eql-gradient-boosted.zip (127.86 MB)
Supplementary material for "Gradient-boosted equivalent sources"
Version 2 2021-08-24, 18:22
Version 1 2021-02-25, 17:18
software
posted on 2021-08-24, 18:22 authored by Santiago Rubén SolerSantiago Rubén Soler, Leonardo UiedaLeonardo UiedaThis paper has been accepted for publication in Geophysical Journal
International.
The version of record is available at doi.org/10.1093/gji/ggab297
A preprint version is available on EarthArXiv at doi.org/10.31223/X58G7C
This is a snapshot of the git repository hosted by GitHub:
https://github.com/compgeolab/eql-gradient-boosted
We present the gradient-boosted equivalent sources: a new methodology for
interpolating very large datasets of gravity and magnetic observations even on
modest personal computers, without the high computer memory needs of the
classical equivalent sources technique.
This new method is inspired by the gradient-boosting technique, mainly used in machine learning solutions.
All source code is made available under a BSD 3-clause license. You can freely
use and modify the code, without warranty, so long as you provide attribution
to the authors. See LICENSE.md
for the full license text.
Data and the results of numerical tests are available under the Creative Commons Attribution 4.0 License (CC-BY).