Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “inversion methods”

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Artificial Intelligence for Conjugated Polymers

Conjugated polymers have garnered significant attention due to their diverse applications in electronics, photonics, and energy storage. However, realizing their full potential poses a formidable challenge, as their design has historically relied on iterative adjustments and continuous inspiration from researchers. Traditional methods often struggle to efficiently navigate their vast chemical landscape. In this work, the application of artificial intelligence (AI), specifically machine learning (ML), needs to be discussed in the realm of conjugated polymers. Our paper emphasizes the importance of understanding the structure–property relationships of these polymers and how ML can facilitate property prediction and inverse-design. We delve into various chemical fingerprints, structural descriptors, and ML algorithms, showcasing their utility across a spectrum of applications, including simulations, glass transition temperature determination, photovoltaics, reorganization energy for charge transport, photocatalysts, and sensors. Finally, we give some outlooks in this filed and propose unexplored areas within the field that hold the potential to benefit from ML techniques.

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

Parameter estimation for X-ray scattering analysis with Hamiltonian Markov Chain Monte Carlo

Bayesian-inference-based approaches, in particular the random-walk Markov Chain Monte Carlo (MCMC) method, have received much attention recently for X-ray scattering analysis. Hamiltonian MCMC, a state-of-the-art development in the field of MCMC, has become popular in recent years. It utilizes Hamiltonian dynamics for indirect but much more efficient drawings of the model parameters. We described the principle of the Hamiltonian MCMC for inversion problems in X-ray scattering analysis by estimating high-dimensional models for several motivating scenarios in small-angle X-ray scattering, reflectivity, and X-ray fluorescence holography. Hamiltonian MCMC with appropriate preconditioning can deliver superior performance over the random-walk MCMC, and thus can be used as an efficient tool for the statistical analysis of the parameter distributions, as well as model predictions and confidence analysis.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

A Search for Pulsars around Sgr A* in the First Event Horizon Telescope Data Set

In 2017 the Event Horizon Telescope (EHT) observed the supermassive black hole at the center of the Milky Way, Sagittarius A* (Sgr A*), at a frequency of 228.1 GHz (λ = 1.3 mm). The fundamental physics tests that even a single pulsar orbiting Sgr A* would enable motivate searching for pulsars in EHT data sets. The high observing frequency means that pulsars—which typically exhibit steep emission spectra—are expected to be very faint. However, it also negates pulse scattering, an effect that could hinder pulsar detections in the Galactic center. Additionally, magnetars or a secondary inverse Compton emission could be stronger at millimeter wavelengths than at lower frequencies. We present a search for pulsars close to Sgr A* using the data from the three most sensitive stations in the EHT 2017 campaign: the Atacama Large Millimeter/submillimeter Array, the Large Millimeter Telescope, and the IRAM 30 m Telescope. We apply three detection methods based on Fourier-domain analysis, the fast folding algorithm, and single-pulse searches targeting both pulsars and burst-like transient emission. We use the simultaneity of the observations to confirm potential candidates. No new pulsars or significant bursts were found. Being the first pulsar search ever carried out at such high radio frequencies, we detail our analysis methods and give a detailed estimation of the sensitivity of the search. We conclude that the EHT 2017 observations are only sensitive to a small fraction (≲2.2%) of the pulsars that may exist close to Sgr A*, motivating further searches for fainter pulsars in the region.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Extending water vapor measurement capability of photon-limited differential absorption lidars through simultaneous denoising and inversion

Abstract. The micropulse differential absorption lidar (MPD) was developed at Montana State University (MSU) and the National Center for Atmospheric Research (NCAR) to perform range-resolved water vapor (WV) measurements using low-power lasers and photon-counting detectors. The MPD has proven to produce accurate WV measurements up to 6 km altitude. However, the MPD's ability to produce accurate higher-altitude WV measurements is impeded by the current standard differential absorption lidar (DIAL) retrieval methods. These methods are built upon a fundamental methodology that algebraically solves for the WV using the MPD forward models and noisy observations, which exacerbates any random noise in the lidar observations. The work in this paper introduces the adapted Poisson total variation (PTV) specifically for the MPD instrument. PTV was originally developed for a ground-based high spectral resolution lidar, and this paper reports on the adaptations that were required in order to apply PTV on MPD WV observations. The adapted PTV method, coined PTV-MPD, extends the maximum altitude of the MPD from 6 to 8 km and substantially increases the accuracy of the WV retrievals starting above 2 km. PTV-MPD achieves the improvement by simultaneously denoising the MPD noisy observations and inferring the WV by separating the random noise from the non-random WV. An analysis with 130 radiosonde (RS) comparisons shows that the relative root-mean-square difference (RRMSE) of WV measurements between RS and PTV-MPD exceeds 100 % between 6 and 8 km, whereas the RRMSE between RS and the standard method exceeds 100 % near 3 km. In addition, we show that by employing PTV-MPD, the MPD is able to extend its useful range of WV estimates beyond that of the ARM Southern Great Plains Raman lidar (RRMSE exceeding 100 % between 3 and 4 km); the Raman lidar has a power-aperture product 500 times greater than that of the MPD.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Apparatus and methods for location and sizing of trace gas sources

A system for detecting gas leaks and determining their location and size. A data gathering portion of the system utilizes a chosen geometrical configuration to collect path-integrated spectroscopic data over multiple paths around an area. A processing portion of the system applies a transport model together with meteorological data of the area to generate an influence function of possible leak locations on gas detector measurement paths, and applies an inversion model to the influence function, prior data, and the spectroscopic data to generate gas source size and location.

03 NATURAL GAS↗
DOE OSTI2024

Reactor antineutrino flux and anomaly

Reactor antineutrinos have played a significant role in establishing the standard model of particle physics and the theory of neutrino oscillations. In this article, we review the reactor antineutrino flux and in particular the reactor antineutrino anomaly (RAA) coined over a decade ago. RAA refers to a deficit of the measured antineutrino inverse beta decay rates at very short-baseline reactor experiments compared to the theoretically improved predictions (i.e. the Huber–Mueller model). Since the resolution of several previous experimental anomalies have led to the discovery of non-zero neutrino mass and mixing, many efforts have been invested to study the origin of RAA both experimentally and theoretically. The progress includes the observation of discrepancies in antineutrino energy spectrum between data and the Huber–Mueller model, the re-evaluation of the Huber–Mueller model uncertainties, the potential isotope-dependent rate deficits, and the better agreement between data and new model predictions using the improved summation method. Importantly, these developments disfavor the hypothesis of a light sterile neutrino as the explanation of RAA and supports the deficiencies of Huber–Mueller model as the origin. Looking forward, more effort from both the theoretical and experimental sides is needed to fully understand the root of RAA and to make accurate predictions of reactor antineutrino flux and energy spectrum for future discoveries.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Creating high-precision reference gas standards of 85Kr for groundwater age-dating

Absolute gas counting (AGC) was applied to two gas blends of 85Kr in argon-methane (P10) counting gas to establish a high-precision specific activity (Bq/cm3) reference value for characterizing 85Kr detection efficiency for groundwater age dating measurements. The AGC or length-compensated technique has been utilized by the metrology community for decades and is an accepted method for developing radioactive gas standards. The AGC capability at Pacific Northwest National Laboratory (PNNL) uses a set of nine unequal-length proportional counters with precisely-measured internal volumes, and a gas loading system with high-precision pressure and temperature sensors. A series of AGC measurements were collected at multiple pressures to determine the inverse pressure relationship (1/P) for 85Kr and define a wall-effect correction that accounts for events decaying into the detector wall and not depositing sufficient energy in the gas to be detected. In addition to the wall-effect, two additional corrections were evaluated and are discussed in detail. Specifically, the threshold effect which accounts for events deposited below the analysis threshold and a detection efficiency as a function of detector volume effect that was observed during analysis. A robust uncertainty model was developed using the Guide to the expression of Uncertainty in Measurements (GUM) approach. The combination of carefully scrutinized correction factors, precise measurements of pressure, temperature and detector volume, and robust counting statistics resulted in the determination of high-precision specific activity values with 0.50% or less total combined uncertainty for two Kr-in-P10 reference gas standards (KP10) that will enable new groundwater age-dating measurements at PNNL.

Kr-85↗
DOE OSTI2022

Physics‐Informed Machine Learning Method for Large‐Scale Data Assimilation Problems

Abstract We develop a physics‐informed machine learning approach for large‐scale data assimilation and parameter estimation and apply it for estimating transmissivity and hydraulic head in the two‐dimensional steady‐state subsurface flow model of the Hanford Site given synthetic measurements of said variables. In our approach, we extend the physics‐informed conditional Karhunen‐Loéve expansion (PICKLE) method to modeling subsurface flow with unknown flux (Neumann) and varying head (time‐dependent Dirichlet) boundary conditions. We demonstrate that the PICKLE method is comparable in accuracy with the standard maximum a posteriori (MAP) method, but is significantly faster than MAP for large‐scale problems. Both methods use a mesh to discretize the computational domain. In MAP, the parameters and states are discretized on the mesh; therefore, the size of the MAP parameter estimation problem directly depends on the mesh size. In PICKLE, the mesh is used to evaluate the residuals of the governing equation, while the parameters and states are approximated by the truncated conditional Karhunen‐Loéve expansions with the number of parameters controlled by the smoothness of the parameter and state fields, and not by the mesh size. For a considered example, we demonstrate that the computational cost of PICKLE increases near linearly (as N 1.15 ) with the number of grid nodes N , while that of MAP increases much faster (as N 3.28 ). We also show that once trained for one set of Dirichlet boundary conditions (i.e., one river stage), the PICKLE method provides accurate estimates of the hydraulic head for any value of the Dirichlet boundary conditions (i.e., for any river stage).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Lyapunov and Clearing Timescales in Planetary Chaotic Zones

Debris disks in planetary systems are known to possess gaps “opened” by planets in their close-to-coorbital neighborhoods; the gaps are free from low-mass material such as planetesimals. We consider the escape process of the initially zero-eccentric particles from the gap zone in a scenario consisting of two basic consequent stages: (1) the particle orbit's eccentricity is inflated, while its specific energy is relatively constant, and (2) the particle orbit's semimajor axis is inflated, while its specific angular momentum is relatively constant. During the first stage, the chaotic transport (diffusion) proceeds along the “staircase” of (p + 1):p (with integer p ≫ 1) overlapping particle–planet resonances, and during the second stage, it proceeds along the p:1 particle–planet resonance staircase. A specialized two-dimensional area-preserving map (a “tokamap” version) is derived to describe the first stage, while a multiharmonic Kepler map theory is used to describe the second stage. We derive the μ (mass parameter) scaling for the clearing timescale in the planetary chaotic zone. At small μ, it turns out to be inverse-quadratic in μ. The μ scaling for the Lyapunov timescale inside the gap is also derived. The derived scalings are in qualitative agreement with available numerical-experimental data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Comparative Evaluation of Spectral Methods for Robust Reactor Noise Estimation

Reactor noise analysis provides a noninvasive means to determine neutron kinetic parameters from stochastic fluctuations in detector signals. However, standard cross-power spectral density (CPSD) analyses can be sensitive to numerical processing choices, which may introduce processing-dependent systematic shifts in estimates of the prompt neutron decay constant (α) and limit reproducibility. This study uses a hybrid multitaper–Welch spectral estimator to analyze subcritical noise measurements from a fast-spectrum critical assembly. The decay constant α was extracted using three frequency-domain methods: the CPSD, the magnitude-squared coherence (MSC), and the generalized magnitude-squared coherence (GMSC). These coherence-based estimators normalize detector auto-spectral structure and are expected to reduce the sensitivity of fitted α values to processing parameters. A Sobol global sensitivity analysis identified which numerical inputs most strongly influence the fitted values of α. All estimators produced a linear dependence of α on inverse count rate, with delayed-critical extrapolations near 1.7 × 10 4 s −1 , in agreement within 8% of MCNP6.3 KOPTS benchmark calculations. Sensitivity results show that while the CPSD depends on both time-bin width and taper selection, the MSC and GMSC are dominated by time-bin width alone, indicating reduced parameter coupling and greater robustness to processing variability. These findings demonstrate the feasibility and practical value of coherence-based spectral estimators for extracting α from reactor noise and support their broader application to multi-detector and irregular datasets in subcritical system characterization.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Predicting Dynamic-to-Static Correction Factor from Petrophysical Data and Chemostratigraphy using Unsupervised Machine Learning

Estimating static mechanical properties of stratigraphic layers is critical for optimizing subsurface engineering applications. To estimate dynamic-to-static correction factor F ds (static-to-dynamic Young’s modulus ratio) across the Caney shale interval in Oklahoma, USA, we integrated triaxial test measurements and petrophysical data, including well logs and X-ray fluorescence (XRF) using unsupervised machine learning (ML). We used a novel workflow that includes principal component analysis (PCA) to reduce data set dimensionality of well logs and XRF data sets—both separately and combined—creating three scenarios, and later applied inverse distance weighting (IDW) to derive F ds profiles for these scenarios. Furthermore, we applied K-means clustering on each scenario to predict depositional facies, and built a stiffness zonation profile through chemostratigraphic analysis of the terrigenous elements to validate the predicted F ds . The predicted F ds profile from each scenario using the PCA-IDW method was compared with the constant F ds approach from our previous study by calculating the root mean square error (RMSE). The combined data sets scenario yielded the lowest RMSE value of 0.113, while the RMSE values for the well logs and XRF scenarios were 0.131 and 0.129, respectively. In addition, the predicted F ds from the XRF scenario well-matched the stiffness zonation from the chemostratigraphic analysis that was built using the optimized K-means clustering of nine clusters for that scenario. These methods and findings offer a valuable tool for refining lithological classification and improving the F ds profile, potentially enhancing drilling and stimulation strategies for subsurface energy engineering applications.

clastic rock↗
DOE OSTI2021

Removing the Effects of Tropical Dynamics from North Pacific Climate Variability

Teleconnections from the Tropics energize variations of the North Pacific climate, but detailed diagnosis of this relationship has proven difficult. Simple univariate methods, such as regression on El Niño-Southern Oscillation (ENSO) indices, may be inadequate since the key dynamical processes involved -- including ENSO diversity in the Tropics, re-emergence of mixed layer thermal anomalies, and oceanic Rossby wave propagation in the North Pacific -- have a variety of overlapping spatial and temporal scales. Here we use a multivariate Linear Inverse Model to quantify tropical and extra-tropical multi-scale dynamical contributions to North Pacific variability, in both observations and CMIP6 models. In observations, we find that the Tropics are responsible for almost half of the seasonal variance, and almost three quarters of the decadal variance, along the North American coast and within the subtropical front region northwest of Hawaii. SST anomalies that are generated by local dynamics within the Northeast Pacific have much shorter time scales, consistent with transient weather forcing by Aleutian low anomalies. Variability within the Kuroshio-Oyashio Extension (KOE) region is considerably less impacted by the Tropics, on all time scales. Consequently, without tropical forcing the dominant pattern of North Pacific variability would be a KOE pattern, rather than the Pacific Decadal Oscillation (PDO). In contrast to observations, most CMIP6 historical simulations produce North Pacific variability that maximizes in the KOE region, with amplitude significantly higher than observed. Correspondingly, the simulated North Pacific in all CMIP6 models is shown to be relatively insensitive to the Tropics, with a dominant spatial pattern generally resembling the KOE pattern, not the PDO.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Study on Emulsification/Demulsification Behavior and Mechanism of Produced Liquid from Polymer Flooding on Alaska North Slope

Heavy oil reservoirs on Alaska North Slope (ANS) are unconsolidated and contain abundant clay minerals, where the first-ever field pilot is currently implemented to validate the use of polymer floods for heavy oil enhanced oil recovery (EOR). The polymer molecules and/or fine clay particles carried with the produced liquid could potentially affect the oil/water separation, which is one of the major concerns for field operators. This dissertation aims to investigate the emulsification behavior of produced liquid, understand the emulsifying mechanism, and seek an adaptive and cost-effective method to treat the produced liquid from polymer flooding. Emulsions were prepared by mechanically mixing the actual heavy oil and the produced water from the pilot site, of which the stability was investigated by bottle test method or multiple light scattering method. Drop size distribution and interfacial properties were measured via microscope and pendant drop technique to probe the stability mechanism further. Results showed that oil-continuous or water-continuous emulsion could be generated depending on the water cut, clay types, clay concentration, and polymer concentration. In the crude oil/water system, the increasing water cut triggered the phase inversion of oil-continuous emulsion to water-continuous emulsion, resulting in faster separation and lower emulsion stability. Whereas, clay particles, no matter added to the oil or water phase, resulted in an unfavorable phase inversion from the loose water-continuous emulsion to the tight oil-continuous emulsion as clay concentration increased. For all four types of clay except Ca-montmorillonite, clay particles added to water led to an earlier phase inversion and higher emulsion stability than that added to the oil. The dual function of polymer on emulsion stability was observed. On the one hand, both sheared and unsheared polymer tended to convert the oil-continuous emulsion formed in either crude oil/water system or complex crude oil/water/clay particle system to the water-continuous emulsion, acting as a weak demulsifier to accelerate the oil/water separation. On the other hand, the addition of polymer to the water-continuous emulsion could result in enhanced emulsion stability, which is primarily attributed to the increased viscosity of the continuous phase and the decreased drop size of the dispersed oil phase. Particularly, the sheared polymer had a weaker ability to stabilize the o/w emulsion than the unsheared polymer due to the lower viscosity of the sheared polymer solution resulting from the breakdown of the polymer macromolecules. As for the chemical demulsification tests, the performance of demulsifiers showed a complex dependency upon the water cut, the shearing intensity, demulsifier type and dosage, and the polymer concentration. A compound emulsion breaker, E12+E18, exhibited the most satisfactory demulsification performance despite the varied test conditions. For severe water-continuous emulsions that might require a multi-fold dosage of demulsifier, a less expensive electrolyte, KCl, was proposed to be used in combination with demulsifier E12+E18 to improve the demulsification performance. In the proposed demulsifier formula, the effectiveness of the commercial demulsifier relied on its destructive effect on the interfacial film, while the efficacy of KCl was mainly dependent on its viscosity reduction effect on the continuous phase. This dissertation illustrates that intermediate layer elimination and water clarification are the major challenges for produced liquid treatment from polymer flooding. It also provides practical and theoretical guidance in advance for the demulsification strategy of the produced liquid from the ongoing first-ever polymer flooding pilot on ANS.

Chang, Hongli↗
DOE OSTI2023

Parameter estimation with maximal updated densities

A recently developed measure-theoretic framework solves a stochastic inverse problem (SIP) for models where uncertainties in model output data are predominantly due to aleatoric (i.e., irreducible) uncertainties in model inputs (i.e., parameters). The subsequent inferential target is a distribution on parameters. Another type of inverse problem is to quantify uncertainties in estimates of “true” parameter values under the assumption that such uncertainties should be reduced as more data are incorporated into the problem, i.e., the uncertainty is considered epistemic. A major contribution of this work is the formulation and solution of such a parameter identification problem (PIP) within the measure-theoretic framework developed for the SIP. The approach is novel in that it utilizes a solution to a stochastic forward problem (SFP) to update an initial density only in the parameter directions informed by the model output data. In other words, this method performs “selective regularization” only in the parameter directions not informed by data. Further, the solution is defined by a maximal updated density (MUD) point where the updated density defines the measure-theoretic solution to the PIP. Another significant contribution of this work is the full theory of existence and uniqueness of MUD points for linear maps with Gaussian distributions. Data-constructed Quantity of Interest (QoI) maps are also presented and analyzed for solving the PIP within this measure-theoretic framework as a means of reducing uncertainties in the MUD estimate. We conclude with a demonstration of the general applicability of the method on two problems involving either spatial or temporal data for estimating uncertain model parameters. The first problem utilizes spatial data from a stationary partial differential equation to produce a MUD estimate of an uncertain boundary condition. The second problem utilizes temporal data obtained from the state-of-the-art ADvanced CIRCulation (ADCIRC) model to obtain a MUD estimate of uncertain wind drag coefficients for a simulated extreme weather event near the Shinnecock Inlet located in the Outer Barrier of Long Island, NY, USA.

42 ENGINEERING↗
DOE OSTI2022

Bayesian Estimation of Oscillator Parameters: Toward Anomaly Detection and Cyber-Physical System Security

Cyber-physical system security presents unique challenges to conventional measurement science and technology. Anomaly detection in software-assisted physical systems, such as those employed in additive manufacturing or in DNA synthesis, is often hampered by the limited available parameter space of the underlying mechanism that is transducing the anomaly. As a result, the formulation of anomaly detection for such systems often leads to inverse or ill-posed problems, requiring statistical treatments. Here, we present Bayesian inference of unknown parameters associated with a generic actuator considered as a representative vital element of a cyber-physical system. Via a series of experimental input-output measurements, a transfer function for the actuator is obtained numerically, which serves as our model for the proposed method. Linear, nonlinear, and delayed dynamics may be assumed for the actuator response. By devising a code-based malicious signal, we study the efficacy of Bayesian inference for its potential to produce a detection, including uncertainty quantification, with a remarkably small number of input data points. Our approach should be adaptable to a variety of real-time cyber-physical anomaly detection scenarios.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Cyber-attack detection and neutralization

The example embodiments are directed to a system and method for neutralizing abnormal signals in a cyber-physical system. In one example, the method includes receiving input signals comprising time series data associated with an asset and transforming the input signals into feature values in a feature space, detecting one or more abnormal feature values in the feature space based on a predetermined normalcy boundary associated with the asset, and determining an estimated true value for each abnormal feature value, and performing an inverse transform of each estimated true value to generate neutralized signals comprising time series data and outputting the neutralized signals.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Modeling hydrogen markets: Energy system model development status and decarbonization scenario results

Hydrogen can be used as an energy carrier and chemical feedstock to reduce greenhouse gas emissions, especially in difficult-to-decarbonize markets such as medium- and heavy-duty vehicles, aviation and maritime, iron and steel, and the production of fuels and chemicals. Significant literature has been accumulated on engineering-based assessments of various hydrogen technologies, and real-world projects are validating technology performance at larger scales and for low-carbon supply chains. While energy system models continue to be updated to track this progress, many are currently limited in their representation of hydrogen, and as a group they tend to generate highly variable results under decarbonization constraints. Here, the present work provides insights into the development status and decarbonization scenario results of 15 energy system models participating in study 37 of the Stanford Energy Modeling Forum (EMF37), focusing on the U.S. energy system. The models and scenario results vary widely in multiple respects: hydrogen technology representation, scope and type of hydrogen end-use markets, relative optimism of hydrogen technology input assumptions, and market uptake results reported for 2050 under various decarbonization assumptions. Most models report hydrogen market uptake increasing with decarbonization constraints, though some models report high carbon prices being required to achieve these increases and some find hydrogen does not compete well when assuming optimistic assumptions for all advanced decarbonization technologies. Across various scenarios, hydrogen market success tends to have an inverse relationship to success with direct air capture (DAC) and carbon capture and storage (CCS) technologies. While most model-scenario combinations predict modest hydrogen uptake by 2050 – <10 million metric tons (MMT) – aggregating the top 10 % of market uptake results across sectors suggests an upper range demand potential of 42–223 MMT. The high degree of variability across both modeling methods and market uptake results suggests that increased harmonization of both input assumptions and subsector competition scope would lead to more consistent results across energy system models. The wide variability in results indicates strongly divergent conclusions on the role of hydrogen in a decarbonized energy future.

08 HYDROGEN↗
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↗