Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling
arXiv:2606.13695v1 Announce Type: cross Abstract: Mineral prospectivity modelling (MPM) underpins exploration economics, yet most operational pipelines reduce to data-driven classifiers trained on shallow surface proxies. Such models are blind to the subsurface physics that actually localises ore: heat advection, fluid flow, and lithology-dependent precipitation. We present Korzhinskii-Net, a 2-D radial physics-informed neural network (PINN) that couples Darcy flow, advective-diffusive heat transport, and a softplus-saturated reaction rate into a single differentiable forward model, weakly sup
The increasing maturity of Physics-Informed Neural Networks (PINNs) allows for more sophisticated integration of domain knowledge into AI models, addressing limitations of purely data-driven approaches in complex physical systems.
This development allows for more accurate and efficient mineral exploration, potentially lowering costs and increasing the discovery rate of critical resources, which has implications for global supply chains and economic development.
Mineral prospectivity modelling can now incorporate subsurface physics directly, moving beyond shallow surface proxies to guide exploration more effectively.
- · Mining companies
- · Geophysical consulting firms
- · AI software developers
- · Resource-dependent nations
- · Traditional exploration methodologies without advanced AI
- · Companies relying solely on surface data
Increased efficiency and accuracy in resource identification will lead to more targeted and potentially less environmentally impactful exploration efforts.
Reduced exploration costs and improved success rates could stabilize or lower raw material prices for critical minerals, impacting industrial sectors.
The widespread adoption of PINNs in geology might accelerate their application in other complex subsurface domains like geothermal energy or carbon sequestration, further integrating AI with fundamental physics across industries.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI