A Kernel-based Resource-efficient Neural Surrogate for Multi-fidelity Prediction of Aerodynamic Field

2025/12/11 by A. H. M. Raihan Sarker, Sarker, Apurba, Batley, Reza T. +4
Computer Science · Engineering · Physics and Astronomy · #Advanced Multi-Objective Optimization Algorithms #Computational Fluid Dynamics and Aerodynamics #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Machine Learning (cs.LG) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2512.10287

openalex publication_date 2025/12/11 · openalex created_date 2025/12/13 · openalex updated_date 2026/07/28

Abstract

Surrogate models provide fast alternatives to costly aerodynamic simulations and are extremely useful in design and optimization applications. This study proposes the use of a recent kernel-based neural surrogate, KHRONOS. In this work, we blend sparse high-fidelity (HF) data with low-fidelity (LF) information to predict aerodynamic fields under varying constraints in computational resources. Unlike traditional approaches, KHRONOS is built upon variational principles, interpolation theory, and tensor decomposition. These elements provide a mathematical basis for heavy pruning compared to dense neural networks. Using the AirfRANS dataset as a high-fidelity benchmark and NeuralFoil to generate low-fidelity counterparts, this work compares the performance of KHRONOS with three contemporary model architectures: a multilayer perceptron (MLP), a graph neural network (GNN), and a physics-informed neural network (PINN). We consider varying levels of high-fidelity data availability (0%, 10%, and 30%) and increasingly complex geometry parameterizations. These are used to predict the surface pressure coefficient distribution over the airfoil. Results indicate that, whilst all models eventually achieve comparable predictive accuracy, KHRONOS excels in resource-constrained conditions. In this domain, KHRONOS consistently requires orders of magnitude fewer trainable parameters and delivers much faster training and inference than contemporary dense neural networks at comparable accuracy. These findings highlight the potential of KHRONOS and similar architectures to balance accuracy and efficiency in multi-fidelity aerodynamic field prediction.

Citations

• KHRONOS: a Kernel-Based Neural Architecture for Rapid, Resource-Efficient Scientific Computation
• NeuralFoil: An Airfoil Aerodynamics Analysis Tool Using Physics-Informed Machine Learning
• Active learning-assisted multi-fidelity surrogate modeling based on geometric transformation
• Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
• Multi-fidelity surrogate modeling for temperature field prediction using deep convolution neural network
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems
• Two-equation eddy-viscosity turbulence models for engineering applications

Related

• Towards scalable surrogate models based on Neural Fields for large scale aerodynamic simulations
• A Multi-fidelity Double-Delta Wing Dataset and Empirical Scaling Laws for GNN-based Aerodynamic Field Surrogate
• Efficient aerodynamic coefficients prediction with a long sequence neural network
• Accelerated Airfoil Design Using Neural Network Approaches
• A Hybrid CNN-Cheby-KAN Framework for Efficient Prediction of Two-Dimensional Airfoil Pressure Distribution