SEARCH · Engineering Papers

Results for “Training Time”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,189 records · Page 66

All sources NASA NTRS DOE OSTI

NASA NTRS2010

The History of the Animal Care Program at NASA Johnson Space Center

This slide presentation reviews the work of the Animal Care Program (ACP). Animals have been used early in space exploration to ascertain if it were possible to launch a manned spacecraft. The program is currently involved in many studies that assist in enhancing the scientific knowledge of the effect of space travel. The responsibilities of the ACP are: (1) Organize and supervise animal care operations & activities (research, testing & demonstration). (2) Maintain full accreditation by the International Association for the Assessment and Accreditation of Laboratory Animal Care (AAALAC) (3) Ensure protocol compliance with IACUC recommendations (4) Training astronauts for in-flight animal experiments (5) Maintain accurate & timely records for all animal research testing approved by JSC IACUC (6) Organize IACUC meetings and assist IACUC members (7) Coordinate IACUC review of the Institutional Program for Humane Care and Use of Animals (every 6 mos)

Khan-Mayberry, Noreen↗

NASA NTRS2011

Rapid Detection of the Varicella Zoster Virus

1.Technology Description-Researchers discovered that when the Varicella Zoster Virus (VZV) reactivates from latency in the body, the virus is consistently present in saliva before the appearance of skin lesions. A small saliva sample is mixed with a specialized reagent in a test kit. If the virus is present in the saliva sample, the mixture turns a red color. The sensitivity and specificity emanates from an antibody-antigen reaction. This technology is a rapid, non-invasive, point of-of-care testing kit for detecting the virus from a saliva sample. The device is easy to use and can be used in clinics and in remote locations to quickly detect VZV and begin treatment with antiviral drugs. 2.Market Opportunity- RST Bioscience will be the first and only company to market a rapid, same day test kit for the detection of VZV in saliva. The RST detection test kit will have several advantages over existing, competitive technology. The test kit is self contained and laboratory equipment is not required for analysis of the sample. Only a single saliva sample is required to be taken instead of blood or cerebral spinal fluid. The test kit is portable, sterile and disposable after use. RST detection test kits require no electrical power or expensive storage equipment and can be used in remote locations. 3.Market Analysis- According to the CDC, it is estimated that 1 million cases of shingles occur each year in the U.S. with more than half over the age of sixty. There is a high demand for rapid diagnostics by the public. The point-of-care testing (POCT) market is growing faster than other segments of in vitro diagnostics. According to a July 2007 InteLab Corporation industry report the overall market for POCT was forecast to increase from $10.3 billion in 2005 to $18.7 billion by 2011. The market value of this test kit has not been determined. 4.Competition- The VZV vaccine prevents 50% of cases and reduces neuralgia by 66%. The most popular test detects VZV-specific IgM antibody in blood. Other tests include running a sample in a polymerase chain reaction analyzer, enzyme immunoassay, latex agglutination, indirect fluorescent antibody and fluorescent antibody to membrane antigen assay. These existing tests require laboratory analysis by trained personnel, expensive equipment, invasive procedures and a longer period of time to obtain test results.

Lewis, Michelle P.↗

NASA NTRS2018

Aerosol-Radiation-Cloud Interactions in the South-East Atlantic: Model-Relevant Observations and the Beneficiary Modeling Efforts in the Realm of the EVS-2 Project ORACLES

Globally, aerosols remain a major contributor to uncertainties in assessments of anthropogenically-induced changes to the Earth climate system, despite concerted efforts using satellite and suborbital observations and increasingly sophisticated models. The quantification of direct and indirect aerosol radiative effects, as well as cloud adjustments thereto, even at regional scales, continues to elude our capabilities. Some of our limitations are due to insufficient sampling and accuracy of the relevant observables, under an appropriate range of conditions to provide useful constraints for modeling efforts at various climate scales. In this talk, I will describe (1) the efforts of our group at NASA Ames to develop new airborne instrumentation to address some of the data insufficiencies mentioned above; (2) the efforts by the EVS-2 ORACLES project to address aerosol-cloud-climate interactions in the SE Atlantic and (3) time permitting, recent results from a synergistic use of A-Train aerosol data to test climate model simulations of present-day direct radiative effects in some of the AEROCOM phase II global climate models.

Redemann, Jens↗

NASA NTRS2015

Development of a Complete Landsat Evapotranspiration and Energy Balance Archive to Support Agricultural Consumptive Water Use Reporting and Prediction in the Central Valley, CA

Mapping evapotranspiration (ET) from agricultural areas in Californias Central Valley is critical for understanding historical consumptive use of surface and groundwater. In addition, long histories of ET maps provide valuable training information for predictive studies of surface and groundwater demands. During times of drought, groundwater is commonly pumped to supplement reduced surface water supplies in the Central Valley. Due to the lack of extensive groundwater pumping records, mapping consumptive use using satellite imagery is an efficient and robust way for estimating agricultural consumptive use and assessing drought impacts. To this end, we have developed and implemented an algorithm for automated calibration of the METRIC remotely sensed surface energy balance model on NASAs Earth Exchange (NEX) to estimate ET at the field scale. Using automated calibration techniques on the NEX has allowed for the creation of spatially explicit historical ET estimates for the Landsat archive dating from 1984 to the near present. Further, our use of spatial NLDAS and CIMIS weather data, and spatial soil water balance simulations within the NEX METRIC workflow, has helped overcome challenges of time integration between satellite image dates. This historical and near present time archive of agricultural water consumption for the Central Valley will be an extremely useful dataset for water use and drought impact reporting, and predictive analyses of groundwater demands.

valleys↗

DOE OSTI2020

Development of a Convolutional Neural Network Classifier for Data Starved Spectra - 20199

The Institute for Clean Energy Technology (ICET) at Mississippi State University is exploring the utility of machine learning in augmenting its mobile radiation surveying platforms, which are currently being developed as means to survey depleted uranium contaminated areas in support of remediation and decommissioning efforts. Mobile survey platforms provide a means to efficiently scan large areas of interest while reducing human exposure to radiation and other hazards. The survey platforms can also be used for scanning for any gamma emitting isotope in addition to depleted uranium. The spectral data that the platforms collect may be data starved with relatively low counts and poorly defined spectral features depending on the speed of the platforms and scintillation detector selection. Such data-starved spectra are difficult to use for isotope identification, requiring advanced knowledge of the possible radionuclides that could be present and environmental factors that could attenuate signals or introduce background noise. These factors in combination with the volume of survey data increases the time it takes to perform analysis of survey data when the source type is unknown. There are a number of algorithms in the field of machine learning that can be used to classify data that would be challenging and time-consuming for a human to identify. Supervised machine learning algorithms train models based on extensive amounts of human-labeled training data. Once sufficiently trained, these models can be used to quickly make high-fidelity predictions on new data. Convolutional neural networks are machine learning algorithms that excel in learning representations of 'shapes'. They do this by taking numerical input data and convolving them with spatial feature detectors referred to as filters. These filters are incrementally adjusted to reduce the prediction error on the data during the backpropagation step of training. Discussed in this paper is the development of a convolutional neural network classifier (CNNC) that can utilize spectral survey data for source discrimination and isotope identification. Bench-top laboratory experiments data using LaBr{sub 3}(Ce) scintillation detectors were used to train and evaluate the performance of the developed CNNC. The CNNC is capable of discriminating a variety of gamma emitting source types, differentiating different forms of uranium (depleted vs. natural), and estimating the amount of uranium for a known geometry. The discussed CNNC may be useful in scenarios where survey systems are deployed in situations where hazardous radioactive material maybe present, but the type is unknown. When used in remediation applications the CNNC can be used to screen-out false positives, helping reduce remediation costs. (authors)

07 ISOTOPE AND RADIATION SOURCES↗

DOE OSTI2022

Dynamic Learning of Correlation Potentials for a Time-Dependent Kohn-Sham System

We develop methods to learn the correlation potential for a time-dependent Kohn-Sham (TDKS) system in one spatial dimension. We start from a low-dimensional two-electron system for which we can numerically solve the time-dependent Schr¨odinger equation; this yields electron densities suitable for training models of the correlation potential. We frame the learning problem as one of optimizing a least-squares objective subject to the constraint that the dynamics obey the TDKS equation. Applying adjoints, we develop efficient methods to compute gradients and thereby learn models of the correlation potential. Our results show that it is possible to learn values of the correlation potential such that the resulting electron densities match ground truth densities. We also show how to learn correlation potential functionals with memory, demonstrating one such model that yields reasonable results for trajectories outside the training set.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Novel, Middle and Long Wave Infrared Laser Sources For Accelerator Applications

The main accomplishment during Years 2020-2024 of the DOE Accelerator Stewardship Program is proof-of-principle demonstration of amplification of an ultrashort 10 µm seed pulse in a multiatmosphere CO 2 laser optically pumped by nanosecond pulses of either a ~4.3 µm Fe:ZnSe laser or a 2.8 µm electro-optically (EO) Q-switched Er: Laser. This has been accomplished at the UCLA Neptune Laboratory by using about 100 mJ, ~100 ns long pulses generated by the pump laser built for this purpose by the UAB team. Implementation of EO Q-switching regime in the solid-state Er:laser system made possible nanosecond synchronization between the pump pulse and the 0.5 ps seed pulse produced by a commercial Ti:sapphire laser based mid-IR OPA/DFG. The injection mode-locking regime realized in a compact Mult atmosphere 3 Hz CO 2 -He regenerative amplifier enabled generation of a train of ultrashort pulses separated by the cavity round-trip time of ~3.2 ns. The measured gain lifetime of ~1 µs at a total pressure of ~12-15 atm indicates that lifetime of the upper laser level is a critical limiting factor in designing high-pressure CO 2 amplifiers. A single picosecond 10 mm pulse with an energy 0.1-0.2 mJ was extracted from the amplifier’s cavity using an ultrafast Ge semiconductor switch whose reflectivity was photo-induced by a femtosecond 800 nm pulse. For direct amplification regime, nonlinear absorption in Ge at 10 mm at GW/cm 2 intensities limited the extracted energy. Therefore, the generated energy could be further increased by minimizing losses in the switch and optimizing the cavity mode size. Based on the obtained data in collaboration with BNL colleagues, we have designed a high-pressure CO 2 amplifier to be used as a preamplifier for the future experiments at the ATF BNL. The latter work is the subject of funding availability.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2026

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗

DOE OSTI2026

Real-Time Anomaly Detection for Searches Beyond the Standard Model in the ProtoDUNE Horizontal Drift Detector

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events—making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving 31.9 ± 0.2% (26.6 ± 0.2%) ν efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, 17.5 ± 0.3% (18.3 ± 0.3%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, C. [Cincinnati U., RWC]↗

DOE OSTI2022

A Probabilistic Autoencoder for Type Ia Supernova Spectral Time Series

We construct a physically parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of Type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an autoencoder that is interpreted probabilistically after training using a normalizing flow. We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multistage training setup alongside our physically parameterized network, we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including the automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an rms of 0.091 ± 0.010 mag, which corresponds to 0.074 ± 0.010 mag if peculiar velocity contributions are removed.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

An Observationally Trained Markov Model for MJO Propagation

A Markovian stochastic model is developed for studying the propagation of the Madden-Julian Oscillation (MJO). This model represents the daily changes in real time multivariate MJO (RMM) indices as random functions of their current state and background conditions. The probability distribution function of the RMM changes is obtained using a machine learning algorithm trained to maximize MJO forecast skills using observed daily indices of RMM and different modes of variability. Skillful forecasts are obtained for lead times between 8 and 27 days. Large ensemble simulations by the stochastic model show that with monsoonal changes in the background state, MJO propagation across the Maritime Continent (MC) is most likely to be disrupted in boreal spring and summer when MJO events propagate from favorable conditions over the Indian Ocean to unfavorable ones over the MC, and predictability is higher during spring and summer when MJO activity is away from the MC region.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2009

TurboTech Technical Evaluation Automated System

TurboTech software is a Web-based process that simplifies and semiautomates technical evaluation of NASA proposals for Contracting Officer's Technical Representatives (COTRs). At the time of this reporting, there have been no set standards or systems for training new COTRs in technical evaluations. This new process provides boilerplate text in response to interview style questions. This text is collected into a Microsoft Word document that can then be further edited to conform to specific cases. By providing technical language and a structured format, TurboTech allows the COTRs to concentrate more on the actual evaluation, and less on deciding what language would be most appropriate. Since the actual word choice is one of the more time-consuming parts of a COTRs job, this process should allow for an increase in quantity of proposals evaluated. TurboTech is applicable to composing technical evaluations of contractor proposals, task and delivery orders, change order modifications, requests for proposals, new work modifications, task assignments, as well as any changes to existing contracts.

Tiffany, Dorothy J.↗

NASA NTRS2008

Instrument Display Visual Angles for Conventional Aircraft and the MQ-9 Ground Control Station

Aircraft instrument panels should be designed such that primary displays are in optimal viewing location to minimize pilot perception and response time. Human Factors engineers define three zones (i.e. cones ) of visual location: 1) "Easy Eye Movement" (foveal vision); 2) "Maximum Eye Movement" (peripheral vision with saccades), and 3) "Head Movement (head movement required). Instrument display visual angles were measured to determine how well conventional aircraft (T-34, T-38, F- 15B, F-16XL, F/A-18A, U-2D, ER-2, King Air, G-III, B-52H, DC-10, B747-SCA) and the MQ-9 ground control station (GCS) complied with these standards, and how they compared with each other. Selected instrument parameters included: attitude, pitch, bank, power, airspeed, altitude, vertical speed, heading, turn rate, slip/skid, AOA, flight path, latitude, longitude, course, bearing, range and time. Vertical and horizontal visual angles for each component were measured from the pilot s eye position in each system. The vertical visual angles of displays in conventional aircraft lay within the cone of "Easy Eye Movement" for all but three of the parameters measured, and almost all of the horizontal visual angles fell within this range. All conventional vertical and horizontal visual angles lay within the cone of Maximum Eye Movement. However, most instrument vertical visual angles of the MQ-9 GCS lay outside the cone of Easy Eye Movement, though all were within the cone of Maximum Eye Movement. All the horizontal visual angles for the MQ-9 GCS were within the cone of "Easy Eye Movement". Most instrument displays in conventional aircraft lay within the cone of Easy Eye Movement, though mission-critical instruments sometimes displaced less important instruments outside this area. Many of the MQ-9 GCS systems lay outside this area. Specific training for MQ-9 pilots may be needed to avoid increased response time and potential error during flight. The learning objectives include: 1) Know three physiologic cones of eye/head movement; 2) Understand how instrument displays comply with these design principles in conventional aircraft and an uninhabited aerial vehicle system. Which of the following is NOT a recognized physiologic principle of instrument display design? Cone of Easy Eye Movement 2) Cone of Binocular Eye Movement 3) Cone of Maximum Eye Movement 4) Cone of Head Movement 5) None of the above. Answer: # 2) Cone of Binocular Eye Movement

Kamine, Tovy Haber↗

NASA NTRS2008

Instrument Display Visual Angles for Conventional Aircraft and the MQ-9 Ground Control Station

Aircraft instrument panels should be designed such that primary displays are in optimal viewing location to minimize pilot perception and response time. Human Factors engineers define three zones (i.e. "cones") of visual location: 1) "Easy Eye Movement" (foveal vision); 2) "Maximum Eye Movement" (peripheral vision with saccades), and 3) "Head Movement" (head movement required). Instrument display visual angles were measured to determine how well conventional aircraft (T-34, T-38, F- 15B, F-16XL, F/A-18A, U-2D, ER-2, King Air, G-III, B-52H, DC-10, B747-SCA) and the MQ-9 ground control station (GCS) complied with these standards, and how they compared with each other. Methods: Selected instrument parameters included: attitude, pitch, bank, power, airspeed, altitude, vertical speed, heading, turn rate, slip/skid, AOA, flight path, latitude, longitude, course, bearing, range and time. Vertical and horizontal visual angles for each component were measured from the pilot s eye position in each system. Results: The vertical visual angles of displays in conventional aircraft lay within the cone of "Easy Eye Movement" for all but three of the parameters measured, and almost all of the horizontal visual angles fell within this range. All conventional vertical and horizontal visual angles lay within the cone of "Maximum Eye Movement". However, most instrument vertical visual angles of the MQ-9 GCS lay outside the cone of "Easy Eye Movement", though all were within the cone of "Maximum Eye Movement". All the horizontal visual angles for the MQ-9 GCS were within the cone of "Easy Eye Movement". Discussion: Most instrument displays in conventional aircraft lay within the cone of "Easy Eye Movement", though mission-critical instruments sometimes displaced less important instruments outside this area. Many of the MQ-9 GCS systems lay outside this area. Specific training for MQ-9 pilots may be needed to avoid increased response time and potential error during flight.

Bendrick, Gregg A.↗

NASA NTRS1992

Potential of adult mammalian lumbosacral spinal cord to execute and acquire improved locomotion in the absence of supraspinal input

The neural circuitry of the lumbar spinal cord can generate alternating extension and flexion of the hindlimbs. The hindlimbs of adult cats with complete transection of the spinal cord at a low thoracic level (T12-T13) can perform full weight-supporting locomotion on a treadmill belt moving at a range of speeds. Some limitations in the locomotor capacity can be associated with a deficit in the recruitment level of the fast extensors during the stance phase and the flexors during the swing phase of a step cycle. The level of locomotor performance, however, can be enhanced by daily training on a treadmill while emphasizing full weight-support stepping and by providing appropriately timed sensory stimulation, loading, and/or pharmacologic stimulation of the hindlimb neuromuscular apparatus. Furthermore, there appears to be an interactive effect of these interventions. For example, the maximum treadmill speed that a spinal adult cat can attain and maintain is significantly improved with daily full weight-supporting treadmill training, but progressive recruitment of fast extensors becomes apparent only when the hindlimbs are loaded by gently pulling down on the tail during the stepping. Stimulation of the sural nerve at the initiation of the flexion phase of the step cycle can likewise markedly improve the locomotor capability. Administration of clonidine, in particular in combination with an elevated load, resulted in the most distinct and consistent alternating bursts of electromyographic activity during spinal stepping. These data indicate that the spinal cord has the ability to execute alternating activation of the extensor and flexor musculature of the hindlimbs (stepping) and that this ability can be improved by several interventions such as training, sensory stimulation, and use of some pharmacologic agents. Thus, it appears that the spinal cord, without supraspinal input, is highly plastic and has the potential to "learn," that is, to acquire and improve its ability to execute full weight-supporting locomotion on a treadmill belt.

NASA Discipline Musculoskeletal↗

DOE OSTI2022

Quantitative interpretation of time-lapse seismic data at Farnsworth field unit: Rock physics modeling, and calibration of simulated time-lapse velocity responses

Here, this study investigates the contribution of fluid saturation variation to the time-lapse velocity response by performing fluid substitution modeling. The methodology is exemplified by the time-lapse seismic monitoring of carbon dioxide at Farnsworth field unit (FWU). In order to evaluate the fluid distribution in a matured oil reservoir, the Southwest Regional Partnership (SWP) acquired multiple vertical seismic profile (VSP) surveys at different times during the CO 2 –water alternatinggas (WAG) injection period. In this work, we present a thorough methodology for computing the elastic response of the saturated rock for different fluid saturations using a site-specific petro-elastic model (PEM). The output from the PEM was combined with results from a fluid compositional model to compute the seismic velocities at times corresponding to each VSP survey. To produce a calibrated simulated response, the measured time-lapse seismic velocities were integrated into the numerical simulation model. The mismatches between the predicted and measured time-lapse velocities were minimized through an iterative calibration process using a trained artificial neural network proxy (ANN) coupled with a particle swarm optimizer (PSO). Our study indicates that the hybrid optimization workflow can effectively perform the history matching. With an accurate prediction of the hydrodynamic properties, the migration of CO 2 within the subsurface was modeled by predicting the spatial velocity distribution for a radius of 305 m around the injection well. The technology demonstrated and the expertise gained from this study can guide similar CO 2 -WAG projects.

58 GEOSCIENCES↗

DOE OSTI2023

Neutron (and other Particle) Transport at LANL: An Overview [Presentation]

For decades, Los Alamos National Laboratory has been at the forefront of neutron transport methods research and code development. One such code is PARTISN, the LANL parallel time-dependent discrete ordinate neutron transport code. In this presentation, we describe the various research efforts currently underway by the PARTISN and other code teams. Some examples of current research are a block automated mesh refinement scheme, the application of tensor trains to the discretized neutron transport equation, and GPU code porting. The block automated mesh refinement scheme uses cross section information to refine and coarsen the solution mesh to improve time to solution and reduce memory. The tensor train approach expresses discretized transport operators as tensor products of vectors and matrices to compress the size of linear systems being solved by transport codes. Rather than relying on matrix-free methods such as the transport sweep, we have access to an operator that can be inverted, reshaped, or manipulated algebraically. Finally, we describe how PARTISN is used, what problems we are looking to solve, and what the future holds for neutron transport at LANL. In addition to this, we briefly describe the various research efforts in other particle transport teams using both deterministic and Monte Carlo methods. In the presentation, we list possible opportunities for collaboration between the laboratory and faculty and students.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2024

Efficient and generalizable nested Fourier-DeepONet for three-dimensional geological carbon sequestration

Geological carbon sequestration (GCS) involves injecting CO2 into subsurface geological formationsfor permanent storage. Numerical simulations could guide decisions in GCS projects by predictingCO 2 migration pathways and the pressure distribution in storage formation. However, these simula-tions are often computationally expensive due to highly coupled physics and large spatial-temporalsimulation domains. Surrogate modelling with data-driven machine learning has become a promis-ing alternative to accelerate physics-based simulations. Among these, the Fourier neural operator(FNO) has been applied to three-dimensional synthetic subsurface models. Despite its good accuracyin simulating CO 2 plume migration, it requires large computational resources in training and alsolacks generalizability. Here, to further improve performance, we have developed a nested Fourier-DeepONet by combining the expressiveness of the FNO with the modularity of a deep operatornetwork (DeepONet). This new framework is twice as efficient as a nested FNO for training and has atleast 80% lower GPU memory requirement due to its flexibility to treat temporal coordinates sepa-rately. These performance improvements are achieved without compromising prediction accuracy.In addition, the generalization and extrapolation ability of nested Fourier-DeepONet beyond thetraining range has been thoroughly evaluated. Nested Fourier-DeepONet outperformed the nestedFNO for extrapolation in time with more than 50% reduced error. It also exhibited good extrapolationaccuracy beyond the training range in terms of reservoir properties, number of wells, and injectionrate.

Lee, Jonathan E. [Department of Chemical and Envir↗