Ground Truth Parameters Research Articles

Tools for Parameterization of a Single Particle Model with Electrolyte Dynamics (SPMe) with Bayesian Experimental Design to Capture Degradation-Induced Capacity Fade in Lithium-Ion Batteries

The intelligent design of durable, next-generation lithium-ion batteries can be facilitated through the use of computationally efficient models that capture battery physics. In this work, we demonstrate a single particle model with electrolyte dynamics (SPMe), which accounts for battery capacity fade caused by mechanisms such as solid electrolyte interface (SEI) growth, lithium plating, and stress-induced particle cracking. The model is trained using both experimental data and data generated using a higher-fidelity Doyle-Fuller-Newman model so the ground truth parameters are known. To quantify and reduce the uncertainty in the unknown model parameters, we are developing a Bayesian experimental design approach that, with the aid of multiple models with varying fidelity, can rapidly identify optimal experimental input conditions leading to the greatest expected information gain.

Enhanced network inference from sparse incomplete time series through automatically adapted L1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_1$$\\end{document} regularization

Reconstructing dynamics of complex systems from sparse, incomplete time series data is a challenging problem with applications in various domains. Here, we develop an iterative heuristic method to infer the underlying network structure and parameters governed by Ising dynamics from incomplete spin configurations based on sparse and small-sized samples. Our method iterates between imputing missing spin states given current coupling strengths and re-estimating couplings from completed spin state data. Central to our approach is the novel application of adaptive l1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l_1$$\\end{document} regularization on updating coupling strengths, which features an automatic adjustment of the regularization strength throughout the iterative inference process. By doing so, we aim at preventing over-fitting and enforcing the sparsity of couplings without access to ground truth parameters. We demonstrate that this approach accurately recovers parameters and imputes missing spins even with substantial missing data and short time series, providing improvements in the inference of Ising model parameters even for relatively small sample sizes.

Spherical convolutional neural networks can improve brain microstructure estimation from diffusion MRI data.

Diffusion magnetic resonance imaging is sensitive to the microstructural properties of brain tissue. However, estimating clinically and scientifically relevant microstructural properties from the measured signals remains a highly challenging inverse problem that machine learning may help solve. This study investigated if recently developed rotationally invariant spherical convolutional neural networks can improve microstructural parameter estimation. We trained a spherical convolutional neural network to predict the ground-truth parameter values from efficiently simulated noisy data and applied the trained network to imaging data acquired in a clinical setting to generate microstructural parameter maps. Our network performed better than the spherical mean technique and multi-layer perceptron, achieving higher prediction accuracy than the spherical mean technique with less rotational variance than the multi-layer perceptron. Although we focused on a constrained two-compartment model of neuronal tissue, the network and training pipeline are generalizable and can be used to estimate the parameters of any Gaussian compartment model. To highlight this, we also trained the network to predict the parameters of a three-compartment model that enables the estimation of apparent neural soma density using tensor-valued diffusion encoding.

Fusing Numerical Weather Prediction Ensembles with Refractivity Inversions during Surface Ducting Conditions

Abstract This study investigates the use of numerical weather prediction (NWP) ensembles to aid refractivity inversion problems during surface ducting conditions. Thirteen sets of measured thermodynamic atmospheric data from an instrumented helicopter during the Wallops Island field experiment are fit to a two-layer parametric surface duct model to characterize the duct. This modeled refractivity is considered “ground truth” for the environment and is used to generate the synthetic radar propagation loss field that then drives the inversion process. The inverse solution (refractivity derived from the synthetic radar data) is compared with this ground truth refractivity. For the inversion process, parameters of the two-layer model are iteratively estimated using genetic algorithms to determine which parameters likely produced the synthetic radar propagation field. Three numerical inversion experiments are conducted. The first experiment utilizes a randomized set of two-layer model parameters to initialize the inversion process, while the second experiment initializes the inversion using NWP ensembles, and the third experiment uses NWP ensembles to both initialize and restrict the parameter search intervals used in the inversion process. The results show that incorporation of NWP data benefits the accuracy and speed of the inversion result. However, in a few cases, an extended NWP ensemble forecast period was needed to encompass the ground truth parameters in the restricted search space. Furthermore, it is found that NWP ensemble populations with smaller spreads are more likely to hinder the inverse process than to aid it.

Data-driven modeling of noise time series with convolutional generative adversarial networks ∗ ∗U.S. government work not protected by U.S. copyright.

Random noise arising from physical processes is an inherent characteristic of measurements and a limiting factor for most signal processing and data analysis tasks. Given the recent interest in generative adversarial networks (GANs) for data-driven modeling, it is important to determine to what extent GANs can faithfully reproduce noise in target data sets. In this paper, we present an empirical investigation that aims to shed light on this issue for time series. Namely, we assess two general-purpose GANs for time series that are based on the popular deep convolutional GAN architecture, a direct time-series model and an image-based model that uses a short-time Fourier transform data representation. The GAN models are trained and quantitatively evaluated using distributions of simulated noise time series with known ground-truth parameters. Target time series distributions include a broad range of noise types commonly encountered in physical measurements, electronics, and communication systems: band-limited thermal noise, power law noise, shot noise, and impulsive noise. We find that GANs are capable of learning many noise types, although they predictably struggle when the GAN architecture is not well suited to some aspects of the noise, e.g. impulsive time-series with extreme outliers. Our findings provide insights into the capabilities and potential limitations of current approaches to time-series GANs and highlight areas for further research. In addition, our battery of tests provides a useful benchmark to aid the development of deep generative models for time series.

A Clonal Evolution Simulator for Planning Somatic Evolution Studies.

Somatic evolution plays a key role in development, cell differentiation, and normal aging, but also in diseases such as cancer. Understanding mechanisms of somatic mutability and how they can vary between cell lineages will likely play a crucial role in biological discovery and medical applications. This need has led to a proliferation of new technologies for profiling single-cell variation, each with distinctive capabilities and limitations that can be leveraged alone or in combination with other technologies. The enormous space of options for assaying somatic variation, however, presents unsolved informatics problems with regard to selecting optimal combinations of technologies for designing appropriate studies for any particular scientific questions. Versatile simulation tools are needed to explore and optimize potential study designs if researchers are to deploy multiomic technologies most effectively. In this study, we present a simulator allowing for the generation of synthetic data from a wide range of clonal lineages, variant classes, and sequencing technology choices, intended to provide a platform for effective study design in somatic lineage analysis. Users can input various properties of the somatic evolutionary system, mutation classes, and biotechnology options, and then generate samples of synthetic sequence reads and their corresponding ground truth parameters for a given study design. We demonstrate the utility of the simulator for testing and optimizing study designs for various experimental queries.

How Will It Drape Like? Capturing Fabric Mechanics from Depth Images

AbstractWe propose a method to estimate the mechanical parameters of fabrics using a casual capture setup with a depth camera. Our approach enables to create mechanically‐correct digital representations of real‐world textile materials, which is a fundamental step for many interactive design and engineering applications. As opposed to existing capture methods, which typically require expensive setups, video sequences, or manual intervention, our solution can capture at scale, is agnostic to the optical appearance of the textile, and facilitates fabric arrangement by non‐expert operators. To this end, we propose a sim‐to‐real strategy to train a learning‐based framework that can take as input one or multiple images and outputs a full set of mechanical parameters. Thanks to carefully designed data augmentation and transfer learning protocols, our solution generalizes to real images despite being trained only on synthetic data, hence successfully closing the sim‐to‐real loop. Key in our work is to demonstrate that evaluating the regression accuracy based on the similarity at parameter space leads to an inaccurate distances that do not match the human perception. To overcome this, we propose a novel metric for fabric drape similarity that operates on the image domain instead on the parameter space, allowing us to evaluate our estimation within the context of a similarity rank. We show that out metric correlates with human judgments about the perception of drape similarity, and that our model predictions produce perceptually accurate results compared to the ground truth parameters.

A proof-of-concept pipeline to guide evaluation of tumor tissue perfusion by dynamic contrast-agent imaging: Direct simulation and inverse tracer-kinetic procedures.

Dynamic contrast-enhanced (DCE) perfusion imaging has shown great potential to non-invasively assess cancer development and its treatment by their characteristic tissue signatures. Different tracer kinetics models are being applied to estimate tissue and tumor perfusion parameters from DCE perfusion imaging. The goal of this work is to provide an in silico model-based pipeline to evaluate how these DCE imaging parameters may relate to the true tissue parameters. As histology data provides detailed microstructural but not functional parameters, this work can also help to better interpret such data. To this aim in silico vasculatures are constructed and the spread of contrast agent in the tissue is simulated. As a proof of principle we show the evaluation procedure of two tracer kinetic models from in silico contrast-agent perfusion data after a bolus injection. Representative microvascular arterial and venous trees are constructed in silico. Blood flow is computed in the different vessels. Contrast-agent input in the feeding artery, intra-vascular transport, intra-extravascular exchange and diffusion within the interstitial space are modeled. From this spatiotemporal model, intensity maps are computed leading to in silico dynamic perfusion images. Various tumor vascularizations (architecture and function) are studied and show spatiotemporal contrast imaging dynamics characteristic of in vivo tumor morphotypes. The Brix II also called 2CXM, and extended Tofts tracer-kinetics models common in DCE imaging are then applied to recover perfusion parameters that are compared with the ground truth parameters of the in silico spatiotemporal models. The results show that tumor features can be well identified for a certain permeability range. The simulation results in this work indicate that taking into account space explicitly to estimate perfusion parameters may lead to significant improvements in the perfusion interpretation of the current tracer-kinetics models.

RTGEN++: A Relative Temporal Graph GENerator

Graph management systems have become popular for storing and querying graph-oriented data, and they are often evaluated with benchmarks based on large-scale graphs. However, obtaining such graphs is difficult due to their limited public availability. Several graph generators have been developed to address this challenge, producing synthetic graphs with characteristics similar to real-world graphs, such as degree distribution, community structure, and diameter. Generating synthetic graphs with constantly changing topology has received less attention despite its importance in developing useful benchmarks for temporal graph systems. In this paper, we present RTGEN++, a temporal graph generator that supports two evolution models. The first model generates temporal graphs by controlling the evolution of their degree distributions, using optimal transport methods to minimize the transformation effort. We also extend our method in order to consider the community structure of the generated graphs. The second model allows one to control the number of added and removed graph entities, thus enabling the modeling of the evolution of real-world graphs in many use cases. Our generator also includes a decorator that adds types and time-varying attributes to nodes and edges, enhancing the generated graphs and aligning with data platforms that use the property graph model. We validate our approach with experiments that demonstrate the reliability of the generated graphs in approximating ground-truth parameters.

MRXCAT2.0: Synthesis of realistic numerical phantoms by combining left-ventricular shape learning, biophysical simulations and tissue texture generation

BackgroundStandardised performance assessment of image acquisition, reconstruction and processing methods is limited by the absence of images paired with ground truth reference values. To this end, we propose MRXCAT2.0 to generate synthetic data, covering healthy and pathological function, using a biophysical model. We exemplify the approach by generating cardiovascular magnetic resonance (CMR) images of healthy, infarcted, dilated and hypertrophic left-ventricular (LV) function. MethodIn MRXCAT2.0, the XCAT torso phantom is coupled with a statistical shape model, describing population (patho)physiological variability, and a biophysical model, providing known and detailed functional ground truth of LV morphology and function. CMR balanced steady-state free precession images are generated using MRXCAT2.0 while realistic image appearance is ensured by assigning texturized tissue properties to the phantom labels. FindingPaired CMR image and ground truth data of LV function were generated with a range of LV masses (85–140 g), ejection fractions (34–51%) and peak radial and circumferential strains (0.45 to 0.95 and − 0.18 to − 0.13, respectively). These ranges cover healthy and pathological cases, including infarction, dilated and hypertrophic cardiomyopathy. The generation of the anatomy takes a few seconds and it improves on current state-of-the-art models where the pathological representation is not explicitly addressed. For the full simulation framework, the biophysical models require approximately two hours, while image generation requires a few minutes per slice. ConclusionMRXCAT2.0 offers synthesis of realistic images embedding population-based anatomical and functional variability and associated ground truth parameters to facilitate a standardized assessment of CMR acquisition, reconstruction and processing methods.

Adaptive Bayesian inference of Markov transition rates

Optimal designs minimize the number of experimental runs (samples) needed to accurately estimate model parameters, resulting in algorithms that, for instance, efficiently minimize parameter estimate variance. Governed by knowledge of past observations, adaptive approaches adjust sampling constraints online as model parameter estimates are refined, continually maximizing expected information gained or variance reduced. We apply adaptive Bayesian inference to estimate transition rates of Markov chains, a common class of models for stochastic processes in nature. Unlike most previous studies, our sequential Bayesian optimal design is updated with each observation and can be simply extended beyond two-state models to birth–death processes and multistate models. By iteratively finding the best time to obtain each sample, our adaptive algorithm maximally reduces variance, resulting in lower overall error in ground truth parameter estimates across a wide range of Markov chain parameterizations and conformations.

Machine learning of all-dielectric core-shell nanostructures: the critical role of the objective function in inverse design.

To integrate nanophotonics into light-based technologies, it is critical to elicit a desired optical response from its fundamental component, a nanoresonator. Because the optical resonance of a nanoresonator depends strongly on its base material and structural features, machine learning has been contemplated to enhance the design and optimization processes. However, its accuracy in searching the vast parameter space of nanophotonics still poses unresolved questions. Here, we show how the choice of objective functions, in combination with trained neural networks, can drastically change the optimization process-even for a simple nanophotonic structure. To assess how different objective functions select the correct structural parameters that generate a desired optical Mie response, we use a simple core-shell, all-dielectric nanostructure as the benchmark. By controlling the proportion of training data, which represents the "experience" level, we also quantify how the various objective functions perform in finding the ground-truth parameters. Our findings demonstrate that certain objective functions exhibit improved accuracy when used with highly "experienced" neural networks. Surprisingly, we also find other objective functions that perform better when paired with less "experienced" neural networks. Taken together, our results emphasize that it is critical to understand how neural networks are coupled to optimization schemes, as is evident even when a simple core-shell nanostructure is used.

On polynomial-time computation of high-dimensional posterior measures by Langevin-type algorithms

The problem of generating random samples of high-dimensional posterior distributions is considered. The main results consist of non-asymptotic computational guarantees for Langevin-type MCMC algorithms which scale polynomially in key quantities such as the dimension of the model, the desired precision level, and the number of available statistical measurements. As a direct consequence, it is shown that posterior mean vectors as well as optimisation based maximum a posteriori (MAP) estimates are computable in polynomial time, with high probability under the distribution of the data. These results are complemented by statistical guarantees for recovery of the ground truth parameter generating the data. Our results are derived in a general high-dimensional non-linear regression setting (with Gaussian process priors) where posterior measures are not necessarily log-concave, employing a set of local ‘geometric’ assumptions on the parameter space, and assuming that a good initialiser of the algorithm is available. The theory is applied to a representative non-linear example from PDEs involving a steady-state Schrödinger equation.

Bayesian modeling of pattern formation from one snapshot of pattern.

Partial differential equations(PDEs) have been widely used to reproduce patterns in nature and to give insight into the mechanism underlying pattern formation. Although many PDE models have been proposed, they rely on the pre-request knowledge of physical laws and symmetries, and developing a model to reproduce a given desired pattern remains difficult. We propose a method, referred to as Bayesian modeling of PDEs (BM-PDEs), to estimate the best dynamical PDE for one snapshot of a objective pattern under the stationary state without ground truth. We apply BM-PDEs to nontrivial patterns, such as quasicrystals (QCs), a double gyroid, and Frank-Kasper structures. We also generate three-dimensional dodecagonal QCs from a PDE model. This is done by using the estimated parameters for the Frank-Kasper A15 structure, which closely approximates the local structures of QCs. Our method works for noisy patterns and the pattern synthesized without the ground-truth parameters, which are required for the application toward experimental data.

Arterial spin labeling signal in the CSF: Implications for partial volume correction and blood-CSF barrier characterization.

For better quantification of perfusion with arterial spin labeling (ASL), partial volume correction (PVC) is used to disentangle the signals from gray matter (GM) and white matter within any voxel. Based on physiological considerations, PVC algorithms typically assume zero signal in the cerebrospinal fluid (CSF). Recent measurements, however, have shown that CSF-ASL signal can exceed 10% of GM signal, even when using recommended ASL labeling parameters. CSF signal is expected to particularly affect PVC results in the choroid plexus. This study aims to measure the impact of CSF signal on PVC perfusion measurements, and to investigate the potential use of PVC to retrieve pure CSF-ASL signal for blood-CSF barrier characterization. In vivo imaging included six pCASL sequences with variable label duration and post-labeling delay (PLD), and an eight-echo 3D-GRASE readout. A dataset was simulated to estimate the effect of CSF-PVC with known ground-truth parameters. Differences between the results of CSF-PVC and non-CSF-PVC were estimated for regions of interest (ROIs) based on GM probability, and a separate ROI isolating the choroid plexus. In vivo, the suitability of PVC-CSF signal as an estimate of pure CSF was investigated by comparing its time course with the long-TE CSF signal. Results from both simulation and in vivo data indicated that including the CSF signal in PVC improves quantification of GM CBF by approximately 10%. In simulated data, this improvement was greater for multi-PLD (model fitting) quantification than for single PLD (~1-5% difference). In the choroid plexus, the difference between CSF-PVC and non-CSF-PVC was much larger, averaging around 30%. Long-TE (pure) CSF signal could not be estimated from PVC CSF signal as it followed a different time course, indicating the presence of residual macrovascular signal in the PVC. The inclusion of CSF adds value to PVC for more accurate measurements of GM perfusion, and especially for quantification of perfusion in the choroid plexus and study of the glymphatic system.

Physics-informed neural networks for myocardial perfusion MRI quantification

Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, as they are physiologically plausible and resolve directly for blood flow and microvascular function. However, the reliability of model fitting is limited by the low signal-to-noise ratio, temporal resolution, and acquisition length. This may result in inaccurate parameter estimates. This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification, which provides a versatile scheme for the inference of kinetic parameters. These neural networks can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws described by a multi-compartment exchange model. Here, we provide a framework for the implementation of PINNs in myocardial perfusion MR. The approach is validated both in silico and in vivo. In the in silico study, an overall decrease in mean-squared error with the ground-truth parameters was observed compared to a standard non-linear least squares fitting approach. The in vivo study demonstrates that the method produces parameter values comparable to those previously found in literature, as well as providing parameter maps which match the clinical diagnosis of patients.

Automatic prosthetic‐parameter estimation from anteroposterior pelvic radiographs after total hip arthroplasty using deep learning‐based keypoint detection

X-ray is a necessary tool for post-total hip arthroplasty (THA) check-ups; however, parameter measurements are time-consuming. We proposed a deep learning tool, BKNet that automates localization of landmarks with parameter measurements. About 3072 radiographs from 3021 patients who underwent THA at our institute between 2013 and 2017 were used. We employed BKNet to perform landmark localization with parameter measurements in these radiographs. The performance of BKNet was assessed and compared with that of human observers. The 75-percentile cut-off errors were <0.5cm in all key points. The Bland-Altman methods show the agreement between the predicted and ground truth parameters. Human and BKNet comparison revealed the model could match the repeatability for 7/10 of the parameters. The accuracy of BKNet is equivalent to that of human observers, and BKNet was able to perform prosthetic-parameter estimation from keypoint detection with superior cost-effectiveness, repeatability, and timesaving compared to human observers.

Neural Circuits for Dynamics-Based Segmentation of Time Series.

The brain must extract behaviorally relevant latent variables from the signals streamed by the sensory organs. Such latent variables are often encoded in the dynamics that generated the signal rather than in the specific realization of the waveform. Therefore, one problem faced by the brain is to segment time series based on underlying dynamics. We present two algorithms for performing this segmentation task that are biologically plausible, which we define as acting in a streaming setting and all learning rules being local. One algorithm is model based and can be derived from an optimization problem involving a mixture of autoregressive processes. This algorithm relies on feedback in the form of a prediction error and can also be used for forecasting future samples. In some brain regions, such as the retina, the feedback connections necessary to use the prediction error for learning are absent. For this case, we propose a second, model-free algorithm that uses a running estimate of the autocorrelation structure of the signal to perform the segmentation. We show that both algorithms do well when tasked with segmenting signals drawn from autoregressive models with piecewise-constant parameters. In particular, the segmentation accuracy is similar to that obtained from oracle-like methods in which the ground-truth parameters of the autoregressive models are known. We also test our methods on data sets generated by alternating snippets of voice recordings. We provide implementations of our algorithms at https://github.com/ttesileanu/bio-time-series.

Deep learning Bayesian inference for low-luminosity active galactic nuclei spectra

ABSTRACT Most active supermassive black holes in present-day galaxies are underfed and consist of low-luminosity active galactic nuclei (LLAGN). LLAGNs display complex multiwavelength broadband spectral energy distributions (SED), dominated by non-thermal processes which are explained to first order by a radiatively inefficient accretion flow (RIAF) and a relativistic jet. Due to the computational cost of generating such SEDs, it has not been hitherto possible to perform statistical fits to observed broadband SEDs, since such procedures require generating many thousands of models on-the-fly. Here, we have used a deep learning (DL) method to interpolate a large grid consisting of dozens of thousands of model SEDs for RIAFs and jets covering the parameter space appropriate for LLAGNs. Not only the DL method computes accurate models, it does so hundreds of thousands of times faster than solving the underlying dynamical and radiative transfer equations. This brings RIAF and jet models to the realm of Bayesian inference. We demonstrate that the combination of a DL interpolator and a Markov chain Monte Carlo ensemble sampler can recover the ground truth parameters of Mock LLAGN data. We apply our model to existing radio-to-X-rays observations of three LLAGNs: M87, NGC 315, and NGC 4261. We demonstrate that our model can estimate the relevant parameters of these accreting black holes such as the mass accretion and outflow rate at a small fraction of the computational cost of previous approaches.

Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy * *This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce

A shift-invariant variational autoencoder (shift-VAE) is developed as an unsupervised method for the analysis of spectral data in the presence of shifts along the parameter axis, disentangling the physically-relevant shifts from other latent variables. Using synthetic data sets, we show that the shift-VAE latent variables closely match the ground truth parameters. The shift VAE is extended towards the analysis of band-excitation piezoresponse force microscopy data, disentangling the resonance frequency shifts from the peak shape parameters in a model-free unsupervised manner. The extensions of this approach towards denoising of data and model-free dimensionality reduction in imaging and spectroscopic data are further demonstrated. This approach is universal and can also be extended to analysis of x-ray diffraction, photoluminescence, Raman spectra, and other data sets.