Skip to main content

Map feature extraction challenge training and validation data

Dates

Publication Date
Start Date
2022
End Date
2023

Citation

Goldman, M.A., Rosera, J.M., Lederer, G.W., Graham, G.E., Mishra, A., and Yepremyan, A., 2023, Training and validation data from the AI for Critical Mineral Assessment Competition: U.S. Geological Survey data release, https://doi.org/10.5066/P9FXSPT1.

Summary

Extracting useful and accurate information from scanned geologic and other earth science maps is a time-consuming and laborious process involving manual human effort. To address this limitation, the USGS partnered with the Defense Advanced Research Projects Agency (DARPA) to run the AI for Critical Mineral Assessment Competition, soliciting innovative solutions for automatically georeferencing and extracting features from maps. The competition opened for registration in August 2022 and concluded in December 2022. Training and validation data from the map feature extraction challenge are provided here, as well as competition details and a baseline solution. The data were derived from published sources and are provided to the public [...]

Contacts

Attached Files

Click on title to download individual files attached to this item.


“Training set”
16.95 GB application/x-gzip

“Updated validation jsons”
42.18 KB application/x-gzip

“Validation set answer key”
107.46 MB application/x-gzip

“Validation set”
6.08 GB application/gzip
test_data2.zip
“Test data for baseline”
54.06 MB application/zip
AI4CMA_FeatureExtraction_Challenge_Baseline.ipynb
“Baseline notebook”
1.57 MB text/plain
Map Feature Extraction Challenge Details.pdf
“Overview of map feature extraction challenge”
1.86 MB application/pdf
MapFeatureExtractionReferences.csv 65.59 KB text/csv

Purpose

The training and validation data were provided to participants in the DARPA AI for Critical Mineral Assessment Competition to develop automated map georeferencing and feature extraction tools, two tasks that the USGS currently does manually using GIS software. The USGS prepares a wide range of maps (various scales, resolutions, and themes) when conducting mineral resource assessments. Manually performing these tasks is time- and labor-intensive. The purpose of the competition was to find innovative approaches to automatically georeference and extract features from diverse maps, with the overall goal of accelerating advances in critical mineral resource science and assessment.

Map

Communities

  • USGS Geology, Geophysics, and Geochemistry Science Center

Tags

Provenance

Data source
Input directly
Level 1 revision on February 22, 2024 by Margaret A Goldman. The reference file "MapFeatureExtractionReferences.csv" was uploaded.

Item Actions

View Item as ...

Save Item as ...

View Item...