Transfer learning and Auto-ML: A geoscience perspective

Ehsan Zabihi Naeini; Joshua Uwaifo

doi:10.3997/1365-2397.n0060

ISSN: 0263-5046
E-ISSN: 1365-2397

Transfer learning and Auto-ML: A geoscience perspective
Authors Ehsan Zabihi Naeini¹, Joshua Uwaifo¹
View Affiliations Hide Affiliations

Affiliations: ¹ Ikon Science
Source: First Break, Volume 37, Issue 9, Sep 2019, p. 65 - 71
DOI: https://doi.org/10.3997/1365-2397.n0060
- Published online: 01 Sep 2019

Abstract

Deep learning continues to receive increasing attention from researchers and has been successfully applied to many domains. This paper further extends the work from Zabihi Naeini and Prindle (2018) by adopting and examining two classes of Machine Learning techniques and their applications in geoscience with a pragmatic view. These are Transfer Learning and Automated Machine Learning or Auto-ML (Feurer and Klein, 2015). Although machine learning (ML) is known to be most efficient and accurate when trained on a large volume of data, there are cases in practice where ML methods are also implemented with limited available data. In such cases ML algorithms are less efficient in generalising to new data and it is where Transfer Learning can add value. This is shown in an automatic petrophysical interpretation task where Transfer Learning is compared with training from scratch given a new geological area of interest, i.e., a set of wells in a different area. We show the efficiency of Transfer Learning in obtaining a model that generalizes successfully for the new wells investigated.

EAGE Publications BV

Article metrics loading...

/content/journals/10.3997/1365-2397.n0060

2019-09-01

2024-04-25

From This Site

/content/journals/10.3997/1365-2397.n0060

dcterms_title,dcterms_subject,pub_keyword

-contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution

10

5

Full text loading...

References

Bergstra, J., Yamins, D. and Cox, D.
[2013]. Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms, SCIPY
[Google Scholar]
Feurer, M. and Klein, A.
[2015]. Efficient and robust automated machine learning, Advances in Neural Information Processing Systems. Advances in Neural Information Processing Systems, 28.
[Google Scholar]
Sarkar, D., Ghosh, T. and Bali, R.
[2018]. Hands-On Transfer Learning with Python. Packt Publishing, 1.
[Google Scholar]
Guyon, I. and Sun-Hosoya, L.
[2019]. Analysis of the Auto-ML Challenge Series 2015–2018. Automated Machine Learning, Methods, Systems, Challenges, Springer Series on the Challenges in Machine Learning, 177–219.
[Google Scholar]
Jin, H., and Song, Q.
[2018]. Auto-Keras: An Efficient Neural Architecture Search. arXiv:1806.10282.
[Google Scholar]
Khoshgoftaar, T.M. and Weiss, K.
[2016]. A survey of transfer learning, Journal of Big Data.
[Google Scholar]
Mendoza, H. and Klein, A.
[2016]. Towards automatically-tuned neural networks. ICML Workshop on Auto-ML, 58–65.
[Google Scholar]
Pedregosa, F.
[2011]. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
[Google Scholar]
Pham, H., and Guan, M.Y.
[2018]. Efficient Neural Architecture Search via Parameter Sharing. arXiv:1802.03268.
[Google Scholar]
Yang, L. and Hannek, S.
[2013]. A theory of transfer learning with applications to active learning. Machine Learning, 161–189.
[Google Scholar]
Yang, Q.
[2008]. An Introduction to Transfer Learning, Advanced Data Mining and Applications, ADMA 2008. Lecture Notes in Computer Science, 5139.
[Google Scholar]
Zabihi, Naeini E. and Prindle, K.
[2018]. Machine learning and learning from machines. The Leading Edge, 886–893.
[Google Scholar]

http://instance.metastore.ingenta.com/content/journals/10.3997/1365-2397.n0060

Transfer learning and Auto-ML: A geoscience perspective

First Break 37, 65 (2019); https://doi.org/10.3997/1365-2397.n0060

/content/journals/10.3997/1365-2397.n0060

Data & Media loading...

Article Type: Research Article

Most Cited This Month Most Cited RSS feed

- Curvature attributes and their application to 3D interpreted horizons
  
  By A. Roberts
- Distributed Acoustic Sensing – a new tool for seismic applications
  
  Authors Tom Parker, Sergey Shatalin and Mahmoud Farhadiroushan
- Effects of igneous intrusions on the petroleum system: a review
  
  Authors Kim Senger, John Millett, Sverre Planke, Kei Ogata, Christian Haug Eide, Marte Festøy, Olivier Galland and Dougal A. Jerram
- Seismic Inversion Methods and some of their constraints
  
  Authors P.C.H. Veeken and M. Da Silva
- MEMS-based accelerometers: expectations and practical achievements
  
  Authors D. Mougenot, A. Cherepovskiy and L. JunJie
- Thematic Set: Full waveform inversion: the next leap forward in imaging at Valhall
  
  Authors L. Sirgue, O.I. Barkved, J. Dellinger, J. Etgen, U. Albertin and J.H. Kommedal
- Automatic seismic prediction ahead of the tunnel boring machine
  
  Authors G. Kneib, A. Kassel and K. Lorenz
- Well log and seismic data analysis using rock physics templates
  
  Authors P. A. Avseth and E. Odegaard
- Geostatistical inversion - a sequential method of stochastic reservoir modelling constrained by seismic data
  
  Authors A. Haas and O. Dubrule
- Two-dimensional resistivity mapping with a computer-controlled array
  
  Authors D.H. Griffiths, J. Turnbull and A.I. Olayinka
More Less

Transfer learning and Auto-ML: A geoscience perspective

Abstract

Most Read This Month

Most Cited This Month Most Cited RSS feed