Using machine learning for hydrocarbon prospecting in Reconcavo Basin, Brazil

Machine Learning techniques are being widely used in Social Sciences to find connections amongst various variables. Machine Learning connects features across different fields that do not seem to have known mathematical relationships with each other. In natural resource prospecting, machine learning can be applied to connect geochemical, geophysical, and geological variables. However, the biggest challenge in machine learning remains obtaining the data to train the ML algorithms. Here, we have applied machine learning on data extracted from maps via image processing. While the overall accuracy of prediction remains as low as 33% at this stage, we see places where the algorithm can be improved and the accuracy increased.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Earth, Atmospheric, and Planetary Sciences.

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2016

Author dc:creator

• Zhakiya, Elezhan

Advisor dc:contributor.advisor

• Bradford Hager.

• Earth, Atmospheric, and Planetary Sciences.

Statement dc:rights

• MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/115039

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/115039