Tag: surrogate modeling

A computational study found that the hybrid plant’s verified break-even price was $1.77–$3.12 per kilowatt-hour versus an uncooled PV-plus-OTEC reference, ...

A neural-network surrogate paired with differential evolution reduced model-predicted EV battery thermal risk by 94.8% across charging rates from 0.5C ...

A physics-informed residual network reconstructed aneurysm blood-flow fields more accurately than standard machine-learning models, with its strongest gains appearing in ...

A new heterogeneous graph Kolmogorov-Arnold network called HG-KAN predicts how water injected into layered oil reservoirs will perform, achieving high ...

Researchers have built a self-calibrating, physics-aware active learning workflow that finds well-matched microstrip patch antenna designs across four substrates and ...

An interpretable machine-learning framework trained on electro-thermal finite-element simulations predicts hidden temperature rise in bolted switchgear busbar joints, with XGBoost ...

A new hybrid reliability method called AK-FOCM combines active learning Kriging with first order control variates to estimate rare failure ...

Researchers have trained a deep neural network on 130,000 simulated samples to predict the reflection coefficients of an eight-port terahertz ...

Researchers used Bayesian optimization with Gaussian process surrogate modeling to design microfluidic deterministic lateral displacement chips that separate circulating tumor ...

Researchers at Yangzhou University have developed an AI-driven evolutionary algorithm that reconfigures electrical distribution networks to reduce power losses, validated ...