DOI | Resolve DOI: https://doi.org/10.1190/segam2019-3215629.1 |
---|
Author | Search for: Naprstek, Tomas1; Search for: Smith, Richard |
---|
Affiliation | - National Research Council of Canada. Aerospace
|
---|
Format | Text, Article |
---|
Conference | SEG Technical Program Expanded Abstracts 2019, 15 September 15-20, 2019, San Antonio, Texas |
---|
Abstract | We investigate potential applications of two machine learning methods, random forest regression and support vector regression, in aeromagnetic data interpolation. By developing relevant predictors, and training these two methods on synthetic aeromagnetic data, we are able to interpolate a new dataset with success. We show that a “filter”-based approach where standard interpolation methods are fed into the training as predictors allows the machine learning to produce an interpolation that is better than any one of the standard interpolations by themselves. |
---|
Publication date | 2019-08-10 |
---|
Publisher | Society of Exploration Geophysicists |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | cb39dad9-f13e-4849-ae74-87e9e9d91bca |
---|
Record created | 2021-12-20 |
---|
Record modified | 2021-12-20 |
---|