The Geologic Enhanced Mapping System (GEMS) Prize Challenge

Identify hidden geologic faults to discover new geothermal resources. #energy #science

$300,000 in prizes
3 weeks left
925 joined

Welcome to the Geologic Enhanced Mapping System (GEMS) Prize Challenge!

U.S. geothermal resources can be harnessed for power production and heating and cooling without importing fuel. One major hurdle in this process is the identification of new hidden geothermal prospects. The Geologic Enhanced Mapping System (GEMS) Prize, presented by the U.S. Department of Energy’s Office of Geothermal, will prioritize efforts to accelerate the ongoing, detailed geologic mapping of the United States, with a focus on locating previously unknown deposits of critical minerals and geothermal resources.

The GEMS Prize seeks to address the challenge of creating an algorithm that will generate enhanced geologic fault datasets to support geologic and geophysical mapping and modeling that will assist geothermal and critical mineral studies. This work is vital to accelerate discoveries of new, commercially viable hidden geothermal systems while reducing the exploration and development risks for all geothermal resources.


Competition End Date

Dec. 3, 2026, 10 p.m. UTC

Total Prize Pool: $300,000

Initial Prize Round — $50,000
Top 5 participants on private test set
1st – 5th Place (each) $10,000
Final Prize Round — $250,000
Top 5 participants on re-labeled dataset
1st $100,000
2nd $70,000
3rd $40,000
4th $25,000
5th $15,000

The same submission is scored twice — once against a private expert-labeled test set for the Initial Prize Round, and again against a revised label set built from expert review of all submissions for the Final Prize Round. See the competition structure section of the problem description for a full walkthrough.


How to compete

  1. Click the "Compete!" button in the sidebar on the competition homepage to enroll in the competition.
  2. Get familiar with the problem through the overview and problem description. You might also want to reference additional resources available on the about page.
  3. Download the data from the data tab.
  4. Create and train your own model. This reference solution implements a simple approach.
  5. Use your model to generate predictions that match the submission format.
  6. Click “Submit” in the sidebar, and then “Make new submission”. You’re in!

Competition rules

The challenge rules are in place to promote fair competition and useful solutions. If you are ever unsure whether your solution meets the competition rules, ask the challenge organizers in the competition forum or send an email to info@drivendata.org. A few key rules are highlighted below. For more details, see the official rules page.

Accounts and teams

Each person may participate through only one DrivenData account. Submission limits are set per person, and every competitor certifies at registration that they follow the rules and that their information is true. Using more than one account breaks both. Violators of the rules may be disqualified. Each account may join only one team, and each team member must be a different person. Before any prize is awarded, finalists' identities will be verified, and each finalist, and each member of a finalist team, will certify that they used only one account.

Submission limits

Each person may make one scored submission per UTC day, using their one account. The allowance resets at midnight UTC. The limit is per person, so each member of a team has their own daily allowance.

Final submission

Each team, or individual not on a team, selects one final submission before the deadline. That submission is scored in both prize rounds. Finalists must provide complete code, documentation, and all data used, including external data and any hand labels, sufficient to reproduce their final submission.

Eligibility

Please refer to the official rules page for full eligibility criteria.

Use of test data

A unique feature of this challenge is that there is spatial overlap between the training dataset (the USGS quaternary fault dataset) and the test dataset (newly identified faults within the GeoDAWN region). For this challenge, you may use the provided set of faults for training purposes. Participants will be evaluated based on their performance predicting faults contained in a newly labeled, private set of faults.

Use of external data

The use of external data is encouraged in this competition, provided you or your team possess the necessary licenses to use the data for this challenge. All data used must be shareable with the challenge organizers to allow for independent result verification. For more information, see the complete rules document.


This challenge is sponsored by the United States Department of Energy (DOE) Office of Geothermal (OG)


with additional support from the United States National Lab of the Rockies (NLR).


Images courtesy of NLR.