Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “inverse problems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

RandONets: Shallow networks with random projections for learning linear and nonlinear operators

Deep neural networks have been extensively used for the solution of both the forward and the inverse problem for dynamical systems. However, their implementation necessitates optimizing a high-dimensional space of parameters and hyperparameters. This fact, along with the requirement of substantial computational resources, pose a barrier to achieving high numerical accuracy, but also interpretability. Here, to address the above challenges, we present Random Projection-based Operator Networks (RandONets): shallow networks with random projections and tailor-made numerical analysis methods that learn accurately and fast linear and nonlinear operators. Building on previous works, we prove that RandOnets are universal approximators of linear and nonlinear operators. Due to their simplicity, RandONets provide a one-step transformation of the input space, facilitating interpretability. For the evaluation of their performance, we focus on operators of PDEs. We show, that RandONets outperform by several orders of magnitude, both in terms of numerical approximation accuracy and computational cost, the “vanilla” DeepONets. Hence, we believe that our method will trigger further developments in the field of scientific machine learning, for the development of new ‘’light”schemes that will provide high accuracy while reducing dramatically the computational cost. A MATLAB toolbox for RandONets, including demos, is available on GitHub at https://github.com/GianlucaFabiani/RandONets.

Interpretable machine learning↗
DOE OSTI2020

Polymer informatics: Current status and critical next steps

Artificial intelligence (AI) based approaches are beginning to impact several domains of human life, science and technology. Polymer informatics is one such domain where AI and machine learning (ML) tools are being used in the efficient development, design and discovery of polymers. Surrogate models are trained on available polymer data for instant property prediction, allowing screening of promising polymer candidates with specific target property requirements. Questions regarding synthesizability, and potential (retro)synthesis steps to create a target polymer, are being explored using statistical means. Data-driven strategies to tackle unique challenges resulting from the extraordinary chemical and physical diversity of polymers at small and large scales are being explored. Other major hurdles for polymer informatics are the lack of widespread availability of curated and organized data, and approaches to create machine-readable representations that capture not just the structure of complex polymeric situations but also synthesis and processing conditions. Methods to solve inverse problems, wherein polymer recommendations are made using advanced AI algorithms that meet application targets, are being investigated. As various parts of the burgeoning polymer informatics ecosystem mature and become integrated, efficiency improvements, accelerated discoveries and increased productivity can result. Here in this paper, we review emergent components of this polymer informatics ecosystem and discuss imminent challenges and opportunities.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Quantitative and three-dimensional assessment of holdup material

Nuclear material deposited in equipment, transfer lines, and ventilation systems of a processing facility is usually referred to as holdup. Operators need to know the location and amount of holdup in their facility for radiation safety and material accountability. In this work, we propose to use an array of detectors co-axial to the inspected pipe to measure the holdup material. This method is implementable into an automated system capable of crawling on surfaces and pipes of various curvatures, which would enable faster, easier, and more accurate holdup safeguards measurements. We first demonstrated that the current holdup assay procedure could lead to a non-negligible bias in the estimate of special nuclear material mass, due to the simplified assumption of deposited geometry introduced by the Generalized Geometry Holdup (GGH) model. The new approach consists of imaging the inner holdup material by characterizing the detector array’s response and unfolding it from the measured light output. Our experimental proof of principle consists of three NaI(Tl) detectors surrounding an aluminum pipe containing two cesium-137 ( 137 Cs) sources. We derived the source distribution inside the pipe by first calculating the detector response matrix using a method adaptive to the surface geometry of the object containing the measured holdup material. Creating a matrix of the detector array’s measured counts, we then proceed to solve an inverse problem, resulting in an accurately located source position and activity distribution within the response matrix’s spatial resolution. Furthermore, we then developed a simulated model of the envisioned experimental setup, which accurately described both the activity and position of the source in 2D. Finally, we extended our model onto a discretized three-dimensional model of the system, encompassing 36 detectors. The model was simulated to measure the source distribution and activity of multiple sources in pipes of varied geometries, which could then be conveniently translated to a real-time holdup measurement protocol. For the 3D simulation of four different source geometries, the model accurately localized the source position in 3D, while the activity retained a maximum relative error of ±5.32%.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Ultrasonic measurement of temperature distributions in extreme environments: Electrical power plants testing in utility-scale steam generators

Thermal heterogeneities within energy conversion and storage, material processing, nuclear processes, aerospace, and military applications are often inaccessible to characterization by insertion sensors. When sensor deployment is possible, conventional pointwise temperature probes quickly degrade when inserted into harsh environments typical of such processes. We developed spatially-resolved ultrasonic thermometry to noninvasively measure the spatial distributions of thermal properties in such applications, even when sizable thermal gradients are present. Our method divides the path of ultrasonic propagation into segments bound by echogenic features, which create echoes in pulse-echo mode, encoding the information about interior temperature distributions. We use the acquired ultrasonic responses to estimate the internal temperature distributions by solving an inverse problem or concatenating segmental estimates. This work describes the implementation and industrial testing of the developed method at a coal-fired electrical power generation plant. We inserted an echogenically segmented Inconel 625 waveguide into the combustion zone of the utility-scale boiler and continuously acquired ultrasonic data while keeping sensitive components away from the damaging combustion environment. The accuracy of the time-dependent temperature distributions reconstructed from the ultrasonic measurements was comparable to that of thermocouples. The resiliency of ultrasonic thermometry to harsh combustion conditions was far superior to conventional insertion sensors. The measurements obtained during plant operation captured daily steam generation cycles in response to changing customer demand and intermittent contributions of renewable power sources to the power grid. These measurements have revealed new insights into the relationship between the dynamic power generation load and the conditions inside the steam generator. As a result, the successful industrial testing of spatially-resolved ultrasonic thermometry in solids indicates that the developed technology has matured to become an attractive alternative to conventional sensing in solving challenging problems of long-term thermal characterizations in extreme environments.

42 ENGINEERING↗
DOE OSTI2021

Artificial Neural Networks as Mappings between Proton Potentials, Wave Functions, Densities, and Energy Levels

We report artificial neural networks (ANNs) have become important in quantum chemistry. Herein, applications to nuclear quantum effects, such as zero-point energy, vibrationally excited states, and hydrogen tunneling, are explored. ANNs are used to solve the time-independent Schrödinger equation for single- and double-well potentials representing hydrogen-bonded molecular systems capable of proton transfer. ANN mappings are trained to predict the lowest five proton vibrational energies, wave functions, and densities from the proton potentials and to predict the excited state proton vibrational energies and densities from the proton ground state density. For the inverse problem, ANN mappings are trained to predict the proton potential from the proton vibrational energy levels or the proton ground state density. This latter mapping is theoretically justified by the first Hohenberg-Kohn theorem establishing a one-to-one correspondence between the external potential and the ground state density. ANNs for two- and three-dimensional systems are also presented to illustrate the straightforward extension to higher dimensions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

An Efficient Bayesian Approach to Learning Droplet Collision Kernels: Proof of Concept Using “Cloudy,” a New n -Moment Bulk Microphysics Scheme

The small-scale microphysical processes governing the formation of precipitation particles cannot be resolved explicitly by cloud resolving and climate models. Instead, they are represented by microphysics schemes that are based on a combination of theoretical knowledge, statistical assumptions, and fitting to data (“tuning”). Historically, tuning was done in an ad hoc fashion, leading to parameter choices that are not explainable or repeatable. Recent work has treated it as an inverse problem that can be solved by Bayesian inference. The posterior distribution of the parameters given the data—the solution of Bayesian inference—is found through computationally expensive sampling methods, which require over $\mathcal{O}$(10 5 ) evaluations of the forward model; this is prohibitive for many models. We present a proof of concept of Bayesian learning applied to a new bulk microphysics scheme named “Cloudy,” using the recently developed Calibrate-Emulate-Sample (CES) algorithm. Cloudy models collision-coalescence and collisional breakup of cloud droplets with an adjustable number of prognostic moments and with easily modifiable assumptions for the cloud droplet mass distribution and the collision kernel. The CES algorithm uses machine learning tools to accelerate Bayesian inference by reducing the number of forward evaluations needed to $\mathcal{O}$(10 2 ). It also exhibits a smoothing effect when forward evaluations are polluted by noise. In a suite of perfect-model experiments, we show that CES enables computationally efficient Bayesian inference of parameters in Cloudy from noisy observations of moments of the droplet mass distribution. In an additional imperfect-model experiment, a collision kernel parameter is successfully learned from output generated by a Lagrangian particle-based microphysics model.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Transient Storage Model Parameter Optimization Using the Simulated Annealing Method

Hyporheic exchange in streams is critical to ecosystem functions such as nutrient cycling along river corridors, especially for slowly moving or small stream systems. The transient storage model (TSM) has been widely used for modeling of hyporheic exchange. TSM calibration, for hyporheic exchange, is typically used to estimate four parameters, including the mass exchange rate coefficient, the dispersion coefficient, stream cross-sectional area, and hyporheic zone cross-sectional area. Prior studies have raised concerns regarding the non-uniqueness of the inverse problem for the TSM, that is, the occurrence of different parameter vectors resulting in TSM solution that reproduces the observed in-stream tracer break through curve (BTC) with the same error. This leads to practical non-identifiability in determining the unknown parameter vector values even when global-optimal values exist, and the parameter optimization becomes practically non-unique. To address this problem, we applied the simulated annealing method to calibrate the TSM to BTCs, because it is less susceptible to local minima-induced non-identifiability. A hypothetical (or synthetic) tracer test data set with known parameters was developed to demonstrate the capability of the simulated annealing method to find the global minimum parameter vector, and it identified the “hypothetically-true” global minimum parameter vector even with input data that were modified with up to 10% noise without increasing the number of iterations required for convergence. The simulated annealing TSM was then calibrated using two in-stream tracer tests conducted in East Fork Poplar Creek, Tennessee. In conclusion, simulated annealing was determined to be appropriate for quantifying the TSM parameter vector because of its search capability for the global minimum parameter vector.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Improving the Quasi‐Biennial Oscillation via a Surrogate‐Accelerated Multi‐Objective Optimization

Accurate simulation of the quasi-biennial oscillation (QBO) is challenging due to uncertainties in representing convectively generated gravity waves. We develop an end-to-end uncertainty quantification workflow that calibrates these gravity wave processes in E3SM for a realistic QBO. Central to our approach is a domain knowledge-informed, compressed representation of high-dimensional spatio-temporal wind fields. By employing a parsimonious statistical model that learns the fundamental frequency from complex observations, we extract interpretable and physically meaningful quantities capturing key attributes. Building on this, we train a probabilistic surrogate model that approximates the fundamental characteristics of the QBO as functions of critical physics parameters governing gravity wave generation. Leveraging the Karhunen–Loève decomposition, our surrogate efficiently represents these characteristics as a set of orthogonal features, capturing cross-correlations among multiple physics quantities evaluated at different pressure levels and enabling rapid surrogate-based inference at a fraction of the computational cost of full-scale simulations. Finally, we analyze the inverse problem using a multi-objective approach. Our study reveals a tension between amplitude and period that constrains the QBO representation, precluding a single optimal solution. To navigate this, we quantify the bi-criteria trade-off and generate a set of Pareto optimal parameter values that balance the conflicting objectives. This integrated workflow improves the fidelity of QBO simulations and offers a versatile template for uncertainty quantification in complex geophysical models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

All-optical image denoising using a diffractive visual processor

Abstract Image denoising, one of the essential inverse problems, targets to remove noise/artifacts from input images. In general, digital image denoising algorithms, executed on computers, present latency due to several iterations implemented in, e.g., graphics processing units (GPUs). While deep learning-enabled methods can operate non-iteratively, they also introduce latency and impose a significant computational burden, leading to increased power consumption. Here, we introduce an analog diffractive image denoiser to all-optically and non-iteratively clean various forms of noise and artifacts from input images – implemented at the speed of light propagation within a thin diffractive visual processor that axially spans <250 × λ, where λ is the wavelength of light. This all-optical image denoiser comprises passive transmissive layers optimized using deep learning to physically scatter the optical modes that represent various noise features, causing them to miss the output image Field-of-View (FoV) while retaining the object features of interest. Our results show that these diffractive denoisers can efficiently remove salt and pepper noise and image rendering-related spatial artifacts from input phase or intensity images while achieving an output power efficiency of ~30–40%. We experimentally demonstrated the effectiveness of this analog denoiser architecture using a 3D-printed diffractive visual processor operating at the terahertz spectrum. Owing to their speed, power-efficiency, and minimal computational overhead, all-optical diffractive denoisers can be transformative for various image display and projection systems, including, e.g., holographic displays.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Generative modeling enables molecular structure retrieval from Coulomb explosion imaging

Capturing the structural changes that molecules undergo during chemical reactions in real space and time is a long-standing dream and an essential prerequisite for understanding and ultimately controlling femtochemistry. A key approach to tackle this challenging task is Coulomb explosion imaging, which benefited decisively from recently emerging high-repetition-rate X-ray free-electron laser sources. With this technique, information on the molecular structure is inferred from the momentum distributions of the ions produced by the rapid Coulomb explosion of molecules. Retrieving molecular structures from these distributions poses a highly non-linear inverse problem that remains unsolved for molecules consisting of more than a few atoms. Here, we address this challenge using a diffusion-based Transformer neural network. We show that the network reconstructs unknown molecular geometries from ion-momentum distributions with a mean absolute error below one Bohr radius, which is half the length of a typical chemical bond.

Artificial Intelligence (cs.AI)↗
DOE OSTI2021

Differential programming enabled functional imaging with Lorentz transmission electron microscopy

Abstract Lorentz transmission electron microscopy is an advanced characterization technique that enables the simultaneous imaging of both the microstructure and functional properties of materials. Information such as magnetization and electric potentials is carried by the phase of the electron wave, and is lost during image acquisition. Various methods have been proposed to retrieve the phase of the electron wavefunction using intensities of the acquired images, most of which work only in the small defocus limit. Imaging at strong defoci not only carries more quantitative phase information, but is essential to the study of weak magnetic and electrostatic fields at the nanoscale. In this work we develop a method based on differentiable programming to solve the inverse problem of phase retrieval. We show that our method maintains a high spatial resolution and robustness against noise even at the upper defocus limit of the microscope. More importantly, our proposed method can go beyond recovering just the phase information. We demonstrate this by retrieving the electron-optical parameters of the contrast transfer function alongside the electron exit wavefunction.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Inferring topological transitions in pattern-forming processes with self-supervised learning

Abstract The identification of transitions in pattern-forming processes are critical to understand and fabricate microstructurally precise materials in many application domains. While supervised methods can be useful to identify transition regimes, they need labels, which require prior knowledge of order parameters or relevant microstructures describing these transitions. Instead, we develop a self-supervised, neural-network-based approach that does not require predefined labels about microstructure classes to predict process parameters from observed microstructures. We show that assessing the difficulty of solving this inverse problem can be used to uncover microstructural transitions. We demonstrate our approach by automatically discovering microstructural transitions in two distinct pattern-forming processes: the spinodal decomposition of a two-phase mixture and the formation of binary-alloy microstructures during physical vapor deposition of thin films. This approach opens a path forward for discovering unseen or hard-to-discern transitions and ultimately controlling complex pattern-forming processes.

Abram, Marcin↗
DOE OSTI2020

Learning to Predict Crystal Plasticity at the Nanoscale: Deep Residual Networks and Size Effects in Uniaxial Compression Discrete Dislocation Simulations

The density and configurational changes of crystal dislocations during plastic deformation influence the mechanical properties of materials. These influences have become clearest in nanoscale experiments, in terms of strength, hardness and work hardening size effects in small volumes. The mechanical characterization of a model crystal may be cast as an inverse problem of deducing the defect population characteristics (density, correlations) in small volumes from the mechanical behavior. In this work, we demonstrate how a deep residual network can be used to deduce the dislocation characteristics of a sample of interest using only its surface strain profiles at small deformations, and then statistically predict the mechanical response of size-affected samples at larger deformations. As a testbed of our approach, we utilize high-throughput discrete dislocation simulations for systems of widths that range from nano- to micro- meters. We show that the proposed deep learning model significantly outperforms a traditional machine learning model, as well as accurately produces statistical predictions of the size effects in samples of various widths. By visualizing the filters in convolutional layers and saliency maps, we find that the proposed model is able to learn the significant features of sample strain profiles.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2022

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

In this work we investigate the use of deep inverse models (DIMs) for designing artificial electromagnetic materials (AEMs) – such as metamaterials, photonic crystals, and plasmonics – to achieve some desired scattering properties (e.g., transmission or reflection spectrum). DIMs are deep neural networks (i.e., deep learning models) that are specially-designed to solve ill-posed inverse problems. There has recently been tremendous growth in the use of DIMs for solving AEM design problems however there has been little comparison of these approaches to examine their absolute and relative performance capabilities. In this work we compare eight state-of-the-art DIMs on three unique AEM design problems, including two models that are novel to the AEM community. Our results indicate that DIMs can rapidly produce accurate designs to achieve a custom desired scattering on all three problems. Although no single model always performs best, the Neural-Adjoint approach achieves the best overall performance across all problem settings. As a final contribution we show that not all AEM design problems are ill-posed, and in such cases a conventional deep neural network can perform better than DIMs. We recommend that a deep neural network is always employed as a simple baseline approach when addressing AEM design problems. Furthermore, we publish python code for our AEM simulators and our DIMs to enable easy replication of our results, and benchmarking of new DIMs by the AEM community.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Super resolution convolutional neural network for feature extraction in spectroscopic data

Two dimensional (2D) peak finding is a common practice in data analysis for physics experiments, which is typically achieved by computing the local derivatives. However, this method is inherently unstable when the local landscape is complicated or the signal-to-noise ratio of the data is low. In this work, we propose a new method in which the peak tracking task is formalized as an inverse problem, which thus can be solved with a convolutional neural network (CNN). In addition, we show that the underlying physics principle of the experiments can be used to generate the training data. By generalizing the trained neural network on real experimental data, we show that the CNN method can achieve comparable or better results than traditional derivative based methods. This approach can be further generalized in different physics experiments when the physical process is known.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

Guided search for desired functional responses via Bayesian optimization of generative model: Hysteresis loop shape engineering in ferroelectrics

Advances in theoretical modeling across multiple disciplines have yielded generative models capable of high veracity in predicting macroscopic functional responses of materials emerging as a result of complex non-local interactions. Correspondingly, of interest is the inverse problem of finding the model parameter that will yield desired macroscopic responses, such as stress–strain curves, ferroelectric hysteresis loops, etc. Here, we suggest and implement Gaussian process based methods that allow to effectively sample the degenerate parameter space of a complex non-local model to output regions of parameter space which yield desired functionalities. In this work, we discuss the specific adaptation of the acquisition function and sampling function to make the process efficient and balance the efficient exploration of parameter space for multiple possible minima and exploitation to densely sample the regions of interest where target behaviors are optimized. Additionally, this approach is illustrated via the hysteresis loop engineering in ferroelectric materials but can be adapted to other functionalities and generative models.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

Machine learning for detection of 3D features using sparse x-ray tomographic reconstruction

In many inertial confinement fusion (ICF) experiments, the neutron yield and other parameters cannot be completely accounted for with one and two dimensional models. This discrepancy suggests that there are three dimensional effects that may be significant. Sources of these effects include defects in the shells and defects in shell interfaces, the fill tube of the capsule, and the joint feature in double shell targets. Due to their ability to penetrate materials, x rays are used to capture the internal structure of objects. Methods such as computational tomography use x-ray radiographs from hundreds of projections, in order to reconstruct a three dimensional model of the object. In experimental environments, such as the National Ignition Facility and Omega-60, the availability of these views is scarce, and in many cases only consists of a single line of sight. Mathematical reconstruction of a 3D object from sparse views is an ill-posed inverse problem. These types of problems are typically solved by utilizing prior information. Neural networks have been used for the task of 3D reconstruction as they are capable of encoding and leveraging this prior information. We utilize half a dozen, different convolutional neural networks to produce different 3D representations of ICF implosions from the experimental data. Deep supervision is utilized to train a neural network to produce high-resolution reconstructions. These representations are used to track 3D features of the capsules, such as the ablator, inner shell, and the joint between shell hemispheres. Machine learning, supplemented by different priors, is a promising method for 3D reconstructions in ICF and x-ray radiography, in general.

Wolfe, Bradley T. (ORCID:0000000268301614)↗