌های متداول برای تفکیک آنومالی‌های گرانی منطقه رودان بندرعباس، چهاردهمین کنفرانس ژئوفیزیک ایران، تهران.

    1.  دولتی ارده جانی، ف. مرادزاده، ع. یعقوبی پور، م. 1390. بررسی قابلیت روش اجزاء محدود در جداسازی بی هنجاری‌های گرانی ساختمان‌های نفتی، مجله فیزیک زمین و فضا، 37، 2،180-191.

    6. کیا م. 1390، شبکه‌های عصبی درMATLAB، انتشارات کیان رایانه.

    7. مهرنیا س.ر.، ابراهیم زاده اردستانی و., تیموریان آ.، 1392، استفاده از روش برخال برای تعیین چگالی بوگه لوح سنگی در منطقه چارک (جنوب ایران)، مجله ژئوفیزیک ایران 7(1):34-50.

      8. رضاییم.، 1384، زمین‌شناسی نفت، انتشارات علوی تهران، چاپ دوم.

    9. Bain, J.E., Weyand, J., Horscroft, T.R., Saad, A.H., and Bulling, D.N,1993, Complex Salt Features Resolved by Integrating Seismic, Gravity, and Magnetics, EAEG/EAPG Annual Conference and Exhibition, expanded abstracts.

    10. Gravesen, P., 1990, Geological map of Denmark 1:50.000, Kortobladet 116I Thirsted, Geological basis datakort, Geological Survey of Denmark, Map series no.13.

     

     11. Hajian, A. 2008. Depth estimation of gravity anomalies by Hopfield Network, proceeding of 5th Annual meeting, AOGS: Asia Oceania Geosciences Society Busan, Korea, 16-20 Jun.

     

    12. Hajian, A., Styles P., Zomorrodian H., Depth Estimation of Cavities from Microgravity Data through Multi Adaptive Neuro-Fuzzy Interference System,2011, 17th Near Surface European Meeting of Environmental and Engineering Geophysics Leicester, UK, 12-14 September 2011.

      

    13. Helen I. J. and Donald. C. L., 2007, Benefit of integrated seismic and gravity exploration. An example from Norman wells NWT. Fold-Fault Research Project, University of Calgary.

     

                                                                                      

    14. Jorgensen.F. Sandersen B.E. P., Auken E., Lykke-Andersen H. and Sorensen K. 2005. Contributions to the geological mapping of Mors, Denmark – A study based on a large –scale TEM survey, Bulletin of the Geological Society of Denmark 52, 53-75.

     

    15.Osman O., Albora A.M. and Ucan O.N., 2007, Forward modeling with forced Neural Network for Gravity Anomaly Profile. Mathematical Geology 39,593-605. doi 10.1007/s 11004-007-9114-8.

     

    16.Pedersen, G.K.& Shurlyk F., 1983, The Fur Formation, a late Paleocene ash-bearing diatomite from northern Denmark, Bulletin of the Geological Society of Denmark 32,43-65.

     

    17. Specht,A. 1991, A General Regression Neural Network,IEEE Transaction on Neural Networks 2(6), 56-64.

    18.Styles, P., Hajia A., 2012,Generalized Regression Neural Networks for Cavities Depth Estimation using microgravity Data, Case Study: Kalgorlie Gold, Near Surface Geosciences – 18th European Meeting of Environmental and Engineering Geophysics Paris, France, 3-5 September.

Journal of the Earth and Space Physics
Volume 41, Issue 3 - Serial Number 3
October 2015
Pages 425-438

Files

Share

How to cite

Statistics