Related papers: From Physics to Surrogate Intelligence: A Unified …
Machine Learning surrogates for Computational Fluid Dynamics (CFD), particularly Graph Neural Networks (GNNs) and Transformers, have become a new important approach for accelerating physics simulations. However, we identify a critical…
Reliable artificial-intelligence models have the potential to accelerate the discovery of materials with optimal properties for various applications, including superconductivity, catalysis, and thermoelectricity. Advancements in this field…
Neural networks can be used as surrogates for PDE models. They can be made physics-aware by penalizing underlying equations or the conservation of physical properties in the loss function during training. Current approaches allow to…
Deep learning has significantly advanced automatic medical diagnostics and released the occupation of human resources to reduce clinical pressure, yet the persistent challenge of data scarcity in this area hampers its further improvements…
Predicting nutrient transport and salinity distribution is crucial for mitigating climate-related threats to agromaritime systems. Traditional PDE-based models can capture the physics of nutrient dispersion, salinity and water quality.…
Disorder, though naturally present in experimental samples and strongly influencing a wide range of material phenomena, remains underexplored in first-principles studies due to the computational cost of sampling the large supercell and…
Wire-arc directed energy deposition (DED) has emerged as a promising additive manufacturing (AM) technology for large-scale structural engineering applications. However, the complex thermal dynamics inherent to the process present…
Improving predictive understanding of Earth system variability and change requires data-model integration. Efficient data-model integration for complex models requires surrogate modeling to reduce model evaluation time. However, building a…
The highly sparse activations in Spiking Neural Networks (SNNs) can provide tremendous energy efficiency benefits when carefully exploited in hardware. The behavior of sparsity in SNNs is uniquely shaped by the dataset and training…
Accurately predicting the behavior of a nuclear reactor requires multiphysics simulation of coupled neutronics, thermal-hydraulics and fuel thermo-mechanics. The fuel thermo-mechanical response provides essential information for operational…
We present surrogate models for heat transfer and pressure drop prediction of complex fin geometries generated using composite Bezier curves. Thermal design process includes iterative high fidelity simulation which is complex,…
Thermoelectric (TE) generators can directly convert heat into electricity, but their performance is often constrained by limited temperature gradients. Here it is shown that width-modulated metamaterials with constrictions and expansions…
As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as…
Modern computational methods, involving highly sophisticated mathematical formulations, enable several tasks like modeling complex physical phenomenon, predicting key properties and design optimization. The higher fidelity in these computer…
Inhomogeneous current and temperature distributions are harmful to the durability of the solid oxide electrolysis cell (SOEC). Segmented SOEC experiments reveal that a high steam utilization, which is favorable for system efficiency, leads…
In this paper we study the thermal effective behaviour for 3D multiphase composite material consisting of three isotropic phases which are the matrix, the inclusions and the coating media. For this purpose we use an accelerated FFT-based…
Vertical equilibrium (VE) models have been introduced as computationally efficient alternatives to traditional mass and momentum balance equations for fluid flow in porous media. Since VE models are only accurate in regions where phase…
Since the internal temperature is less accessible than surface temperature, there is an urgent need to develop accurate and real-time estimation algorithms for better thermal management and safety. This work presents a novel framework for…
Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate…
Simulation-based optimization is a useful method for practical design problems. However, it is difficult for complicated problems due to expensive-computational costs. A popular way to overcome this issue is to use a surrogate model to save…