Search NASA⌕ Search

Engineering topics

Tran, Hoang

Publications and source records attributed to Tran, Hoang.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Spatio–Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology

Integrated hydrologic models can simulate coupled surface and subsurface processes but are computationally expensive to run at high resolutions over large domains. Here we develop a novel deep learning model to emulate subsurface flows simulated by the integrated ParFlow–CLM model across the contiguous US. We compare convolutional neural networks like ResNet and UNet run autoregressively against our novel architecture called the Forced SpatioTemporal RNN (FSTR). The FSTR model incorporates separate encoding of initial conditions, static parameters, and meteorological forcings, which are fused in a recurrent loop to produce spatiotemporal predictions of groundwater. We evaluate the model architectures on their ability to reproduce 4D pressure heads, water table depths, and surface soil moisture over the contiguous US at 1 km resolution and daily time steps over the course of a full water year. The FSTR model shows superior performance to the baseline models, producing stable simulations that capture both seasonal and event–scale dynamics across a wide array of hydroclimatic regimes. The emulators provide over 1,000× speedup compared to the original physical model, which will enable new capabilities like uncertainty quantification and data assimilation for integrated hydrologic modeling that were not previously possible. Our results demonstrate the promise of using specialized deep learning architectures like FSTR for emulating complex process–based models without sacrificing fidelity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Quantifying the Impacts of Land-Cover Change on the Hydrologic Response to Hurricane Ida in the Lower Mississippi River Basin

Abstract The Lower Mississippi River basin (LMRB) has experienced significant changes in land cover and is one of the most vulnerable regions to hurricanes in the United States. Here, we study the impacts of land-cover change on the hydrologic response to Hurricane Ida in LMRB. By using an integrated surface–subsurface hydrologic model, Energy Exascale Earth System Model (E3SM) Land Model coupled with the three-dimensional ParFlow subsurface flow model (ELM-ParFlow), we simulate the effects of land-cover change on the flood volume and peak timing induced by rainfall from Hurricane Ida. The results show that land-cover changes from 1850 to 2015, which resulted in a smoother surface and less vegetation, exacerbated both flood peak time and volume induced by Hurricane Ida. The effects of land-cover changes can be decomposed into two mechanisms: a smoother surface routes more water faster to a watershed outlet and less vegetation allows more water to contribute to surface runoff. By comparing scenarios in which the two mechanisms were isolated, we found that changes in soil moisture due to vegetation cover change have more dominant effects on floods in the southern part and changes in Manning’s coefficient have the largest effect on floods in the northern part of the LMRB. The study provides important insights into the complex relationship between land-use, land-cover, and hydrologic processes in coastal regions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Material Model Parameters Optimization in Liquid Mercury Target Dynamics Simulation With Machine Learning Surrogates

A pulsed spallation target is subjected to very short (∼0.7μs) but intense loads (23.3 kJ) from repeated proton pulses, which knock away neutrons from the mercury atoms’ nuclei for a wide range application in physics, engineering, medicine, petroleum exploration, biology, chemistry, etc. The effect of this pulsed loading on the stainless-steel target module which contains the flowing mercury target material is difficult to predict not only due to its short but intense explosive-like physical reaction, but also the nonlinear material behavior of the liquid mercury in the structure. Injecting small helium bubbles in the mercury has been an efficient method of mitigating the pressure wave at high power level stage. However, prediction of the resultant loading on the target is more difficult when helium gas is intentionally injected into the mercury. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this complex multi-physics dynamics problem by including the bubble dynamics in the liquid mercury. A parameter sensitivity study was firstly employed to understand their impact on the simulation strains. The investigated parameters included E, μ, γ, σ, n, VFgas, and gas cumulative volume curve control parameters a and b. Verification and validation results from sparse polynomial expansions (SPE) method and directional Gaussian smoothing (DGS) optimization show that the surrogate model had training error of ∼7% and validation error of ∼15%, indicating that machine learning methods and surrogate models can help optimize the uncertain parameters in the complex 2-phase material model. This approach is expected to fill the knowledge gap between unknown liquid-gas mixture material model and measured vessel strain responses.

Lin, Lianshan↗
DOE OSTI2024

Calibration of the 2-Phase Bubble Tracking Model for Liquid Mercury Target Simulation with Machine Learning Surrogate Models

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory is one of the most powerful accelerator-driven neutron sources in the world. The intense protons strike on SNS's mercury target to provide bright neutron beams, which also leads to severe fluid-structure interactions inside the target. Prediction of resultant loading on the target is difficult particularly when helium gas is injected into mercury to reduce the loading and mitigate the pitting damage on vessel walls. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this multi-physics problem. However, several uncertain parameters in the R-P model require intensive simulations to determine their optimal values. With the help of machine learning and the measured target strain, we have studied the major uncertain parameters in this R-P model and developed a framework to identify optimal parameters that significantly reduce the discrepancy between simulations and experimental strains. The preliminary results show the possibility of using this mercury/helium mixture and surrogate models to predict a better match of target strain response when the helium gas is injected.

Lin, Lianshan↗
DOE OSTI2023

Uncertainty Quantification of Capacitor Switching Transient Location using Machine Learning

Identification of capacitor switching transient location provides valuable insight into the state of the associated equipment. Machine learning (ML) models, and convolutional neural networks (CNNs) in particular, have demonstrated remarkable performance in signal location. However, ML models are data driven whose predictions are affected by noise in data and may also suffer from large extrapolation errors when applied to new conditions. Uncertainty quantification (UQ) is necessary to ensure model trustworthiness and avoid overconfident predictions in extrapolation. Here, in this work, we propose a novel UQ method, called PI3NN, to quantify prediction uncertainty of ML models and integrate the method with CNNs for transient source location. PI3NN calculates Prediction Intervals by training 3 Neural Networks and uses root-finding methods to determine the interval precisely. Additionally, PI3NN can identify out-of-distribution (OOD) data in a nonstationary condition to avoid overconfident prediction. Results indicate that with PI3NN, transient signals are not only correctly identified, but when said signals are subject to corruptions characteristic of an actual power monitoring system (e.g. non-ideal sensors), the model recognizes when it is uncertain about its predictions, effectively letting the user know when to accept or discard the results.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Climate lags and genetics determine phenology in quaking aspen ( Populus tremuloides )

Spatiotemporal patterns of phenology may be affected by mosaics of environmental and genetic variation. Environmental drivers may have temporally lagged impacts, but patterns and mechanisms remain poorly known. Here, we combine multiple genomic, remotely sensed, and physically modeled datasets to determine the spatiotemporal patterns and drivers of canopy phenology in quaking aspen, a widespread clonal dioecious tree species with diploid and triploid cytotypes. We show that over 391 km 2 of southwestern Colorado: greenup date, greendown date, and growing season length vary by weeks and differ across sexes, cytotypes, and genotypes; phenology has high phenotypic plasticity and heritabilities of 31–61% (interquartile range); and snowmelt date, soil moisture, and air temperature predict phenology, at temporal lags of up to 3 yr. Our study shows that lagged environmental effects are needed to explain phenological variation and that the effect of cytotype on phenology is obscured by its correlation with topography. Phenological patterns are consistent with responses to multiyear accumulation of carbon deficit or hydraulic damage.

carbon allocation↗
DOE OSTI2022

Exploiting the Local Parabolic Landscapes of Adversarial Losses to Accelerate Black-Box Adversarial Attack

Existing black-box adversarial attacks on image classifiers update the perturbation at each iteration from only a small number of queries of the loss function. Since the queries contain very limited information about the loss, black-box methods usually require much more queries than white-box methods. We propose to improve the query efficiency of black-box methods by exploiting the smoothness of the local loss landscape. However, many adversarial losses are not locally smooth with respect to pixel perturbations. To resolve this issue, our first contribution is to theoretically and experimentally justify that the adversarial losses of many standard and robust image classifiers behave like parabolas with respect to perturbations in the Fourier domain. Our second contribution is to exploit the parabolic landscape to build a quadratic approximation of the loss around the current state, and use this approximation to interpolate the loss value as well as update the perturbation without additional queries. Since the local region is already informed by the quadratic fitting, we use large perturbation steps to explore far areas. We demonstrate the efficiency of our method on MNIST, CIFAR-10 and ImageNet datasets for various standard and robust models, as well as on Google Cloud Vision. The experimental results show that exploiting the loss landscape can help significantly reduce the number of queries and increase the success rate. Our codes are available at https://github.com/HoangATran/BABIES.

Tran, Hoang↗
DOE OSTI2022

Field Work Proposal ERKJ358: Black-box training for scientific machine learning models (Final Report)

The overarching goal of this project is to develop a scalable black-box training capability for scientific machine learning (SciML) problems that are non-trainable with existing automatic differentiation (AD)-based algorithms. AD assumes that a loss function can be decomposed into a sequence of elementary operations whose derivatives are known. This assumption is violated when the loss function includes a black-box physical model (e.g., a legacy simulator). The current strategy, converting a black-box simulator to an AD-enabled code via differential programming, is inflexible and time-, labor-consuming. Thus, black-box optimization is a main workhorse for training SciML models, e.g., in scientific reinforcement learning, hyper-parameter fine tuning, designing SciML models with adversarial robustness, etc.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Benchmarking and Exploring Parameter Space of the 2-Phase Bubble Tracking Model for Liquid Mercury Target Simulation

High intensity proton pulses strike the Spallation Neutron Source (SNS)’s mercury target to provide bright neutron beams. These strikes deposit extensive energy into the mercury and its steel vessel. Prediction of the resultant loading on the target is difficult when helium gas is intentionally injected into the mercury to reduce the loading and to mitigate the pitting damage on the vessel. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this complex multi-physics dynamics problem by including the bubble dynamics in the liquid mercury. We present a study comparing the measured target strains in the SNS target station with the simulation results of the solid mechanics simulation framework. We investigate a wide range of various physical model parameters, including the number of bubble families, bubble size distribution, viscosity, surface tension, etc. to understand their impact on simulation accuracy. Our initial findings reveal that using 8-10 bubble families in the model renders a simulation strain envelope that covers the experimental ones. Further optimization studies are planned to predict the strain response more accurately.

Lin, Lianshan↗
DOE OSTI2022

Model calibration of the liquid mercury spallation target using evolutionary neural networks and sparse polynomial expansions

The mercury constitutive model predicting the strain and stress in the target vessel plays a central role in improving the lifetime prediction and future target designs of the mercury targets at the Spallation Neutron Source. We leverage the experiment strain data collected over multiple years to improve the mercury constitutive model through a combination of large scale simulations of the target behavior and the use of machine learning tools for parameter estimation. We present two interdisciplinary approaches for surrogate-based model calibration of expensive simulations using evolutionary neural networks and sparse polynomial expansions. The newly calibrated simulations achieve 7% average improvement on the prediction accuracy and 8% reduction in mean absolute error compared to previously reported reference parameters, with some individual sensors experiencing up to 30% improvement. The calibrated simulations can aid in fatigue analysis to estimate the mercury target lifetime, which reduces abrupt failure and saves tremendous amount of costs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

A dictionary learning algorithm for compression and reconstruction of streaming data in preset order

There has been an emerging interest in developing and applying dictionary learning (DL) to process massive datasets in the last decade. Many of these efforts, however, focus on employing DL to compress and extract a set of important features from data, while considering restoring the original data from this set a secondary goal. On the other hand, although several methods are able to process streaming data by updating the dictionary incrementally as new snapshots pass by, most of those algorithms are designed for the setting where the snapshots are randomly drawn from a probability distribution. In this paper, we present a new DL approach to compress and denoise massive dataset in real time, in which the data are streamed through in a preset order (instances are videos and temporal experimental data), so at any time, we can only observe a biased sample set of the whole data. Here, our approach incrementally builds up the dictionary in a relatively simple manner: if the new snapshot is adequately explained by the current dictionary, we perform a sparse coding to find its sparse representation; otherwise, we add the new snapshot to the dictionary, with a Gram-Schmidt process to maintain the orthogonality. To compress and denoise noisy datasets, we apply the denoising to the snapshot directly before sparse coding, which deviates from traditional dictionary learning approach that achieves denoising via sparse coding. Compared to full-batch matrix decomposition methods, where the whole data is kept in memory, and other mini-batch approaches, where unbiased sampling is often assumed, our approach has minimal requirement in data sampling and storage: i) each snapshot is only seen once then discarded, and ii) the snapshots are drawn in a preset order, so can be highly biased. Through experiments on climate simulations and scanning transmission electron microscopy (STEM) data, we demonstrate that the proposed approach performs competitively to those methods in data reconstruction and denoising.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Analysis of sparse recovery for Legendre expansions using envelope bound

We provide novel sufficient conditions for the uniform recovery of sparse Legendre expansions using ℓ 1 minimization, where the sampling points are drawn according to orthogonalization (uniform) measure. So far, conditions of the form m ≳ Θ 2 s x log factors have been relied on to determine the minimum number of samples m that guarantees successful reconstruction of s-sparse vectors when the measurement matrix is associated to an orthonormal system. However, in case of sparse Legendre expansions, the uniform bound Θ of Legendre systems is so high that these conditions are unable to provide meaningful guarantees. Here, in this paper, we present an analysis which employs the envelop bound of all Legendre polynomials instead, and prove a new recovery guarantee for s-sparse Legendre expansions, m ≳ Θs 2 x log factors, which is independent of Θ. Arguably, this is the first recovery condition established for orthonormal systems without assuming the uniform boundedness of the sampling matrix. The key ingredient of our analysis is an extension of chaining arguments, recently developed in Bourgain and Chkifa et al., to handle the envelope bound. Furthermore, our recovery condition is proved via restricted eigenvalue property, a less demanding replacement of restricted isometry property which is perfectly suited to the considered scenario. Along the way, we derive simple criteria to detect good sample sets. Our numerical tests show that sets of uniformly sampled points that meet these criteria will perform better recovery on average.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A hydrological simulation dataset of the Upper Colorado River Basin from 1983 to 2019

Abstract This article presents a hydrological reconstruction of the Upper Colorado River Basin with an hourly temporal resolution, and 1-km spatial resolution from October 1982 to September 2019. The validated dataset includes a suite of hydrologic variables including streamflow, water table depth, snow water equivalent (SWE) and evapotranspiration (ET) simulated by an integrated hydrological model, ParFlow-CLM. The dataset was validated over the period with a combination of point observations and remotely sensed products. These datasets provide a long-term, natural-flow, simulation for one of the most over-allocated basins in the world.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Analysis of the ratio of ℓ 1 and ℓ 2 norms in compressed sensing

We study the ratio of ℓ 1 and ℓ 2 norms ( ℓ 1 / ℓ 2 ) as a sparsity-promoting objective in compressed sensing. We first propose a novel criterion that guarantees that an s-sparse signal is the local minimizer of the ℓ 1 / ℓ 2 objective; our criterion is interpretable and useful in practice. We also give the first uniform recovery condition using a geometric characterization of the null space of the measurement matrix, and show that this condition is satisfied for a class of random matrices. We also present analysis on the robustness of the procedure when noise pollutes data. Numerical experiments are provided that compare ℓ 1 / ℓ 2 with some other popular non-convex methods in compressed sensing. Finally, we propose a novel initialization approach to accelerate the numerical optimization procedure. We call this initialization approach support selection, and we demonstrate that it empirically improves the performance of existing ℓ 1 / ℓ 2 algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Enabling Long-range Exploration in Minimization of Multimodal Functions

We consider the problem of minimizing multi-modal loss functions with a large number of local optima. Since the local gradient points to the direction of the steepest slope in an infinitesimal neighborhood, an optimizer guided by the local gradient is often trapped in a local minimum. To address this issue, we develop a novel nonlocal gradient to skip small local minima by capturing major structures of the loss’s landscape in black-box optimization. The nonlocal gradient is defined by a directional Gaussian smoothing (DGS) approach. The key idea of DGS is to conducts 1D long-range exploration with a large smoothing radius along d orthogonal directions in Rd, each of which defines a nonlocal directional derivative as a 1D integral. Such long-range exploration enables the nonlocal gradient to skip small local minima. The d directional derivatives are then assembled to form the nonlocal gradient. We use the Gauss-Hermite quadrature rule to approximate the d 1D integrals to obtain an accurate estimator. The superior performance of our method is demonstrated in three sets of examples, including benchmark functions for global optimization, and two real-world scientific problems.

Zhang, Jiaxin↗
DOE OSTI2021

On the Strong Convergence of Forward-Backward Splitting in Reconstructing Jointly Sparse Signals

We consider the problem of reconstructing an infinite set of sparse, finite-dimensional vectors, that share a common sparsity pattern, from incomplete measurements. This is in contrast to the work (Daubechies et al., Pure Appl. Math. 57(11), 1413–1457, 2004), where the single vector signal can be infinite-dimensional, and (Fornasier and Rauhut, SIAM J. Numer. Anal. 46(2), 577613, 2008), which extends the aforementioned work to the joint sparse recovery of finite number of infinite-dimensional vectors. In our case, to take account of the joint sparsity and promote the coupling of nonvanishing components, we employ a convex relaxation approach with mixed norm penalty ℓ 2,1 . This paper discusses the computation of the solutions of linear inverse problems with such relaxation by a forward-backward splitting algorithm. However, since the solution matrix possesses infinitely many columns, the arguments of Daubechies et al. (Pure Appl. Math. 57(11), 1413–1457, 2004) no longer apply. As such, we establish new strong convergence results for the algorithm, in particular when the set of jointly sparse vectors is infinite.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Application of Machine Learning to Predict the Response of the Liquid Mercury Target at the Spallation Neutron Source

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory is currently the most powerful accelerator-driven neutron source in the world. The intense proton pulses strike on SNS’s mercury target to provide bright neutron beams, which also leads to severe fluid-structure interactions inside the target. Prediction of resultant loading on the target is difficult particularly when helium gas is intentionally injected into mercury to reduce the loading and mitigate the pitting damage on the target’s internal walls. Leveraging the power of machine learning and the measured target strain, we have developed machine learning surrogates for modeling the discrepancy between simulations and experimental strain data. We then employ these surrogates to guide the refinement of the high-fidelity mercury/helium mixture model to predict a better match of target strain response.

Lin, Lianshan↗