From traditional extrapolation to neural networks: Time-depth relationship innovations in the subsurface characterization of Drava Basin, Pannonian Super Basin

Abstract

The estimation of time-to-depth relationships can prove challenging in regions with rare acoustic logs. This study focuses on the eastern part of the Drava Basin in north Croatia, chosen as a mature hydrocarbon exploration area with abundant geophysical and well data. As only a small portion of wells have well log measurements or seismic profiling performed, a time-to-depth extrapolation is often performed, which potentially results in the erroneous placement of well log markers in the time domain and affects the interpretation of seismic sections or volumes. This study proposes a novel methodology for predicting two-way travel time values in wells without vertical seismic profiling or acoustic logging. This research evaluates the parameters for the characterization of the velocity distribution in the subsurface and the efficiency of artificial neural networks versus conventional methods for this task. The constructed artificial neural network model has a correlation coefficient above 0.99 for the training, testing, and validation datasets, with a mean absolute error of approximately 25 milliseconds for each network. Artificial neural networks proved to have a lesser error in predicting the two-way time and are not sensitive to outlier values.

Document Type: Original article

Cited as: Kamenski, A., Cvetković, M., Kapuralić, J., Kolenković Močilac, I., Brcković, A. From traditional extrapolation to neural networks: Time-depth relationship innovations in the subsurface characterization of Drava Basin, Pannonian Super Basin. Advances in Geo-Energy Research, 2024, 14(1): 25-33. https://doi.org/10.46690/ager.2024.10.05

References

Aker, E., Tveiten, O. G., and Wynn, T.: Seismic pore pressure prediction at the Halten Terrace in the Norwegian Sea, Petroleum Geoscience, 26, 346–354, https://doi.org/10.1144/petgeo2019-053, 2020.

Alfarraj, M. and AlRegib, G.: Petrophysical-property estimation from seismic data using recurrent neural networks, in: SEG Technical Program Expanded Abstracts 2018, 2141–2146, https://doi.org/10.1190/segam2018-2995752.1, 2018.

Al-Khazraji, O. N. A.: Cross-validation of time-depth conversion and evaluation of different approaches in the Mesopotamian Basin, Iraq, Exploration Geophysics, 54, 288–315, https://doi.org/10.1080/08123985.2022.2140653, 2023.

Bartel, D. C., Busby, M., Nealon, J., and Zaske, J.: Time to depth conversion and uncertainty assessment using average velocity modeling, in: SEG Technical Program Expanded Abstracts 2006, 2166–2170, https://doi.org/10.1190/1.2369965, 2006.

Bassiouni, Z.: Theory, Measurement, and Interpretation of Well Logs, 4th ed., Society of Petroleum Engineers, 1–384 pp., 2013.

Brown, W. M., Gedeon, T. D., Groves, D. I., and Barnes, R. G.: Artificial neural networks: A new method for mineral prospectivity mapping, Australian Journal of Earth Sciences, 47, 757–770, https://doi.org/10.1046/j.1440-0952.2000.00807.x, 2000.

Cao, J., Shi, Y., Wang, D., and Zhang, X.: Acoustic Log Prediction on the Basis of Kernel Extreme Learning Machine for Wells in GJH Survey, Erdos Basin, Journal of Electrical and Computer Engineering, 2017, 1–7, https://doi.org/10.1155/2017/3824086, 2017.

Chen, G., Qi, H., Yu, J., Li, W., Xian, C., Lu, M., Song, Y., and Wu, J.: Application of a multi-layer feedforward neural network to predict fracture density in shale oil, Junggar Basin, China, Front Earth Sci (Lausanne), 11, https://doi.org/10.3389/feart.2023.1114389, 2023.

Chen, H., Zeng, Z., and Tang, H.: Landslide Deformation Prediction Based on Recurrent Neural Network, Neural Process Lett, 41, 169–178, https://doi.org/10.1007/s11063-013-9318-5, 2015.

Ćorić, S., Pavelić, D., Rögl, F., Mandic, O., Vrabac, S., Avanić, R., Jerković, L., and Vranjković, A.: Revised Middle Miocene datum for initial marine flooding of North Croatian Basins (Pannonian Basin System, Central Paratethys), Geologia Croatica, 62, 31–43, https://doi.org/10.4154/gc.2013.05, 2009.

Hansen, L. K. and Salamon, P.: Neural network ensembles, IEEE Trans Pattern Anal Mach Intell, 12, 993–1001, https://doi.org/10.1109/34.58871, 1990.

Hart, D. M., Balch, R. S., Weiss, W. W., and Wo, S.: Time-to-Depth Conversion of Nash Draw “L” Seismic Horizon using Seismic Attributes and Neural Networks, in: 2000 SPE Permian Basin Oil and Gas Recovery Conference, 1–13, 2000.

HGI-CGS: Basic Geological Map of Croatia 1:300,000, HGI-CGS, Zagreb, 1–1 pp., 2009.

Inichinbia, S. and Saule, P. O.: Well-to-Seismic Tie of a Field Onshore of the Nigerian Delta, Journal of Applied Sciences and Environmental Management, 25, 53–58, https://doi.org/10.4314/jasem.v25i1.7, 2021.

Jeong, J., Park, E., Chen, H., Kim, K.-Y., Shik Han, W., and Suk, H.: Estimation of groundwater level based on the robust training of recurrent neural networks using corrupted data, J Hydrol (Amst), 582, 124512, https://doi.org/10.1016/j.jhydrol.2019.124512, 2020.

Lučić, D., Saftić, B., Krizmanić, K., Prelogović, E., Britvić, V., Mesić, I., and Tadej, J.: The Neogene evolution and hydrocarbon potential of the Pannonian Basin in Croatia, Mar Pet Geol, 18, 133–147, https://doi.org/10.1016/S0264-8172(00)00038-6, 2001.

Malvić, T. and Cvetković, M.: Lithostratigraphic units in the Drava Depression (Croatian and Hungarian parts) – a correlation, Nafta, 63, 27–33, 2013.

Mari, J.-L., Vergniault, C., and Coppens, F.: Acoustic logging, in: Well seismic surveying and acoustic logging, edited by: Mari. J.-L. and Verginault, C., EDP Sciences, 77–102, https://doi.org/10.1051/978-2-7598-2263-8.c005, 2020.

Matošević, M., Garzanti, E., Šuica, S., Bersani, D., Marković, F., Razum, I., Grizelj, A., Petrinjak, K., Kovačić, M., and Pavelić, D.: The Alps as the main source of sand for the Late Miocene Lake Pannon (Pannonian Basin, Croatia), Geologia Croatica, 77, 69–83, https://doi.org/10.4154/gc.2024.05, 2024.

Ojha, V. K., Abraham, A., and Snášel, V.: Metaheuristic design of feedforward neural networks: A review of two decades of research, Eng Appl Artif Intell, 60, 97–116, https://doi.org/10.1016/j.engappai.2017.01.013, 2017.

Pamić, J.: Crystalline basement of the South Pannonian Basin based on surface and subsurface dana, Nafta, 49, 371–390, 1998.

Pamić, J. and Lanphere, M.: Hercynian granites and metamorphic rocks from the Mts. Papuk, Psunj, Krndija, and the surrounding basement of the Pannonian Basin in Slavonija (Northern Croatia, Yugoslavia), Geologija, 34, 81–253, https://doi.org/10.5474/geologija.1991.004, 1991.

Pavelić, D.: Tectonostratigraphic model for the North Croatian and North Bosnian sector of the Miocene Pannonian Basin System, Basin Research, 13, 359–376, https://doi.org/10.1046/j.0950-091x.2001.00155.x, 2001.

Pavelić, D. and Kovačić, M.: Sedimentology and stratigraphy of the Neogene rift-type North Croatian Basin (Pannonian Basin System, Croatia): A review, Mar Pet Geol, 91, 455–469, https://doi.org/10.1016/j.marpetgeo.2018.01.026, 2018.

Pavlin, I.: Formation water salinity in deep permeable layers in Eastern part of Drava Basin (In Croatian: Saliniteti slojne vode u dubokim propusnim slojevima na području istočnog dijela Dravske depresije), University of Zagreb, Faculty of Mining, Geology and Petroleum Engineering, Zagreb, 1–26 pp., 2022.

Pham, N., Wu, X., and Zabihi Naeini, E.: Missing well log prediction using convolutional long short-term memory network, GEOPHYSICS, 85, WA159–WA171, https://doi.org/10.1190/geo2019-0282.1, 2020.

Prieto, A., Prieto, B., Ortigosa, E. M., Ros, E., Pelayo, F., Ortega, J., and Rojas, I.: Neural networks: An overview of early research, current frameworks and new challenges, Neurocomputing, 214, 242–268, https://doi.org/10.1016/j.neucom.2016.06.014, 2016.

Rider, M.: The Geological Interpretation of Well Logs, 2nd ed., Rider-French Consulting Ltd., Sutherland, 1–280 pp., 2002.

Rukavina, D., Saftić, B., Matoš, B., Kolenković Močilac, I., Premec Fuček, V., and Cvetković, M.: Tectonostratigraphic analysis of the syn-rift infill in the Drava Basin, southwestern Pannonian Basin System, Mar Pet Geol, 152, 106235, https://doi.org/10.1016/j.marpetgeo.2023.106235, 2023.

Saftić, B., Velić, J., Sztanó, O., Juhász, G., and Ivković, Ž.: Tertiary subsurface facies, source rocks and hydrocarbon reservoirs in the SW part of the Pannonian Basin (Northern Croatia and south-western Hungary), Geologia Croatica, 56, 101–122, 2003.

Santos, D. T. dos, Roisenberg, M., and Nascimento, M. dos S.: Deep Recurrent Neural Networks Approach to Sedimentary Facies Classification Using Well Logs, IEEE Geoscience and Remote Sensing Letters, 19, 1–5, https://doi.org/10.1109/LGRS.2021.3053383, 2022.

da Silva, I. N., Angelo, J., and Jose, N.: Recurrent Neural Network Based Approach for Solving Groundwater Hydrology Problems, in: Artificial Neural Networks - Architectures and Applications, InTech, https://doi.org/10.5772/51598, 2013.

Singer, D. A. and Kouda, R.: Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan, Math Geol, 28, 1017–1023, https://doi.org/10.1007/BF02068587, 1996.

Song, S., Hou, J., Dou, L., Song, Z., and Sun, S.: Geologist-level wireline log shape identification with recurrent neural networks, Comput Geosci, 134, 104313, https://doi.org/10.1016/j.cageo.2019.104313, 2020.

Špelić, M., Kovács, Á., Saftić, B., and Sztanó, O.: Competition of deltaic feeder systems reflected by slope progradation: a high-resolution example from the Late Miocene-Pliocene, Drava Basin, Croatia, International Journal of Earth Sciences, https://doi.org/10.1007/s00531-023-02290-w, 2023.

Stegena, L., Géczy, B., and Horváth, F.: Late Cenozoic evolution of the Pannonian basin, Tectonophysics, 26, 71–90, https://doi.org/10.1016/0040-1951(75)90114-6, 1975.

Sun, Z., Yang, S., Zhang, F., Lu, J., Wang, R., Ou, X., Lei, A., Han, F., Cen, W., Wei, D., and Liu, M.: A Reconstructed Method of Acoustic Logging Data and Its Application in Seismic Lithological Inversion for Uranium Reservoir, Remote Sens (Basel), 15, 1260, https://doi.org/10.3390/rs15051260, 2023.

Thimm, G. and Fiesler, E.: High-order and multilayer perceptron initialization, IEEE Trans Neural Netw, 8, 349–359, https://doi.org/10.1109/72.557673, 1997.

Velić, J.: Geologija nafte [Petroleum Geology], University of Zagreb, Faculty of Mining, Geology and Petroleum Engineering, Zagreb, 342 pp., 2007.

Velić, J., Krasić, D., and Kovačević, I.: Exploitation, reserves and transport of natural gas in the Republic of Croatia, Tehnicki Vjesnik-Technical Gazette, 13, 633–641, 2012a.

Velić, J., Malvić, T., Cvetković, M., and Vrbanac, B.: Reservoir geology, hydrocarbon reserves and production in the Croatian part of the pannonian Basin System, Geologia Croatica, 65, https://doi.org/10.4154/gc.2012.07, 2012b.

Wacha, L., Galović, L., Koloszár, L., Magyari, Á., Chikán, G., and Marsi, I.: The chronology of the Šarengrad II loess-palaeosol section (Eastern Croatia), Geologia Croatica, 66, 191–203, https://doi.org/10.4154/GC.2013.18, 2013.

Wang, J., Cao, J., You, J., Cheng, M., and Zhou, P.: A method for well log data generation based on a spatio-temporal neural network, Journal of Geophysics and Engineering, 18, 700–711, https://doi.org/10.1093/jge/gxab046, 2021.

Yadav, A., Yadav, K., and Anirbid Sircar: Feedforward Neural Network for joint inversion of geophysical data to identify geothermal sweet spots in Gandhar, Gujarat, India, Energy Geoscience, 2, 189–200, https://doi.org/10.1016/j.engeos.2021.01.001, 2021.

Zeng, L., Ren, W., Shan, L., Huo, F., and Meng, F.: Lithology spatial distribution prediction based on recurrent neural network with Kriging technology, J Pet Sci Eng, 214, 110538, https://doi.org/10.1016/j.petrol.2022.110538, 2022.

Zhang, D., Chen, Y., and Meng, J.: Synthetic well logs generation via Recurrent Neural Networks, Petroleum Exploration and Development, 45, 629–639, https://doi.org/10.1016/S1876-3804(18)30068-5, 2018.