AI Learns Geochemistry: New Explainable Model Targets Rare Earth Deposits
Researchers have developed EBGT, an explainable machine learning framework that embeds geochemical constraints into gradient-boosted trees to identify ion-adsorption rare ...
Researchers have developed EBGT, an explainable machine learning framework that embeds geochemical constraints into gradient-boosted trees to identify ion-adsorption rare ...
A new dual-masked graph autoencoder called DM-GAE maps mineral prospectivity in Tibet with high accuracy despite scarce labeled deposits, outperforming ...
Researchers have combined GradientSHAP and 3D Contrast Grad-CAM to reveal how a 3D convolutional neural network identifies deep concealed orebodies ...
Integrated laboratory measurements at South Korea's Myeonsan titanium deposit show that density and induced polarization most reliably distinguish titanium-bearing ores ...
A self-training LightGBM framework developed at Jilin University recognizes mineralization-related geochemical anomalies in Inner Mongolia using sparse labeled and vast ...
A new label-scarce graph AI framework reliably detects deep, subtle mineralization anomalies at the Kalatongke copper-nickel deposit using only 906 ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine