Critical minerals are vital components in modern technology and the global economy, playing essential roles in products like smartphones, computers, electric vehicles, and renewable energy storage. However, geological maps and reports that are necessary for locating mine deposits often exist in non-analytic formats. Therefore, we are undertaking a two-part project that includes AIM (AI for Maps) and MinMod. AIM focuses on automating critical mineral assessments by utilizing machine learning algorithms to georeference geological maps and extract valuable features, streamlining the exploration and security efforts for critical minerals. On the other hand, MinMod aims to automate the creation of grade and tonnage models and rich mineral site data by harnessing AI and machine learning techniques to process academic, governmental, and industry datasets and reports. This innovative approach seeks to significantly reduce the time required for generating mineral models, making it possible to maintain up-to-date information for prospectivity modeling and ensure the availability of current grade and tonnage models and mineral site data for various minerals and deposit types.
- [2023/09/08] Our paper The mapKurator System: A complete Pipeline for Extracting and Linking Text From Historical Maps for extracting text labels on maps is accepted as a demo paper at the ACM SIGSPATIAL’23
- [2023/09/08] Our paper Exploiting Polygon Metadata to Understand Raster Maps focusing on polygonal feature extraction is accepted as a full paper at the ACM SIGSPATIAL’23
- [2023/08/15] We are excited to attend the project kick-off meeting at Shepherdstown, WV hosted by DARPA, USGS and MITRE :earth_americas: