arXiv Machine Learning
Jul 28
From Physics to Surrogate Intelligence: A Unified Electro-Thermo-Optimization Framework for TSV Networks
arXiv:2603. 29268v2 Announce Type: replace Abstract: High-density through-substrate vias (TSVs) enable 2.
Compositional Embedding Architecture for Physical Field Prediction in Componentized Aerospace Systems
The paper introduces the Tree-Structured Factor Composition Network (TFCN), a surrogate model that decomposes spacecraft thermal configurations into reusable local physical factors and learns their global temperature-field response via a tree-structured composition module. Trained on configurations with up to 15 heat-generating components, TFCN is evaluated on unseen setups with 16–25 components, achieving out-of-distribution RMSE reductions of 65.6% and 33.6% compared to the best baseline for prescribed-temperature and radiative-flux boundary conditions, respectively. These results demonstrate that TFCN can reliably predict temperature fields across varying component counts, enabling efficient rapid evaluation and large-scale screening in spacecraft thermal design.
Related stories
arXiv Machine Learning
Aug 10
Defining Energy Indicators for Impact Identification on Aerospace Composites: A Structured Feature Selection Approach Guided by Domain Knowledge
arXiv:2511. 01592v2 Announce Type: replace Abstract: Energy estimation is critical to impact identification on aerospace composites, where low-velocity impacts can induce internal damage that is undetectable at the surface.
arXiv Machine Learning
Sep 15
Architecture--Optimization Co-Design for Physics-Informed Neural Networks via Layer-wise Coordinate Adaptation and Gradient Conflict Resolution
arXiv:2601.12971v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) can be limited by coordinate representations and conflicting gradients from heterogeneous physical constra...
arXiv Machine Learning
Jun 30
Implementation of Hyperelastic Physics-Augmented Neural Networks in the Explicit Finite Element Codes Simcenter Radioss and OpenRadioss with Applications to Impact Events
arXiv:2606. 29874v1 Announce Type: cross Abstract: Data-driven material modeling techniques have gained significant attention due to their ability to capture complex constitutive behaviors beyond the limitations of classical material models.
arXiv Machine Learning
Aug 18
DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design
arXiv:2608. 16080v1 Announce Type: new Abstract: Thermal-aware optimization of multi-die 3D integrated circuits evaluates many designs, each a costly heat-equation solve.
arXiv Machine Learning
Jun 16
Machine Learning-Driven Chemical Reactor Network Modeling of the Sandia-D Flame
arXiv:2606. 14729v1 Announce Type: cross Abstract: Turbulent combustion simulations are crucial for many scientific and engineering systems.
arXiv Machine Learning
Sep 18
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks
The paper introduces a method to amortize physics-informed neural networks (PINNs) across related partial differential equations (PDEs) by explicitly modeling equation relationships in an operator graph. Coefficient vectors encode numerical parameters, while the graph hypernetwork generates diagonal codes that initialize a meta‑trained factorized PINN for each target equation. Experiments on scalar convection‑diffusion‑reaction, two‑field Fisher‑KPP, and a capacitively coupled plasma model show that term‑based descriptors and graph conditioning improve solution accuracy compared to coefficient‑vector conditioning, especially for high‑reaction and coupled systems.
Hugging Face Trending Papers
Sep 17
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks
The paper proposes a method to amortize physics-informed neural networks (PINNs) across related partial differential equations (PDEs) by explicitly modeling equation relationships in an operator graph. Coefficient vectors encode numerical parameters, while the graph hypernetwork generates diagonal codes that initialize a meta‑trained factorized PINN for each target equation. Experiments on scalar convection‑diffusion‑reaction, two‑field Fisher‑KPP, and a capacitively coupled plasma model show that term‑based descriptors and graph conditioning improve solution accuracy compared to coefficient‑vector conditioning alone.
arXiv Machine Learning
Jun 4
Causal Multi-fidelity Surrogate Forward and Inverse Models for ICF Implosions
arXiv:2509. 05510v3 Announce Type: replace-cross Abstract: Continued progress in inertial confinement fusion (ICF) requires solving inverse problems relating experimental observations to simulation input parameters, followed by design optimization.
arXiv AI
Jul 1
Temperature Field Reconstruction of Tungsten Monoblock Divertor on EAST using Physics-aware Neural Operator Transformer
arXiv:2606. 31574v1 Announce Type: cross Abstract: Accurate modeling of the divertor temperature field is essential for preventing material melting and damage and for extending the service life of fusion devices.
arXiv Machine Learning
4d ago
A foundation model for energy and radiation systems built on heterogeneous scientific interfaces
arXiv:2609.38067v1 Announce Type: new Abstract: Scientific foundation models are commonly evaluated after heterogeneous physical problems have already been translated into a compatible gridded, token...
arXiv Machine Learning
Jul 21
SciForma: Structure-Faithful Generation of Scientific Diagrams
arXiv:2607. 18091v1 Announce Type: cross Abstract: Structural fidelity is essential to scientific methodology diagrams.