Skip to main content
Log in

Machine learning assisted lithology prediction using geophysical logs: A case study from Cambay basin

  • Published:
Journal of Earth System Science Aims and scope Submit manuscript

Abstract

Identification and characterisation of reservoir facies is a prime factor in delimiting the hydrocarbon potential zones of a reservoir for hydrocarbon exploration. The geophysical logs, which are physical parameters of reservoir facies measured in the vicinity of boreholes, play a crucial role in the interpretation of reservoir facies. The present study deals with the identification of the lithology of the Limbodara oil field in the Cambay basin using machine learning (ML) techniques on geophysical logs. The supervised techniques of machine learning, such as support vector machines (SVM), artificial neural networks (ANN), and k-nearest neighbours (kNN), are used as nonlinear classifiers for the identification of lithology from nonlinear geophysical logs. The hyperparameters of the ML model are optimised using the grid search cross-validation (CV) method to increase the performance of the model, as evaluated by confusion matrix, area under receiver operating characteristics curve (AUC), precision, recall, and F1 score. The ML model used five geophysical parameters of two wells with four known distinguished lithologies (Class-A, Class-B, Class-C, and Class-D) for optimisation and training of the model. The optimised and trained model for each lithology for kNN, SVM, and ANN shows an overall correct prediction of true values with 85.4, 87.0, and 88.9%, respectively, from the confusion matrix. Apart from this, the receiver operative characteristics (ROC) also show that the overall area under the curve for each lithology is greater than 90%, and other evaluation parameters such as precision, recall, and F1 score show accuracy greater than 84%, except for the cases of Class C and Class D from SVM and ANN. Thus, the accuracy of each model from evaluation parameters suggests that the combined analysis of different ML models offers to select the optimised ML model for better results and validation to achieve and model the lithology with better precision.

Highlights

  • A way out for obtaining litholog supplements at uncored section in boreholes

  • Established ML assisted mapping function between wireline logs and lithologs

  • Predicted litholog sequence with secure level of accuracy (>80%)

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13

Similar content being viewed by others

References

  • Abiodun O I, Jantan A, Omolara A E, Dada K V, Mohamed N A and Arshad H 2018 State-of-the-art in artificial neural network applications: A survey; Heliyon 4(11) e00938, https://doi.org/10.1016/j.heliyon.2018.e00938.

    Article  Google Scholar 

  • Amoura S, Gaci S, Barbosa S, Farfour M and Bounif M A 2022 Investigation of lithological heterogeneities from velocity logs using EMD-Hölder technique combined with multifractal analysis and unsupervised statistical methods; J. Pet. Sci. Eng. 208 109588, https://doi.org/10.1016/j.petrol.2021.109588.

    Article  CAS  Google Scholar 

  • Barbosa L F F M, Nascimento A, Mathias M H and de Carvalho Jr J A 2019 Machine learning methods applied to drilling rate of penetration prediction and optimisation – A review; J. Pet. Sci. Eng. 183 106332.

    Article  CAS  Google Scholar 

  • Bhattacharya S, Carr T R and Pal M 2016 Comparison of supervised and unsupervised approaches for mudstone lithofacies classification: Case studies from the Bakken and Mahantango–Marcellus Shale, USA; J. Nat. Gas Sci. Eng. 33 1119–1133.

    Article  CAS  Google Scholar 

  • Biswas S K 1987 Regional tectonic framework structure and evolution of the western marginal basins of India; Tectonophys. 135 307–327.

    Article  Google Scholar 

  • Borsaru M, Zhou B, Aizawa T, Karashima H and Hashimoto T 2006 Automated lithology prediction from PGNAA and other geophysical logs; Appl. Radiat. Isot. 64 272–282.

    Article  CAS  Google Scholar 

  • Bressan T S, de Souza M K, Girelli T J and Junior F C 2020 Evaluation of machine learning methods for lithology classification using geophysical data; Comput. Geosci. 139 104475.

    Article  Google Scholar 

  • Busch J M, Fortney W G and Berry L N 1987 Determination of lithology from well logs by statistical analysis; SPE Form. Eval. 2 412–418.

    Article  Google Scholar 

  • Chandra K, Mishra C S, Samanta U Gupta and A Mehrotra K L 1994 Correlation of different maturity parameters in the Ahmedabad–Mehsana block of the Cambay basin; Org. Geochem. 21 313–321.

  • Chang C-C and Lin C-J 2011 LIBSVM: A library for support vector machines; ACM Trans. Intell. Syst. Technol. 2 1–27.

    Article  Google Scholar 

  • Chen G and Cheng Q 2017 Fractal density modeling of crustal heterogeneity from the KTB deep hole; J. Geophys. Res. Solid Earth 122 1919–1933, https://doi.org/10.1002/2016JB013684.

    Article  Google Scholar 

  • Chen W, Yang L, Zha B, Zhang M and Chen Y 2020 Deep learning reservoir porosity prediction based on multilayer long short-term memory network; Geophysics 85 WA213–WA225.

    Article  Google Scholar 

  • Dramsch J S 2020 70 years of machine learning in geoscience in review; Adv. Geophys. 61 1–55.

    Article  Google Scholar 

  • Fajana A O, Ayuk M A and Enikanselu P A 2019 Application of multilayer perceptron neural network and seismic multiattribute transforms in reservoir characterisation of Pennay field Niger Delta; J. Pet. Explor. Prod. Technol. 9 31–49.

    Article  CAS  Google Scholar 

  • Fallon G N, Fullagar P K and Zhou B 2000 Towards grade estimation via automated interpretation of geophysical borehole logs; Explor. Geophys. 31 236–242.

    Article  Google Scholar 

  • Fullagar P K, Zhou B and Fallon G N 1999 Automated interpretation of geophysical borehole logs for orebody delineation and grade estimation; Miner. Resour. Eng. 8 269–284.

    Article  Google Scholar 

  • Fullagar P K, Zhou B and Biggs M 2004 Stratigraphically consistent autointerpretation of borehole data; J. Appl. Geophys. 55 91–104.

    Article  Google Scholar 

  • Ghosh S, Chatterjee R and Shanker P 2016 Estimation of ash moisture content and detection of coal lithofacies from well logs using regression and artificial neural network modelling; Fuel 177 279–287.

    Article  CAS  Google Scholar 

  • Jaadi Z 2019 When and why to standardise your data; https://builtin.com/data-science/when.

  • Keynejad S, Sbar M L and Johnson R A 2019 Assessment of machine-learning techniques in predicting lithofluid facies logs in hydrocarbon wells; Interpretation 7 SF1–SF13.

    Article  Google Scholar 

  • Kitzig M C, Kepic A and Kieu D T 2017 Testing cluster analysis on combined petrophysical and geochemical data for rock mass classification; Explor. Geophys. 48 344–352.

    Article  CAS  Google Scholar 

  • Kumar T, Kumar N and Rao G S 2022 Lithology prediction from well log data using machine learning techniques: A case study from Talcher coalfield, Eastern India; J. Appl. Geophys. 199 104605, https://doi.org/10.1016/j.jappgeo.2022.104605.

    Article  Google Scholar 

  • Lanning E N and Johnson D M 1983 Automated identification of rock boundaries: An application of the Walsh transform to geophysical well-log analysis; Geophysics 48 197–205.

    Article  Google Scholar 

  • Lary D J, Alavi A H, Gandomi A H and Walker A L 2016 Machine learning in geosciences and remote sensing; Geosci. Frontiers 7 3–10.

    Article  Google Scholar 

  • Liu J J and Liu J-C 2021 An intelligent approach for reservoir quality evaluation in tight sandstone reservoir using gradient boosting decision tree algorithm – A case study of the Yanchang Formation, mid-eastern Ordos Basin, China; Mar. Pet. Geol. 126 104939, https://doi.org/10.1016/j.marpetgeo.2021.104939.

    Article  Google Scholar 

  • López M and Aldana M 2007 Facies recognition using wavelet based fractal analysis and waveform classifier at the Oritupano-A Field, Venezuela; Nonlinear Process. Geophys. 14 325–335.

    Article  Google Scholar 

  • MacLEOD N 2019 Artificial intelligence & machine learning in the earth sciences; Acta Geol. Sin. Ed. 93 48–51.

    Article  Google Scholar 

  • Maiti S and Tiwari R K 2005 Automatic detection of lithologic boundaries using the Walsh transform: A case study from the KTB borehole; Comput. Geosci. 31 949–955.

    Article  Google Scholar 

  • Mehrotra R B and Ramakrishna V 1980 A relook in the stratigraphy and hyrocarbon occurrences of North Cambay Basin with special reference to Kadi Formation; Unpubl. Report ONGC Ahmedabad.

  • Meshalkin Y, Shakirov A, Orlov D and Koroteev D 2020 Well-logging based lithology prediction using Machine Learning; In: Data science in oil & gas, European Association of Geoscientists & Engineers, pp. 1–5.

  • Morris S 2022 Data normalisation: Definition importance and advantages; https://coresignal.com/blog/data-normalization/.

  • Mucherino A, Papajorgji P and Pardalos P M 2009 Data mining in agriculture; Springer Science & Business Media.

  • Mukherjee B and Sain K 2019 Bed boundary identification from well log data using Walsh transform technique: A case study from NGHP Expedition-02 in the Krishna–Godavari basin, India; J. Earth Syst. Sci. 128 214, https://doi.org/10.1007/s12040-019-1240-4.

    Article  CAS  Google Scholar 

  • Mukherjee B and Sain K 2021 Vertical lithological proxy using statistical and artificial intelligence approach: A case study from Krishna–Godavari Basin, offshore India; Mar. Geophys. Res. 42 3, https://doi.org/10.1007/s11001-020-09424-8.

    Article  Google Scholar 

  • Mukherjee B and Sain K 2023 Semi-automated rock layer recognition from borehole log data using combined wavelet and Fourier transform: A case study in the KG basin, India; J. Geol. Soc. India 99 1659–1670, https://doi.org/10.1007/s12594-023-2522-7.

    Article  Google Scholar 

  • Mukherjee B, Srivardhan V and Roy P N S 2016 Identification of formation interfaces by using wavelet and Fourier transforms; J. Appl. Geophys. B 128 140–149, https://doi.org/10.1016/j.jappgeo.2016.03.025.

  • Negi A S, Sahu S K, Thomas P D, Raju D S A N, Chand R and Ram J 2006 Fusing geologic knowledge and seismic in searching for subtle hydrocarbon traps in India’s Cambay Basin; Lead. Edge 25 872–880, https://doi.org/10.1190/1.2221366.

    Article  Google Scholar 

  • Oyler D C, Mark C and Molinda G M 2010 In situ estimation of roof rock strength using sonic logging; Int. J. Coal Geol. 83 484–490.

    Article  CAS  Google Scholar 

  • Pandey J, Singh N P, Krishna B R, Sharma D D, Paraikh A K and Nath S S 1993 Lithostratigraphy of Indian Petroliferous Basins. Document III: Cambay Basin KDM; Inst. Pet. Explor. ONGC Dehradun Allied Printers, 166p.

  • Peng J, Han H, Xia Q and Li B 2018 Evaluation of the pore structure of tight sandstone reservoirs based on multifractal analysis: A case study from the Kepingtage Formation in the Shuntuoguole uplift, Tarim Basin, NW China; J. Geophys. Eng. 15 1122–1136.

    Article  Google Scholar 

  • Prajapati R and Singh U K 2020 Delineation of stratigraphic pattern using combined application of wavelet-Fourier transform and fractal dimension: A case study over Cambay Basin, India; Mar. Pet. Geol. 120 104562, https://doi.org/10.1016/j.marpetgeo.2020.104562.

    Article  Google Scholar 

  • Prajapati R, Kumar R and Singh U K 2023 Assessment of reservoir heterogeneities and hydrocarbon potential zones using wavelet-based fractal and multifractal analysis of geophysical logs of Cambay basin, India; Mar. Pet. Geol. 160 106633, https://doi.org/10.1016/j.marpetgeo.2023.106633.

    Article  Google Scholar 

  • Pramanik A G, Singh V, Vig R, Srivastava A K and Tiwary D N 2004 Estimation of effective porosity using geostatistics and multiattribute transforms: A case study; Geophysics 69 352–372.

    Article  Google Scholar 

  • Prokoph A and Agterberg F P 2000 Wavelet analysis of well-logging data from oil source rock Egret Member offshore eastern Canada; Am. Assoc. Pet. Geol. Bull. 84 1617–1632.

    Google Scholar 

  • Qiuming C 2016 Fractal density and singularity analysis of heat flow over ocean ridges; Sci. Rep. 6 1–10, https://doi.org/10.1038/srep19167.

    Article  CAS  Google Scholar 

  • Raju A T R 1968 Geological evolution of Assam and Cambay Tertiary basins of India; Am. Assoc. Pet. Geol. Bull. 52 2422–2437.

    Google Scholar 

  • Ren X, Hou J, Song S, Liu Y, Chen D, Wang X and Dou L 2019 Lithology identification using well logs: A method by integrating artificial neural networks and sedimentary patterns; J. Pet. Sci. Eng. 182 106336.

    Article  CAS  Google Scholar 

  • Saini A 2023 Guide on Support Vector Machine (SVM) Algorithm; https://www.analyticsvidhya.com/blog/2021/10/support-vector-machinessvm-a-complete-guide-for-beginners/.

  • Sakrikar C and Deshpande K 2020 Use of machine learning and artificial intelligence in earth science; In: ICSITS–2020 Conference Proceedings ICSITS, Int. J. Eng. Res. Technol. (IJERT).

  • Schmitt P, Veronez M R, Tognoli F M W, Todt V, Lopes R da C and Silva C A U da 2013 Electrofacies modelling and lithological classification of coals and mud-bearing fine-grained siliciclastic rocks based on neural network; repositorio.ufc.br.

  • Serra O and Abbott H T 1980 The contribution of logging data to sedimentology and stratigraphy; SPE 9270, 55th Annual Fall Technical Conference and Exhibition, Dallas, Texas.

  • Singh U K, Prajapati R and Kumar T 2018 Geological stratigraphy and spatial distribution of microfractures over the Costa Rica convergent margin, Central America – A wavelet-fractal analysis; Geosci. Instrum. Methods Data Syst. 7 179–187, https://doi.org/10.5194/gi-7-179-2018.

    Article  Google Scholar 

  • Sun Z, Jiang B, Li X, Li J and Xiao K 2020 A data-driven approach for lithology identification based on parameter-optimised ensemble learning; Energies 13 3903.

    Article  Google Scholar 

  • Tabasi S, Soltani P, Rajabi M, Wood D A, Davoodi S, Ghorbani H, Mohamadian N and Ahmadi M 2022 Optimised machine learning models for natural fractures prediction using conventional well logs; Fuel 326 124952, https://doi.org/10.1016/j.fuel.2022.124952.

    Article  CAS  Google Scholar 

  • Tiwari R K 1987 A Walsh spectral comparison of oxygen (δ18O) and carbon isotope (δ13C) variations of the Pleistocene bore hole (Eureka 67–135) from the Gulf of Mexico and their orbital significance; Mar. Geol. 78 167–174.

    Article  CAS  Google Scholar 

  • Vapnik V 1999 The nature of statistical learning theory; Springer Science & Business Media.

  • Vidiyala R 2020 Normalisation vs. standardisation; https://towardsdatascience.com/normalization-vs-standardization-cb8fe15082eb.

  • Wang G and Carr T R 2012 Methodology of organic-rich shale lithofacies identification and prediction: A case study from Marcellus shale in the Appalachian basin; Comput. Geosci. 49 151–163.

    Article  CAS  Google Scholar 

  • Wolf M and Pelissier-Combescure J 1982 FACIOLOG-automatic electrofacies determination; SPWLA 23rd Annual Logging Symposium, Society of Petrophysicists and Well-Log Analysts.

  • Xie Y, Zhu C, Zhou W, Li Z, Liu X and Tu M 2018 Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances; J. Pet. Sci. Eng. 160 182–193.

    Article  CAS  Google Scholar 

  • Xu Z, Shi H, Lin P and Liu T 2021 Integrated lithology identification based on images and elemental data from rocks; J. Pet. Sci. Eng. 205 108853.

    Article  CAS  Google Scholar 

  • Yıldırım S 2020 Follow How Important is the K in KNN Algorithm; https://towardsdatascience.com/how-important-is-the-k-in-knn-algorithm3b6fce726110.

  • Zhang J, He Y, Zhang Y, Li W and Zhang J 2022 Well-logging-based lithology classification using machine learning methods for high-quality reservoir identification: A case study of Baikouquan Formation in Mahu area of Junggar Basin, NW China; Energies 15 3675.

    Article  Google Scholar 

  • Zhou B, Guo H, Hatherly P and Poulsen B 2001 Automated geotechnical characterisation from geophysical logs: Examples from Southern Colliery, Central Queensland; ASEG Ext. Abstr. 1–4.

  • Zhou K, Zhang J, Ren Y, Huang Z and Zhao L 2020 A gradient boosting decision tree algorithm combining synthetic minority oversampling technique for lithology identification; Geophysics 85 WA147–WA158.

    Article  Google Scholar 

Download references

Acknowledgements

Authors are grateful to the Director of the Wadia Institute of Himalayan Geology in Dehradun for granting permission to publish this paper. They are also thankful to the Director, IIT-ISM, for permission to carry out the research work and use available academic resources. The authors are grateful to the Director General of Hydrocarbon (DGH) and Oil and Natural Gas Corporation (ONGC), India, for providing the necessary data to carry out research work and permission to publish the work. KS acknowledges DST-SERB for JC Bose National Fellowship. The authors are thankful to the anonymous reviewers, Editor-in-Chief, Prof. Somnath Dasgupta, and Guest Editor Dr. Upasana Swaroop Banerji for their constructive suggestions to improve the manuscript within the necessary time and effort.

Author information

Authors and Affiliations

Authors

Contributions

RP: Written original draft and data curation. BM: Conceptualisation, data curation, software, methodology, editing, and finalising manuscript. UKS: Resources & project management, validation, and editing manuscript. KS: Supervision and editing.

Corresponding author

Correspondence to Bappa Mukherjee.

Additional information

Communicated by Upasana S Banerji

This article is part of the Topical Collection: AI/ML in Earth System Sciences

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Prajapati, R., Mukherjee, B., Singh, U.K. et al. Machine learning assisted lithology prediction using geophysical logs: A case study from Cambay basin. J Earth Syst Sci 133, 108 (2024). https://doi.org/10.1007/s12040-024-02326-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12040-024-02326-y

Keywords

Navigation