University of Alaska Fairbanks

DARPA AI for Critical Mineral Assessment Competition 

At the core of many U.S. supply chains, you’ll find “critical minerals,” i.e. non-fuel materials used to manufacture products considered essential to national security, economic growth, and scalability of green energy technologies.

The U.S. Geological Survey (USGS) conducts assessments of these minerals using maps to quantify potential from domestic sources. Information from these assessments helps increase domestic production of critical minerals and reduce our reliance on imports.

But here’s the problem…

The current assessment process is highly manual. Roughly 10% of the USGS’ core database of 100,000 maps have been partially digitized, and an even smaller share have had the data extracted in a way that is usable. Because of this, it takes appx. 2-4 years to do a single assessment. You can read more about this issue here.

The good news is that we believe we can significantly speed up the assessment of the nation’s critical mineral resources by automating key steps in the process.

Here’s where you come in…

Today through September 23, we’re seeking participants with machine learning, computer vision, and/or AI experience for the following challenge as part of the broader competition. The first challenge is already underway. 

Map Feature Extraction Challenge: Automated map feature extraction is a difficult task because map features (polygons, points, lines) often overlap and are sometimes discontinuous. Not only do the features come in all shapes and sizes, but the same feature type can be depicted in different maps using different symbols or patterns. This makes it challenging to create a universal identifier for even a single feature such as a mine location or mineral resource tracts. Participants are provided a training set consisting of maps with each legend item labeled and characterized (as point, line, or polygon) and a binary pixel map reflecting the feature’s coverage in the map. The goal of the challenge is to identify the features in a map given the legend location and classification of the feature type. Register Now – Sept. 23.


For each of the two challenges, DARPA will award:

$10,000 for the first prize

$3,000 for the second prize

$1,000 for the third prize

In addition to cash prizes, you’ll also have an opportunity to participate in the Voices from DARPA podcast, brief members of DARPA leadership and staff on your work, and more.

So will you join us?

We encourage you to visit our webpage,, for complete details on how you can compete. 

Thank you for your interest in DSO and DARPA.