Physics-informed neural network advances mineral prospectivity modeling

Researchers have developed Korzhinskii-Net, a novel physics-informed neural network designed for mineral prospectivity modeling. This 2D radial PINN integrates physical principles like fluid flow and heat transport into a differentiable forward model, supervised by surface data. Tested across five diverse ore provinces, Korzhinskii-Net significantly outperformed classical machine learning baselines, demonstrating its ability to identify subsurface ore localization patterns that purely data-driven methods miss. AI

IMPACT This physics-informed approach could enable more accurate subsurface exploration, reducing costs and improving discovery rates in resource-rich regions.

RANK_REASON The cluster describes a new academic paper detailing a novel physics-informed neural network for a specific scientific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Dmitri S. Korzhinskii
• Korzhinskii-Net
• Mirny
• Norilsk
• Pechenga
• Sukhoi Log mine
• Udokan Plateau

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →