Sanjay Choudhry

Deepak Akhare, Mohammad Amin Nabian, Corey Adams et al.

Automotive crashworthiness optimization remains a safety-critical challenge, requiring the management of large-scale nonlinear structural deformations and energy dissipation through iterative, high-fidelity simulations. While traditional finite element solvers are computationally prohibitive, emerging operator learning frameworks provide rapid surrogate predictions; however, applying them to industrial-scale crash analysis, where complex geometry, contact nonlinearities, and rapidly evolving transient deformation coexist, remains an open challenge. In this paper, we demonstrate that the GeoTransolver framework provides a viable solution for accurate, high-fidelity crash dynamics prediction at industrial scale. Benchmarked on complex bumper beam and full-vehicle crash datasets, GeoTransolver captures multi-scale geometric context and accurately resolves plastic deformation patterns as well as acceleration profiles at critical occupant locations. Beyond the architecture itself, we propose and systematically evaluate a suite of temporal prediction recipes, including one-shot, time-conditional, and autoregressive rollout strategies, demonstrating that the one-shot approach achieves state-of-the-art accuracy with significantly reduced training overhead and inference latency. As a secondary contribution, we introduce a Fast Low-rank Attention Routing Engine (FLARE)-based modification to the GeoTransolver attention backbone that reduces memory overhead by approximately 2x while further improving predictive accuracy for O(N) long-range, high-frequency transients, preserving the geometry-aware cross-attention strengths of the base framework. Our results highlight the practical viability of geometry-aware operator learning for high-fidelity surrogate modeling of complex, safety-critical automotive dynamics.

Corey Adams, Rishikesh Ranade, Ram Cherukuri et al.

We present GeoTransolver, a Multiscale Geometry-Aware Physics Attention Transformer for CAE that replaces standard attention with GALE, coupling physics-aware self-attention on learned state slices with cross-attention to a shared geometry/global/boundary-condition context computed from multi-scale ball queries (inspired by DoMINO) and reused in every block. Implemented and released in NVIDIA PhysicsNeMo, GeoTransolver persistently projects geometry, global and boundary condition parameters into physical state spaces to anchor latent computations to domain structure and operating regimes. We benchmark GeoTransolver on DrivAerML, Luminary SHIFT-SUV, and Luminary SHIFT-Wing, comparing against Domino, Transolver (as released in PhysicsNeMo), and literature-reported AB-UPT, and evaluate drag/lift R2 and Relative L1 errors for field variables. GeoTransolver delivers better accuracy, improved robustness to geometry/regime shifts, and favorable data efficiency; we include ablations on DrivAerML and qualitative results such as contour plots and design trends for the best GeoTransolver models. By unifying multiscale geometry-aware context with physics-based attention in a scalable transformer, GeoTransolver advances operator learning for high-fidelity surrogate modeling across complex, irregular domains and non-linear physical regimes.

Pouria Mistani, Samira Pakravan, Rajesh Ilango et al.

We present a highly scalable strategy for developing mesh-free neuro-symbolic partial differential equation solvers from existing numerical discretizations found in scientific computing. This strategy is unique in that it can be used to efficiently train neural network surrogate models for the solution functions and the differential operators, while retaining the accuracy and convergence properties of state-of-the-art numerical solvers. This neural bootstrapping method is based on minimizing residuals of discretized differential systems on a set of random collocation points with respect to the trainable parameters of the neural network, achieving unprecedented resolution and optimal scaling for solving physical and biological systems.

Kaustubh Tangsali, Rishikesh Ranade, Mohammad Amin Nabian et al.

In this paper, we introduce a benchmarking framework within the open-source NVIDIA PhysicsNeMo-CFD framework designed to systematically assess the accuracy, performance, scalability, and generalization capabilities of AI models for automotive aerodynamics predictions. The open extensible framework enables incorporation of a diverse set of metrics relevant to the Computer-Aided Engineering (CAE) community. By providing a standardized methodology for comparing AI models, the framework enhances transparency and consistency in performance assessment, with the overarching goal of improving the understanding and development of these models to accelerate research and innovation in the field. To demonstrate its utility, the framework includes evaluation of both surface and volumetric flow field predictions on three AI models: DoMINO, X-MeshGraphNet, and FIGConvNet using the DrivAerML dataset. It also includes guidelines for integrating additional models and datasets, making it extensible for physically consistent metrics. This benchmarking study aims to enable researchers and industry professionals in selecting, refining, and advancing AI-driven aerodynamic modeling approaches, ultimately fostering the development of more efficient, accurate, and interpretable solutions in automotive aerodynamics

Corey Adams, Peter Harrington, Akshay Subramaniam et al.

Scientific Machine Learning (SciML) faces unique challenges for extreme-resolution data, with mitigations that often fail to scale or degrade the accuracy of trained models. While some specialized methods have achieved remarkable results in training models or performing inference on massive spatial datasets with bespoke techniques, there is no generalized framework for parallelization over input data below batch size one per device. In this work we introduce ShardTensor: a novel paradigm of domain parallelism that enables flexible scaling of input data to arbitrary sizes. By decoupling the spatial dimensionality of input data from hardware constraints, ShardTensor enables scientific machine learning workloads to reach new levels of high fidelity training and inference. We demonstrate both strong and weak scaling of workloads during training and inference, showing improved latency with strong scaling and demonstrating the capacity to process higher data sizes with weak scaling. Additionally, we demonstrate multiple dimensions of parallelization, removing barriers to SciML on extreme-scale inputs.

Oliver Hennigh, Susheela Narasimhan, Mohammad Amin Nabian et al.

We present SimNet, an AI-driven multi-physics simulation framework, to accelerate simulations across a wide range of disciplines in science and engineering. Compared to traditional numerical solvers, SimNet addresses a wide range of use cases - coupled forward simulations without any training data, inverse and data assimilation problems. SimNet offers fast turnaround time by enabling parameterized system representation that solves for multiple configurations simultaneously, as opposed to the traditional solvers that solve for one configuration at a time. SimNet is integrated with parameterized constructive solid geometry as well as STL modules to generate point clouds. Furthermore, it is customizable with APIs that enable user extensions to geometry, physics and network architecture. It has advanced network architectures that are optimized for high-performance GPU computing, and offers scalable performance for multi-GPU and multi-Node implementation with accelerated linear algebra as well as FP32, FP64 and TF32 computations. In this paper we review the neural network solver methodology, the SimNet architecture, and the various features that are needed for effective solution of the PDEs. We present real-world use cases that range from challenging forward multi-physics simulations with turbulence and complex 3D geometries, to industrial design optimization and inverse problems that are not addressed efficiently by the traditional solvers. Extensive comparisons of SimNet results with open source and commercial solvers show good correlation.

Mohammad Amin Nabian, Chang Liu, Rishikesh Ranade et al.

Graph Neural Networks (GNNs) have gained significant traction for simulating complex physical systems, with models like MeshGraphNet demonstrating strong performance on unstructured simulation meshes. However, these models face several limitations, including scalability issues, requirement for meshing at inference, and challenges in handling long-range interactions. In this work, we introduce X-MeshGraphNet, a scalable, multi-scale extension of MeshGraphNet designed to address these challenges. X-MeshGraphNet overcomes the scalability bottleneck by partitioning large graphs and incorporating halo regions that enable seamless message passing across partitions. This, combined with gradient aggregation, ensures that training across partitions is equivalent to processing the entire graph at once. To remove the dependency on simulation meshes, X-MeshGraphNet constructs custom graphs directly from tessellated geometry files (e.g., STLs) by generating point clouds on the surface or volume of the object and connecting k-nearest neighbors. Additionally, our model builds multi-scale graphs by iteratively combining coarse and fine-resolution point clouds, where each level refines the previous, allowing for efficient long-range interactions. Our experiments demonstrate that X-MeshGraphNet maintains the predictive accuracy of full-graph GNNs while significantly improving scalability and flexibility. This approach eliminates the need for time-consuming mesh generation at inference, offering a practical solution for real-time simulation across a wide range of applications. The code for reproducing the results presented in this paper is available through NVIDIA Modulus.

Rishikesh Ranade, Mohammad Amin Nabian, Kaustubh Tangsali et al.

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.

Peter Sharpe, Rishikesh Ranade, Kaustubh Tangsali et al.

Transient computational fluid dynamics (CFD) simulations are essential for many industrial applications, but suffer from high compute costs relative to steady-state simulations. This is due to the need to: (a) reach statistical steadiness by physically advecting errors in the initial field sufficiently far downstream, and (b) gather a sufficient sample of fluctuating flow data to estimate time-averaged quantities of interest. We present a machine learning-based initialization method that aims to reduce the cost of transient solve by providing more accurate initial fields. Through a case study in automotive aerodynamics on a 17M-cell unsteady incompressible RANS simulation, we evaluate three proposed ML-based initialization strategies against existing methods. Here, we demonstrate 50% reductions in time-to-convergence compared to traditional uniform and potential flow-based initializations. Two ML-based initialization strategies are recommended for general use: (1) a hybrid method combining ML predictions with potential flow solutions, and (2) an approach integrating ML predictions with uniform flow. Both strategies enable CFD solvers to achieve convergence times comparable to computationally-expensive steady RANS initializations, while requiring far less wall-clock time to compute the initialization field. Notably, these improvements are achieved using an ML model trained on a different dataset of diverse automotive geometries, demonstrating generalization capabilities relevant to specific industrial application areas. Because this Hybrid-ML workflow only modifies the inputs to an existing CFD solver, rather than modifying the solver itself, it can be applied to existing CFD workflows with relatively minimal changes; this provides a practical approach to accelerating industrial CFD simulations using existing ML surrogate models.

Dibyajyoti Chakraborty, Romit Maulik, Peter Harrington et al.

Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel paradigm to overcome these limitations, not by creating a new forecaster, but by optimally combining the outputs of existing models. The MoWE model is trained with significantly lower computational resources than the individual experts. Our model employs a Vision Transformer-based gating network that dynamically learns to weight the contributions of multiple "expert" models at each grid point, conditioned on forecast lead time. This approach creates a synthesized deterministic forecast that is more accurate than any individual component in terms of Root Mean Squared Error (RMSE). Our results demonstrate the effectiveness of this method, achieving up to a 10% lower RMSE than the best-performing AI weather model on a 2-day forecast horizon, significantly outperforming individual experts as well as a simple average across experts. This work presents a computationally efficient and scalable strategy to push the state of the art in data-driven weather prediction by making the most out of leading high-quality forecast models.

Mohammad Amin Nabian, Sanjay Choudhry

The computational cost associated with high-fidelity CFD simulations remains a significant bottleneck in the automotive design and optimization cycle. While ML-based surrogate models have emerged as a promising alternative to accelerate aerodynamic predictions, the field is characterized by a diverse and rapidly evolving landscape of specialized neural network architectures, with no single model demonstrating universal superiority. This paper introduces a novel meta-learning framework that leverages this architectural diversity as a strength. We propose a Mixture of Experts (MoE) model that employs a dedicated gating network to dynamically and optimally combine the predictions from three heterogeneous, state-of-the-art surrogate models: DoMINO, a decomposable multi-scale neural operator; X-MeshGraphNet, a scalable multi-scale graph neural network; and FigConvNet, a factorized implicit global convolution network. The gating network learns a spatially-variant weighting strategy, assigning credibility to each expert based on its localized performance in predicting surface pressure and wall shear stress fields. To prevent model collapse and encourage balanced expert contributions, we integrate an entropy regularization term into the training loss function. The entire system is trained and validated on the DrivAerML dataset, a large-scale, public benchmark of high-fidelity CFD simulations for automotive aerodynamics. Quantitative results demonstrate that the MoE model achieves a significant reduction in L-2 prediction error, outperforming not only the ensemble average but also the most accurate individual expert model across all evaluated physical quantities. This work establishes the MoE framework as a powerful and effective strategy for creating more robust and accurate composite surrogate models by synergistically combining the complementary strengths of specialized architectures.

Benjamin Wu, Oliver Hennigh, Jan Kautz et al.

Physics-informed neural networks allow models to be trained by physical laws described by general nonlinear partial differential equations. However, traditional architectures struggle to solve more challenging time-dependent problems due to their architectural nature. In this work, we present a novel physics-informed framework for solving time-dependent partial differential equations. Using only the governing differential equations and problem initial and boundary conditions, we generate a latent representation of the problem's spatio-temporal dynamics. Our model utilizes discrete cosine transforms to encode spatial frequencies and recurrent neural networks to process the time evolution. This efficiently and flexibly produces a compressed representation which is used for additional conditioning of physics-informed models. We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations. Our proposed model achieves state-of-the-art performance on the Taylor-Green vortex relative to other physics-informed baseline models.