Thanks

[wouterk1MSS]

Thanks for organizing this ML contest. It was fun and a very useful learning experience. I blame the data for my poor result :) Looking forward to the MLevent at the EAGE-Paris this year.

Is there interest for a geo-ML linkedin group for connecting and further discussions? or does it already exist?

Also, are there any plans to have a follow-up on this? I thought being able to see other people's notebook was helpful on one hand but also leads to drags down the plurality of methods. Maybe for a next one I would suggest keep the top5 hidden, or make sharing optional till the results.

[kwinkunks]

The closest thing I know of to a chat group for ML in geoscience is 'Software Underground' --- a Slack group with about 300 people. You can join at http://swung.rocks/ Please do!

Thanks for the suggestions. Definitely a learning experience for me too! The openness was something of a feature, and I thought it was interesting that the later entries (there were several new teams yesterday) did not do well, on the whole. In other words, I think we got up to 0.6+ partly because of the openness. But I know what you mean about the plurality.

Once we get this dataset released properly, I hope we see it a lot as a benchmark of sorts. We need more such datasets --- with seismic, production data, core photos, etc. This is just the start!

Anyway, thank you for your participation. I look forward very much to meeting you in Paris.