Extreme Learning Machine combined with a Differential Evolution algorithm for lithology identification

Camila Martins Saporetti; Grasiele Regina Duarte; Tales Lima Fonseca; Leonardo Goliatt da Fonseca; Egberto Pereira

doi:10.22456/2175-2745.80702

Authors

Camila Martins Saporetti Federal University of Juiz de Fora
Grasiele Regina Duarte Federal University of Juiz de Fora
Tales Lima Fonseca Federal University of Juiz de Fora
Leonardo Goliatt da Fonseca Federal University of Juiz de Fora
Egberto Pereira Rio de Janeiro State University

DOI:

https://doi.org/10.22456/2175-2745.80702

Keywords:

Extreme Learning Machines, Differential Evolution, Lithology

Abstract

Lithology identification, obtained through the analysis of several geophysical properties, has an important role in the process of characterization of oil reservoirs. The identification can be accomplished by direct and indirect methods, but these methods are not always feasible because of the cost or imprecision of the results generated. Consequently, there is a need to automate the procedure of reservoir characterization and, in this context, computational intelligence techniques appear as an alternative to lithology identification. However, to acquire proper performance, usually some parameters should be adjusted and this can become a hard task depending on the complexity of the underlying problem. This paper aims to apply an Extreme Learning Machine (ELM) adjusted with a Differential Evolution (DE) to classify data from the South Provence Basin, using a previously published paper as a baseline reference. The paper contributions include the use of an evolutionary algorithm as a tool for search on the hyperparameters of the ELM. In addition, an activation function recently proposed in the literature is implemented and tested. The computational approach developed here has the potential to assist in petrographic data classification and helps to improve the process of reservoir characterization and the production development planning.

Downloads

Download data is not yet available.

References

VASINI, E. M. et al. Interpretation of production tests in geothermal wells with t2well-ewasg. Geothermics, v. 73, n. 1, p. 158–167, 2018.

HORROCKS, T.; HOLDEN, E.-J.; WEDGE, D. Evaluation of automated lithology classification architectures

using highly-sampled wireline logs for coal exploration. Comput. Geosci-uk., v. 83, n. 1, p. 209 – 218, 2015.

YANG, H. et al. Performance of the synergetic wavelet transform and modified k-means clustering in lithology classification using nuclear log. J. Petrol. Sci. Eng., v. 144, p. 1 – 9, 2016.

BORSARU, M. et al. Automated lithology prediction from pgnaa and other geophysical logs. Appl. Radiat. Isotopes, v. 64, n. 2, p. 272 – 282, 2006.

POUR, A. B. et al. Lithological and alteration mineral mapping in poorly exposed lithologies using landsat-8 and aster satellite data: North-eastern graham land, antarctic peninsula. Ore Geol. Rev., v. 1, n. 1, p. –, 2017.

XIE, Y. et al. Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances. J. Petrol. Sci. Eng., v. 139, n. 27, p. 182–193, 2018.

GIFFORD, C. M.; AGAH, A. Collaborative multi-agent rock facies classification from wireline well log data. Eng. Appl. Artif. Intel., v. 23, n. 7, p. 1158 – 1172, 2010.

AKINYOKUN, O. et al. Well log interpretation model for the determination of lithology and fluid contents. Pac. J. Sci. Technol., v. 10, n. 1, p. 507–517, 2009.

DONG, S.; WANG, Z.; ZENG, L. Lithology identification using kernel fisher discriminant analysis with well logs. J. Petrol. Sci. Eng., v. 143, n. 1, p. 95 – 102, 2016.

KONATE,A.A.etal.Lithologyandmineralogy recognition from geochemical logging tool data using multivariate statistical analysis. Appl. Radiat. Isotopes, v. 128, n. 1, p. 55 – 67, 2017.

RAMKUMAR, M.; BERNER, Z.; STu ̈BEN, D. Multivariate statistical discrimination of selected carbonate petrographic classifications: Implications on applicability of classification systems and predictability of petrographic

types. Chem. Erde, v. 62, n. 2, p. 145–159, 2002.

AL-ANAZI, A.; GATES, I. On the capability of support vector machines to classify lithology from well logs. Nat. Resour. Res., v. 19, n. 2, p. 125–139, 2010.

SEBTOSHEIKH, M. A.; SALEHI, A. Lithology prediction by support vector classifiers using inverted seismic attributes data and petrophysical logs as a new approach and investigation of training data set size effect on its performance in a heterogeneous carbonate reservoir. J. Petrol. Sci. Eng., v. 134, n. 1, p. 143 – 149, 2015.

CRACKNELL, M. J.; READING, A. M. Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput. Geosci-uk., v. 63, n. 1, p. 22 – 33, 2014.

HARRIS, J.; GRUNSKY, E. Predictive lithological mapping of canada’s north using random forest classification applied to geophysical and geochemical data. Comput. Geosci-uk., v. 80, n. 1, p. 9 – 25, 2015.

PLASTINO, A. et al. Combining classification and regression for improving permeability estimations from 1h nmr relaxation data. J. Appl. Geophys., v. 146, n. 1, p. 95 – 102, 2017.

ZHU, Q.-Y. et al. Evolutionary extreme learning machine. Pattern Recogn., v. 38, n. 10, p. 1759 – 1763, 2005.

YANG, W.-A.; ZHOU, Q.; TSUI, K.-L. Differential evolution-based feature selection and parameter optimisation for extreme learning machine in tool wear estimation. Int. J. Prod. Res., v. 54, n. 15, p. 4703–4721, 2016.

BAZI, Y. et al. Differential evolution extreme learning machine for the classification of hyperspectral images. IEEE Geosci. Remote Sens. Lett., v. 11, n. 6, p. 1066–1070, 2014.

SHAO, Y.; CHEN, Q. Application genetic neural network in lithology recognition and prediction: Evidence from china. In: QI, L.; ZHOU, Q. (Ed.). Intelligent Information Technology Application, 2008. Second International Symposium on. Shanghai, China: IEEE, 2008. (IITA ’08, v. 2).

AN-NAN, J.; LU, J. Studying the lithology identification method from well logs based on de-svm. In: Control

and Decision Conference, 2009. Studying the lithology identification method from well logs based on de-svm: IEEE, 2009. (CCDC, ’09).

ZOPH, P. R. anf B.; LE, Q. V. Searching for activation functions. CoRR, abs/1710.05941, n. 1, p. 1–13, 2017.

HUANG, G.-B.; ZHU, Q.-Y.; SIEW, C.-K. Extreme learning machine: a new learning scheme of feedforward neural networks. In: Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on. Budapest, Hungary: IEEE, 2004. v. 2.

STORN, R.; PRICE, K. Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. J. glob. optim., v. 11, n. 4, p. 341–359, 1997.

FOURNIER, F.; BORGOMANO, J. Critical porosity and elastic properties of microporous mixed carbonate-siliciclastic rocks. Geophysics, v. 74, n. 2, p. E93–E109, 2009.

SILVA, A. A. et al. Artificial neural networks to support petrographic classification of carbonate-siliciclastic rocks using well logs and textural information. J. Appl. Geophys., v. 117, n. 1, p. 118–125, 2015.

BRIGAUD, B. et al. Acoustic properties of ancient shallow-marine carbonates: Effects of depositional environments and diagenetic processes (middle jurassic, paris basin, france). J. Sediment. Res., v. 80, n. 9, p. 791–807, 2010.

MATONTI, C. et al. Structural and petrophysical characterization of mixed conduit/seal fault zones in

carbonates: Example from the castellas fault (se france). J. Struct. Geol., v. 39, n. 1, p. 103 – 121, 2012.

CEIA, M. A. de et al. Relationship between the consolidation parameter, porosity and aspect ratio in microporous carbonate rocks. J. of Appl. Geoph., v. 122, p. 111 – 121, 2015.

GUO, P.; CHENG, W.; WANG, Y. Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problems. Expert Syst. Appl., v. 71, n. 1, p. 57 – 68, 2017.

HUANG, G.-B. What are extreme learning machines? filling the gap between frank rosenblatt’s dream and john von neumann’s puzzle. Cogn. Comput., v. 7, n. 3, p. 263–278, 2015.

HUANG, G. et al. Trends in extreme learning machines: A review. Neural Networks, v. 61, n. Supplement C, p. 32–48, 2015.

KUHN, M.; JOHNSON, K. Applied predictive modeling. 1. ed. Berlin, Germany: Springer, 2013. v. 26.

MOOR, M. C. andBart D. Hyperparameter search in machine learning. CoRR, abs/1502.02127, n. 1, p. 1–5, 2015.

PEDREGOSA, F. et al. Scikit-learn: Machine learning in python. J. Mach. Learn. Res., v. 12, n. 1, p. 2825–2830, 2011.

BIAN, X.-Q. et al. Integrating support vector regression with genetic algorithm for co2-oil minimum miscibility pressure (mmp) in pure and impure co2 streams. Fuel, v. 182, n. 1, p. 550 – 557, 2016.

BALAPRAKASH PRASANNAAND BIRATTARI, M. S. T. Improvement strategies for the f-race algorithm: Sampling design and iterative refinement. In: BARTZ- BEIELSTEIN THOMASAND BLESA AGUILERA, M. J. (Ed.). Hybrid Metaheuristics. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007. (HM, ’07).

LOPEZ-IBANEZ,M.etal.Theiracepackage: Iterated racing for automaticalgorithm configuration. Oper. Res. Perspect., v. 3, n. 1, p. 43–58, 2016.

HASTIE, T.; TIBSHIRANI, R.; FRIEDMAN, J. The Elements of Statistical Learning - Data Mining, Inference, and Prediction. 2. ed. Verlag, New York: Springer, 2009. v. 1. (Springer Series in Statistics, v. 1).

GR, L.; GG, K. The measurement of observer agreement for categorical data. Biometrics, v. 33, n. 1, p. 159–174, 1977.

FRIEDMAN, J. H. Multivariate adaptive regression splines. ann. stat., v. 19, n. 1, p. 1–67, 1991.

JONES, E.; OLIPHANT, T.; PETERSON, P. {SciPy}: open source scientific tools for {Python}. 2014.

AKUSOK, A. et al. High-performance extreme learning machines: a complete toolbox for big data applications. IEEE Access, v. 3, n. 1, p. 1011–1025, 2015.

PRICE RAINER M. STORN, J. A. L. K. Differential evolution a practical approach to global optimization. 1. ed. Berlin, Germany: Springer, 2005. v. 1. (Natural Computing Series, v. 1).

SAPORETTI, C. M. et al. Machine learning approaches for petrographic classification of carbonate-siliciclastic rocks using well logs and textural information. J. Appl. Geophys., v. 155, n. 1, p. 217 – 225, 2018.

POLLOCK, D. W.; BARRON, O. V.; DONN, M. J. 3d exploratory analysis of descriptive lithology records using regular expressions. Comput. Geosci-uk., v. 39, n. 1, p. 111 – 119, 2012.

GRAY, J. M.; BISHOP, T. F.; WILFORD, J. R. Lithology and soil relationships for soil modelling and mapping. CATENA, v. 147, n. 1, p. 429 – 440, 2016.