temperature-estimation

Improving hyperthermia treatment by controlling temperature distribution in both 1D and 2D domains and thermal energy applied to cutaneous and subcutaneous tissues, through Bio-Heat equation with Physics-Informed Neural Networks (PINNs).

Internal temperature of a lithium-ion cell reconstructed from surface data alone, validated against a real core thermocouple. Three estimators on identical information: a one-line algebraic relation wins at 0.141 K, the inverse PINN loses at 0.614 K. The negative result is the headline.