Giving life to old yet very valuable geological data is one of the things that ElasticDocs is very good at. We have recently extracted 60,000 pages and 40,000 images of unstructured data from the Northern North Sea, Central Graben, More, Voring including ancient reports from the 70s. How much our geological understanding has changed, since then? Have you missed anything that is worth an exploratory look-back? Send us a note at firstname.lastname@example.org, to find out. hashtag#northsea hashtag#norway hashtag#eage hashtag#unstructureddata hashtag#geology hashtag#ocr hashtag#nlp hashtag#elasticsearch hashtag#machinelearninggeoscience hashtag#irayaenergies hashtag#elasticdocs
We just held the #EarthHack Joining Orientation today. We are very happy to report that the EarthHack community at this side of the world (Asia Pacific and environs), is growing. When we started to brainstorm about EarthHack with EAGE in late 2017, we really have no idea what to expect, and up until few months ago, we were challenged how to get everyone together and investigate this #machinelearninggeoscience thing-y, in a collaborative, fun and open environment.
In today’s telecon, we had participation from 25 earthhackers, with various backgrounds from geoscientists, coders, finance guys, a guy called cooldude (:) ), and more. The Slack EarthHack Community is counted at 107. Definitely theres a lot room for growth, and we look forward to more sharing, participations and discussions in the future.
The EAGE EarthHack Playbook can be found here:
To find the list of themes, and look for fellow neurons, you may use the following link: https://1drv.ms/w/s!AjtF2RTjovEvchujVrqj18YOg5Q
The materials can also be found at the EAGE Official EarthHack page.
We also would like to thank the official sponsors: Microsoft, CGG, Aramco and collaborators: ADAX, LEAD, MDEC and Petronas for supporting this event.
At #EarthHack, All is allowed, except an:
We are testing out a Word Cloud feature on ElasticDocs, and we are making a survey whether the data that we extract are relevant, or not. Most are familiar with this colorful graphics, can they be useful? - the word cloud is a extraction of the most frequently occurring terms within a set of documents, and intended to provide a "general" grasp of the topics within a specified (geological) document. The extraction is unsupervised. The samples are extracted from Well Completion Reports in Australia. We would appreciate your feedback if you found them useful. Pls message us if you are interested to review the dataset,, at email@example.com
EAGE Earth-Hack Update: We will be holding the participant's Joining Orientation next week on 23rd January! We are quite pleased to see the Earth-Hack community growing, we have now more than 65 members from very few just several months ago. We've also received quite big support from various enterprise and kindly thank Microsoft for providing the cloud compute resources for this event. We will be coming up soon with the themes shortly! Give us a shout for any geoscience problematics you want to see tackled!
EAGE in collaboration with Iraya Energies is organizing the first Machine Learning Hackathon in energy geoscience in the region. Through this event, we aim to bring together industry experts, students, hackers, mentors, and geoscientists with love for the earth to explore machine learning techniques as a tool to solve industry problematics.
The EAGE ML Hackathon will be held on the 23-24 Feb, followed by the Symposium on 25-27 Feb, 2019.
Post your interests for the Hackathon here in Earth-Hack Slack workspace. We are working to build our community of earth-hackers around this region, and this is also a venue to discuss common machine-learning interests.
We welcome suggestions for problematics for the hackathon, and encourage sponsorship of open-source data that can be used by the participating teams.
EAGE link to this event can be found here.
For more information, pls do not hesitate to contact Nina Marie Hernandez at firstname.lastname@example.org, or Irene Ng at email@example.com.
Hmmm just noticed, we have a lot of EAGE activities these days…
We are pleased to announce that our technical paper on ElasticDocs, has been accepted to the EAGE Conference on Reservoir Geoscience, which is to be held on 3-5 December 2018 in Kuala Lumpur, Malaysia
Title: ElasticDocs as an Automated Information Retrieval Platform for Unstructured Reservoir Data Utilizing a Sequence of Smart Machine Learning Methods within a Hybrid Cloud Container
Presenter: Nina Marie Hernandez
Hope to see you there!
We are excited to announce that we will be presenting at the First EAGE/ PESGB Workshop on Machine Learning, in London, UK.
The details are as follows:
Title: An Automated Information Retrieval Platform For Unstructured Well Data Utilizing Smart Machine Learning Algorithms Within A Hybrid Cloud Container
Presentor: Dr. Kim Gunn Maver
Paper Number 28
Paper Reference: ML P17
Session Details: Lunch Break / Poster Session
Nov 30, 2018
12:25 PM - 1:30 PM
Fantastic machine learning hackathon and symposium event in Stavanger, Norway last September 18-20, organized by FORCE, attended by more than 130+ participants.
Kim presented a demonstration of Iraya’s ElasticDocs product, an intuitive container for handling voluminous, unstructured data and enabled with digitization, natural language processing, geolocation and autoimage classification of geoscience documents including doc, pdfs, etc.
Watch the youtube demo of the presentation below:
Have fun tinkering with Iraya's automated image clustering demo of T-SNE implementation in Tensorboard! http://demo-tensorboard.irayaenergies.xyz/#projector&run=. Click thru Projector > TSNE > optimize parameters such as learning rate, perplexity to optimize clustering of similar images (seismic, cores, etc..).
Have a bit of patience, when the tensor values are being fetched.