An official website of the United States government
We introduce Neural Flow Maps, a novel simulation method bridging the emerging paradigm of implicit neural representations with fluid simulation based on the theory of flow maps, to achieve state-of-the-art simulation of in-viscid fluid phenomena. We devise a novel hybrid neural field representation, Spatially Sparse Neural Fields (SSNF), which fuses small neural networks with a pyramid of overlapping, multi-resolution, and spatially sparse grids, to compactly represent long-term spatiotemporal velocity fields at high accuracy. With this neural velocity buffer in hand, we compute long-term, bidirectional flow maps and their Jacobians in a mechanistically symmetric manner, to facilitate drastic accuracy improvement over existing solutions. These long-range, bidirectional flow maps enable high advection accuracy with low dissipation, which in turn facilitates high-fidelity incompressible flow simulations that manifest intricate vortical structures. We demonstrate the efficacy of our neural fluid simulation in a variety of challenging simulation scenarios, including leapfrogging vortices, colliding vortices, vortex reconnections, as well as vortex generation from moving obstacles and density differences. Our examples show increased performance over existing methods in terms of energy conservation, visual complexity, adherence to experimental observations, and preservation of detailed vortical structures.
more »
« less
This content will become publicly available on July 1, 2026
Signed distance function–biased flow importance sampling for implicit neural compression of flow fields
Abstract The rise of exascale supercomputing has motivated an increase in high‐fidelity computational fluid dynamics (CFD) simulations. The detail in these simulations, often involving shape‐dependent, time‐variant flow domains and low‐speed, complex, turbulent flows, is essential for fueling innovations in fields like wind, civil, automotive, or aerospace engineering. However, the massive amount of data these simulations produce can overwhelm storage systems and negatively affect conventional data management and postprocessing workflows, including iterative procedures such as design space exploration, optimization, and uncertainty quantification. This study proposes a novel sampling method harnessing the signed distance function (SDF) concept: SDF‐biased flow importance sampling (BiFIS) and implicit compression based on implicit neural network representations for transforming large‐size, shape‐dependent flow fields into reduced‐size shape‐agnostic images. Designed to alleviate the above‐mentioned problems, our approach achieves near‐lossless compression ratios of approximately :, reducing the size of a bridge aerodynamics forced‐vibration simulation from roughly to about while maintaining low reproduction errors, in most cases below , which is unachievable with other sampling approaches. Our approach also allows for real‐time analysis and visualization of these massive simulations and does not involve decompression preprocessing steps that yield full simulation data again. Given that image sampling is a fundamental step for any image‐based flow field prediction model, the proposed BiFIS method can significantly improve the accuracy and efficiency of such models, helping any application that relies on precise flow field predictions. The BiFIS code is available onGitHub.
more »
« less
- Award ID(s):
- 2503131
- PAR ID:
- 10642221
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Computer-Aided Civil and Infrastructure Engineering
- Volume:
- 40
- Issue:
- 17
- ISSN:
- 1093-9687
- Page Range / eLocation ID:
- 2434 to 2463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Global optical flow estimation is the foundation stone for obtaining odometry which is used to enable aerial robot navigation. However, such a method has to be of low latency and high robustness whilst also respecting the size, weight, area and power (SWAP) constraints of the robot. A combination of cameras coupled with inertial measurement units (IMUs) has proven to be the best combination in order to obtain such low latency odometry on resource‐constrained aerial robots. Recently, deep learning approaches for visual inertial fusion have gained momentum due to their high accuracy and robustness. However, an equally noteworthy benefit for robotics of these techniques are their inherent scalability (adaptation to different sized aerial robots) and unification (same method works on different sized aerial robots). To this end, we present a deep learning approach called PRGFlow for obtaining global optical flow and then loosely fuse it with an IMU for full 6‐DoF (Degrees of Freedom) relative pose estimation (which is then integrated to obtain odometry). The network is evaluated on the MSCOCO dataset and the dead‐reckoned odometry on multiple real‐flight trajectories without any fine‐tuning or re‐training. A detailed benchmark comparing different network architectures and loss functions to enable scalability is also presented. It is shown that the method outperforms classical feature matching methods by 2 under noisy data. The supplementary material and code can be found athttp://prg.cs.umd.edu/PRGFlow.more » « less
-
Abstract In this paper we present a reconstruction technique for the reduction of unsteady flow data based on neural representations of time‐varying vector fields. Our approach is motivated by the large amount of data typically generated in numerical simulations, and in turn the types of data that domain scientists can generatein situthat are compact, yet useful, for post hoc analysis. One type of data commonly acquired during simulation are samples of the flow map, where a single sample is the result of integrating the underlying vector field for a specified time duration. In our work, we treat a collection of flow map samples for a single dataset as a meaningful, compact, and yet incomplete, representation of unsteady flow, and our central objective is to find a representation that enables us to best recover arbitrary flow map samples. To this end, we introduce a technique for learning implicit neural representations of time‐varying vector fields that are specifically optimized to reproduce flow map samples sparsely covering the spatiotemporal domain of the data. We show that, despite aggressive data reduction, our optimization problem — learning a function‐space neural network to reproduce flow map samples under a fixed integration scheme — leads to representations that demonstrate strong generalization, both in the field itself, and using the field to approximate the flow map. Through quantitative and qualitative analysis across different datasets we show that our approach is an improvement across a variety of data reduction methods, and across a variety of measures ranging from improved vector fields, flow maps, and features derived from the flow map.more » « less
-
Abstract Obtaining meteoroid mass from head echo radar cross section depends on the assumed plasma density distribution around the meteoroid. An analytical model presented in Dimant and Oppenheim (2017a,https://doi.org/10.1002/2017JA023960; 2017b,https://doi.org/10.1002/2017JA023963) and simulation results presented in Sugar et al. (2018,https://doi.org/10.1002/2018JA025265) suggest the plasma density distribution is significantly different than the spherically symmetric Gaussian distribution used to calculate meteoroid masses in many previous studies. However, these analytical and simulation results ignored the effects of electric and magnetic fields and assumed quasi‐neutrality. This paper presents results from the first particle‐in‐cell simulations of head echo plasma that include electric and magnetic fields. The simulations show that the fields change the ion density distribution by less than ∼2% in the meteor head echo region, but the electron density distribution changes by up to tens of percent depending on the location, electron energies, and magnetic field orientation with respect to the meteoroid path.more » « less
-
Abstract Galaxies are biased tracers of the underlying cosmic web, which is dominated by dark matter (DM) components that cannot be directly observed. Galaxy formation simulations can be used to study the relationship between DM density fields and galaxy distributions. However, this relationship can be sensitive to assumptions in cosmology and astrophysical processes embedded in galaxy formation models, which remain uncertain in many aspects. In this work, we develop a diffusion generative model to reconstruct DM fields from galaxies. The diffusion model is trained on the CAMELS simulation suite that contains thousands of state-of-the-art galaxy formation simulations with varying cosmological parameters and subgrid astrophysics. We demonstrate that the diffusion model can predict the unbiased posterior distribution of the underlying DM fields from the given stellar density fields while being able to marginalize over uncertainties in cosmological and astrophysical models. Interestingly, the model generalizes to simulation volumes ≈500 times larger than those it was trained on and across different galaxy formation models. The code for reproducing these results can be found athttps://github.com/victoriaono/variational-diffusion-cdm✎.more » « less
