Critical Minerals

AI-driven targeting and characterization for critical mineral exploration.

About Critical Minerals

From regional screening to prospect-scale targeting, our AI integrates geophysics, geochemistry, and remote sensing to reveal patterns linked to mineral systems and favorable geology.

Anomaly detection and ranking
Predictive mapping and prospectivity modeling
Structural and lithologic interpretations
Uncertainty quantification, risk assessment, and decision support

Related publications

Characterizing Boron and Lithium Partitioning in Martian Analog Materials Using Comprehensive Geo-Chemical Analysis, Principal Component Analysis, and Machine Learning (2024) — D Das et al. — 55th Lunar and Planetary Science Conference, 2024
Abstract
We established that Boron and Lithium enrichment processes are likely be different (i.e., evaporative and adsorptive in alkaline pH environments over multiple aqueous cycles) and this hypothesis is rein-forced by machine learning data analysis techniques such as PCA and NMFk. The inferences made using these analog samples can be applicable to both Gale crater and potential terrestrial Lithium sources.

Critical Minerals

AI-driven targeting and characterization for critical mineral exploration.

About Critical Minerals

From regional screening to prospect-scale targeting, our AI integrates geophysics, geochemistry, and remote sensing to reveal patterns linked to mineral systems and favorable geology.

Anomaly detection and ranking
Predictive mapping and prospectivity modeling
Structural and lithologic interpretations
Uncertainty quantification, risk assessment, and decision support

Related publications

Characterizing Boron and Lithium Partitioning in Martian Analog Materials Using Comprehensive Geo-Chemical Analysis, Principal Component Analysis, and Machine Learning (2024) — D Das et al. — 55th Lunar and Planetary Science Conference, 2024
Abstract
We established that Boron and Lithium enrichment processes are likely be different (i.e., evaporative and adsorptive in alkaline pH environments over multiple aqueous cycles) and this hypothesis is rein-forced by machine learning data analysis techniques such as PCA and NMFk. The inferences made using these analog samples can be applicable to both Gale crater and potential terrestrial Lithium sources.