Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data similarity”

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 1,099 records · Page 61
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

PDBspheres: a method for finding 3D similarities in local regions in proteins

Abstract We present a structure-based method for finding and evaluating structural similarities in protein regions relevant to ligand binding. PDBspheres comprises an exhaustive library of protein structure regions (‘spheres’) adjacent to complexed ligands derived from the Protein Data Bank (PDB), along with methods to find and evaluate structural matches between a protein of interest and spheres in the library. PDBspheres uses the LGA (Local–Global Alignment) structure alignment algorithm as the main engine for detecting structural similarities between the protein of interest and template spheres from the library, which currently contains >2 million spheres. To assess confidence in structural matches, an all-atom-based similarity metric takes side chain placement into account. Here, we describe the PDBspheres method, demonstrate its ability to detect and characterize binding sites in protein structures, show how PDBspheres—a strictly structure-based method—performs on a curated dataset of 2528 ligand-bound and ligand-free crystal structures, and use PDBspheres to cluster pockets and assess structural similarities among protein binding sites of 4876 structures in the ‘refined set’ of the PDBbind 2019 dataset.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Combining Planck and SPT Cluster Catalogs: Cosmological Analysis and Impact on the Planck Scaling Relation Calibration

We provide the first combined cosmological analysis of the South Pole Telescope (SPT) and Planck cluster catalogs. The aim is to provide an independent calibration for Planck scaling relations, exploiting the cosmological constraining power of the SPT-SZ cluster catalog and its dedicated weak lensing (WL) and X-ray follow-up observations. We build a new version of the Planck cluster likelihood. In the νΛ CDM scenario, focusing on the mass slope and mass bias of Planck scaling relations, we find ${\alpha }_{\mathrm{SZ}}={1.49}_{-0.10}^{+0.07}$ and ${\left(1-b\right)}_{\mathrm{SZ}}={0.69}_{-0.14}^{+0.07}$, respectively. The results for the mass slope show a ~4 σ departure from the self-similar evolution, α SZ ~ 1.8. This shift is mainly driven by the matter density value preferred by SPT data, Ωm = 0.30 ± 0.03, lower than the one obtained by Planck data alone, ${{\rm{\Omega }}}_{m}={0.37}_{-0.06}^{+0.02}$. The mass bias constraints are consistent both with outcomes of hydrodynamical simulations and external WL calibrations, (1 – b) ~ 0.8, and with results required by the Planck cosmic microwave background cosmology, (1 – b) ~ 0.6. From this analysis, we obtain a new catalog of Planck cluster masses M 500 . We estimate the ratio between the published Planck M SZ masses and our derived masses M 500 , as a "measured mass bias," ${\left(1-b\right)}_{M}$. We analyze the mass, redshift, and detection noise dependence of ${\left(1-b\right)}_{M}$, finding an increasing trend toward high redshift and low mass. These results mimic the effect of departure from self-similarity in cluster evolution, showing different dependencies for the low-mass, high-mass, low-z, and high-z regimes.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Viscosity bounds in liquids with different structure and bonding types

Recently, it was realized that liquid viscosity has a lower bound which is nearly constant for all liquids and is governed by fundamental physical constants. This was supported by experimental data in noble and molecular liquids. Here, we perform large-scale molecular dynamics simulations to ascertain this bound in two other important liquid types: the ionic molten salt system LiF and metallic Pb. We find that these ionic and metallic systems similarly have lower viscosity bounds corresponding to the minimum of kinematic viscosity of ∼ 10 − 7 m 2 / s . We show that this agrees with experimental data in other systems with different structures and bonding types, including noble, molecular, metallic, and covalent liquids. This expands the universality of viscosity bounds into the main system types known. Published by the American Physical Society 2024

Materials Science↗
DOE OSTI2024

Denoising Seismic Waveforms Using a Wavelet-Transform-Based Machine-Learning Method

Seismic waveform data recorded at stations can be thought of as a superposition of the signal from a source of interest and noise from other sources. Frequency‐based filtering methods for waveform denoising do not result in desired outcomes when the targeted signal and noise occupy similar frequency bands. Recently, denoising techniques based on deep‐learning convolutional neural networks (CNNs), in which a recorded waveform is decomposed into signal and noise components, have led to improved results. These CNN methods, which use short‐time Fourier transform representations of the time series, provide signal and noise masks for the input waveform. These masks are used to create denoised signal and designaled noise waveforms, respectively. However, advancements in the field of image denoising have shown the benefits of incorporating discrete wavelet transforms (DWTs) into CNN architectures to create multilevel wavelet CNN (MWCNN) models. The MWCNN model preserves the details of the input due to the good time–frequency localization of the DWT. In this report we use a data set of over 382,000 constructed seismograms recorded by the University of Utah Seismograph Stations network to compare the performance of CNN and MWCNN‐based denoising models. Evaluation of both models on constructed test data shows that the MWCNN model outperforms the CNN model in the ability to recover the ground‐truth signal component in terms of both waveform similarity and preservation of amplitude information. Model evaluation of real‐world data shows that both the CNN and MWCNN models outperform standard band‐pass filtering (BPF; average improvement in signal‐to‐noise ratio of 9.6 and 19.7 dB, respectively, with respect to BPF). Evaluation of continuous data suggests the MWCNN denoiser can improve both signal detection capabilities and phase arrival time estimates.

58 GEOSCIENCES↗
DOE OSTI2022

A High‐Resolution Tropical Mesoscale Convective System Reanalysis (TMeCSR)

Abstract Modern global reanalysis products have greatly accelerated meteorological research in synoptic‐to‐planetary‐scale phenomena. However, their use in studying tropical mesoscale convective systems (MCSs) and their regional‐to‐global impact has mostly been limited to supplying initial and boundary conditions for MCS‐resolving simulations and providing information about the large‐scale environments of MCSs. These limitations are due to difficulties in resolving tropical MCS dynamics in the relatively low‐resolution global models and that tropical MCSs often occur over poorly observed regions. In this work, a Tropical MCS‐resolving Reanalysis product (TMeCSR) was created over a region with frequent tropical MCSs. This region spans the tropical Indian Ocean, tropical continental Asia, Maritime Continent, and Western Pacific. TMeCSR is produced by assimilating all‐sky infrared radiances from geostationary satellites and other conventional observations into an MCS‐resolving regional model using the Ensemble Kalman Filter. The resulting observation‐constrained high‐resolution (9‐km grid spacing) data set is available hourly during the boreal summer (June‐August) of 2017, during which widespread severe flooding occurred. Comparisons of TMeCSR and European Center for Medium Range Weather Forecast Reanalysis version 5 (ERA5) against independent satellite retrievals indicate that TMeCSR's cloud and multiscale rain fields are better than those of ERA5. Furthermore, TMeCSR better captured the diurnal variability of rainfall and the statistical characteristics of MCSs. Forecasts initialized from TMeCSR also have more accurate rain and clouds than those initialized from ERA5. The TMeCSR and ERA5 forecasts have similar performances with respect to sounding and surface observations. These results indicate that TMeCSR is a promising MCS‐resolving data set for tropical MCS studies.

Chan, Man‐Yau↗
DOE OSTI2023

Measurement of Dielectric Loss in Silicon Nitride at Centimeter and Millimeter Wavelengths

This work presents a suite of measurement techniques for characterizing the dielectric loss tangent across a wide frequency range from similar to 1 GHz to 150 GHz using the same test chip. In the first method, we fit data from a microwave resonator at different temperatures to a model that captures the two-level system (TLS) response to extract and characterize both the real and imaginary components of the dielectric loss. The inverse of the internal quality factor is a second measure of the overall loss of the resonator, where TLS loss through the dielectric material is typically the dominant source. The third technique is a differential optical measurement at 150 GHz. The same antenna feeds two microstrip lines with different lengths that terminate in two microwave kinetic inductance detectors (MKIDs). The difference in the detector response is used to estimate the loss per unit length of the microstrip line. Our results suggest a larger loss for SiNx at 150 GHz of tan delta similar to 4 x 10(-3) compared to 2.0 x 10(-3) and greater than or similar to 1 x 10(-3) measured at similar to 1 GHz using the other two methods. These measurement techniques can be applied to other dielectrics by adjusting the microstrip lengths to provide enough optical efficiency contrast and other mm/sub-mm frequency ranges by tuning the antenna and feedhorn accordingly.

Dielectrics loss↗
DOE OSTI2022

Structure of the divergent human astrovirus MLB capsid spike

Despite their worldwide prevalence and association with human disease, the molecular bases of human astrovirus (HAstV) infection and evolution remain poorly characterized. Here, we report the structure of the capsid protein spike of the divergent HAstV MLB clade (HAstV MLB). While the structure shares a similar folding topology with that of classical-clade HAstV spikes, it is otherwise strikingly different. We find no evidence of a conserved receptor-binding site between the MLB and classical HAstV spikes, suggesting that MLB and classical HAstVs utilize different receptors for host-cell attachment. We provide evidence for this hypothesis using a novel HAstV infection competition assay. Comparisons of the HAstV MLB spike structure with structures predicted from its sequence reveal poor matches, but template-based predictions were surprisingly accurate relative to machine-learning-based predictions. Our data provide a foundation for understanding the mechanisms of infection by diverse HAstVs and can support structure determination in similarly unstudied systems.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

ESM data downscaling: a comparison of super-resolution deep learning models

Abstract Climate projections at fine spatial resolutions are required to conduct accurate risk assessment for critical infrastructure and design adaptation planning. Generating these projections using advanced Earth system models (ESM) requires significant computational resources. To address this issue, various statistical downscaling techniques have been introduced to generate fine-resolution data from coarse-resolution simulations. In this study, we evaluate and compare five deep learning-based downscaling techniques, namely, super-resolution convolutional neural networks, fast super-resolution convolutional neural network ESM, efficient sub-pixel convolutional neural network, enhanced deep residual network (EDRN), and super-resolution generative adversarial network (SRGAN). These techniques are applied to a dataset generated by the Energy Exascale Earth System Model (E3SM), focusing on key surface variables such as surface temperature, shortwave heat flux, and longwave heat flux. Models are trained and validated using paired fine-resolution (0.25 $$^{\circ }$$ ∘ ) and coarse-resolution (1 $$^{\circ }$$ ∘ ) monthly data obtained from a 9-year simulation. Next, blind testing is performed using monthly data obtained from two different years outside of the training and validation set. To evaluate the efficiency of each technique, different statistical metrics are used, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS). The results show that EDRN outperforms other algorithms in terms of PSNR, SSIM, and MSE, but struggles to capture fine-scale features in the data. In contrast, SRGAN, a generative model that uses perceptual loss, excels in capturing fine details at boundaries and internal structures, resulting in lower LPIPS than other methods.

Pawar, Nikhil M. (ORCID:0000000211613289)↗
DOE OSTI2021

Photoionization from the Xe 4d orbitals of XeF 2

Here, we present a comparison of the photoionization dynamics of the 4d shell of XeF 2 from threshold to 250 eV to those of the prototypical 4d shell of atomic Xe. The new experimental data include spin–orbit and ligand-field-resolved partial cross sections, photoelectron angular distributions, branching fractions, and lifetime widths for the 4d-hole states. The spin–orbit branching fractions and angular distributions are remarkably similar to the corresponding distributions from atomic Xe across a broad energy interval that includes both the intense shape resonance in the f continuum and a Cooper minimum in the same channel. The angular distributions and branching fractions are also in reasonably good agreement with our first-principles theoretical calculations on XeF 2 . Data are also presented on the lifetime widths of the substate-resolved 4d-hole states of XeF 2 . While the trends in the widths are similar to those in the earlier experimental and theoretical work, the linewidths are considerably smaller than in the previous measurements, which may require some reinterpretation of the decay mechanism. Finally, we present new data and an analysis of the Auger electron spectra for ionization above the 4d thresholds and resonant Auger spectra for several pre-edge features.

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

DEEP CELLULAR RECURRENT NEURAL ARCHITECTURE FOR EFFICIENT MULTIDIMENSIONAL TIME-SERIES DATA PROCESSING

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in complexity and size to accommodate the additional dimensionality of time. Specifically, the biologically inspired learning based models known as artificial neural networks that have shown extraordinary success in pattern recognition, tend to grow prohibitively large and cumbersome in the presence of large scale multi-dimensional time series biomedical data such as EEG. Consequently, this work aims to develop representative ML and DL models for robust and efficient large scale time series processing. First, we design a novel ML pipeline with efficient feature engineering to process a large scale multi-channel scalp EEG dataset for automated detection of epileptic seizures. With the use of a sophisticated yet computationally efficient time-frequency analysis technique known as harmonic wavelet packet transform and an efficient self-similarity computation based on fractal dimension, we achieve state-of-the-art performance for automated seizure detection in EEG data. Subsequently, we investigate the development of a novel efficient deep recurrent learning model for large scale time series processing. For this, we first study the functionality and training of a biologically inspired neural network architecture known as cellular simultaneous recurrent neural network (CSRN). We obtain a generalization of this network for multiple topological image processing tasks and investigate the learning efficacy of the complex cellular architecture using several state-of-the?art training methods. Finally, we develop a novel deep cellular recurrent neural network (CDRNN) architecture based on the biologically inspired distributed processing used in CSRN for processing time series data. The proposed DCRNN leverages the cellular recurrent architecture to promote extensive weight sharing and efficient, individualized, synchronous processing of multi-source time series data. Experiments on a large scale multi-channel scalp EEG, and a machine fault detection dataset show that the proposed DCRNN offers state-of-the-art recognition performance while using substantially fewer trainable recurrent units.

Vidyaratne, Lasitha S.↗
DOE OSTI2026

Statistics of base polytopes in F-theory

We propose a new statistical ensemble of toric bases for elliptic Calabi-Yaus used in F-theory models, by focusing on only the convex hull of the base, i.e., the base polytope. This physically motivated coarse-graining greatly simplifies the combinatorial complexity of the part of the 4d F-theory landscape with toric bases. We develop a Monte Carlo approach that randomly samples the base polytopes within fixed boxes, with proper statistical weights. We first apply the algorithm to the set of 2d base polytopes, generating an enlarged set of toric 2d bases that include certain types of codimension-two (4,6) points, and we validate our approach against exact numbers. We then explore the set of 3d base polytopes which fit in a set of “maximal” 3d boxes, and estimate the total number of inequivalent 3d base polytopes to be 10 85 –10 90 . We provide statistical data such as the distribution of non-Higgsable gauge groups on these bases. Amusingly, a similar method can also be applied to generate reflexive polytopes in various dimensions. In both the reflexive and base polytope cases, the number of relevant polytopes obeys a Gaussian distribution as a function of the number of vertices, which can be understood in terms of other results on random polytopes in the math literature.

Differential and algebraic geometry↗
DOE OSTI2021

The crystal structure of a new calcium aluminate phase containing formate

A new calcium aluminate phase containing formate ions was synthesized and its crystal structure determined. This new phase is indicated as M-phase and was firstly observed in Portland cement pastes hydrated in presence of Ca-formate and in excess of water. The crystal structure of the M-phase was successfully solved in the R-3 space group of the trigonal system on the basis of synchrotron X-ray single crystal diffraction data. The structural model was confirmed by Rietveld refinement of the powder diffraction data acquired on the synthesized pure sample. The crystal structure of the M-phase is similar to that of ettringite, being characterized by columns of AlO{sub 6} octahedra alternating with groups of three edge-sharing CaO{sub 7} polyhedra. The formate ions (HCOO){sup −} share two oxygens with Ca polyhedra and are located in the interspace between the columns. The crystal structure of the M-phase testifies the strong interaction occurring between small organic molecules as formate and the calcium aluminate components of Portland cement.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Dynamic and static corrosion of chromium-alumina refractory in simulated nuclear waste glass

Monofrax® K-3, a chromium–alumina refractory, is widely used in nuclear waste glass melters due to its high durability. However, aggressive vitrification conditions still lead to corrosion that limits melter lifespan. Here, this study investigates two key corrosion modes, subsurface and melt-line corrosion, under static and dynamic conditions, using a custom setup enabling precise control of melt velocity and temperature. Experimental results, interpreted using diffusion-limited dissolution models, show that (i) subsurface corrosion increases by approximately 10% per mm/s increase in melt velocity, while melt-line corrosion remains virtually unaffected, (ii) corrosion rate dependence on temperature is inversely proportional to melt viscosity, and (iii) glass composition affects both corrosion modes similarly, based on Cr 2 O 3 , Al 2 O 3 , and alkali contents. The experimental data also allowed the determination of diffusion coefficients of major dissolving species, which were found to be consistent between the melt-line and subsurface corrosion models, indicating their suitability for future CFD studies.

12 - MGMT OF RADIOACTIVE AND NON-RADIOACTIVE WASTE↗
DOE OSTI2022

Effect of cholesterol on nano-structural alteration of light-activatable liposomes via laser irradiation: Small angle neutron scattering study

Although the light-activated liposomes have been extensively studied for drug delivery applications, the fundamental mechanism of the drug release based on lipid compositions has not been fully understood. Especially, despite the extensive use of cholesterol in the lipid composition, the role of cholesterol in the light-activated drug release has not been studied. Here, in this study, the influence of cholesterol on drug release from light-responsive drug-encapsulated liposomes after activated by near infrared (NIR) laser was investigated. We prepared methotrexate (MTX)-encapsulated DSPC liposomes consisting of 0 mol% (—Chol) or 35 mol% cholesterol (+Chol), with (+Au) or without gold nanorods (—Au) on the lipid bilayer to compare drug release, morphological changes, and nanostructures after laser irradiations. Transmission electron microscopy (TEM) and small angel neutron scattering (SANS) data revealed that only +Chol +Au liposomes showed partial aggregation of the liposomes after laser irradiation. Similar trends on the drug release and structural change were observed when the liposomes were heated to above chain-transition temperature. Overall, we have found that (1) inclusion of 35 mol% cholesterol enhanced the permeability of lipid bilayers above T c ; (2) the mechanism of laser-activated liposomal drug delivery is disrupting lipid bilayer membranes by the photothermal effect in the presence of plasmonic materials. By understanding the fundamentals of the technology, precise controlled drug release at a targeted site with great stability and repeatability is anticipated.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Swelling and permeability effects during propellant cookoff

Large rocket motors may violently explode when exposed to accidental fires. Even hot metal fragments from a nearby accident may penetrate the propellant and ultimately cause thermal ignition. A mechanistic understanding of heated propellants leading to thermal runaway is a major unsolved problem. Here we show that thermal ignition in propellants can be predicted using a universal cookoff model coupled to a micromechanics pressurization model. Our model predicts the time to thermal ignition in cookoff experiments with variable headspace volumes. Furthermore, we found that experiments with headspace volumes are more prone to deformation which distorts pores and causes increased permeability when the propellant expands into this headspace. Delayed ignition with larger headspace volume correlates with lower headspace pressures during decomposition. We found that our predictions matched experimental measurements best when the initial propellant was impermeable to gas flow rather than being permeable. Similar behavior is expected with other energetic materials with rubbery binders. Our model is validated using data from a separate laboratory. We also present an uncertainty analysis using Latin Hypercube Sampling (LHS) of thermal ignition caused by a steel fragment embedded in the propellant.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2020

Mechanical behavior and texture evolution of WE43 magnesium-rare earth alloy in Split-Hopkinson Pressure Bar and Taylor Impact Cylinder Testing

Mechanical behavior and texture evolution of Mg rare-earth alloy WE43 is investigated for strain-rates 10 -3 /s to upwards of 10 5 /s for the two material conditions - as-cast (AC) and T6 age hardened, rolled plate (RT6). The high strain-rate behavior is tested using both Taylor cylinder impact tests (TC) and split Hopkinson pressure bar tests (SHB) and bulk textures are obtained using neutron diffraction. Unlike the quasi-static strained material, AC and RT6 SHB retained high hardening rates throughout the test, even up to 30% true strain. Moreover, the high strain-rate data revealed that the RT6 material has a much higher strength than the AC material, but similar hardening rates despite significantly different initial texture. The flow stress near yield increased up to I 0% for RT6 and up to 30% for AC as the strain-rate increased six orders of magnitude from quasi-static rates 10 -3 /s to 10 3 /s. Neither material exhibited significant plastic anisotropy over the broad range of strain rates, despite the fact that the RT6 material had a moderately strong initial texture. In the TC tests, the geometric cross-sectional changes and texture along the cylinder from the cylindrical sample foot to head are measured and from the neutron diffraction texture analysis, upper-bound estimates of twin volume fraction are obtained as well as dislocation density from analyzing diffraction peak broadening. Recorded geometrical changes along several loading directions show that the material has deformed remarkably homogeneously under impact. Analysis of deformed textures indicates that {101¯2} extension deformation twinning occurred in the RT6 condition over the range of strain rates, with an upper bound estimate of 40% twin volume fraction for approximately 0.10-0.25 true strain. The peak texture components after the impact have their c-axes closely aligned with the impact direction. As a result, these observations are presented and rationalized in the paper.

42 ENGINEERING↗
DOE OSTI2025

Measurement of Spray Chamber Ignition Delay and Cetane Numbers for Aviation Turbine Fuels

Experiments using pure compounds, National Jet Fuels Combustion Program (NJFCP) test fuels, and commercial jet fuels were conducted to demonstrate the equivalence of the indicated cetane number (ICN) and derived cetane number (DCN) for jet fuels. The calibrated range for ICN was also extended to lower cetane number (CN) values (5 to 35) to allow CN quantification for jet fuel synthetic blending components (SBCs) with low CN. ICN and DCN were shown to be highly correlated for values above about 30. This study presents the most comprehensive comparison of these two methods published to date. Because of the importance of low-volume test methods for early-stage SBC production process development, we demonstrated that ICN and DCN can be accurately measured with 15 mL of fuel, well below 40 to 100 mL required by standard methods. ICN or DCN is important for jet fuels because fuels with lower CN are more prone to lean blowout (LBO), an undesirable operational failure in a jet engine. Comparing data on a fuel-to-air ratio (Φ) at LBO for the NJFCP fuels shows similar linear correlations for ICN and DCN. Ignition delay measurements at lower-pressure and higher-temperature conditions may be more directly relevant to LBO. At 675 °C, 0.5 MPa, and a global Φ of roughly 0.68, ignition delay time correlations to LBO were similar to those produced from DCN and ICN. A much weaker correlation was obtained with a global Φ value of 0.34.

09 BIOMASS FUELS↗
DOE OSTI2025

Monitoring Fracture Hydromechanical Evolution in the Lab and Field Using Unsupervised Metric Learning

Fractures evolve in time through thermal‐hydraulic‐mechanical‐chemical (THMC) processes that alter their long‐range hydraulic transport properties and modify subsurface behavior and activities. The location of subsurface fractures makes it necessary to use remote sensing techniques such as passive or active seismic monitoring for fracture characterization. In this paper, we develop a machine learning approach to monitor the evolution of fracture properties using passive seismic sources in a laboratory setting and using active seismic monitoring from the Sanford Underground Research Facility in Lead, South Dakota, at a depth of 1.25 km in amphibolite rock during stimulation of natural fractures as well as during induced fracturing. The unsupervised metric learning technique applies tandem neural networks (twin (Siamese) or triplet) with contrastive loss and adaptive margins to track slowly varying systems for which class or similarity labels are not available. The approach adopts locality‐sensitive hashing to divide time‐ordered contiguous data into an arbitrary number of pseudo‐classes. Contrastive‐loss training with many hash bins generates an evolving latent‐space trajectory. This approach enables unsupervised metric learning for seismic data stacks under the condition of contiguous state sampling and slowly varying fracture properties. The displacement discontinuity theory provides a mechanistic foundation for the fracture‐dependent trajectories that are related to relaxation of fractures with time‐dependent specific stiffness responding to changes in stress or fluid saturation.

02 PETROLEUM↗