REVIEW 6 cited by
DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Numerical simulations play a critical role in design and development of engineering products and processes. Traditional computational methods, such as CFD, can provide accurate predictions but are computationally expensive, particularly for complex geometries. Several machine learning (ML) models have been proposed in the literature to significantly reduce computation time while maintaining acceptable accuracy. However, ML models often face limitations in terms of accuracy and scalability and depend on significant mesh downsampling, which can negatively affect prediction accuracy and generalization. In this work, we propose a novel ML model architecture, DoMINO (Decomposable Multi-scale Iterative Neural Operator) developed in NVIDIA Modulus to address the various challenges of machine learning based surrogate modeling of engineering simulations. DoMINO is a point cloudbased ML model that uses local geometric information to predict flow fields on discrete points. The DoMINO model is validated for the automotive aerodynamics use case using the DrivAerML dataset. Through our experiments we demonstrate the scalability, performance, accuracy and generalization of our model to both in-distribution and out-of-distribution testing samples. Moreover, the results are analyzed using a range of engineering specific metrics important for validating numerical simulations.
Forward citations
Cited by 6 Pith papers
-
Evaluation of State-of-the-Art Deep Learning Architectures for Aerodynamical Predictions
Benchmarking four neural operators for airfoil and NASA CRM pressure prediction: Transolver best on 2D, BSMS-GNN best on 3D; UPT and GAOT lag.
-
NeuroForge: A Self-Correcting, Geometry-Native Neural CFD Engine with Calibrated Physics-Residual Trust
The steady-RANS residual of a neural CFD prediction is a backbone-robust case-level trust signal but a poor correction objective; a supervised DEQ corrector cuts field MSE on a SOTA backbone without needing residual c...
-
A Benchmarking Framework for AI models in Automotive Aerodynamics
A new benchmarking framework standardizes evaluation of AI automotive aerodynamics models, demonstrated on three models with the DrivAerML dataset.
-
Multi-Granularity Conformal Prediction for Reliable Neural-Operator Automotive Aerodynamic Surrogates
Conformal calibration converts deterministic neural-operator aerodynamic predictions into case- and surface-adaptive 90% reliability intervals on DrivAerML, with out-of-fold scoring stabilizing coverage.
-
A Mixture of Experts Gating Network for Enhanced Surrogate Modeling in External Aerodynamics
A mixture-of-experts gating network that fuses predictions from DoMINO, X-MeshGraphNet, and FigConvNet reduces L-2 prediction error for automotive surface pressure and wall shear stress below each individual expert on...
-
GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer
GeoTransolver, a geometry-aware attention transformer, improves surrogate CFD accuracy over existing baselines on three automotive/aerospace datasets, but the paper has major reporting gaps.
Discussion (0). Sign in to comment.