Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network alignment”

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 OSTI2025

Evaluation of historical precipitation interannual variability in CMIP6 over the United States

Interannual precipitation variability profoundly influences society via its effects on agriculture, water resources, infrastructure, and disaster risks. In this study, we use daily in situ precipitation observations from the global historical climatology network-daily (GHCN-D) to assess the ability of 21 Coupled Model Intercomparison Project Phase 6 (CMIP6) models, including the 50-member fifth-generation Canadian Earth System Model single model initial-condition large ensemble (CanESM5_SMILE), to realistically simulate historical interannual precipitation variability trends within 17 regions of the contiguous United States (CONUS). We assess how accurately the CMIP6 simulations align with observational data across annual, summer, and winter periods, focusing on four key hydrometeorological metrics, including interannual precipitation variability, relative interannual precipitation variability (coefficient of variation), annual mean precipitation, and annual wet day frequency. Our findings reveal that CMIP6 ensemble members generally reproduce the spatial patterns of observed trends in annual mean precipitation. In most regions, models agree well with the signs of observed changes in annual mean precipitation, though discrepancies in trend magnitude are evident. Further, observed trends in winter mean precipitation broadly exhibit a spatial pattern similar to that of the observed annual mean. However, analysis of the CanESM5_SMILE shows that trends in precipitation variability may primarily be the result of model-simulated internal variability, suggesting caution in interpreting multi-model single-realization ensemble results. Challenges in accurately simulating interannual precipitation variability underscore the need for ongoing model refinement and validation to enhance climate projections, especially in regions vulnerable to extreme precipitation events.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2013

HUBBLE SPACE TELESCOPE OBSERVATIONS OF DUSTY FILAMENTS IN HERCULES A: EVIDENCE FOR ENTRAINMENT

We present U-, V-, and I-band images of the host galaxy of Hercules A (3C 348) obtained with HST/WFC3/UVIS. We find a network of dusty filaments which are more complex and extended than seen in earlier Hubble Space Telescope (HST) observations. The filaments are associated with a faint blue continuum light (possibly from young stars) and faint H{alpha} emission. It seems likely that the cold gas and dust has been stripped from a companion galaxy now seen as a secondary nucleus. There are dusty filaments aligned with the base of the jets on both eastern and western sides of the galaxy. The morphology of the filaments is different on the two sides-the western filaments are fairly straight, while the eastern filaments are mainly in two loop-like structures. We suggest that despite the difference in morphologies, both sets of filaments have been entrained in a slow-moving boundary layer outside the relativistic flow. As suggested by Fabian et al., magnetic fields in the filaments may stabilize them against disruption. We consider a speculative scenario to explain the relation between the radio source and the shock and cavities in the hot intracluster medium seen in the Chandra data. We suggest that the radio source originally ({approx}60 Myr ago) propagated along a position angle of {approx}35 Degree-Sign where it created the shock and cavities. The radio source axis changed to its current orientation ({approx}100 Degree-Sign ) possibly due to a supermassive black hole merger and began its current epoch of activity about 20 Myr ago.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Foundations for Engineering Education for Distributed Energy Resources (FEEDER)

Foundations for Engineering Education for Distributed Energy Resources (FEEDER), as one of the four Distributed Technology Training Consortia (DTTCs) of the Grid Engineering for Accelerated Renewable Energy Deployment (GEARED) National Network, provided programs to meet the project goals, and works closely with the GEARED National Network Administrator (NNA) to foster student competence and career interest in advanced engineering and professional skills that support a robust electrical utility sector. This educational effort also included annual gatherings to share best practices and specific advances in knowledge, instructional best practice and educational integration throughout disciplines supporting power systems analysis and integration of distributed generation, with a focus on renewable energy. This effort aligned with the goals and objectives of the Department of Energy SunShot initiative. The project goals included the creation of a larger skilled electric grid workforce that is able to manage widespread deployment of distributed energy resources by developing and sharing new courses and curricula across the participating FEEDER institutions. FEEDER was expanded to add four institutions under the Solar Training & Education for Professionals (STEP) program, with the title Strategic Expansion to Achieve GEARED Goals and award number DE- EE0007327. Program components were selected based on gap analysis and advices of FEEDER industry advisory board, with a focus on student participation in power programs, research and formative experiences that led them to successful careers in power-related industries.

14 SOLAR ENERGY↗
DOE OSTI2011

Identification of quantitative trait loci affecting ectomycorrhizal symbiosis in an interspecific F1 poplar cross and differential expression of genes in ectomycorrhizas of the two parents: Populus deltoides and Populus trichocarpa

A Populus deltoides Populus trichocarpa F1 pedigree was analyzed for quantitative trait loci (QTLs) affecting ectomycorrhizal development and for microarray characterization of gene networks involved in this symbiosis. A 300 genotype progeny set was evaluated for its ability to form ectomycorrhiza with the basidiomycete Laccaria bicolor. The percentage of mycorrhizal root tips was determined on the root systems of all 300 progeny and their two parents. QTL analysis identified four significant QTLs, one on the P. deltoides and three on the P. trichocarpa genetic maps. These QTLs were aligned to the P. trichocarpa genome and each contained several megabases and encompass numerous genes. NimbleGen whole-genome microarray, using cDNA from RNA extracts of ectomycorrhizal root tips from the parental genotypes P. trichocarpa and P. deltoides, was used to narrow the candidate gene list. Among the 1,543 differentially expressed genes (p value 0.05; 5.0-fold change in transcript level) having different transcript levels in mycorrhiza of the two parents, 41 transcripts were located in the QTL intervals: 20 in Myc_d1, 14 in Myc_t1, and seven in Myc_t2, while no significant differences among transcripts were found in Myc_t3. Among these 41 transcripts, 25 were overrepresented in P. deltoides relative to P. trichocarpa; 16 were overrepresented in P. trichocarpa. The transcript showing the highest overrepresentation in P. trichocarpa mycorrhiza libraries compared to P. deltoides mycorrhiza codes for an ethylene-sensitive EREBP-4 protein which may repress defense mechanisms in P. trichocarpa while the highest overrepresented transcripts in P. deltoides code for proteins/genes typically associated with pathogen resistance.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

A finite viscoelastic constitutive model for low to high strain rate response of elastomers with application of strain rate-induced glass transition

Amorphous elastomers exhibit significant rate-stiffening and unique viscous flow characteristics across a wide range of strain rates, often undergoing glass transition above a strain rate threshold. We have developed a thermodynamically-consistent and micromechanically-inspired constitutive model for soft elastomeric materials to capture the rate-dependent stress-strain behavior and hysteresis when subjected to low to high strain rates. Here, our proposed constitutive model encapsulates the viscous flow of materials through molecular motion at low strain rates and local rearrangement and alignment of the molecules trying to overcome the intermolecular resistance at high strain rates, essentially covering the glass transition. We applied our constitutive model to uniaxial compression experiments performed at low and high strain rates for polyborosiloxane (PBS) to identify the material parameters, and subsequently, performed numerical simulations of single and multi-cycle compression, stress relaxation, and small amplitude oscillatory tension-compression. Our analyses indicate that the model predicts higher total energy dissipation with increasing strain rate; however, dissipation associated with molecular relaxation decreases (forming a cusp) because, beyond a crossover strain rate, intermolecular rearrangement and alignment become dominant, which is consistent with the onset of the glass transition. For cyclic loading-unloading, we observed that dissipation over a cycle remains constant at low strain rates but decreases non-monotonically at high strain rates before becoming constant, with the peak stress over the cycle becoming higher, which can be interpreted as more loading being carried elastically by the polymer network as the intermolecular rearrangement process occurs. Additionally, our model was able to predict the qualitative nature of the storage modulus and loss modulus in the limit of small strain over a wide range of frequency sweeps.

36 MATERIALS SCIENCE↗
DOE OSTI2018

NSLS-II Booster Survey and Alignment Systems

This section outlines the survey and alignment requirements and the technology and tools for achieving the NSLS-II equipment positioning goals. The required alignment tolerances are defined primarily by the physics requirements of the accelerator. The tight tolerances dictated by the physics requirements are an order of magnitude tighter than the tolerances of second generation light sources (NSLS) and on level with those at third generation light sources (Soleil, Diamond). These extraordinary position requirements necessitate a concerted R&D engineering effort to identify and develop the survey methodology needed to meet these requirements. As of this date, the methodology is still evolving to balance cost and time constraints while still maintaining the integrity of the survey and alignment systems. State-of-the art equipment including Laser Trackers and Laser Arms have been purchased and used extensively in the pursuit of meeting the NSLS-II survey tolerances. No new technology will need to be developed to meet the alignment requirements but new techniques will be pursued and developed. Survey and alignment provides the foundation for positioning the beam-guiding magnet structures in all 6 degrees of freedom within the required tolerances. Although the tools and instrumentation available for this task have changed over the years and faster and more accurate measurements are possible, only limited control of the environmental conditions is possible. This ultimately sets an upper limit for the achievable measurement and subsequent control network accuracy. At the same time, the control of environmental variables (temperature, humidity) will be fully taken advantage of during the building of NSLS-II , opening up the possibility of ever-increasing accuracy unheard of only five years ago.

42 ENGINEERING↗
DOE OSTI2019

Secondary Pore Network Design Optimization Analytical Diffusion Model for Lithium Ion Battery

Fast ion transport along the electrode thickness is required for Lithium ion battery (LIB) to sustain continuous high-rate discharge or charge currents, which is a desired feature for the fast charging of electric vehicle batteries. Advance in LIB electrode manufacturing allows to control, to a certain extent, the electrode microstructure architecture in order to improve the macroscopic performances of these devices. For instance, several groups have experimentally tested architectures tailored specifically to increase the through plane ionic diffusion in regards for fast charge application by adding channels or groove-like large pores oriented along the electrode thickness. These voids do not replace the existing pores of the electrode microstructure but consist in a second, coarser, pore network, called the secondary pore network (SPN). The model quantifies the impact of SPN on ionic diffusion with a composite electrode through a simple analytical approach, considering various pore channel geometries and comparing to standard electrodes with identical gravimetric and identical volumetric specific theoretical capacity. The goal is to find optimal SPN design parameters according to three optimization objectives aiming to balance the improved overall through-plane, thanks to the coarse aligned channels, and the degraded in-plane diffusion, due to the porous matrix densification required to maintain gravimetric and volumetric specific theoretical capacity. The analytical model must be considered as a pre-screening tool to quickly investigate large design space, that can be refined later with more complex electrochemical CPU-expensive numerical models.

Usseglio Viretta, Francois↗
DOE OSTI2024

STFM: Accurate Spatio-Temporal Fusion Model for Weather Forecasting

Meteorological prediction is crucial for various sectors, including agriculture, navigation, daily life, disaster prevention, and scientific research. However, traditional numerical weather prediction (NWP) models are constrained by their high computational resource requirements, while the accuracy of deep learning models remains suboptimal. In response to these challenges, we propose a novel deep learning-based model, the Spatiotemporal Fusion Model (STFM), designed to enhance the accuracy of meteorological predictions. Our model leverages Fifth-Generation ECMWF Reanalysis (ERA5) data and introduces two key components: a spatiotemporal encoder module and a spatiotemporal fusion module. The spatiotemporal encoder integrates the strengths of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), effectively capturing both spatial and temporal dependencies. Meanwhile, the spatiotemporal fusion module employs a dual attention mechanism, decomposing spatial attention into global static attention and channel dynamic attention. This approach ensures comprehensive extraction of spatial features from meteorological data. The combination of these modules significantly improves prediction performance. Experimental results demonstrate that STFM excels in extracting spatiotemporal features from reanalysis data, yielding predictions that closely align with observed values. In comparative studies, STFM outperformed other models, achieving a 7% improvement in ground and high-altitude temperature predictions, a 5% enhancement in the prediction of the u/v components of 10 m wind speed, and an increase in the accuracy of potential height and relative humidity predictions by 3% and 1%, respectively. This enhanced performance highlights STFM’s potential to advance the accuracy and reliability of meteorological forecasting.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

The use of digital thread for reconstruction of local fiber orientation in a compression molded pin bracket via deep learning

A deep convolutional neural network (DCNN) was used for microstructure reconstruction using artificial intelligence (MR-AI) by predicting local average fiber orientation distributions (FOD) in a 3D prepreg platelet molded composite (PPMC) pin bracket. To train the MR-AI model, surface strain fields from residual stresses simulated in PPMC plates were used as the input to the DCNN. A training dataset included PPMC plates with various degrees of global fiber alignment, based on the information obtained from high-fidelity flow simulation of a pin bracket. Further, the MR-AI model was then deployed to analyze FOD in the 3D pin bracket by conducting thermo-elastic residual stress analysis. Initially, the MR-AI model was established entirely on the synthetic simulation data. Then, a μCT scan of a physically molded pin bracket was used to create a finite element model that provided data for additional validation of the DCNN model. For the μCT scan finite element pin bracket the MR-AI model predicted the distribution of fiber orientation tensor components with MAE of 0.10 indicating a global prediction error of 10%. For the flow simulated pin bracket, the MR-AI model predicted the distribution of fiber orientation tensor components with a global prediction error of 11%. The MR-AI model showed the ability to predict regions of varying alignment in the base and flange of the pin bracket. The proposed MR-AI methodology allows for rapid prediction of FOD in geometrically complex parts and offers a promising path to detecting unique fiber orientation states in molded components.

42 ENGINEERING↗
DOE OSTI2024

Dark energy survey year 3 results: likelihood-free, simulation-based w CDM inference with neural compression of weak-lensing map statistics

We present simulation-based cosmological wcold dark matter (wCDM) inference using dark energy survey year 3 weak-lensing maps, via neural data compression of weak-lensing map summary statistics: power spectra, peak counts, and direct map-level compression/inference with convolutional neural networks (CNN). Using simulation-based inference, also known as likelihood-free or implicit inference, we use forward-modelled mock data to estimate posterior probability distributions of unknown parameters. This approach allows all statistical assumptions and uncertainties to be propagated through the forward-modelled mock data; these include sky masks, non-Gaussian shape noise, shape measurement bias, source galaxy clustering, photometric redshift uncertainty, intrinsic galaxy alignments, non-Gaussian density fields, neutrinos, and non-linear summary statistics. We include a series of tests to validate our inference results. This paper also describes the Gower Street simulation suite: 791 full-sky pkdgrav3 dark matter simulations, with cosmological model parameters sampled with a mixed active-learning strategy, from which we construct over 3000 mock dark energy survey lensing data sets. For wCDM inference, for which we allow –1 < w < –$\frac{1}{3}$⁠, our most constraining result uses power spectra combined with map-level (CNN) inference. Using gravitational lensing data only, this map-level combination gives Ω m = 0.283$^{+0.020}_{–0.027}$⁠, S 8 = 0.804$^{+0.025}_{–0.017⁠}$, and w < –0.80 (with a 68 per cent credible interval); compared to the power spectrum inference, this is more than a factor of two improvement in dark energy parameter (Ω⁠ DE , w⁠) precision.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Copper–Carbon Nanotube Composites Enabled by Electrospinning for Advanced Conductors

The power losses associated with the electrical resistance of copper (Cu) have generated considerable interest in the development of advanced conductors that incorporate carbon nanotubes (CNTs) into the Cu matrix—ultraconductive Cu (UCC) composites—to increase energy efficiency in various industrial and residential applications, ranging from electric power transmission and rotating machinery to electronic devices. To meet this demand, we describe an electrospinning-based polymer nanofiber templating strategy for the fabrication of UCC composites with electrical and mechanical performance exceeding that of Cu. Our approach involves electrospinning of polyvinylpyrrolidone (PVP)-based solutions containing CNTs into aligned PVP/CNT nanofibers onto Cu foil substrates, followed by vacuum-assisted thermal removal of organic solvent/polymer from the CNT matrix to achieve a uniformly distributed CNT layer on the Cu surface. Following additional Cu deposition, the Cu–CNT–Cu composites demonstrated similar electrical conductivity, higher current carrying capacity, and improved mechanical properties compared with those obtained from reference Cu. Importantly, after the heat treatment, Raman analysis of the CNT network displayed an increased metallic character that supports the enhanced electrical properties of the UCC composites. Thus, we believe that these performance characteristics together with the commercial viability of the present approach could open new possibilities in designing advanced conductors for a broad range of electrical systems and industrial applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2014

Astrometrically registered simultaneous observations of the 22 GHz H{sub 2}O and 43 GHz SiO masers toward R Leonis Minoris using KVN and source/frequency phase referencing

Oxygen-rich asymptotic giant branch (AGB) stars can be intense emitters of SiO (v = 1 and 2, J = 1 → 0) and H{sub 2}O maser lines at 43 and 22 GHz, respectively. Very long baseline interferometry (VLBI) observations of the maser emission provide a unique tool to probe the innermost layers of the circumstellar envelopes in AGB stars. Nevertheless, the difficulties in achieving astrometrically aligned H{sub 2}O and v = 1 and v = 2 SiO maser maps have traditionally limited the physical constraints that can be placed on the SiO maser pumping mechanism. We present phase-referenced simultaneous spectral-line VLBI images for the SiO v = 1 and v = 2, J = 1 → 0, and H{sub 2}O maser emission around the AGB star R LMi, obtained from the Korean VLBI Network (KVN). The simultaneous multi-channel receivers of the KVN offer great possibilities for astrometry in the frequency domain. With this facility, we have produced images with bona fide absolute astrometric registration between high-frequency maser transitions of different species to provide the positions of the H{sub 2}O maser emission and the center of the SiO maser emission, hence reducing the uncertainty in the proper motions for R LMi by an order of magnitude over that from Hipparcos. This is the first successful demonstration of source frequency phase referencing for millimeter VLBI spectral-line observations and also where the ratio between the frequencies is not an integer.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

SiO MASERS AROUND WX PSC MAPPED WITH THE KVN AND VERA ARRAY (KaVA)

We present the first images of the v = 1 and v = 2 J = 1 → 0 SiO maser lines taken with KaVA, i.e., the combined array of the Korean Very Long Baseline Interferometry (VLBI) Network and the VLBI Exploration of Radio Astrometry (VERA), toward the OH/IR star WX Psc. The combination of long and short antenna baselines enabled us to detect a large number of maser spots, which exhibit a typical ring-like structure in both the v = 1 and v = 2 J = 1 → 0 SiO masers as those that have been found in previous VLBI observational results of WX Psc. The relative alignment of the v = 1 and v = 2 SiO maser spots are precisely derived from astrometric analysis, due to the absolute coordinates of the reference maser spot that were well determined in an independent astrometric observation with VERA. The superposition of the v = 1 and v = 2 maser spot maps shows a good spatial correlation between the v = 1 and v = 2 SiO maser features. Nevertheless, it is also shown that the v = 2 SiO maser spot is distributed in an inner region compared to the v = 1 SiO maser by about 0.5 mas on average. These results provide good support for the recent theoretical studies of the SiO maser pumping, in which both the collisional and the radiative pumping predict the strong spatial correlation and the small spatial discrepancy between the v = 1 and v = 2 SiO maser.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

State of the art astronomical simulations have provided datasets which enabled the training of novel deep learning techniques for constraining cosmological parameters. However, differences in subgrid physics implementation and numerical approximations among simulation suites lead to differences in simulated datasets, which pose a hard challenge when trying to generalize across diverse data domains and ultimately when applying models to observational data. Recent work reveals deep learning algorithms are able to extract more information from complex cosmological simulations than summary statistics like power spectra. We introduce Domain Adaptive Graph Neural Networks (DA-GNNs), trained on CAMELS data, inspired by CosmoGraphNet (Villanueva-Domingo et al 2023). By utilizing GNNs, we can capitalize on their capacity to capture both astrophysical and topological features of galaxy distributions. Mixing these capabilities with domain adaptation techniques such as Maximum Mean Discrepancy (MMD), which enable extraction of domain-invariant features, our framework demonstrates enhanced accuracy and robustness. We present experimental results, including the alignment of distributions across domains through data visualization. These findings suggest that DA-GNNs are an efficient way of extracting domain independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Multimodal imaging and machine learning to enhance microscope images of shale

A machine learning based image processing workflow is presented to enhance shale source rock microscopic images obtained using diverse imaging platforms. Images were acquired from a 30 μm diameter cylindrical Vaca Muerta shale sample using both nondestructive Transmission X-Ray Microscopy (TXM, alternately referred to as nano computed tomography) and destructive Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM). Output cross-sectional images from each modality were aligned using a combination of manual and automated registration techniques to create a registered image dataset. We then apply this dataset for two image processing tasks: prediction of image cross sections with SEM-like resolution from nondestructive TXM data and repair of charged region artifacts (localized accumulation of electrons) within SEM images. The image processing algorithms for both tasks use deep learning models, specifically image-to-image Convolutional Neural Networks (CNNs) and conditional Generative Adversarial Networks (cGANs). In the image enhancement tasks, we are able to achieve significant qualitative and quantitative improvement in TXM images. Here, the best model reaches an average Peak Signal to Noise Ratio (PSNR) of 15.8 dB. Conditioning on TXM data is also shown to reduce artifacts from SEM charging, achieving an average PSNR of 25.8 dB. Furthermore, our results suggest that properly trained and validated networks are capable of significant enhancement of images obtained using nondestructive techniques, thereby improving interpretation of two- and three-dimensional images while preserving samples for future use.

58 GEOSCIENCES↗
DOE OSTI2017

Ordered and Patterned Assembly of Organic Micro/Nanocrystals for Flexible Electronic and Optoelectronic Devices

Organic semiconductor micro/nanocrystals (OSMCs) have attracted intensive research over the past few decades. Their unique electrical and mechanical properties afford them applications in a vast network of active flexible electronic and optoelectronic fields, such as organic field‐effect transistors (OFETs), photodetectors (PDs), and organic light‐emitting diodes (OLEDs) etc. However, the growth orientation and location of OSMCs are usually stochastic in nature, which hinders the further use of OSMCs in large‐area plastic electronic devices. On the other hand, traditional microelectronic processing techniques like photolithography may damage the plastic substrates, polymer insulators, and organic materials. Thus the alignment and patterning of OSMCs and development of new device construction technologies are prerequisite for their flexible device applications in practice. In this progress report,the important advancement for fabricating the aligned and patterned OSMCs, with a focus on their applications in next‐generation flexible electronic and optoelectronic devices, is highlighted. Also, the challenges and outlooks of the ordered and patterned OSMCs in the flexible device applications are presented.

Deng, Wei↗
DOE OSTI2024

Machine Learning‐Assisted Microearthquake Location Workflow for Monitoring the Newberry Enhanced Geothermal System

Abstract Enhanced geothermal systems (EGS) offer a sustainable energy source but face challenges in accurately locating microearthquakes induced during reservoir stimulation. Locating these microearthquakes provides reliable feedback on the stimulation progress. Current deep learning methods for locating earthquakes require extensive data sets for training, which is problematic as detected microearthquakes are often limited. To address the scarcity of training data, we propose a practical workflow using probabilistic multilayer perceptron (PMLP) which predicts microearthquake locations from cross‐correlation time lags in waveforms. Utilizing a 3D velocity model of Newberry site derived from ambient noise interferometry, we generate numerous synthetic microearthquakes and 3D acoustic waveforms for PMLP training. Accurate synthetic tests prompt us to apply the trained network to the 2012 and 2014 stimulation field waveforms. To enhance the accuracy of source localization, we carefully handpick the P‐arrival times. Predictions on the 2012 stimulation data set show major microseismic activity at depths of 0.5–1.2 km, correlating with a known casing leakage scenario. In the 2014 data set, the majority of predictions concentrate at 2.0–2.9 km depths, consistent with results obtained from conventional physics‐based inversion, and align with the presence of natural fractures from 2.0 to 2.7 km. We validate our findings by comparing the synthetic and field picks, demonstrating a satisfactory match for the first arrivals. By combining the benefits of quick inference speeds and accurate location predictions, we demonstrate the feasibility of using realistic synthetic data set to locate microseismicity for EGS monitoring.

15 GEOTHERMAL ENERGY↗