Unknown
CEUR
In:
[Paper] In: MAChine Learning for EArth ObservatioN Workshop 2020, 14.-18.09.2020, Virtual Conference . Proceedings of MACLEAN: MAChine Learning for EArth ObservatioN Workshop ; paper 4 .
Publication Date:
2021-01-06
Description:
A huge amount of ocean observation data is available. A pur-pose of interpreting that data in marine–geophysical applications is tofind, for instance, anomalies which are the signs of reservoirs in earth lay-ers beneath the ocean floor. In this position paper, we compare differentmachine learning methods to predict the overall trend of seismic P-wavevelocity as a function of depth for any marine location. Our study isbased on a dataset consisting of data from 333 boreholes and 38 geologi-cal and spatial predictors. Our preliminary results indicate that randomforests provide best results on this dataset, but also suggest to applydata augmentation for improved results with other methods.
Type:
Conference or Workshop Item
,
PeerReviewed
Format:
text
Permalink
|
Location |
Call Number |
Limitation |
Availability |