n the first two days of the live conference, there will be workshops of general interest. These will run from 1:15 – 2:15 pm (EDT or GMT-4). Since both of these

workshops will be pitched to a general audience, and do not need any special knowledge or interest in geostatistics, they are open to the public. Anyone can listen in, even if they have not registered for the conference, just by sending a request for the online link using the buttons below each of the summaries below. People who have formally registered for the conference, using the "Register" button on this website, do not need to register separately for these workshops; each registrant will get an e-mail with the workshop links.


Monday, July 12th, 2021 @ 1:15 – 2:15 pm.

Okay, can we agree that any field of study that uses "hidden layers", "random forests" and "adversarial networks" needs a bit of explaining? There are many in the geostatistics community who are kind of fascinated by the things we hear about artificial intelligence (AI) and machine learning (ML), but who wait like shy eight-year-olds at the edge of the school playground because we just don't understand the game that the other kids are playing.

Michael Pyrcz, who is about the friendliest explainer you will ever meet, is offering to demystify AI and ML ... or, if not completely demystify it, at least teach you the jargon and the rules of the game. Basically, if you get hit by the ball, you're out.

There will be time for questions and discussion. At the end of the hour, you will hopefully know a little bit more about how artificial intelligence and machine learning might improve models of the sub-surface, and how to start exploring the AI/ML toolkits on your own.


Tuesday, July 13th, 2021 @ 1:15 – 2:15 pm.

Twice as mysterious as the dark and confusing world of AI/ML is the Byzantine process of finding a home for your research and case studies in a refereed technical journal. 


Two of the High Priests in the Church of Mathematical Geosciences have offered to peel back the layers of secrecy and discuss their Ten Commandments: the dos and don'ts of submitting an article, responding to peer-review commentary, and why not to throw yourself off the nearest tall building when your brilliant masterpiece is returned with the comment "Needs Major Revision".

Jaime Gómez-Hernández and Roussos Dimitrakopoulos will present the most common mistakes that are made when people try to get their work into a technical journal, with examples of each of these Cardinal Sins, and suggestions for how to work your way out of the deep, deep hole you have dug for yourself and your career.

Discussion is welcome. But dissent will not be tolerated.

Michael Pyrcz (University of Texas at Austin) researches and teaches on subsurface modeling, spatial data analytics, geostatistics and machine learning. He is also the principal investigator of the freshmen research initiative and a core faculty in the Machine Learn Laboratory in UT Austin's College of Natural Sciences. 

Michael has written over 60 peer-reviewed publications, a Python package for spatial, subsurface data analytics, and coauthored a textbook on spatial data analytics, Geostatistical Reservoir Modeling. All of Michael's university lectures are available on his YouTube channel, to support his students and working professionals with evergreen educational content. 

Jaime Gómez-Hernández (Universitat Politècnica de València) is is a member of the Editorial Board of several journals, such as: Mathematical Geosciences; Advances in Water Resources; Frontiers in AI in Food, Agriculture and Water; and Frontiers in Earth Sciences.

Roussos Dimitrakopoulos (McGill University) is the Editor-in-Chief of Mathematical Geosciences, the principal technical journal of the International Association of Mathematical Geosciences, and serves on the Editorial Board of several mining engineering journals.

There is a hands-on component for anyone who wants to follow along, using a machine-learning toolkit. The instructions for how to set up the toolkit on your computer are in the PDF file below.