Related papers: Gaussian processes at the Helm(holtz): A more fluid model for ocean currents

Gaussian processes at the Helm(holtz): A more fluid model for ocean currents

URL: http://arxiv.org/abs/2302.10364v3
Date: Tue, 20 Jun 2023 08:53:12 GMT
Title: Gaussian processes at the Helm(holtz): A more fluid model for ocean currents
Authors: Renato Berlinghieri, Brian L. Trippe, David R. Burt, Ryan Giordano, Kaushik Srinivasan, Tamay \"Ozg\"okmen, Junfei Xia, Tamara Broderick
Abstract summary: Oceanographers are interested in reconstructing ocean currents away from buoys and identifying divergences in a current vector field. We show that applying a GP with a standard stationary kernel directly to buoy data can struggle at both current reconstruction and divergence identification. We propose to instead put a standard stationary kernel on the divergence and curl-free components of a vector field obtained through a Helmholtz decomposition.
Score: 15.287734986163077
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Given sparse observations of buoy velocities, oceanographers are interested in reconstructing ocean currents away from the buoys and identifying divergences in a current vector field. As a first and modular step, we focus on the time-stationary case - for instance, by restricting to short time periods. Since we expect current velocity to be a continuous but highly non-linear function of spatial location, Gaussian processes (GPs) offer an attractive model. But we show that applying a GP with a standard stationary kernel directly to buoy data can struggle at both current reconstruction and divergence identification, due to some physically unrealistic prior assumptions. To better reflect known physical properties of currents, we propose to instead put a standard stationary kernel on the divergence and curl-free components of a vector field obtained through a Helmholtz decomposition. We show that, because this decomposition relates to the original vector field just via mixed partial derivatives, we can still perform inference given the original data with only a small constant multiple of additional computational expense. We illustrate the benefits of our method with theory and experiments on synthetic and real ocean data.

Related papers

von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
We explore a family of expressive and interpretable distributions over circle-valued random functions. The resulting probability model has connections with continuous spin models in statistical physics. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
arXiv Detail & Related papers (2024-06-19T01:57:21Z)
On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models [13.597551064547503]
Diffusion models are generative models that have recently demonstrated impressive performances in terms of sampling quality and density estimation in high dimensions. In the original formulation of the diffusion model, this vector field is assumed to be the score function. We show that exact density estimation and exact sampling is achieved when the conservative component is exactly equals to the true score.
arXiv Detail & Related papers (2024-02-06T09:41:43Z)
HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction [66.38369833561039]
HelmFluid is an accurate and interpretable predictor for fluid. Inspired by Helmholtz theorem, we design a HelmDynamics block to learn Helmholtz dynamics. By embedding the HelmDynamics block into a Multiscale Multihead Integral Architecture, HelmFluid can integrate learned Helmholtz dynamics along temporal dimension in multiple spatial scales.
arXiv Detail & Related papers (2023-10-16T16:38:32Z)
Bayesian Renormalization [68.8204255655161]
We present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference. The main insight of Bayesian Renormalization is that the Fisher metric defines a correlation length that plays the role of an emergent RG scale. We provide insight into how the Bayesian Renormalization scheme relates to existing methods for data compression and data generation.
arXiv Detail & Related papers (2023-05-17T18:00:28Z)
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems [64.29491112653905]
We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods. Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space. Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
arXiv Detail & Related papers (2023-03-10T07:42:49Z)
Kernel Learning for Explainable Climate Science [19.654936516882803]
We propose non-stationary kernels to model precipitation patterns in the Upper Himalayas Indus Basin. We account for the spatial variation in precipitation with a non-stationary Gibbs kernel parameterised with an input dependent lengthscale. In ablation experiments we motivate each component of the proposed kernel by demonstrating its ability to model the spatial covariance, temporal structure and joint-temporal reconstruction.
arXiv Detail & Related papers (2022-09-11T22:10:08Z)
Vorticity of Twisted Spinor Fields [0.0]
Relatively new is the observation in a certain context that the vortex center of this field structure is, unlike a classical whirlpool, not singular. There are several ways to calculate the local velocity of the spinor field and that all but one show a singular vorticity at the vortex line.
arXiv Detail & Related papers (2022-08-17T15:41:06Z)
Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition [20.55025648415664]
We propose NON FActor Trajectory learning for dynamic tensor decomposition (NONFAT) We use a second-level GP to sample the entry values and to capture the temporal relationship between the entities. We have shown the advantage of our method in several real-world applications.
arXiv Detail & Related papers (2022-07-06T05:33:00Z)
Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
arXiv Detail & Related papers (2021-02-12T12:23:13Z)
Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-Informed Deep Generative Models [27.623119767592385]
We propose a new method for inferring the governing ordinary differential equations (SODEs) by observing particle ensembles at discrete and sparse time instants. Particle coordinates at a single time instant, possibly noisy or truncated, are recorded in each snapshot but are unpaired across the snapshots. By training a physics-informed generative model that generates "fake" sample paths, we aim to fit the observed particle ensemble distributions with a curve in the probability measure space.
arXiv Detail & Related papers (2020-08-05T03:06:40Z)
SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives [86.01677297601624]
We propose a novel approach for scaling GP regression with derivatives based on quadrature Fourier features. We prove deterministic, non-asymptotic and exponentially fast decaying error bounds which apply for both the approximated kernel as well as the approximated posterior.
arXiv Detail & Related papers (2020-03-05T14:33:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.