Extracting data from maps: applying lessons learned from the AI for Critical Mineral Assessment Competition
This project will share techniques developed in two AI/ML competitions run in Fall 2022, Automated Map Georeferencing, and Automated Map Feature Extraction with USGS stakeholders. We will develop a strategy to operationalize successful approaches, benefiting any activity that uses legacy map data.
The goal of this project is to introduce the broader USGS community to machine learning tools for automated map georeferencing and feature extraction that were developed in the AI for Critical Mineral Assessment Competition (AI4CMA). The project builds on the collaborative effort between the USGS and the Defense Advanced Research Projects Agency (DARPA) to explore the potential of Artificial Intelligence tools for transforming mineral resource assessment activities focused on commodities critical for clean energy development. The competition, completed in December, surpassed expectations, and provided promising solutions from multiple teams comprised of leading AI scientists. The machine learning models have potential to benefit any activity that uses legacy map data. This project will organize two workshops to engage USGS stakeholders in developing a strategy to 1) continue to develop automated methods, 2) ensure successful approaches are preserved and shared, and 3) create guidance for operationalizing machine learning techniques at USGS.
Training and validation data from the AI for Critical Mineral Assessment Competition
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
This project will share techniques developed in two AI/ML competitions run in Fall 2022, Automated Map Georeferencing, and Automated Map Feature Extraction with USGS stakeholders. We will develop a strategy to operationalize successful approaches, benefiting any activity that uses legacy map data.
The goal of this project is to introduce the broader USGS community to machine learning tools for automated map georeferencing and feature extraction that were developed in the AI for Critical Mineral Assessment Competition (AI4CMA). The project builds on the collaborative effort between the USGS and the Defense Advanced Research Projects Agency (DARPA) to explore the potential of Artificial Intelligence tools for transforming mineral resource assessment activities focused on commodities critical for clean energy development. The competition, completed in December, surpassed expectations, and provided promising solutions from multiple teams comprised of leading AI scientists. The machine learning models have potential to benefit any activity that uses legacy map data. This project will organize two workshops to engage USGS stakeholders in developing a strategy to 1) continue to develop automated methods, 2) ensure successful approaches are preserved and shared, and 3) create guidance for operationalizing machine learning techniques at USGS.
Training and validation data from the AI for Critical Mineral Assessment Competition
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