M. Shao, T. Tasdizen, S. Joshi. Analyzing the Domain Shift Immunity of Deep Homography Estimation, Subtitled arXiv:2304.09976v1, 2023.
Homography estimation is a basic image-alignment method in many applications. Recently, with the development of convolutional neural networks (CNNs), some learning based approaches have shown great success in this task. However, the performance across different domains has never been researched. Unlike other common tasks (e.g., classification, detection, segmentation), CNN based homography estimation models show a domain shift immunity, which means a model can be trained on one dataset and tested on another without any transfer learning. To explain this unusual performance, we need to determine how CNNs estimate homography. In this study, we first show the domain shift immunity of different deep homography estimation models. We then use a shallow network with a specially designed dataset to analyze the features used for estimation. The results show that networks use low-level texture information to estimate homography. We also design some experiments to compare the performance between different texture densities and image features distorted on some common datasets to demonstrate our findings. Based on these findings, we provide an explanation of the domain shift immunity of deep homography estimation.
N. Shingde, M. Berzins, T. Blattner, W. Keyrouz, A. Bardakoff. Extending Hedgehog’s dataflow graphs to multi-node GPU architectures, In Workshop on Asynchronous Many-Task Systems and Applications (WAMTA23), 2023.
Asynchronous task-based systems offer the possibility of making it easier to take advantage of scalable heterogeneous architectures.
This paper extends the National Institute of Standards and Technology’s Hedgehog dataflow graph models, which target a single high-end
compute node, to run on a cluster by borrowing aspects of Uintah’s cluster-scale task graphs and applying them to a sample implementation
of matrix multiplication. These results are compared to implementations using the leading libraries, SLATE and DPLASMA, for illustrative purposes only. The motivation behind this work is to demonstrate that using general purpose high-level abstractions, such as Hedgehog’s dataflow graphs, does not negatively impact performance.
K. Shukla, V. Oommen, A. Peyvan, M. Penwarden, L. Bravo, A. Ghoshal, R.M. Kirby, G. Karniadakis. Deep neural operators can serve as accurate surrogates for shape optimization: A case study for airfoils, Subtitled arXiv:2302.00807v1, 2023.
Deep neural operators, such as DeepONets, have changed the paradigm in high-dimensional nonlinear regression from function regression to (differential) operator regression, paving the way for significant changes in computational engineering applications. Here, we investigate the use of DeepONets to infer flow fields around unseen airfoils with the aim of shape optimization, an important design problem in aerodynamics that typically taxes computational resources heavily. We present results which display little to no degradation in prediction accuracy, while reducing the online optimization cost by orders of magnitude. We consider NACA airfoils as a test case for our proposed approach, as their shape can be easily defined by the four-digit parametrization. We successfully optimize the constrained NACA four-digit problem with respect to maximizing the lift-to-drag ratio and validate all results by comparing them to a high-order CFD solver. We find that DeepONets have low generalization error, making them ideal for generating solutions of unseen shapes. Specifically, pressure, density, and velocity fields are accurately inferred at a fraction of a second, hence enabling the use of general objective functions beyond the maximization of the lift-to-drag ratio considered in the current work.
R. Tohid, S. Shirzad, C. Taylor, S.A. Sakin, K.E. Isaacs, H. Kaiser. Halide Code Generation Framework in Phylanx, In Euro-Par 2022: Parallel Processing Workshops, Springer Nature Switzerland, pp. 32--45. 2023.
Separating algorithms from their computation schedule has become a de facto solution to tackle the challenges of developing high performance code on modern heterogeneous architectures. Common approaches include Domain-specific languages (DSLs) which provide familiar APIs to domain experts, code generation frameworks that automate the generation of fast and portable code, and runtime systems that manage threads for concurrency and parallelism. In this paper, we present the Halide code generation framework for Phylanx distributed array processing platform. This extension enables compile-time optimization of Phylanx primitives for target architectures. To accomplish this, (1) we implemented new Phylanx primitives using Halide, and (2) partially exported Halide's thread pool API to carry out parallelism on HPX (Phylanx's runtime) threads. (3) showcased HPX performance analysis tools made available to Halide applications. The evaluation of the work has been done in two steps. First, we compare the performance of Halide applications running on its native runtime with that of the new HPX backend to verify there is no cost associated with using HPX threads. Next, we compare performances of a number of original implementations of Phylanx primitives against the new ones in Halide to verify performance and portability benefits of Halide in the context of Phylanx.
K. Williams, A. Bigelow, K.E. Isaacs. Data Abstraction Elephants: The Initial Diversity of Data Representations and Mental Models, In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23), ACM, 2023.
Two people looking at the same dataset will create diferent mental models, prioritize diferent attributes, and connect with diferent visualizations. We seek to understand the space of data abstractions associated with mental models and how well people communicate their mental models when sketching. Data abstractions have a profound infuence on the visualization design, yet it’s unclear how universal they may be when not initially infuenced by a representation. We conducted a study about how people create their mental models from a dataset. Rather than presenting tabular data, we presented each participant with one of three datasets in paragraph form, to avoid biasing the data abstraction and mental model. We observed various mental models, data abstractions, and depictions from the same dataset, and how these concepts are infuenced by communication and purpose-seeking. Our results have implications for visualization design, especially during the discovery and data collection phase.
H. Xu, S. Elhabian. Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions, Subtitled arXiv:2305.11946, 2023.
Statistical shape modeling (SSM) is an essential tool for analyzing variations in anatomical morphology. In a typical SSM pipeline, 3D anatomical images, gone through segmentation and rigid registration, are represented using lower-dimensional shape features, on which statistical analysis can be performed. Various methods for constructing compact shape representations have been proposed, but they involve laborious and costly steps. We propose Image2SSM, a novel deep-learning-based approach for SSM that leverages image-segmentation pairs to learn a radial-basis-function (RBF)-based representation of shapes directly from images. This RBF-based shape representation offers a rich self-supervised signal for the network to estimate a continuous, yet compact representation of the underlying surface that can adapt to complex geometries in a data-driven manner. Image2SSM can characterize populations of biological structures of interest by constructing statistical landmark-based shape models of ensembles of anatomical shapes while requiring minimal parameter tuning and no user assistance. Once trained, Image2SSM can be used to infer low-dimensional shape representations from new unsegmented images, paving the way toward scalable approaches for SSM, especially when dealing with large cohorts. Experiments on synthetic and real datasets show the efficacy of the proposed method compared to the state-of-art correspondence-based method for SSM.
N. Zhou, G. Scorzelli, J. Luettgau, R.R. Kancharla, J. Kane, R. Wheeler, B. Croom, B. Newell, V. Pascucci, M. Taufer. Orchestration of materials science workflows for heterogeneous resources at large scale, In The International Journal of High Performance Computing Applications, Sage, 2023.
In the era of big data, materials science workflows need to handle large-scale data distribution, storage, and computation. Any of these areas can become a performance bottleneck. We present a framework for analyzing internal material structures (e.g., cracks) to mitigate these bottlenecks. We demonstrate the effectiveness of our framework for a workflow performing synchrotron X-ray computed tomography reconstruction and segmentation of a silica-based structure. Our framework provides a cloud-based, cutting-edge solution to challenges such as growing intermediate and output data and heavy resource demands during image reconstruction and segmentation. Specifically, our framework efficiently manages data storage, scaling up compute resources on the cloud. The multi-layer software structure of our framework includes three layers. A top layer uses Jupyter notebooks and serves as the user interface. A middle layer uses Ansible for resource deployment and managing the execution environment. A low layer is dedicated to resource management and provides resource management and job scheduling on heterogeneous nodes (i.e., GPU and CPU). At the core of this layer, Kubernetes supports resource management, and Dask enables large-scale job scheduling for heterogeneous resources. The broader impact of our work is four-fold: through our framework, we hide the complexity of the cloud’s software stack to the user who otherwise is required to have expertise in cloud technologies; we manage job scheduling efficiently and in a scalable manner; we enable resource elasticity and workflow orchestration at a large scale; and we facilitate moving the study of nonporous structures, which has wide applications in engineering and scientific fields, to the cloud. While we demonstrate the capability of our framework for a specific materials science application, it can be adapted for other applications and domains because of its modular, multi-layer architecture.
J. Adams, N. Khan, A. Morris, S. Elhabian. Spatiotemporal Cardiac Statistical Shape Modeling: A Data-Driven Approach, Subtitled arXiv preprint arXiv:2209.02736, 2022.
Clinical investigations of anatomy’s structural changes over time could greatly benefit from population-level quantification of shape, or spatiotemporal statistic shape modeling (SSM). Such a tool enables characterizing patient organ cycles or disease progression in relation to a cohort of interest. Constructing shape models requires establishing a quantitative shape representation (e.g., corresponding landmarks). Particle-based shape modeling (PSM) is a data-driven SSM approach that captures population-level shape variations by optimizing landmark placement. However, it assumes cross-sectional study designs and hence has limited statistical power in representing shape changes over time. Existing methods for modeling spatiotemporal or longitudinal shape changes require predefined shape atlases and pre-built shape models that are typically constructed cross-sectionally. This paper proposes a data-driven approach inspired by the PSM method to learn population-level spatiotemporal shape changes directly from shape data. We introduce a novel SSM optimization scheme that produces landmarks that are in correspondence both across the population (inter-subject) and across time-series (intra-subject). We apply the proposed method to 4D cardiac data from atrial-fibrillation patients and demonstrate its efficacy in representing the dynamic change of the left atrium. Furthermore, we show that our method outperforms an image-based approach for spatiotemporal SSM with respect to a generative time-series model, the Linear Dynamical System (LDS). LDS fit using a spatiotemporal shape model optimized via our approach provides better generalization and specificity, indicating it accurately captures the underlying time-dependency.
M. Alirezaei, T. Tasdizen. Adversarially Robust Classification by Conditional Generative Model Inversion, Subtitled arXiv preprint arXiv:2201.04733, 2022.
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by attacks which approximate and use the corrected gradient. Defenses that do not obfuscate gradients such as adversarial training exist, but these approaches generally make assumptions about the attack such as its magnitude. We propose a classification model that does not obfuscate gradients and is robust by construction without assuming prior knowledge about the attack. Our method casts classification as an optimization problem where we "invert" a conditional generator trained on unperturbed, natural images to find the class that generates the closest sample to the query image. We hypothesize that a potential source of brittleness against adversarial attacks is the high-to-low-dimensional nature of feed-forward classifiers which allows an adversary to find small perturbations in the input space that lead to large changes in the output space. On the other hand, a generative model is typically a low-to-high-dimensional mapping. While the method is related to Defense-GAN, the use of a conditional generative model and inversion in our model instead of the feed-forward classifier is a critical difference. Unlike Defense-GAN, which was shown to generate obfuscated gradients that are easily circumvented, we show that our method does not obfuscate gradients. We demonstrate that our model is extremely robust against black-box attacks and has improved robustness against white-box attacks compared to naturally trained, feed-forward classifiers.
E.E. Anstadt, W. Tao, E. Guo, L. Dvoracek, M.K. Bruce, P.J. Grosse, L. Wang, L. Kavan, R. Whitaker, J.A. Goldstein. Quantifying the Severity of Metopic Craniosynostosis Using Unsupervised Machine Learning, In Plastic and Reconstructive Surgery, November, 2022.
Quantifying the severity of head shape deformity and establishing a threshold for operative intervention remains challenging in patients with Metopic Craniosynostosis (MCS). This study combines 3D skull shape analysis with an unsupervised machine-learning algorithm to generate a quantitative shape severity score (CMD) and provide an operative threshold score.
Head computed tomography (CT) scans from subjects with MCS and normal controls (age 5-15 months) were used for objective 3D shape analysis using ShapeWorks software and in a survey for craniofacial surgeons to rate head-shape deformity and report whether they would offer surgical correction based on head shape alone. An unsupervised machine-learning algorithm was developed to quantify the degree of shape abnormality of MCS skulls compared to controls.
124 CTs were used to develop the model; 50 (24% MCS, 76% controls) were rated by 36 craniofacial surgeons, with an average of 20.8 ratings per skull. The interrater reliability was high (ICC=0.988). The algorithm performed accurately and correlates closely with the surgeons assigned severity ratings (Spearman’s Correlation coefficient r=0.817). The median CMD for affected skulls was 155.0 (IQR 136.4-194.6, maximum 231.3). Skulls with ratings ≥150.2 were highly likely to be offered surgery by the experts in this study.
This study describes a novel metric to quantify the head shape deformity associated with metopic craniosynostosis and contextualizes the results using clinical assessments of head shapes by craniofacial experts. This metric may be useful in supporting clinical decision making around operative intervention as well as in describing outcomes and comparing patient population across centers.
A. Arzani, K.W. Cassel, R.M. D'Souza. Theory-guided physics-informed neural networks for boundary layer problems with singular perturbation, In Journal of Computational Physics, 2022.
Physics-informed neural networks (PINNs) are a recent trend in scientific machine learning research and modeling of differential equations. Despite progress in PINN research, large gradients and highly nonlinear patterns remain challenging to model. Thin boundary layer problems are prominent examples of large gradients that commonly arise in transport problems. In this study, boundary-layer PINN (BL-PINN) is proposed to enable a solution to thin boundary layers by considering them as a singular perturbation problem. Inspired by the classical perturbation theory and asymptotic expansions, BL-PINN is designed to replicate the procedure in singular perturbation theory. Namely, different parallel PINN networks are defined to represent different orders of approximation to the boundary layer problem in the inner and outer regions. In different benchmark problems (forward and inverse), BL-PINN shows superior performance compared to the traditional PINN approach and is able to produce accurate results, whereas the classical PINN approach could not provide meaningful solutions. BL-PINN also demonstrates significantly better results compared to other extensions of PINN such as the extended PINN (XPINN) approach. The natural incorporation of the perturbation parameter in BL-PINN provides the opportunity to evaluate parametric solutions without the need for retraining. BL-PINN demonstrates an example of how classical mathematical theory could be used to guide the design of deep neural networks for solving challenging problems.
T. M. Athawale, D. Maljovec. L. Yan, C. R. Johnson, V. Pascucci, B. Wang. Uncertainty Visualization of 2D Morse Complex Ensembles Using Statistical Summary Maps, In IEEE Transactions on Visualization and Computer Graphics, Vol. 28, No. 4, pp. 1955-1966. April, 2022.
Morse complexes are gradient-based topological descriptors with close connections to Morse theory. They are widely applicable in scientific visualization as they serve as important abstractions for gaining insights into the topology of scalar fields. Data uncertainty inherent to scalar fields due to randomness in their acquisition and processing, however, limits our understanding of Morse complexes as structural abstractions. We, therefore, explore uncertainty visualization of an ensemble of 2D Morse complexes that arises from scalar fields coupled with data uncertainty. We propose several statistical summary maps as new entities for quantifying structural variations and visualizing positional uncertainties of Morse complexes in ensembles. Specifically, we introduce three types of statistical summary maps – the probabilistic map , the significance map , and the survival map – to characterize the uncertain behaviors of gradient flows. We demonstrate the utility of our proposed approach using wind, flow, and ocean eddy simulation datasets.
J. Baker, E. Cherkaev, A. Narayan, B. Wang. Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs, Subtitled arXiv:2202.12373, 2022.
Proper orthogonal decomposition (POD) allows reduced-order modeling of complex dynamical systems at a substantial level, while maintaining a high degree of accuracy in modeling the underlying dynamical systems. Advances in machine learning algorithms enable learning POD-based dynamics from data and making accurate and fast predictions of dynamical systems. In this paper, we leverage the recently proposed heavy-ball neural ODEs (HBNODEs) [Xia et al. NeurIPS, 2021] for learning data-driven reduced-order models (ROMs) in the POD context, in particular, for learning dynamics of time-varying coefficients generated by the POD analysis on training snapshots generated from solving full order models. HBNODE enjoys several practical advantages for learning POD-based ROMs with theoretical guarantees, including 1) HBNODE can learn long-term dependencies effectively from sequential observations and 2) HBNODE is computationally efficient in both training and testing. We compare HBNODE with other popular ROMs on several complex dynamical systems, including the von Kármán Street flow, the Kurganov-Petrova-Popov equation, and the one-dimensional Euler equations for fluids modeling.
J. Baker, H. Xia, Y. Wang, E. Cherkaev, A. Narayan, L. Chen, J. Xin, A. L. Bertozzi, S. J. Osher, B. Wang. Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs, Subtitled arXiv preprint arXiv:2204.08621, 2022.
Learning neural ODEs often requires solving very stiff ODE systems, primarily using explicit adaptive step size ODE solvers. These solvers are computationally expensive, requiring the use of tiny step sizes for numerical stability and accuracy guarantees. This paper considers learning neural ODEs using implicit ODE solvers of different orders leveraging proximal operators. The proximal implicit solver consists of inner-outer iterations: the inner iterations approximate each implicit update step using a fast optimization algorithm, and the outer iterations solve the ODE system over time. The proximal implicit ODE solver guarantees superiority over explicit solvers in numerical stability and computational efficiency. We validate the advantages of proximal implicit solvers over existing popular neural ODE solvers on various challenging benchmark tasks, including learning continuous-depth graph neural networks and continuous normalizing flows.
W. Bangerth, C. R. Johnson, D. K. Njeru, B. van Bloemen Waanders. Estimating and using information in inverse problems, Subtitled arXiv:2208.09095, 2022.
For inverse problems one attempts to infer spatially variable functions from indirect measurements of a system. To practitioners of inverse problems, the concept of ``information'' is familiar when discussing key questions such as which parts of the function can be inferred accurately and which cannot. For example, it is generally understood that we can identify system parameters accurately only close to detectors, or along ray paths between sources and detectors, because we have ``the most information'' for these places.
Although referenced in many publications, the ``information'' that is invoked in such contexts is not a well understood and clearly defined quantity. Herein, we present a definition of information density that is based on the variance of coefficients as derived from a Bayesian reformulation of the inverse problem. We then discuss three areas in which this information density can be useful in practical algorithms for the solution of inverse problems, and illustrate the usefulness in one of these areas -- how to choose the discretization mesh for the function to be reconstructed -- using numerical experiments.
J. A. Bergquist, J. Coll-Font, B. Zenger, L. C. Rupp, W. W. Good, D. H. Brooks, R. S. MacLeod. Reconstruction of cardiac position using body surface potentials, In Computers in Biology and Medicine, Vol. 142, pp. 105174. 2022.
Electrocardiographic imaging (ECGI) is a noninvasive technique to assess the bioelectric activity of the heart which has been applied to aid in clinical diagnosis and management of cardiac dysfunction. ECGI is built on mathematical models that take into account several patient specific factors including the position of the heart within the torso. Errors in the localization of the heart within the torso, as might arise due to natural changes in heart position from respiration or changes in body position, contribute to errors in ECGI reconstructions of the cardiac activity, thereby reducing the clinical utility of ECGI. In this study we present a novel method for the reconstruction of cardiac geometry utilizing noninvasively acquired body surface potential measurements. Our geometric correction method simultaneously estimates the cardiac position over a series of heartbeats by leveraging an iterative approach which alternates between estimating the cardiac bioelectric source across all heartbeats and then estimating cardiac positions for each heartbeat. We demonstrate that our geometric correction method is able to reduce geometric error and improve ECGI accuracy in a wide range of testing scenarios. We examine the performance of our geometric correction method using different activation sequences, ranges of cardiac motion, and body surface electrode configurations. We find that after geometric correction resulting ECGI solution accuracy is improved and variability of the ECGI solutions between heartbeats is substantially reduced.
M. Berzins. Energy conservation and accuracy of some MPM formulations, In Computational Particle Mechanics, 2022.
The success of the Material Point Method (MPM) in solving many challenging problems nevertheless raises some open questions regarding the fundamental properties of the method such as time integration accuracy and energy conservation. The traditional MPM time integration methods are often based upon the symplectic Euler method or staggered central differences. This raises the question of how to best ensure energy conservation in explicit time integration for MPM. Two approaches are used here, one is to extend the Symplectic Euler method (Cromer Euler) to provide better energy conservation and the second is to use a potentially more accurate symplectic methods, namely the widely-used Stormer-Verlet Method. The Stormer-Verlet method is shown to have locally third order time accuracy of energy conservation in time, in contrast to the second order accuracy in energy conservation of the symplectic Euler methods that are used in many MPM calculations. It is shown that there is an extension to the Symplectic Euler stress-last method that provides better energy conservation that is comparable with the Stormer-Verlet method. This extension is referred to as TRGIMP and also has third order accuracy in energy conservation. When the interactions between space and time errors are studied it is seen that spatial errors may dominate in computed quantities such as displacement and velocity. This connection between the local errors in space and time is made explicit mathematically and explains the observed results that displacement and velocity errors are very similar for both methods. The observed and theoretically predicted third-order energy conservation accuracy and computational costs are demonstrated on a standard MPM test example.
M. Berzins. Computational Error Estimation for The Material Point Method, In Computational Particle Mechanics, Springer, 2022.
A common feature of many methods in computational mechanics is that there is often a way of estimating the error in the computed solution. The situation for computational mechanics codes based upon the Material Point Method is very different in that there has been comparatively little work on computable error estimates for these methods. This work is concerned with introducing such an approach for the Material Point Method. Although it has been observed that spatial errors may dominate temporal ones at stable time steps, recent work has made more precise the sources and forms of the different MPM errors. There is then a need to estimate these errors computationally through computable estimates of the different errors in the material point method. Estimates of the different spatial errors in the Material Point Method are constructed based upon nodal derivatives of the different physical variables in MPM. These derivatives are then estimated using standard difference approximations calculated on the background mesh. The use of these estimates of the spatial error makes it possible to measure the growth of errors over time. A number of computational experiments are used to illustrate the performance of the computed error estimates. As the key feature of the approach is the calculation of derivatives on the regularly spaced background mesh, the extension to calculating derivatives and hence to error estimates for higher dimensional problems is clearly possible.
J.A. Bergquist, L.C. Rupp, A. Busatto, B. Orkild, B. Zenger, W. Good, J. Coll-Font, A. Narayan, J. Tate, D. Brooks, R.S. MacLeod. Heart Position Uncertainty Quantification in the Inverse Problem of ECGI, In Computing in Cardiology, Vol. 49, 2022.
Electrocardiographic imaging (ECGI) is a clinical and research tool for noninvasive diagnosis of cardiac electrical dysfunction. The position of the heart within the torso is both an input and common source of error in ECGI. Many studies have sought to improve cardiac localization accuracy, however, few have examined quantitatively the effects of uncertainty in the position of the heart within the torso. Recently developed uncertainty quantification (UQ) tools enable the robust application of UQ to ECGI reconstructions. In this study, we developed an ECGI formulation, which for the first time, directly incorporated uncertainty in the heart position. The result is an ECGI solution that is robust to variation in heart position. Using data from two Langendorff experimental preparations, each with 120 heartbeats distributed across three activation sequences, we found that as heart position uncertainty increased above ±10 mm, the solution quality of the ECGI degraded. However, even at large heart position uncertainty (±40 mm) our novel UQ-ECGI formulation produced reasonable solutions (root mean squared error < 1 mV, spatial correlation >0.6, temporal correlation >0.75).
J.D. Blum, J. Beiriger, C. Kalmar, R.A. Avery, S. Lang, D.F. Villavisanis, L. Cheung, D.Y. Cho, W. Tao, R. Whitaker, S.P. Bartlett, J.A. Taylor, J.A. Goldstein, J.W. Swanson. Relating Metopic Craniosynostosis Severity to Intracranial Pressure, In The Journal of Craniofacial Surgery, 2022.
A subset of patients with metopic craniosynostosis are noted to have elevated intracranial pressure (ICP). However, it is not known if the propensity for elevated ICP is influenced by the severity of metopic cranial dysmorphology.