Machine learning for the prediction and Analysis of Bouguer Gravity anomaly of the Kiri uplift in Congo sedimentary Basin

Authors

  • Rais SEKI LENZO Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Munezero Ntibahanana Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Tondozi Keto Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Moise Luemba Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Gradi Kalonji Lelo Faculty of Oil, Gas and Renewable Energies, University of Kinshasa, DR Congo
  • Emmanuel Balu Phoba Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Kevin Lumpungu Lutumba Centre for Research in Géophysique (C.R.G.), Kinshasa, RD Congo
  • Jeaney Lusongo Elua Faculty of Oil, Gas and Renewable Energies, University of Kinshasa, DR Congo
  • Ange Kra National Center for Remote Sensing (CNT), Kinshasa, DR Congo

DOI:

https://doi.org/10.31695/IJASRE.2022.8.7.3

Keywords:

Congo sedimentary basin, Deep learning, Geophysical inversion, Gravity anomalies, Multiple regression

Abstract

Bouguer gravity anomalies (BGA) play an important role in exploration of mineral resources. Allowing the delineation of large geological structures, BGA participate into discovery of the deposits. However, the Kiri uplift region where several oil seeps have been recognized faces sparse coverage of data due to the difficult conditions of data acquisition on the field. This situation increases the non-uniqueness and nonlinearity problems of the solution using inverse methods. Although, potentially good at quantifying uncertainties, inverse approaches involve enormous computational tasks. We used machine-learning algorithms to predict and analyze gravity data in Kiri uplift region. The algorithms learned to perform as a multiple regression. During training steps, each independent variable included X and Y coordinates, digital elevation model (DEM) and geology. BGA values calculated by experts were provided as the dependent variables. K-fold cross-validation has been used ensure the models are well fit. Since the well-trained algorithms should result in small losses and errors, we experimented several optimizers. By comparison, testing results showed that deep neural network-based algorithm (DNN) has proven to be the most efficient with 5.37 Mean Squared Error and 1.75 Mean Absolute Error as model metrics. DNN showed the most accurate prediction, which, together with the measured BGA reported strongest Pearson correlation coefficient of 0.996. In addition, analysis showed that DNN result is one that conforms perfectly to the regional geology information of the study area. Machine learning algorithms proved their effectiveness to predict and analyze BGA in the study area.ML algorithms proved their effectiveness to predict BGA where measurements lackedThe joint analysis of predicted, measured and regional lithology meets expectationsAs predictors are X, Y, DEM and, lithology, we can customize the acquisition grids

References

W. Hinze, R. Von Frese and A. Saad, “The gravity method,” in Gravity and Magnetic Exploration: Principles, Practices, and Applications, Cambridge, Cambridge University Press, 2013, pp. 19-37.

L. Thomas R. and N. Misac N., Fundamentals of gravity exploration, Tulsa: Society of Exploration Geophysicists, 2012.

H. Lyatsky, “Gravity And Magnetic Geophysical Methods In Oil Exploration,” Exploration & Production Magazine, pp. 3-6, 10 March 2016.

Z. Ming-hua, Q. Ji-hua, Z. Geng-xin and L. Xue-yi, “Regional gravity survey and application in oil and gas exploration in China,” China Geology, vol. 2, no. 3, pp. 382-390, 2019.

K. Tondozi, M. J. Ntibahanana, M. Muyer, K. Bakamubia and M. Manzuma, “Spatial analysis of gravity anomalies in Cuvette Centrale sedimentary basin and contribution to the modeling of its petroleum system,” International Journal of Innovation and Applied Studies, vol. 21, no. 3, pp. 522-535, 2017.

K. Tondozi, S. Maneno, S. K. Bahati, J. M. Ntibahanana and J. M. Ndombasi, “Interpretation of Magnetic Data for the Determination of Geological Structures in Southern Part of the Cuvette-Centrale Sedimentary Basin,” International Journal of Advances in Scientific Research and Engineering, vol. 6, no. 2, pp. 145-155, February 2020.

S. Lawrence and M. Makazu, “Zaire's Central basin: prospectivity outlook,” Oil Gas J., vol. 86, no. 38, pp. 105-108, 1888.

M. Daly, S. Lawrence, D. Kimun'a and M. Binga, “Late Paleozoic deformation in central Africa: a result of distant collision,” Nature, pp. 605-607, 1991.

P. Hoffman, “The breakup of Rodinia, birth of Gondwana, true poar wander and the snowball Earth,” J. Afr. Eart Sci, pp. 17-34, 1999.

W. Kennedy, “The Structural Differentiation of Africa in the Pan-African (+/-500m.y.) tectonic episode.,” Research Institute for African Geology, Leeds Univ. 8th Ann. Rep., pp. 48-49, 1964.

A. Kroner, A. Collins, E. Hegner, A. Willner, S. Muhongo and K. Kehelpannala, “The East African Orogen: New Zircon and Nd Ages and implications for Rodinia and Gondwana supercontinent formation and dispersal,” Gondwana Res., pp. 179-181, 2001.

J. Visser and H. Praekelt, “Subduction, mega-shear systems and the late Paleozoic basin development in the African segment of Gondwana,” Geol. Rund., pp. 632-646, 1996.

D. Delvaux, “Tectonic and palaeostress evolution of the Tanganyika-Rukwa-Malawi rif segment, East African Rift System,” Me.m.Mus. National Hist. Nat., pp. 545-567, 2001.

A. Newton, R. Shone and P. Booth, “The Cape fold belt,” Geol. Soc. S. Africa, pp. 521-530, 2006.

F. Grant and G. West, Interpretation theory in applied geophysics, McGrawHill : Book Co., 1965.

P. Vladimir, “Deep learning electromagnetic inversion with convolutional neural networks,” Geophysical Journal International, vol. 218, p. 817–832, 2019.

M. Everett and C. Weiss, “Geological noise in near-surface electronmagnetic induction data,” Geophys. Res. Lett., vol. 29, no. 1, pp. 101-104, 2002.

B. Jason, Deep Learning with Python, Develop Deep Learning Models on Theano and TensorFlow using Keras, v1.18 ed., Melbourne: Machine Learning Mastery, 2019.

W. Xinming, Y. Shi, F. Sergey, L. Luming and Uber, “Convolutional neural networks for fault interpretation in seismic images,” in SEG International Exposition and 88th Annual Meeting, 2018.

F. Wang, S. Chen and Y. Liu, “Deep learning for gravity and magnetic data interpolation,” in International Exposition and 89th Annual Meeting, Texas, 2019.

K. Noh, D. Yoon and J. Byun, “Imaging subsurface resistivity structure from airborne electromagnetic induction data using deep neural network,” Exploration Geophysics, pp. 1834-7533, 2019.

S. Maiti, R. K. Ch., P. Sarkar, T. R. K. and U. Srinu, “Interface depth modelling of gravity data and altitude variations: a Bayesian neural network approach,” Neural Computing and Applications, vol. 32, p. 3183–3202, 2020.

P. Dell'Aversana, B. Ciurlo and S. Colombo, “Integrated Geophysics and Machine Learning for Risk Mitigation in Exploration Geosciences,” in 80th EAGE Conference & Exhibition 2018, Copenhagen, Denmark, 2018.

C. Laudon, “the 2019 Permian Basin Geophysical Society's 60th Annual Exploeration Meeting,” Geophysical Insights, pp. 49-56, 2019.

Nealon, E. Wang and Jeff, “Applying machine learning to 3D seismic image denoising and enhancement,” SEG, pp. 131-139, 2019.

P. Bas, H. Eldad and G. Justin, “Neural networks for geophysicists and their application to seismic data interpretation,” SEG, pp. 534-540, 2019.

Z. Wang, H. Di, M. A. Shafiq, Y. Alaudah and G. AlRegib, “Successful leveraging of image processing and machine learning in seismic structural interpretation: A review,” SEG, pp. 451-461, 2018.

A. Guitton, “3D convolutional neural networks for fault interpretation,” 2018.

X. Wu, S. Yunzhi, S. Fomel, L. Liang and Uber, “Convolutional neural networks for fault interpretation in seismic images,” in SEG International Exposition and 88th Annual Meeting, 2018.

Y. Shi, X. Wu and S. Fomel, “SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network,” SEG, pp. 112-122, 2019.

A. U. Waldeland, A. C. Jensen, L.-J. Gelius and A. H. S. Solberg, “Convolutional neural networks for automated seismic interpretation,” SEG, pp. 529-536, 2018.

L. Liu, L. Rong, L. Jianhai and W. Yang, “Seismic Lithofacies Computation Method Based on Deep Learning,” CGS/SEG International Geophysical Conference, pp. 649-652, 2018.

S. D. Mohaghegh, S. M. Al-Fattah and A. S. Popa, Artificial Intelligence and Data Mining Applications in the Exploration and Production Industry, USA: Society of Petroleum Engineers SPE, 2018.

R. E. Neapolitan and X. Jiang, Artificial Intelligence With an Introduction to Machine Learning, 2nd ed., Boca Raton: Taylor & Francis Group, LLC, 2018.

Z. Peng, L. Chengyan, L. Xiaolei, H. Weicong, W. Yulei and a. Z. Hualian, “Types of Diagenetic Facies of Tight Sandstone Reservoir and Its Quantitative Identification by Well Log Data,” The Open Petroleum Engineering Journal, pp. p308-315, 2015.

M. Venkatesan, “Artificial Intelligence vs. Machine Learning vs. Deep Learning,” 7 May 2018. [Online]. Available: https://www.datasciencecentral.com/profiles/blogs/artificial-intelligence-vs-machine-learning-vs-deep-learning.

J. Brownlee, 14 Different Types of Learning in Machine Learning, Melbourne, Australia: Machine Learning Mastery, 2019.

S. Manohar, Mastering Machine Learning with Python in Six Steps: a practical implementation guide to predictive data analytics using python, Bangalore, Karnataka, India: Apress, 2017.

I. Goodfellow, I. Bengio and A. Courville, “Deep Learning (Adaptative Computation and Machine Learning Serries),” MIT Press, 2016.

C. M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics), Germany: Spinger, 2006.

S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed., Pearson, 2015.

Alvishnu, “Generalisation and Overfitting,” Machine Learning & AI Solutions in Hyderabad, 3 February 2017. [Online]. Available: https://wp.wwu.edu/machinelearning/2017/01/22/generalization-and-overfitting/. [Accessed 4 February 2021].

P. Gupta, “Balancing Bias and Variance to Control Errors in Machine Learning,” 5 May 2017. [Online]. Available: https://towardsdatascience.com/balancing-bias-and-variance-to-control-errors-in-machine-learning-16ced95724db. [Accessed 4 February 2021].

M. Sharma, “Generalization in Machine Learning for better performance,” 29 April 2019. [Online]. Available: https://mathanrajsharma.medium.com/generalization-in-machine-learning-for-better-performance-51bed74a3820. [Accessed 4 February 2021].

L. Bottou and O. Bousquet, “The Tradeoff of Large Scale Learning,” in Optimization for Machine Learning, Cambridge, MIT Press, 2012, pp. 351-368.

L. Bottou, “Online Algorithms and Stochastic Approximations,” Online Learning and Neural Networks, 1998.

H. Geoffrey, “Divide the gradient by a running average of its recent magnitude,” in Lecture 6e rmsprop, Canada, 2020.

D. Kingma and J. L. Ba, “Adam: a Method for Stochastic Optimization,” in International Conference on Learning Representations, 2015.

M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” Advances in Neural Information Processing Systems 30 (NIPS), vol. 30, 2017.

T. Dozat, “Incorporating Nesterov Momentum into Adam,” ICLR Workshop, pp. 1-4, 2016.

A. Mishra, “Metrics to Evaluate your Machine Learning Algorithm,” Towards Data Science, 24 February 2018. [Online]. Available: https://towardsdatascience.com/metrics-to-evaluate-your-machine-learning-algorithm-f10ba6e38234. [Accessed 4 February 2021].

J. L. Mallet, “Numerical Earth Models,” European Association of Geoscientists and Engineers (EAGE Publications), 2008.

J. R. Fanchi, “Shared Earth Modelling: Methodologies for Integrated Reservoir Simulations,” Gulf Professional Publishing (Elsevier imprint), pp. 10-306, 2002.

N. Srivastava, G. Hinton, A. S. I. Krizhevsky and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929-1958, 2014.

D. John, H. Elad and S. Yoram, “Adaptive Subgradient Methods for Online Learning and Stochastic Optimization,” JMLR, vol. 12, pp. 2121-2159, 2011.

L. Nettleton, Elementary gravity and magnetics for geologist and seismologists, Tulsa: Society of Exploration Geophysicists, 1971, pp. 24-46.

D. Parasnis, Principles of applied geophysics, New York, USA: Chapman and Hall, 1986.

E. Kadima, D. Delvaux, N. Sebagenzi, L. Tack and S. Kabeya, “Structure and geological history of the Congo basin: An integrated interpretation of gravity, magnetic and reflection seismic data,” Bassin Research, vol. 23, pp. 499-527, 2011.

A. Ohri, “8 Popular Regression Algorithms In Machine Learning Of 2021,” 16 February 2017. [Online]. Available: https://www.jigsawacademy.com.

J. Brownlee, Understand your data, create accurate models and work projects end-to-end., Melbourne, Australia: Machine Learning Mastery With Python, 2016.

R. Sebastian and M. Vahid, Python Machine Learning, vol. 2, Birmingham: Packt Publishing Ltd, 2017.

R. Rudolph, Step-by-Step Guide To Implement Machine Learning Algorithms with Python, 2018.

D. Michie and D. Spiegelhalter, Machine Learning, Neural and Statistical Classification, C.C. Taylor, 1994.

H. Lyatsky, “Magnetic and Gravity Methods in Mineral Exploration: the Value of Well-Rounded Geophysical Skills,” Geoscience Research & Consulting Ltd, pp. 30-35, October 2010.

E. Kadima, S. Sebagenzi and F. Lucazeau, “A Proterozoic-rift origin for the structure and the evolution of the cratonic Congo basin,” Earth and Planetary Science Letters, pp. EPSL-10785; No of Pages 11, 2011.

D. Amit, “The K-Fold Cross Validation in Machine Learning,” 5 September 2020. [Online]. Available: https://www.knowledgehut.com.

B. Jason, A Gentle Introduction to k-fold Cross-Validation, Melburne: Machine Learning Mastery, 2020.

S. Sarath, “Pairplot vusualization,” 29 September 2019. [Online]. Available: https://medium.com.

Zach, “How to Calculate Correlation in Python,” 3 July 2020. [Online]. Available: https://www.statology.org.

D. A. Otchere, T. O. A. Ganat, R. Gholami and S. Ridha, “Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: Comparative analysis of ANN and SVM models,” Journal of Petroleum Science and Engineering, p. 108182, 2020.

D. Grana, L. Azevedo and M. Liu, “A comparison of deep machine learning and Monte Carlo methods for facies classification from seismic data,” Geophysics, vol. 85, no. 4, pp. WA41-WA52, 2020.

Y. Kim, R. Hardisty, E. Torres and J. Marfurt, “Seismic facies classification using random forest algorithm,” in SEG Technical Program Expanded Abstracts, 2018.

L. Zhang and C. Zhan, “Machine Learning in Rock Facies Classification: An Application of XGBoost,” in International Geophysical Conference, Qingdao, 2017.

Dell'Aversana, “Comparison of different Machine Learning algorithms for lithofacies classification from well logs,” Bollettino di Geofisica Teorica ed Applicata, vol. 60, no. 1, pp. 69-80, 2019.

T. Zhao and P. Mukhopanpadhyay, “A fault-detection workflow using deep learning and image processing,” in 88th Annual International Meeting, Texas, 2018.

A. Apoorva, “Loss Functions and Optimization Algorithms Demystified,” 29 September 2017. [Online]. Available: https://medium.com. [Accessed 4 February 2021].

Downloads

How to Cite

SEKI LENZO, R., Munezero Ntibahanana, Tondozi Keto, Moise Luemba, Gradi Kalonji Lelo, Emmanuel Balu Phoba, Kevin Lumpungu Lutumba, Jeaney Lusongo Elua, & Ange Kra. (2022). Machine learning for the prediction and Analysis of Bouguer Gravity anomaly of the Kiri uplift in Congo sedimentary Basin. International Journal of Advances in Scientific Research and Engineering (IJASRE), ISSN:2454-8006, DOI: 10.31695/IJASRE, 8(7), 24–46. https://doi.org/10.31695/IJASRE.2022.8.7.3

Issue

Vol. 8 No. 7: IJASRE July-2022

Section

Articles

License

Copyright (c) 2022 Rais SEKI LENZO, Munezero Ntibahanana, Tondozi Keto, Moise Luemba, Gradi Kalonji Lelo, Emmanuel Balu Phoba, Kevin Lumpungu Lutumba, Jeaney Lusongo Elua, Ange Kra

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.