Search NASA⌕ Search

SEARCH · Search NASA

Results for “image based modeling”

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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

Thermo-Mechanical Processing in Friction Stir Welds

Friction stir welding is a solid-phase joining, or welding process that was invented in 1991 at The Welding Institute (TWI). The process is potentially capable of joining a wide variety of aluminum alloys that are traditionally difficult to fusion weld. The friction stir welding (FSW) process produces welds by moving a non-consumable rotating pin tool along a seam between work pieces that are firmly clamped to an anvil. At the start of the process, the rotating pin is plunged into the material to a pre-determined load. The required heat is produced by a combination of frictional and deformation heating. The shape of the tool shoulder and supporting anvil promotes a high hydrostatic pressure along the joint line as the tool shears and literally stirs the metal together. To produce a defect free weld, process variables (RPM, transverse speed, and downward force) and tool pin design must be chosen carefully. An accurate model of the material flow during the process is necessary to guide process variable selection. At MSFC a plastic slip line model of the process has been synthesized based on macroscopic images of the resulting weld material. Although this model appears to have captured the main features of the process, material specific interactions are not understood. The objective of the present research was to develop a basic understanding of the evolution of the microstructure to be able to relate it to the deformation process variables of strain, strain rate, and temperature.

Schneider, Judy↗
DOE OSTI2021

Efficient ptychographic phase retrieval via a matrix-free Levenberg-Marquardt algorithm

The phase retrieval problem, where one aims to recover a complex-valued image from far-field intensity measurements, is a classic problem encountered in a range of imaging applications. Modern phase retrieval approaches usually rely on gradient descent methods in a nonlinear minimization framework. Calculating closed-form gradients for use in these methods is tedious work, and formulating second order derivatives is even more laborious. Additionally, second order techniques often require the storage and inversion of large matrices of partial derivatives, with memory requirements that can be prohibitive for data-rich imaging modalities. We use a reverse-mode automatic differentiation (AD) framework to implement an efficient matrix-free version of the Levenberg-Marquardt (LM) algorithm, a longstanding method that finds popular use in nonlinear least-square minimization problems but which has seen little use in phase retrieval. Furthermore, we extend the basic LM algorithm so that it can be applied for more general constrained optimization problems (including phase retrieval problems) beyond just the least-square applications. Since we use AD, we only need to specify the physics-based forward model for a specific imaging application; the first and second-order derivative terms are calculated automatically through matrix-vector products, without explicitly forming the large Jacobian or Gauss-Newton matrices typically required for the LM method. We demonstrate that this algorithm can be used to solve both the unconstrained ptychographic object retrieval problem and the constrained “blind” ptychographic object and probe retrieval problems, under the popular Gaussian noise model as well as the Poisson noise model. We compare this algorithm to state-of-the-art first order ptychographic reconstruction methods to demonstrate empirically that this method outperforms best-in-class first-order methods: it provides excellent convergence guarantees with (in many cases) a superlinear rate of convergence, all with a computational cost comparable to, or lower than, the tested first-order algorithms.

36 MATERIALS SCIENCE↗
DOE OSTI2011

A general framework and review of scatter correction methods in cone beam CT. Part 2: Scatter estimation approaches

The main components of scatter correction procedures are scatter estimation and a scatter compensation algorithm. This paper completes a previous paper where a general framework for scatter compensation was presented under the prerequisite that a scatter estimation method is already available. In the current paper, the authors give a systematic review of the variety of scatter estimation approaches. Scatter estimation methods are based on measurements, mathematical-physical models, or combinations of both. For completeness they present an overview of measurement-based methods, but the main topic is the theoretically more demanding models, as analytical, Monte-Carlo, and hybrid models. Further classifications are 3D image-based and 2D projection-based approaches. The authors present a system-theoretic framework, which allows to proceed top-down from a general 3D formulation, by successive approximations, to efficient 2D approaches. A widely useful method is the beam-scatter-kernel superposition approach. Together with the review of standard methods, the authors discuss their limitations and how to take into account the issues of object dependency, spatial variance, deformation of scatter kernels, external and internal absorbers. Open questions for further investigations are indicated. Finally, the authors refer on some special issues and applications, such as bow-tie filter, offset detector, truncated data, and dual-source CT.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2025

Active Learning Surrogates for Integrating Electron Microscopy and Computational Insights from Simulations in Autonomous Experiments

Artificial Intelligence (AI) combined with simulations and experiments has great potential to accelerate scientific discovery across technology and pharmaceuticals. However, the gap between simulations and experiments is challenging due to disparities in time and scale, making it difficult to estimate properties like energy and electronic states from experiments, and to provide feedback based on theoretical insights.Our research addresses the challenge by developing unique deep kernel based surrogate models that learns from microscopic images, mapping structural features to energy differences from defect formation. We start with full-training using simulated images to determine optimal settings, establishing a baseline for active learning. Using these settings from the baseline, active learning is trained, and predicts structures along simulation trajectories based on uncertainty and energetic stability, thus reducing data requirements, simulation time and computational costs. The results demonstrate that the model achieves a low average error margin of approximately 0.03 meV, indicating good performance. To enhance feature extraction and reconstruction capabilities, we developed an autoencoder-decoder as additional surrogate to create latent space to capture essential features, enabling precise comparisons between simulations and experiments. The results from this model achieved a reconstruction loss of around 0.2 and accurately reconstructed molecular structures.Overall, this work advances the steering of experiments through computational simulations by employing a surrogate models that actively predicts the trajectories of structural evolution, achieving time-to-solution comparable to experimental measurements.

Saranathan, Gayathri [Hewlett-Packard]↗
DOE OSTI2018

On convergent finite difference schemes for variational–PDE-based image processing

We study an adaptive anisotropic Huber functional-based image restoration scheme. Using a combination of L2–L1 regularization functions, an adaptive Huber functional-based energy minimization model provides denoising with edge preservation in noisy digital images. We study a convergent finite difference scheme based on continuous piecewise linear functions and use a variable splitting scheme, namely the Split Bregman (In: Goldstein and Osher, SIAM J Imaging Sci 2(2):323–343, 2009) algorithm, to obtain the discrete minimizer. Experimental results are given in image denoising and comparison with additive operator splitting, dual fixed point, and projected gradient schemes illustrates that the best convergence rates are obtained for our algorithm.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Using compressive sensing to recover images from PET scanners with partial detector rings

Purpose: Most positron emission tomography/computed tomography (PET/CT) scanners consist of tightly packed discrete detector rings to improve scanner efficiency. The authors’ aim was to use compressive sensing (CS) techniques in PET imaging to investigate the possibility of decreasing the number of detector elements per ring (introducing gaps) while maintaining image quality. Methods: A CS model based on a combination of gradient magnitude and wavelet domains (wavelet-TV) was developed to recover missing observations in PET data acquisition. The model was designed to minimize the total variation (TV) and L1-norm of wavelet coefficients while constrained by the partially observed data. The CS model also incorporated a Poisson noise term that modeled the observed noise while suppressing its contribution by penalizing the Poisson log likelihood function. Three experiments were performed to evaluate the proposed CS recovery algorithm: a simulation study, a phantom study, and six patient studies. The simulation dataset comprised six disks of various sizes in a uniform background with an activity concentration of 5:1. The simulated image was multiplied by the system matrix to obtain the corresponding sinogram and then Poisson noise was added. The resultant sinogram was masked to create the effect of partial detector removal and then the proposed CS algorithm was applied to recover the missing PET data. In addition, different levels of noise were simulated to assess the performance of the proposed algorithm. For the phantom study, an IEC phantom with six internal spheres each filled with F-18 at an activity-to-background ratio of 10:1 was used. The phantom was imaged twice on a RX PET/CT scanner: once with all detectors operational (baseline) and once with four detector blocks (11%) turned off at each of 0 °, 90 °, 180 °, and 270° (partially sampled). The partially acquired sinograms were then recovered using the proposed algorithm. For the third test, PET images from six patient studies were investigated using the same strategy of the phantom study. The recovered images using WTV and TV as well as the partially sampled images from all three experiments were then compared with the fully sampled images (the baseline). Comparisons were done by calculating the mean error (%bias), root mean square error (RMSE), contrast recovery (CR), and SNR of activity concentration in regions of interest drawn in the background as well as the disks, spheres, and lesions. Results: For the simulation study, the mean error, RMSE, and CR for the WTV (TV) recovered images were 0.26% (0.48%), 2.6% (2.9%), 97% (96%), respectively, when compared to baseline. For the partially sampled images, these results were 22.5%, 45.9%, and 64%, respectively. For the simulation study, the average SNR for the baseline was 41.7 while for WTV (TV), recovered image was 44.2 (44.0). The phantom study showed similar trends with 5.4% (18.2%), 15.6% (18.8%), and 78% (60%), respectively, for the WTV (TV) images and 33%, 34.3%, and 69% for the partially sampled images. For the phantom study, the average SNR for the baseline was 14.7 while for WTV (TV) recovered image was 13.7 (11.9). Finally, the average of these values for the six patient studies for the WTV-recovered, TV, and partially sampled images was 1%, 7.2%, 92% and 1.3%, 15.1%, 87%, and 27%, 25.8%, 45%, respectively. Conclusions: CS with WTV is capable of recovering PET images with good quantitative accuracy from partially sampled data. Such an approach can be used to potentially reduce the cost of scanners while maintaining good image quality.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1989

Satellite Data Processing System (SDPS) users manual V1.0

SDPS is a menu driven interactive program designed to facilitate the display and output of image and line-based data sets common to telemetry, modeling and remote sensing. This program can be used to display up to four separate raster images and overlay line-based data such as coastlines, ship tracks and velocity vectors. The program uses multiple windows to communicate information with the user. At any given time, the program may have up to four image display windows as well as auxiliary windows containing information about each image displayed. SDPS is not a commercial program. It does not contain complete type checking or error diagnostics which may allow the program to crash. Known anomalies will be mentioned in the appropriate section as notes or cautions. SDPS was designed to be used on Sun Microsystems Workstations running SunView1 (Sun Visual/Integrated Environment for Workstations). It was primarily designed to be used on workstations equipped with color monitors, but most of the line-based functions and several of the raster-based functions can be used with monochrome monitors. The program currently runs on Sun 3 series workstations running Sun OS 4.0 and should port easily to Sun 4 and Sun 386 series workstations with SunView1. Users should also be familiar with UNIX, Sun workstations and the SunView window system.

Caruso, Michael↗
DOE OSTI2020

Machine Vision-based Robot Manipulators for Nuclear Applications - 20370

Decommissioning and dismantling of nuclear facilities are major challenges facing the nuclear industry. Robot manipulators with capabilities of restoring nuclear structures and significantly prolonging nuclear power generation in addition to their applications in decommissioning and dismantling (D and D) would immensely ease the above-mentioned challenge. Ability to remotely sense/monitor and analyze dangerous and hazardous environments such as nuclear reactors as well as performing reparatory tasks in such environments using robot manipulators require additional information from vision sensors. Structural sample collection and inspection as well as restoration require object and position information. Computer vision is used to obtain precise 3D position information. The current work uses the Sawyer robot with the integrated Cognex camera. The research presents an approach to facilitate and improve operations in a nuclear reactor using robotic vision control. The vision control system is modeled with Augmented Image Space-based visual servoing approach. Results showing accurate robot control. Object recognition is used to recognize the image and calculate it poses. To transform coordinates of the object's pose from the camera frame to the robotic frame transformation matrices are employed. Future work will employ a 3D camera (with depth information) using Denso robot. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Model-Based Reconstruction for Multi-Frequency Collimated Beam Ultrasound Systems

Collimated beam ultrasound systems are a technology for imaging inside multi-layered structures such as geothermal wells. These systems work by using a collimated narrow-band ultrasound transmitter that can penetrate through multiple layers of heterogeneous material. A series of measurements can then be made at multiple transmit frequencies. However, commonly used reconstruction algorithms such as Synthetic Aperture Focusing Technique (SAFT) tend to produce poor quality reconstructions for these systems both because they do not model collimated beam systems and they do not jointly reconstruct the multiple frequencies. Here, in this article, we propose a multi-frequency ultrasound model-based iterative reconstruction (UMBIR) algorithm designed for multi-frequency collimated beam ultrasound systems. The combined system targets reflective imaging of heterogeneous, multi-layered structures. For each transmitted frequency band, we introduce a physics-based forward model to accurately account for the propagation of the collimated narrow-band ultrasonic beam through the multi-layered media. We then show how the joint multi-frequency UMBIR reconstruction can be computed by modeling the direct arrival signals, detector noise, and incorporating a spatially varying image prior. Results using both simulated and experimental data indicate that multi-frequency UMBIR reconstruction yields much higher reconstruction quality than either single frequency UMBIR or SAFT.

47 OTHER INSTRUMENTATION↗
NASA NTRS2014

Infrared Contrast Analysis Technique for Flash Thermography Nondestructive Evaluation

The paper deals with the infrared flash thermography inspection to detect and analyze delamination-like anomalies in nonmetallic materials. It provides information on an IR Contrast technique that involves extracting normalized contrast verses time evolutions from the flash thermography infrared video data. The paper provides the analytical model used in the simulation of infrared image contrast. The contrast evolution simulation is achieved through calibration on measured contrast evolutions from many flat bottom holes in the subject material. The paper also provides formulas to calculate values of the thermal measurement features from the measured contrast evolution curve. Many thermal measurement features of the contrast evolution that relate to the anomaly characteristics are calculated. The measurement features and the contrast simulation are used to evaluate flash thermography inspection data in order to characterize the delamination-like anomalies. In addition, the contrast evolution prediction is matched to the measured anomaly contrast evolution to provide an assessment of the anomaly depth and width in terms of depth and diameter of the corresponding equivalent flat-bottom hole (EFBH) or equivalent uniform gap (EUG). The paper provides anomaly edge detection technique called the half-max technique which is also used to estimate width of an indication. The EFBH/EUG and half-max width estimations are used to assess anomaly size. The paper also provides some information on the "IR Contrast" software application, half-max technique and IR Contrast feature imaging application, which are based on models provided in this paper.

Koshti, Ajay↗
NASA NTRS1993

The effects of AVIRIS atmospheric calibration methodology on identification and quantitative mapping of surface mineralogy, Drum Mountains, Utah

The Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) measures reflected light in 224 contiguous spectra bands in the 0.4 to 2.45 micron region of the electromagnetic spectrum. Numerous studies have used these data for mineralogic identification and mapping based on the presence of diagnostic spectral features. Quantitative mapping requires conversion of the AVIRIS data to physical units (usually reflectance) so that analysis results can be compared and validated with field and laboratory measurements. This study evaluated two different AVIRIS calibration techniques to ground reflectance: an empirically-based method and an atmospheric model based method to determine their effects on quantitative scientific analyses. Expert system analysis and linear spectral unmixing were applied to both calibrated data sets to determine the effect of the calibration on the mineral identification and quantitative mapping results. Comparison of the image-map results and image reflectance spectra indicate that the model-based calibrated data can be used with automated mapping techniques to produce accurate maps showing the spatial distribution and abundance of surface mineralogy. This has positive implications for future operational mapping using AVIRIS or similar imaging spectrometer data sets without requiring a priori knowledge.

Kruse, Fred A.↗
DOE OSTI2014

Numerical Methods of Computational Electromagnetics for Complex Inhomogeneous Systems

Understanding electromagnetic phenomena is the key in many scientific investigation and engineering designs such as solar cell designs, studying biological ion channels for diseases, and creating clean fusion energies, among other things. The objectives of the project are to develop high order numerical methods to simulate evanescent electromagnetic waves occurring in plasmon solar cells and biological ion-channels, where local field enhancement within random media in the former and long range electrostatic interactions in the latter are of major challenges for accurate and efficient numerical computations. We have accomplished these objectives by developing high order numerical methods for solving Maxwell equations such as high order finite element basis for discontinuous Galerkin methods, well-conditioned Nedelec edge element method, divergence free finite element basis for MHD, and fast integral equation methods for layered media. These methods can be used to model the complex local field enhancement in plasmon solar cells. On the other hand, to treat long range electrostatic interaction in ion channels, we have developed image charge based method for a hybrid model in combining atomistic electrostatics and continuum Poisson-Boltzmann electrostatics. Such a hybrid model will speed up the molecular dynamics simulation of transport in biological ion-channels.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

On the structural and electronic properties of Ir-silicide nanowires on Si(001) surface

Iridium (Ir) modified Silicon (Si) (001) surface is studied with Scanning Tunneling Microscopy/Spectroscopy (STM/STS) and Density Functional Theory (DFT). A model for Ir-silicide nanowires based on STM images and ab-initio calculations is proposed. According to our model, the Ir adatom is on the top of the substrate dimer row and directly binds to the dimer atoms. I-V curves measured at 77 K shows that the nanowires are metallic. DFT calculations confirm strong metallic nature of the nanowires.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

GRinding Automated Classification Engine

This work is an ML-driven framework for automated surface analysis of microscopy images. We create a training dataset by imaging stainless steel samples to benchmark four developed deep neural network architectures. These models, based on a YOLOv8n-cls backend, integrate image features and process metadata using various fusion methods to distinguish between acceptable and unacceptable surface finishes. This code is associated with publication "Classifying Alloy Surface Preparation Quality with Metadata-Infused Machine Learning for Rapid Alloy Discovery" for project APEX LDRD-ER (25-ERD-039)

Gongora, AldairE [Lawrence Livermore National Labo↗
DOE OSTI2026

Automated Bacterial Identification and Morphological Feature Analysis in Low‐Dose Cryo‐EM Using YOLOv11

Bacteria rapidly adapt to environmental cues through morphological and ultrastructural changes that correlate with physiology and behavior. Cryogenic transmission electron microscopy (cryo‐TEM) can capture these phenotypic changes in near‐native, vitrified states, but manual analysis of low‐dose micrographs is labor intensive and limits throughput. Here, we present an end‐to‐end workflow that combines low‐dose cryo‐TEM imaging with a YOLOv11‐based instance‐segmentation model to automatically identify bacteria and quantify key structural features directly from the micrographs. This workflow enables (i) robust bacterial localization and counting from low‐magnification atlas/montage images, (ii) automated measurements of cell‐envelope (outer–inner membrane) thickness and anisotropy from higher‐magnification views, and (iii) detection and quantification of bacteria–flagella interactions, including overlap length and curvature metrics for interacting versus noninteracting flagella. Using Pantoea sp. YR343 grown under distinct media conditions, we show that the automated measurements agree with manual annotations while substantially reducing analysis time. Together, these tools provide a practical framework for scalable bacterial identification and quantitative phenotyping in low‐dose cryo‐TEM datasets and establish a foundation for extending cryo‐TEM image analysis toward higher‐throughput studies of microbial heterogeneity and biointerfaces.

YOLOv11↗
DOE OSTI2018

Sparsity-based photoacoustic image reconstruction with a linear array transducer and direct measurement of the forward model

Photoacoustic (PA) imaging is an emerging imaging technique for many clinical applications. One of the challenges posed by clinical translation is that imaging systems often rely on a finite-aperture transducer rather than a full tomography system. This results in imaging artifacts arising from an underdetermined reconstruction of the initial pressure distribution (IPD). Furthermore, clinical applications often require deep imaging, resulting in a low-signal-to-noise ratio for the acquired signal because of strong light attenuation in tissue. Conventional approaches to reconstruct the IPD, such as back projection and time-reversal, do not adequately suppress the artifacts and noise. We propose a sparsity-based optimization approach that improves the reconstruction of IPD in PA imaging with a linear array ultrasound transducer. In simulation studies, the forward model matrix was measured from k-Wave simulations, and the approach was applied to reconstruct simulated point objects and the Shepp–Logan phantom. The results were compared with the conventional back projection, time-reversal approach, frequency-domain reconstruction, and the iterative least-squares approaches. In experimental studies, the forward model of our imaging system is directly measured by scanning a graphite point source through the imaging field of view. Experimental images of graphite inclusions in tissue-mimicking phantoms are reconstructed and compared with the back projection and iterative least-squares approaches. Altogether these results show that our proposed optimization approach can leverage the sparsity of the PA images to improve the reconstruction of the IPD and outperform the existing popular reconstruction approaches.

47 OTHER INSTRUMENTATION↗
DOE OSTI2013

Predicting diagnostic error in radiology via eye-tracking and image analytics: Preliminary investigation in mammography

Purpose: The primary aim of the present study was to test the feasibility of predicting diagnostic errors in mammography by merging radiologists’ gaze behavior and image characteristics. A secondary aim was to investigate group-based and personalized predictive models for radiologists of variable experience levels.Methods: The study was performed for the clinical task of assessing the likelihood of malignancy of mammographic masses. Eye-tracking data and diagnostic decisions for 40 cases were acquired from four Radiology residents and two breast imaging experts as part of an IRB-approved pilot study. Gaze behavior features were extracted from the eye-tracking data. Computer-generated and BIRADS images features were extracted from the images. Finally, machine learning algorithms were used to merge gaze and image features for predicting human error. Feature selection was thoroughly explored to determine the relative contribution of the various features. Group-based and personalized user modeling was also investigated.Results: Machine learning can be used to predict diagnostic error by merging gaze behavior characteristics from the radiologist and textural characteristics from the image under review. Leveraging data collected from multiple readers produced a reasonable group model [area under the ROC curve (AUC) = 0.792 ± 0.030]. Personalized user modeling was far more accurate for the more experienced readers (AUC = 0.837 ± 0.029) than for the less experienced ones (AUC = 0.667 ± 0.099). The best performing group-based and personalized predictive models involved combinations of both gaze and image features.Conclusions: Diagnostic errors in mammography can be predicted to a good extent by leveraging the radiologists’ gaze behavior and image content.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗