Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Torch-DPhys: A Torch-Native, MOOSE-Compatible Framework for Differentiable Physics Simulation and Hybrid Machine Learning Integration
Akzhol Almukhametov, Yang Liu
We present Torch-DPhys, a Torch-native framework implemented in PyTorch for differentiable physics simulation and hybrid physics-machine learning. It implements selected thermal-hy…
cs.LG2026
Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability
Akzhol Almukhametov, Doyeong Lim, Rui Hu +1
Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermal-hydraulic states, including locations where physical sensors are unavailable.…