Joint SBGf/SEG Workshop on Machine Learning

15-16 May 2018 | Rio de Janeiro, Brazil

Online Registration for this workshop is now closed. Please register onsite 15-16 May at the SEG/SBGf desk at Grand Mercure Rio de Janeiro Copacabana.


15-16 May 2018
Rio de Janeiro, Brazil

Machine Learning (ML) is a field of Artificial Intelligence (AI) that has experienced rapid growth in the last ten years across diverse industries, including communications, financial services, security, transportation, and others. Applications of Machine Learning have produced dramatic results, enabling new opportunities and business models. Driving the adoption of Machine learning are the volume and velocity of information, the application of deep learning techniques, and economic computing power. Applied to geoscience, these data-driven approaches are complementary tools for physical-based modeling, simulation, and inversion. Machine Learning facilitates an understanding of complex relationships among a large and diverse set of variables, valuable for generating and validating models and answering scientific questions. Machine Learning can enable fast high-quality decisions in the Oil & Gas industry, an essential component for viability given the industry’s long-term outlook. Geoscience datasets are among the largest volumes of data in the industry.  The data has a wide spectrum of properties with scales varying over many orders of magnitude. This workshop will discuss the challenges, opportunities, and trends related to the adoption of Machine Learning in Geoscience research and industrial workflows. Professionals from academia, Oil & Gas, and technology companies will present applications and case studies, promote discussion, and propose practical solutions to take greater advantage of Machine Learning methods.


Grand Mercure Rio de Janeiro Copacabana

Room1 rates: 
Standard: R$ 420,42 (SGL) R$ 466,62 (DBL) 
Superior: R$ 457,38 (SGL) R$ 503,58 (DBL) 
Includes breakfast & taxes. 

No block of rooms available. Confirmation subject to prior availability. 

For hotel reservation, please contact Mrs. Carla Duarte (, phone + 55 21 3545-5445). In order to guarantee the special rates, please mention the meeting name and dates. 

General Co-Chairs

  • Pedro Mário Cruz e Silva (NVIDIA)
  • Klaus Soffried (Geophysical Insights)


SBGf Events Coordinator
Renata Vegasta

SEG Director, Global Events
Julie McGrath

Technical Program

The call for abstracts closed 30 January 2018.

Suggested Topics

  • Applications to geophysics
  • Case studies in Geoscience
  • Case studies in reservoir characterization and management
  • Future Trends

Technical Committee

  • Elita Abreu (Petrobras)
  • Lucas Balancin (Petrobras)
  • Gregori Fabre (Total)
  • Hal Green (Geophysical Insights)
  • Matt Hall (Agile)
  • Paulo Johann (Petrobras)
  • Marcilio Matos (SISMO Signal Processing Research, Training & Consulting)
  • Carlos Rodriguez (Independent Consultant)
  • Yang Xue (Shell)

Download the Call for Abstracts (PDF)


Day One
Tuesday, May 15, 2018

Time Session Presenter Name/Company
7:00 -
8:00 Breakfast
8:30 Opening/Welcome
8:45 Keynote:
Deep Learning for Geoscience in Oil and Gas
Mauricio Araya, PhD
Shell International Exploration and Production Inc.
9:30Geostatistics 2.0 Spatial Interpolation in the Age of Big Data Ítalo Gomes Gonçalves, Universidade Federal do Pampa
10:00Property Prediction from Seismic Attributes Using a Boosted Ensemble Machine Learning SchemeMotaz Alfarraj, Georgia Institute of Technology
10:30Coffee Break
10:45Methodology of Seismic Interpretation and Well Data Integration Using Machine Learning for Multi-attribute Facies ClassificationAlex Laier Bordignon, Institute of Pure and Applied Mathematics of Federal Fluminense University
11:15Comparative Study of Permeability Estimates of a Carbonate Reservoir in Campos Basin using Well Logs Together with an Empirical Model and Machine Learning ApproachesRhanderson Gomes, UENF/CCT/LENEP
11:45Artificial Intelligence for Prediction of Severe Fluid Losses in Pre-Salt CarbonatesSandra Buzini Duarte, Petrobras
13:30Delimitation of Electrofacies and Oil-water Contacts in Carbonate Reservoirs Using Well Logs Together with Linear and Nonlinear Mathematical TechniquesTamires Soares, UENF/CCT/LENEP
14:00Reservoir Characterization Through Artificial Neural Networks (ANN) Approach and its value in Field development - Case Study : Egina field – Deep offshore NigeriaAntoine Massala, Total
14:30Bayesian Networks for decisions under uncertainty in Basin ModelingTanvi Dhiren Chheda, Department of Geological Sciences, Stanford University
15:00Coffee Break
15:15A data-driven methodology for integrating geological measurements from unconventional reservoirs and production data for sweet spot identificationJorge Guevara Diaz, IBM Research
15:45Integrating 3D seismic and well log data for improved estimation of lithological characteristics in the northern Santos Basin using Machine Learning techniquesFrançois Lafferriere, Kognitus
16:15Word Embeddings For The Specific Domain Of Geosciences In PortugueseDiogo da Silva Magalhães Gomes, Coppe/UFRJ, Petrobras
16:45Principal Component Analysis and K means analysis of airborne gamma ray spectrometry surveysRafael Augusto Pires de Lima, The University of Oklahoma / CPRM - Geological Survey of Brazil
17:15Bridging Gaps Between Natural and Seismic Image AnalysisMuhammad Amir Shafiq, Georgia Institute of Technology, Atlanta, GA, USA
17:45Closing section
18:00Icebreaker Reception

Day Two
Wednesday, May 16, 2018

Time Session Presenter Name/Company
8:30Keynote: Artificial Intelligence for Oil & Gas: how AI technologies will change the way we workUlisses T. Mello, IBM Research
9:00Automatic diffraction apex region detection using convolutional neural networksLucas de Magalhães Araújo, Centro de Estudos de Petróleo e Instituto de Computação/Unicamp
9:30Transfer Learning with Deep Convolutional Neural Networks for Seismic Shot-Gather Quality ClassificationBruno Pereira Dias, PETROBRAS
10:00Machine Learning to reduce cycle time in 4D seismic data assimilationYang Xue, Shell International Exploration and Production
10:30Deep Convolutional Network for Seismic CompressionJoão Paulo Peçanha Navarro, Metta Innovations
10:45Coffee Break
11:00Seismic facies prediction using multiple machine learning approachesLong Jin, Shell
11:30Evaluation Of Support Vector Machine To Classify Facies In Peregrino Field, Campos Basin-Rj, BrazilEduardo Bomfin Caldato, Instituto de Geociências - UNICAMP
12:00Lithology classification with incomplete dataErick Costa e Silva Talarico, Petrobras
13:45Machine Learning Provides Faster, Higher-Quality Reservoir InsightsBruno de Ribet, Paradigm
14:15Danet-FCN3 3D Semantic Segmentation of Facies in Seismic CubesDaniel Salles Chevitarese, IBM Research
14:45Reducing Mineral Exploration risk in the Yukon PlateauTelma Aisengart, Geosoft
15:15Coffee Break
15:30Automated machine learning in your machine learning pipelineIvan Marroquin, Geophysical Insights
16:00Implicit geological modeling with Gaussian Process ClassificationÍtalo Gomes Gonçalves, Universidade Federal do Pampa
16:30Weakly-Supervised Subsurface Structure LabelingYazeed Alaudah, Georgia Institute of Technology
17:00Sensitivity Analysis in a Machine Learning Methodology for Reservoir AnaloguesReinaldo Mozart Da Gama e Silva, IBM Research
17:30Deep Convolutional Autoencoder for Petroleum Reservoir Connectivity RecoveryRodrigo Exterkoetter, LTrace Geophysical Solutions

Schedule subject to change

Important Documents

Important Dates

Call for Abstracts closed
30 January 2018

Early registration closed
15 April 2018

Onsite Registration Available
15-16 May 2018

Back to Top


This website uses cookies to improve your experience. If you continue without changing your settings, you consent to our use of cookies in accordance with our cookie policy. You can disable cookies at any time. Learn More

8801 S. Yale Ave. Suite 500
Tulsa, OK 74137
Phone: 918-497-5500

CONNECT with us

Don't miss a thing.

Visit your SEG Communications Center here.
(It's free to create an account, and you don't have to be an SEG member.)

Twitter facebook linkedIn instagram google plus youtube