1471548
doi
10.5281/zenodo.1471548
oai:zenodo.org:1471548
Silva, Reinaldo Mozart
IBM Research
S. Ferreira, Rodrigo
IBM Research
Chevitarese, Daniel
IBM Research
Szwarcman, Daniela
IBM Research
Vital Brazil, Emilio
IBM Research
Netherlands F3 Interpretation Dataset
Baroni, Lais
IBM Research
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
seismic
seismic interpretation
machine learning
<p><strong>Netherlands F3 Interpretation Dataset</strong></p>
<p>Machine learning and, more specifically, deep learning algorithms have seen remarkable growth in their popularity and usefulness in the last years. Such a fact is arguably due to three main factors: powerful computers, new techniques to train deeper networks and more massive datasets. Although the first two are readily available in modern computers and ML libraries, the last one remains a challenge for many domains. It is a fact that big data is a reality in almost all fields today, and geosciences are not an exception. However, to achieve the success of general-purpose applications such as ImageNet - for which there are +14 million labeled images for 1000 target classes - we not only need more data, we need more high-quality labeled data. Such demand is even more difficult when it comes to the Oil & Gas industry, in which confidentiality and commercial interests often hinder the sharing of datasets to others. In this letter, we present the Netherlands interpretation dataset, a contribution to the development of machine learning in seismic interpretation. The Netherlands F3 dataset was acquired in the North Sea, offshore Netherlands. The data is publicly available and comprises pos-stack data, eight horizons and well logs of 4 wells. However, for the dataset to be of practical use for our tasks, we had to reinterpret the seismic, generating nine horizons separating different seismic facies intervals. The interpreted horizons were used to create 651 labeled masks for inlines and 951 for crosslines. We present the results of two experiments to demonstrate the utility of our dataset. </p>
<p><strong>Dataset contents</strong></p>
<ul>
<li>Crosslines:
<ul>
<li>Classes: 10</li>
<li>Number of slices: 651</li>
<li>Records per class: 9,440</li>
<li>Total of records: 94,400</li>
</ul>
</li>
<li>Inlines:
<ul>
<li>Classes: 10</li>
<li>Number of slices: 951</li>
<li>Records per class: 9,720
<ul>
<li>Total of records: 94,720</li>
</ul>
</li>
</ul>
</li>
<li>Configuration:
<ul>
<li>Crop: [0, 0, 0, 0]</li>
<li>Gray levels: 256</li>
<li>Noise: 0.3</li>
<li>Percentile: 5.0</li>
<li>Strides: [20, 48]</li>
<li>Tile shape: [25, 64, 1]</li>
</ul>
</li>
</ul>
Zenodo
2018-09-20
info:eu-repo/semantics/other
1422786
2.0.0
1579893978.179329
288843
md5:7fd2694ccbe500870f2e6020e88000f9
https://zenodo.org/records/1471548/files/examples_inline_tiles.png
639101595
md5:32e4e6228c44995cce218a8f8936bedb
https://zenodo.org/records/1471548/files/crosslines.zip
289379
md5:35d6a1208aacd072ebf17cb6dc0313f3
https://zenodo.org/records/1471548/files/examples_crossline_tiles.png
95320034
md5:30b40f0426d95c5f26878bcd398fc853
https://zenodo.org/records/1471548/files/horizons.tar.gz
637187326
md5:fb5b0d16ca27f7c8c3e19930a28eedbe
https://zenodo.org/records/1471548/files/inlines.zip
4800574
md5:42e42e9955ec2d957901339f49db720f
https://zenodo.org/records/1471548/files/masks.tar.gz
140979246
md5:8e255eab8a223c1a55d856ee2556948f
https://zenodo.org/records/1471548/files/tiles_crosslines.tar.gz
139644717
md5:eae2198d5e9e1f16b3042957fa01176b
https://zenodo.org/records/1471548/files/tiles_inlines.tar.gz
public
10.5281/zenodo.1422786
isVersionOf
doi