Investigation of the Robustness of Neural Density Fields

• URL: http://arxiv.org/abs/2305.19698v1
• Date: Wed, 31 May 2023 09:43:49 GMT
• Title: Investigation of the Robustness of Neural Density Fields
• Authors: Jonas Schuhmacher and Fabio Gratl and Dario Izzo and Pablo G\'omez
• Abstract summary: This work investigates neural density fields and their relative errors in the context of robustness to external factors like noise or constraints during training. It is found that both models trained on a polyhedral and mascon ground truth perform similarly, indicating that the ground truth is not the accuracy bottleneck.
• Score: 7.67602635520562
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent advances in modeling density distributions, so-called neural density fields, can accurately describe the density distribution of celestial bodies without, e.g., requiring a shape model - properties of great advantage when designing trajectories close to these bodies. Previous work introduced this approach, but several open questions remained. This work investigates neural density fields and their relative errors in the context of robustness to external factors like noise or constraints during training, like the maximal available gravity signal strength due to a certain distance exemplified for 433 Eros and 67P/Churyumov-Gerasimenko. It is found that both models trained on a polyhedral and mascon ground truth perform similarly, indicating that the ground truth is not the accuracy bottleneck. The impact of solar radiation pressure on a typical probe affects training neglectable, with the relative error being of the same magnitude as without noise. However, limiting the precision of measurement data by applying Gaussian noise hurts the obtainable precision. Further, pretraining is shown as practical in order to speed up network training. Hence, this work demonstrates that training neural networks for the gravity inversion problem is appropriate as long as the gravity signal is distinguishable from noise. Code and results are available at https://github.com/gomezzz/geodesyNets

Related papers

• Solving deep-learning density functional theory via variational autoencoders [0.0]
  In recent years, machine learning models have revealed suited to learn accurate energy-density functionals from data. In this article, we employ variational autoencoders to build a compressed, flexible, and regular representation of the ground-state density profiles of various quantum models.
  arXiv  Detail & Related papers  (2024-03-14T18:11:50Z)
• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• Surrogate-data-enriched Physics-Aware Neural Networks [0.0]
  We investigate how physics-aware models can be enriched with cheaper, but inexact, data from other surrogate models like Reduced-Order Models (ROMs) As a proof of concept, we consider the one-dimensional wave equation and show that the training accuracy is increased by two orders of magnitude when inexact data from ROMs is incorporated.
  arXiv  Detail & Related papers  (2021-12-10T12:39:07Z)
• Physics-Driven Learning of Wasserstein GAN for Density Reconstruction in Dynamic Tomography [4.970364068620608]
  In this work, we demonstrate the ability of learned deep neural networks to perform artifact removal in noisy density reconstructions. We use a Wasserstein generative adversarial network (WGAN), where the generator serves as a denoiser that removes artifacts in densities obtained from traditional reconstruction algorithms. Preliminary numerical results show that the models trained in our frameworks can remove significant portions of unknown noise in density time-series data.
  arXiv  Detail & Related papers  (2021-10-28T20:23:06Z)
• Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
  Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
  arXiv  Detail & Related papers  (2021-10-20T14:23:54Z)
• Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks [70.7321040534471]
  Magnetic resonance velocimetry (MRV) is a non-invasive technique widely used in medicine and engineering to measure the velocity field of a fluid. Previous studies have required the shape of the boundary (for example, a blood vessel) to be known a priori. We present a physics-informed neural network that instead uses the noisy MRV data alone to infer the most likely boundary shape and de-noised velocity field.
  arXiv  Detail & Related papers  (2021-07-16T12:56:09Z)
• Real-time gravitational-wave science with neural posterior estimation [64.67121167063696]
  We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. We analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog. We find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event.
  arXiv  Detail & Related papers  (2021-06-23T18:00:05Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• Real-Time Well Log Prediction From Drilling Data Using Deep Learning [2.064612766965483]
  We present a workflow for data augmentation and feature engineering using Distance-based Global Sensitivity Analysis. We propose an Inception-based Convolutional Neural Network combined with a Temporal Convolutional Network as the deep learning model. 12 wells from the Equinor dataset for the Volve field in the North Sea are used for learning.
  arXiv  Detail & Related papers  (2020-01-28T03:57:31Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.