Towards Reflectivity profile inversion through Artificial Neural Networks

• URL: http://arxiv.org/abs/2010.07634v3
• Date: Sun, 24 Jan 2021 10:00:18 GMT
• Title: Towards Reflectivity profile inversion through Artificial Neural Networks
• Authors: Juan Manuel Carmona-Loaiza and Zamaan Raza
• Abstract summary: The goal of Specular Neutron and X-ray Reflectometry is to infer materials Scattering Length Density profiles from experimental reflectivity curves. This paper focuses on investigating an original approach to the ill-posed non-invertible problem which involves the use of Artificial Neural Networks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of Specular Neutron and X-ray Reflectometry is to infer materials Scattering Length Density (SLD) profiles from experimental reflectivity curves. This paper focuses on investigating an original approach to the ill-posed non-invertible problem which involves the use of Artificial Neural Networks (ANN). In particular, the numerical experiments described here deal with large data sets of simulated reflectivity curves and SLD profiles, and aim to assess the applicability of Data Science and Machine Learning technology to the analysis of data generated at neutron scattering large scale facilities. It is demonstrated that, under certain circumstances, properly trained Deep Neural Networks are capable of correctly recovering plausible SLD profiles when presented with never-seen-before simulated reflectivity curves. When the necessary conditions are met, a proper implementation of the described approach would offer two main advantages over traditional fitting methods when dealing with real experiments, namely, 1. sample physical models are described under a new paradigm: detailed layer-by-layer descriptions (SLDs, thicknesses, roughnesses) are replaced by parameter free curves $\rho(z)$, allowing a-priori assumptions to be fed in terms of the sample family to which a given sample belongs (e.g. "thin film", "lamellar structure", etc.) 2. the time-to-solution is shrunk by orders of magnitude, enabling faster batch analyses for large datasets.

Related papers

• Learning Coupled Subspaces for Multi-Condition Spike Data [8.114880112033644]
  In neuroscience, researchers typically conduct experiments under multiple conditions to acquire neural responses in the form of high-dimensional spike train datasets. We propose a non-parametric Bayesian approach to learn a smooth tuning function over the experiment condition space.
  arXiv  Detail & Related papers  (2024-10-24T20:44:28Z)
• Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation [73.81105275628751]
  Finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors.
  arXiv  Detail & Related papers  (2024-07-26T10:29:16Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks [89.28881869440433]
  This paper provides the first theoretical characterization of joint edge-model sparse learning for graph neural networks (GNNs) It proves analytically that both sampling important nodes and pruning neurons with the lowest-magnitude can reduce the sample complexity and improve convergence without compromising the test accuracy.
  arXiv  Detail & Related papers  (2023-02-06T16:54:20Z)
• Deep learning for full-field ultrasonic characterization [7.120879473925905]
  This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform. Two logics, namely the direct inversion and physics-informed neural networks (PINNs), are explored.
  arXiv  Detail & Related papers  (2023-01-06T05:01:05Z)
• Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets [57.06026574261203]
  We provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.
  arXiv  Detail & Related papers  (2022-10-25T14:45:15Z)
• An Information-Theoretic Framework for Supervised Learning [22.280001450122175]
  We propose a novel information-theoretic framework with its own notions of regret and sample complexity. We study the sample complexity of learning from data generated by deep neural networks with ReLU activation units. We conclude by corroborating our theoretical results with experimental analysis of random single-hidden-layer neural networks.
  arXiv  Detail & Related papers  (2022-03-01T05:58:28Z)
• Estimating permeability of 3D micro-CT images by physics-informed CNNs based on DNS [1.6274397329511197]
  This paper presents a novel methodology for permeability prediction from micro-CT scans of geological rock samples. The training data set for CNNs dedicated to permeability prediction consists of permeability labels that are typically generated by classical lattice Boltzmann methods (LBM) We instead perform direct numerical simulation (DNS) by solving the stationary Stokes equation in an efficient and distributed-parallel manner.
  arXiv  Detail & Related papers  (2021-09-04T08:43:19Z)
• A robust low data solution: dimension prediction of semiconductor nanorods [5.389015968413988]
  Robust deep neural network-based regression algorithm has been developed for precise prediction of length, width, and aspect ratios of semiconductor nanorods (NRs) Deep neural network is further applied to develop regression model which demonstrated the well performed prediction on both the original and generated data with a similar distribution.
  arXiv  Detail & Related papers  (2020-10-27T07:51:38Z)
• Revealing the Structure of Deep Neural Networks via Convex Duality [70.15611146583068]
  We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of hidden layers. We show that a set of optimal hidden layer weights for a norm regularized training problem can be explicitly found as the extreme points of a convex set. We apply the same characterization to deep ReLU networks with whitened data and prove the same weight alignment holds.
  arXiv  Detail & Related papers  (2020-02-22T21:13:44Z)

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.