Clever Data Trick Doubles the Sharpness of Deep Seismic Images in South China
A new processing strategy that interpolates irregular seismic shot points onto a regular 100-meter grid has dramatically sharpened deep crustal ...
A new processing strategy that interpolates irregular seismic shot points onto a regular 100-meter grid has dramatically sharpened deep crustal ...
A newly analysed carbonatite plug at Khaderpet in southern India is exceptionally enriched in light rare earth elements and occurs ...
New research shows that coarse, smoothed labels in continental-scale AI mineral prospectivity maps artificially inflate model performance while erasing high-probability ...
New processing of aeromagnetic data from the Akonolinga-Nguinda area of Centre-East Cameroon has mapped 51 buried lineaments and a 4-kilometer-deep ...
An integrated aeromagnetic study of Nigeria's Igarra Schist Belt has mapped buried faults and shear zones that align with active ...
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 ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine