FORGE-ing Ahead: Charting the Future of Geothermal Energy

A microseismic event loaded from the Frontier Observatory for Research in Geothermal Energy (FORGE) distributed acoustic sensing (DAS) data into a Jupyter notebook showing energy from a microseismic event arriving at about 7.5 seconds. These microseisms bring information about the process of stimulation. However, in the data set there are relatively few and they are hard to find without specialized processing. Connecting hard-to-get SEG-Y data to easy-to-develop Jupyter notebooks promises to drive innovation in new AI/ML methods for detecting more microseisms and therefore, increasing the value of the existing data.


Geothermal is seriously hot right now (pun intended). Already this year, the DOE has tendered over $50 million worth of grants (here, here and here) to develop enhanced geothermal power in the United States. A $1.4 million grant was recently awarded to Rice University to adapt its DAS technologies for carbon capture and storage applications.

In Utah FORGE there are 71,880 recordings with 110 known microseismic events now visible with expert developed signal processing. Scientists can pull all the data and relevant metadata into their Jupyter notebooks and start exploring. Read on for how…

Enhanced Geothermal Systems in Brief 

Conventional geothermal systems, or hydrothermal systems, occur naturally throughout the world. However, capturing enough steam or energy from heated water to generate sustainable power from them requires highly specific conditions, including sufficient heat, fluid saturation and permeability. By fracturing and pumping water through high-temperature formations, enhanced geothermal systems technology can provide the fluid content and fracture conductivity needed—but not naturally present—to produce continuous steam and energy transfer.    

EGS technology has the potential to power tens of millions of homes and businesses with clean, domestic energy. The United States Geothermal Technologies Office (GTO) pursues emerging, innovative R&D initiatives that support commercially viable EGS by 2030. At the forefront of EGS is the Utah Frontier Observatory for Research in Geothermal Energy (FORGE), a first-of-its-kind accelerator for EGS pioneers. 

Utah FORGE Shows the Way Forward 

The mission of the Utah FORGE observatory is to enable cutting-edge well construction technologies to make commercial enhanced geothermal power possible. It provides a treasure trove of drilling, logging, completion and other geophysical data through the Geothermal Data Repository (GDR). 

The Utah FORGE observatory sits above a large volume of hot crystalline granite up to six miles deep. The site provides a controlled environment where multidisciplinary researchers from universities, national laboratories, and industry partners can develop, test and optimize EGS technologies. 

In 2020, researchers drilled the industry’s first deep, highly deviated geothermal well through the formation. This innovative approach, coupled with unprecedented collaboration and data dissemination, will allow a series of tests, measurements and models to facilitate the development of large-scale, economically sustainable EGS resources. 

In 2021, the FORGE project is focusing its R&D efforts on zonal isolation, field-scale characterization, stimulation and well configuration for geothermal conditions. 

Empowering EGS Understanding with AI/Machine Learning

Applied artificial intelligence makes the necessary understanding possible. The GDR shares open source surface and subsurface data from FORGE, including well plans, survey data, drilling data, well logs, activity reports, an interactive geoscience map, and more. These detailed datasets have the potential to revolutionize the way experts approach EGS by enabling rapid, high-quality modeling—such as fracture simulation and earth modeling—like never before. 

By applying advanced machine learning technology, domain experts will be able to interpret and leverage these complex datasets at scale, often in real-time for operational decision making. New-generation deep learning applications, such as Enthought’s SubsurfaceAI Seismic, will enable scientists to optimize drilling, reservoir stimulation, well connectivity and flow testing as researchers work on developing and accelerating breakthroughs in EGS operations.

Getting to Know FORGE Data 

The 110 discovered microseismic events from within the 71,880 recordings (thanks to Ariel Lelouch for sharing) are very hard to see without specialized signal processing. We’re loading the data and putting all the relevant metadata with it so you can just pull it into your Jupyter notebook and start exploring. The above image is an example. 

A microseismic event loaded from the Frontier Observatory for Research in Geothermal Energy (FORGE)
distributed acoustic sensing (DAS) data into a Jupyter notebook showing energy from a microseismic event arriving at about 7.5 seconds.

At the nerd layer, there’s an opportunity for data scientists, AI experts and seismologists to learn and apply their skills to this new frontier in energy and its associated geophysics.

For access to this collection of AI/ML ready FORGE DAS data, please get in touch with Enthought. 

About the Author: Ben Lasscock, holds a Ph.D. and a B.Sc. in theoretical physics from the University of Adelaide. Before coming to geoscience, Ben worked as a portfolio manager at a large hedge fund in Australia. He has publications in the areas of high energy physics, Bayesian time series analysis and geophysics.

Share this article:

Related Content

Making the Most of Small Data in Scientific R&D

March 9, 2023|Life Sciences, Materials Science, Transformation Making the Most of Small Data in Scientific R&D For many traditional innovation-driven organizations, scientific data is generated…

Read More

ChatGPT on Software Engineering

Recently, I’ve been working on a new course offering in Enthought Academy titled Software Engineering for Scientists and Engineers course. I’ve focused on distilling the…

Read More

What’s in a __name__?

if __name__ == “__main__”: When I was new to Python, I ran into a mysterious block of code that looked something like: def main():  …

Read More

3 Trends for Scientists To Watch in 2023

As a company that delivers Digital Transformation for Science, part of our job at Enthought is to understand the trends that will affect how our…

Read More

Accelerating Science: the Classical Mechanics Perspective

When thinking about enhancing R&D processes, Newton’s second law of motion provides the perfect framework. Classical mechanics teaches us that putting a body into motion…

Read More

Retuning the Heavens: Machine Learning and Ancient Astronomy

What can we learn about machine learning from ancient astronomy? When thinking about Machine Learning it is easy to be model-centric and get caught up…

Read More

Announcing Enthought Academy

Dear Students and Friends of Enthought,  I am pleased to announce Enthought Academy—the culmination of over twenty years of teaching Scientific Python. Since our founding…

Read More

Extracting Target Labels from Deep Learning Classification Models

In the blog post Configuring a Neural Network Output Layer we highlighted how to correctly set up an output layer for deep learning models. Here,…

Read More

True DX in the Pharma R&D Lab Defined by Enthought

Enthought’s team in Japan exhibited at the Pharma IT & Digital Health Expo 2022 life sciences conference in Tokyo, to meet with pharmaceutical industry leaders…

Read More

Exploring Python Objects

Introduction When we teach our foundational Python class, one of the things we do is make sure that our students know how to explore Python…

Read More