Kangwook Lee: Train Both Model Weights and Harness with Data, Links to Physics-Integrated Neural Network Paper on Cryogenic Storage

Kangwook_Lee · x · 2026-09-03

Kangwook Lee tweets that with data, one can and should train both model weights and the 'harness', linking to an arXiv paper. The paper presents a physics-integrated neural network framework for heat and mass transfer in cryogenic liquid storage, combining a conservation-based zero-dimensional nodal model with data-driven closures, validated on 48 experiments.

Original post →

More from Research

Research channel →