ElasticDocs in EAGE / PESGB London on November 30, 2018

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
Conference Room

FORCE Machine Learning Symposium in Stavanger

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:

Iraya in KL

We are very proud and happy to announce that Iraya Energies is now officially in Malaysia! We are looking forward to serve the energy industry with the latest advances in machine learning techniques in geoscience. #malaysiaboleh #KLAI #canlah #machinelearning #iraya 

Opening Iraya in Kuala Lumpur is more than just a company milestone, it is a personal journey. I first came to Malaysia in 2005, barely 25 years old, probably one of the first to hold the official title of “rock physicist” in South East Asia (once, I passed thru immigration and they thought my job was to be a rock star -how cool is that). My first boss was Phil Beale in Odegaard, we were then at Wisma Selangor Dredging with our band-of-brothers/sisters, who are more than just colleagues, but are family. We then moved to Rohas Perkasa when we got acquired by SLB, where I also met and worked with many talented people where I met so many scientists under one roof. Throughout the years, I did a lot of RP works in Malay Basin, Sabah, Sarawak, then across the regions -Thailand, Indonesia, China, Philippines,Brunei,Vietnam etc., therafter I also took more business development roles. One of the greatest perks, though for me in this industry is never ceasing to learn, always keeping us on our toes to come up with something new, and with the opening Iraya in KL, I am very excited to take on this new challenge of promoting the use of machine learning in geoscience,testing it, pushing it beyond its boundaries, and making it work. I am hoping our clients will share the excitement of experimenting, innovating, and invest in making machine learning deliver for the energy industry.

The path of a startup is rarely easy, nor glamorous. To my family, friends, team, colleagues, partners, investors, clients, thank you for being a source of courage and inspiration. You are definitely a part of this journey!
— Nina Marie Hernandez, Managing Director

We love to analyze your analyses...

A pretty cool display of  topic models clustered and identified within a big bunch of well reports, so we can analyze... your analysis!

The input data was composed of 4,542 pages (6.5 GB) of well reports, where we attempt to understand the contents, relationships, and similarities within a bag of words of  geoscientific documents. It is quite interesting to note that the geology pages started to cluster in one section below, and summary pages also do the same. One can see which reports are pretty standardized, and most probably written by the same scientist or at least the same service contractor. 

Stay tuned for how we will integrate this technique in Iraya's Elastic Docs! 

And you, how do you want to use it? 



A child's first ABC

In a way that we teach a child its first alphabet, in Iraya we teach the machine how to identify a seismic image-the colors, the texture, the feels.Then we teach it to differentiate between a core sample, a stratigraphic chart or a map. Because when a child learns its first abc's, the possibilities for learning and education afterwards, is endless!..


Sentiment Analysis

Sentiment Analysis goes beyond Twitter. Here is Iraya's take on the application of natural language processing (NLP) for high-level understanding of a big geoscience text corpus, where words are treated as vectors. Topic models are inferred and most frequently occuring words are identified from a mined dataset. 


Well Twinning

Well Twinning made easy (magic)! In new ventures effort, we often need to go through a huge amount of well data in a short amount of time to find the closest well analog. The genetic "well twin", can provide valuable information on lithology, production history, drilling risks, etc. But how do we go about finding that twin most efficiently in a wildcat exploration area? Here is Iraya's take on this- demo'ed with Australian test data set. If you want to apply Iraya technique to cluster your voluminous, messy well dataset, talk to us!