Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep generative model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,081 records · Page 60

Applying Machine Learning to the Classification of DC-DC Converters. NA-22 Final Report

Tools are now available that enable measurement electromagnetic radiation (EMR) from active electronics in an item. This radiation may be intended WIFI or cellular network links, for example or unintended such as the switching noise generated by DC-to-DC converters. It would be extremely valuable to have the capability to discriminate between the low-voltage DC-to-DC converters or other digital noise prevalent in most modern electronics, versus the high-voltage DC-to-DC converters used in utility firesets. Previous work performed under a Sandia Laboratory Directed Research and Development (LDRD) project on Charge State Detection using a deep neural network has been continued in this effort. A state-of-the-art supervised machine learning algorithm has not only been extended to discriminate between low and high voltage converters but has been validated in determining a converters make and model.

42 ENGINEERING↗

Hyperspectral remote sensing-based plant community map for region around NGEE-Arctic intensive research watersheds at Seward Peninsula, Alaska, 2017-2019

Using airborne hyperspectral remote sensing data from NASA Airborne Visible-Infrared Imaging Spectrometer- Next Generation (AVIRIS-NG) platforms in a region near NGEE-Arctic intensive watersheds at Seward peninsula of Alaska, high resolution (5m) maps of plant community distribution were developed and included in this data collected. AVIRIS-NG data collected over 2017-2019 period were used to develop deep neural networks, trained using vegetation plot observations collected at NGEE-Arctic watersheds at Kougarok, Council and Teller. A hierarchical vegetation classification scheme consisting of six classes at Level I, and 16 classes at Level II contained in two .txt files were used to developed the plant community maps for the region. Two geospatial raster data files (.tif) at both thematic levels are shared in this data collection. Data files in this collection use Alaska Albers Equal Area projection. Readme files available in three formats (*.html, *.md, *.pdf) and one *.png visualization map.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

Generating An Advanced Cross-section Library For HTGR Pebble Bed Depletion Calculations Using Reduced-Order Model Generation Techniques

For code development, Advanced Reactor Technologies - Gas Cooled Reactors Program (ART-GCR) rely on a collaboration with the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program, but the cross sections generation and the methodology definition is part of this program area goals. Based on previous studies in FY23, the size of microscopic cross section libraries increases rapidly with the number of tabulations, requiring significant amount of memory and drastically slowing down the Griffin calculations when evaluating cross sections via the multivariate linear interpolation approach. Rising to these challenges, this work investigates constructing Reduced-order Models (ROMs) for the multi-group microscopic cross sections to accelerate the cross section evaluation in Griffin. A database of multigroup cross sections is first collected considering all possible parameters that a designer could change for optimization. Down-selection of the ROM techniques afterward shows Deep Neural Network (DNN) as the best candidate when jointly consider memory efficiency, predictive accuracy, computational cost, scalability, flexibility and ease of implementation of the algorithms in comparison to the multidimensional interpolation. This work develops a specific interface that enables the cross section predictions using pre-trained DNN models into Griffin leveraging the existing ROM capabilities. DNNs have been trained for all isotopes for use in Griffin. Preliminary Griffin testing shows that DNNs exhibit exceptional predictive accuracy and the use of DNNs provides orders of magnitude improvement in memory efficiency compared to conventional interpolation techniques. With such ROM techniques, it holds great promise to further increase the fidelity of the Pebble Bed Reactor (PBR) simulation by increasing the number of tabulations/state variables during cross section evaluation, while maintaining the computational cost affordable in Griffin.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Pulsed Thermal Tomography Nondestructive Examination of Additively Manufactured Reactor Materials and Components (Final Technical Report)

Metal Additive Manufacturing (AM) is a promising method for cost-efficient fabrication of complex shape structures for applications in harsh environment, such as in a nuclear reactor. However, internal defects (pores) occur in high-strength AM alloys, which are manufactured with Laser Powder Bed Fusion (LPBF) AM method. Pulsed Infrared Thermography (PIT) is an efficient nondestructive evaluation (NDE) method to examine actual structures, because this method offers one-sided non-contact measurements, and fast processing of large sample areas. However, imaging of material defects, particularly defects with sizes at microscopic level, is challenging. In this report, we benchmark the performance of several Unsupervised Learning (UL) algorithms designed to enhance imaging of microscopic defects in metals with PIT. UL aims to learn the latent principal patterns (dictionaries) in PIT data to detect defects with minimal human supervision. Performance of Independent Component Analysis (ICA), Sparse Coding (SC), Principal Component Analysis (PCA) and Exploratory Factor Analysis (EFA) was compared using F-score, UL model training time and defects reconstruction time. We obtained the average F-score of 0.75, and a highest F-score of 0.89 for the EFA algorithm. Overall, EFA outperforms other UL algorithms considered in this study. In another approach, we investigate Thermal Tomography (TT), which is a computational method for reconstruction of depth profile of internal material defects from PIT nondestructive evaluation (NDE). TT algorithm obtains depth reconstructions of thermal effusivity, which has been shown to provide visualization of subsurface internals defects in metals. In many applications, one needs to determine the defect shape and orientation from reconstructed effusivity images. Interpretation of TT images is non-trivial because of blurring, which increases with depth due to heat diffusion-based nature of image formation. We have developed a deep learning convolutional neural network (CNN) to classify size and orientation of subsurface material defects in TT images. CNN was trained with TT images produced with computer simulations of 2D metallic structures (thin plates) containing elliptical subsurface voids. Performance of CNN was investigated using test TT images developed with computer simulations of plates containing elliptical defects, and defects with shape imported from scanning electron microscopy (SEM) images. CNN demonstrated the ability to classify radii and angular orientation of elliptical defects in previously unseen test TT images. We have also demonstrated that CNN trained on TT images of elliptical defects is capable of classifying shape and orientation of irregular defects. Training the CNN on irregular defect shapes instead of on elliptical shapes would make the resulting classifications more descriptive of actual defect shapes. However, this requires a much higher volume of SEM images of material defects, which are difficult to obtain because of random occurrence of defects in LPBF. To address this challenge, we developed a generative adversarial network (GAN) to augment the existing dataset of SEM defect images. The GAN model is demonstrated to create novel yet realistic defect shapes that can be used as input for simulated PTT images to train CNN. We also investigate several approaches based on Gaussian Random Circle and Bezier Curves for constructing parametric models of irregular-shape defects.

36 MATERIALS SCIENCE↗

Activity coefficient acquisition with thermodynamics–informed active learning for phase diagram construction

This work explores the use of thermodynamics-informed Gaussian processes (GPs) and active learning (AL) to model activity coefficients and construct phase diagrams. Relying on synthetic data generated from an excess Gibbs energy model, GPs were found to accurately describe the activity coefficients of several binary mixtures across large composition and temperature ranges. Moreover, GPs could estimate their own uncertainty and identify composition/temperature regions where activity coefficient data provide the most information to the models. This was leveraged to build AL algorithms targeted at modeling phase equilibria. In many cases, a single active-learning-acquired data point was sufficient to describe the phase diagrams studied. Lastly, the ability of AL to greatly reduce the amount of data needed to obtain accurate models was further verified on experimental case studies, namely individual ion activity coefficients, the solid–liquid and vapor–liquid equilibrium of deep eutectic solvents, and phase equilibria in ternary mixtures.

25 ENERGY STORAGE↗

Learning Heterogeneous Features Jointly: A Deep End-to-End Framework for Multi-Step Short-Term Wind Power Prediction

Leveraging multiple heterogeneous measurements to predict wind power has long been a challenging task in the electrical community. In this paper, a deep architecture incorporated with multitask learning and multimodal learning for wind power prediction, termed predictive stacked autoencoder (PSAE), is presented. PSAE is a unified framework integrating multiple stacked autoencoders (SAEs), one feature fusion layer, and one prediction terminal layer, which expands the architecture from two spatial dimensions, including the depth and width, compared to conventional prediction models. Initially, the SAEs at the bottom of PSAE extracted features from multiple kinds of measurements respectively. Following, the feature fusion layer encodes the high-order features extracted by different SAEs into a unified feature that is more informative and representative for wind power prediction. Finally, the prediction terminal layer functions as a regression machine which generates the predicted targets based on the fusion features. Trained in an end-to-end (E2E) manner, PSAE is capable of learning heterogeneous features jointly and achieving the prediction task of sequence-to-sequence (S2S). Experiments for multi-step short-term predictions are conducted on real-world data, and the results demonstrate the superiority of PSAE to prior methods.

17 WIND ENERGY↗

High Temperature Reactor (HTR) Deep Burn Core and Fuel Analysis: Design Selection for the Prismatic Block Reactor With Results from FY-2011 Activities

The Deep Burn (DB) Project is a U.S. Department of Energy sponsored feasibility study of Transuranic Management using high burnup fuel in the high temperature helium cooled reactor (HTR). The DB Project consists of seven tasks: project management, core and fuel analysis, spent fuel management, fuel cycle integration, TRU fuel modeling, TRU fuel qualification, and HTR fuel recycle. In the Phase II of the Project, we conducted nuclear analysis of TRU destruction/utilization in the HTR prismatic block design (Task 2.1), deep burn fuel/TRISO microanalysis (Task 2.3), and synergy with fast reactors (Task 4.2). The Task 2.1 covers the core physics design, thermo-hydraulic CFD analysis, and the thermofluid and safety analysis (low pressure conduction cooling, LPCC) of the HTR prismatic block design. The Task 2.3 covers the analysis of the structural behavior of TRISO fuel containing TRU at very high burnup level, i.e. exceeding 50% of FIMA. The Task 4.2 includes the self-cleaning HTR based on recycle of HTR-generated TRU in the same HTR. Chapter IV contains the design and analysis results of the 600MWth DB-HTR core physics with the cycle length, the average discharged burnup, heavy metal and plutonium consumptions, radial and axial power distributions, temperature reactivity coefficients. Also, it contains the analysis results of the 450MWth DB-HTR core physics and the analysis of the decay heat of a TRU loaded DB-HTR core. The evaluation of the hot spot fuel temperature of the fuel block in the DB-HTR (Deep-Burn High Temperature Reactor) core under full operating power conditions are described in Chapter V. The investigated designs are the 600MWth and 460MWth DB-HTRs. In Chapter VI, the thermo-fluid and safety of the 600MWth DB-HTRs has been analyzed to investigate a thermal-fluid design performance at the steady state and a passive safety performance during an LPCC event. Chapter VII describes the analysis results of the TRISO fuel microanalysis of the 600MWth and 450MWth DB-HTRs. The TRISO fuel microanalysis covers the gas pressure buildup in a coated fuel particle including helium production, the thermo-mechanical behavior of a CFP, the failure probabilities of CFPs, the temperature distribution in a CPF, and the fission product (FP) transport in a CFP and a graphite. In Chapter VIII, it contains the core design and analysis of sodium cooled fast reactor (SFR) with deep burn HTR reactor. It considers a synergistic combination of the DB-MHR and an SFR burner for a safe and efficient transmutation of the TRUs from LWRs. Chapter IX describes the design and analysis results of the self-cleaning (or self-recycling) HTR core. The analysis is considered zero and 5-year cooling time of the spent LWR fuels.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Quantifying Impacts of Renewable Electricity Deployment on Air Quality and Human Health in Southeast Asia Based on Aims III Scenarios

Exposure to outdoor air pollution is the largest environmental risk factor for death and disease worldwide, associated with millions of cases of excess deaths (mortality) each year. Although there are many pollutants in the air that affect our health, the most important class of pollutants is fine particulate matter, PM 2.5 , which are airborne particles of diameter ≤2.5 micrometers (µm). These particles are small enough to deposit deep in the respiratory system where they can then enter the bloodstream, traveling and causing damage to other bodily systems. Exposure to outdoor (ambient) PM 2.5 has been found to be the most important environmental risk factor for mortality in Southeast Asia, associated with 130,000 - 320,000 excess deaths in Association of Southeast Asian Nations (ASEAN) member countries in 2019. Southeast Asia, especially its mega-cities, but also other areas, has some of the worst air quality in the world. Almost all human activity emits air pollutants. Fine particulate matter is both directly emitted and formed in the atmosphere through chemical reactions, the latter of which requires modeling to predict. Power generation is one of the major sources of air pollutants that lead to elevated concentrations of fine particulate matter, including in Southeast Asia. Fossil fuel combustion for power generation, especially coal but also diesel, is the main source of air pollutant emissions from power generation. While natural gas burns cleaner than coal or diesel, in the quantities combusted for power generation in Southeast Asia, it is also a significant emitter. This study augments the ASEAN Interconnection Masterplan Study III (AIMS III) by quantifying changes to air quality and human health that result from its renewable integration and transmission interconnection scenarios. Performing this analysis requires translation of the changes in projected generation from different power sector fuel sources in the AIMS III scenarios to changes in air pollutant emissions, developing what's known as an emissions inventory for each scenario and year evaluated. We then use for the first time a new global, reduced-complexity air quality model to transform the changes in emissions to changes in air pollutant concentration of the deadliest air pollutant for human health, fine particulate matter (or PM 2.5 ). The air quality model, Global InMAP, then utilizes the location of human population in ASEAN countries to calculate exposure to PM 2.5 concentration changes and translates that to estimates of excess mortality attributable to the AIMS III scenarios.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

High Temperature Reactor (HTR) Deep Burn Core and Fuel Analysis: Design Selection for the Prismatic Block Reactor

The Deep Burn (DB) Project is a U.S. Department of Energy sponsored feasibility study of Transuranic Management using high burnup fuel in the high temperature helium cooled reactor (HTR). The DB Project consists of seven tasks: project management, core and fuel analysis, spent fuel management, fuel cycle integration, TRU fuel modeling, TRU fuel qualification, and HTR fuel recycle. In the Phase II of the Project, we conducted nuclear analysis of TRU destruction/utilization in the HTR prismatic block design (Task 2.1), deep burn fuel/TRISO microanalysis (Task 2.3), and synergy with fast reactors (Task 4.2). The Task 2.1 covers the core physics design, thermo-hydraulic CFD analysis, and the thermofluid and safety analysis (low pressure conduction cooling, LPCC) of the HTR prismatic block design. The Task 2.3 covers the analysis of the structural behavior of TRISO fuel containing TRU at very high burnup level, i.e. exceeding 50% of FIMA. The Task 4.2 includes the self-cleaning HTR based on recycle of HTR-generated TRU in the same HTR. Chapter IV contains the design and analysis results of the 600MWth DB-HTR core physics with the cycle length, the average discharged burnup, heavy metal and plutonium consumptions, radial and axial power distributions, temperature reactivity coefficients. Also, it contains the analysis results of the 450MWth DB-HTR core physics and the analysis of the decay heat of a TRU loaded DB-HTR core. The evaluation of the hot spot fuel temperature of the fuel block in the DB-HTR (Deep-Burn High Temperature Reactor) core under full operating power conditions are described in Chapter V. The investigated designs are the 600MWth and 460MWth DB-HTRs. In Chapter VI, the thermo-fluid and safety of the 600MWth DB-HTRs has been analyzed to investigate a thermal-fluid design performance at the steady state and a passive safety performance during an LPCC event. Chapter VII describes the analysis results of the TRISO fuel microanalysis of the 600MWth and 450MWth DB-HTRs. The TRISO fuel microanalysis covers the gas pressure buildup in a coated fuel particle including helium production, the thermo-mechanical behavior of a CFP, the failure probabilities of CFPs, the temperature distribution in a CPF, and the fission product (FP) transport in a CFP and a graphite. In Chapter VIII, it contains the core design and analysis of sodium cooled fast reactor (SFR) with deep burn HTR reactor. It considers a synergistic combination of the DB-MHR and an SFR burner for a safe and efficient transmutation of the TRUs from LWRs. Chapter IX describes the design and analysis results of the self-cleaning (or self-recycling) HTR core. The analysis is considered zero and 5-year cooling time of the spent LWR fuels.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Engineered barrier material interactions at elevated temperatures: Bentonite-metal interactions under elevated temperature conditions

The development of deep repository concepts in the USA is evaluating generic options for disposal of heat-generating nuclear spent nuclear fuel (SNF) waste for a suite of host rock media (clay rock, granite, salt). Large waste canister designs (e.g., dual purpose canisters or DPC’s) are currently being considered to accommodate many SNF assemblies. Large amounts of SNF in the waste packages will produce high thermal loads generating temperatures in excess of 200 °C for long periods of time. For a bentonite backfilled repository concept, prolonged exposure to high temperatures will induce chemical reactions in the engineered barrier system (EBS), particularly at barrier interfaces. Our focus is on experimental investigations and the application of thermodynamic modeling to evaluate clay-zeolite phase equilibria as a function of temperature and fluid chemistry. Experimental work on barrier material interactions under hydrothermal conditions (150 – 300 °C, 15-16 MPa) has elucidated mineral phase changes in Wyoming (Colony mine) bentonite in the presence of steel phases. Glassy material in bentonite is replaced by analcime-wairakite phases, and through apparent clinoptilolite recrystallization. The initial increase in dissolved silica leads to authigenic quartz formation. Such mineral assemblage suggests an initially silica-rich environment (analcime, clinoptilolite) moving towards Si-depleted conditions. Analcime-wairakite compositions suggest a well-defined solid-solution between these Na and Ca end-members. Smectite clay in these experiments is stable with Fe-saponite and chlorite growth co-existing with binary/ternary sulfides at steel interfaces. Little or no illite was observed in the reaction products which could be tied to silica oversaturation and low K in the system. The thermodynamic analysis is used to evaluate thermodynamic data and develop phase diagrams to describe stability field relations of secondary mineral phase occurrences. This analysis allows for delineation of potential reaction pathways in bentonite clay degradation and interactions with metallic phases. One example of this is the important role of dissolved silica plus other phase components to the formation of alteration mineralogy observed in these interactions. All these investigations are key to the assessment of thermally-induced degradation zones in the EBS during the thermal period and their effect on barrier performance in the safety assessment.

Jove-Colon, Carlos↗

Homogeneous, Micron-Scale High-Energy-Density Matter Generated by Relativistic Laser-Solid Interactions

Short-pulse, laser-solid interactions provide a unique platform for studying complex high-energy-density mat ter. We present the first demonstration of solid density, micron-scale keV plasmas uniformly heated by a high contrast, 400 nm laser at intensities up to 2×10 21 W/cm 2 . High-resolution spectral analysis of X-ray emission reveals uniform heating up to 3.0 keV over 1 µm depths. Particle-in-cell simulations indicate the production of a uniformly heated keV plasma to depths of 2 µm. The significant bulk heating and presence of highly-ionized ions deep within the target are attributed to the few MeV hot electrons that become trapped and undergo refluxing within the target sheath fields. In conclusion, these conditions enable the differentiation of atomic physics models such as ionization potential depression in high energy density environments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

AI Meets Exascale Computing: Advancing Cancer Research With Large-Scale High Performance Computing

The application of data science in cancer research has been boosted by major advances in three primary areas: (1) Data: diversity, amount, and availability of biomedical data; (2) Advances in Artificial Intelligence (AI) and Machine Learning (ML) algorithms that enable learning from complex, large-scale data; and (3) Advances in computer architectures allowing unprecedented acceleration of simulation and machine learning algorithms. These advances help build in silico ML models that can provide transformative insights from data including: molecular dynamics simulations, next-generation sequencing, omics, imaging, and unstructured clinical text documents. Unique challenges persist, however, in building ML models related to cancer, including: (1) access, sharing, labeling, and integration of multimodal and multi-institutional data across different cancer types; (2) developing AI models for cancer research capable of scaling on next generation high performance computers; and (3) assessing robustness and reliability in the AI models. In this paper, we review the National Cancer Institute (NCI) -Department of Energy (DOE) collaboration, Joint Design of Advanced Computing Solutions for Cancer (JDACS4C), a multi-institution collaborative effort focused on advancing computing and data technologies to accelerate cancer research on three levels: molecular, cellular, and population. This collaboration integrates various types of generated data, pre-exascale compute resources, and advances in ML models to increase understanding of basic cancer biology, identify promising new treatment options, predict outcomes, and eventually prescribe specialized treatments for patients with cancer.

60 APPLIED LIFE SCIENCES↗

Predictive understanding of the surface tension and velocity of sound in ionic liquids using machine learning

Knowledge of the physical properties of ionic liquids (ILs), such as the surface tension and speed of sound, is important for both industrial and research applications. Unfortunately, technical challenges and costs limit exhaustive experimental screening efforts of ILs for these critical properties. Previous work has demonstrated that the use of quantum-mechanics-based thermochemical property prediction tools, such as the conductor-like screening model for real solvents, when combined with machine learning (ML) approaches, may provide an alternative pathway to guide the rapid screening and design of ILs for desired physiochemical properties. However, the question of which machine-learning approaches are most appropriate remains. In the present study, we examine how different ML architectures, ranging from tree-based approaches to feed-forward artificial neural networks, perform in generating nonlinear multivariate quantitative structure–property relationship models for the prediction of the temperature- and pressure-dependent surface tension of and speed of sound in ILs over a wide range of surface tensions (16.9–76.2 mN/m) and speeds of sound (1009.7–1992 m/s). The ML models are further interrogated using the powerful interpretation method, shapley additive explanations. We find that several different ML models provide high accuracy, according to traditional statistical metrics. The decision tree-based approaches appear to be the most accurate and precise, with extreme gradient-boosting trees and gradient-boosting trees being the best performers. However, our results also indicate that the promise of using machine-learning to gain deep insights into the underlying physics driving structure–property relationships in ILs may still be somewhat premature.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗

DOE FAIR Surrogate Benchmarks Supporting AI and Simulation Research (SBI Surrogate Benchmark Initiative) (Final Report)

Computational Science is being revolutionized by integrating AI and simulation and, in particular, by deep learning surrogate models that can replace all or part of traditional large‐scale HPC computations. Such surrogates can achieve remarkable performance improvements, as much as several orders of magnitude, and save both compute time and energy. The Surrogate Benchmark Initiative (SBI) project creates a community repository and FAIR (Findable, Accessible, Interoperable, and Reusable) data ecosystem for HPC application surrogate benchmarks. The SBI team comes from Argonne National Laboratory (ANL), Indiana University (IU), Rutgers University, the University of Tennessee, Knoxville (UTK), and the University of Virginia(UVA). SBI repositories include data, code, and all relevant collateral artifacts, that the science and engineering community needs to use and reuse these data sets and surrogates. SBI repositories generate active research from both participants in SBI and the broader AI and domain science communities. This project develops surrogates that use several different neural nets to learn and quickly infer the results of simulations and data systems and capture them as surrogate benchmarks with a rich set of metadata, covering. Data; Model; Metrics specification; Machine specification; Science, Speed, Power Results, We research FAIR metadata for these benchmarks. We develop application surrogate examples as benchmarks across many fields (ANL, UTK, IU, UVA). We also study non Surrogate benchmarks that have many common features and similar issues regarding FAIRness. We work with MLCommons (UVA, UTK), which is a major machine learning benchmarking activity where we get metadata ontologies, software, and benchmarks, benchmarks have datasets, models, and metadata, and they need a technical framework developed by UTK and Rutgers and deployed by UVA. We study features of Surrogates, including performance, training set size, and uncertainty quantification (Rutgers, UVA and IU).

97 MATHEMATICS AND COMPUTING↗

FAIR Surrogate Benchmarks Supporting AI and Simulation Research (Final Report)

Computational Science is being revolutionized by integrating AI and simulation and, in particular, by deep learning surrogate models that can replace all or part of traditional large‐scale HPC computations. Such surrogates can achieve remarkable performance improvements, as much as several orders of magnitude, and save both compute time and energy. The Surrogate Benchmark Initiative (SBI) project creates a community repository and FAIR (Findable, Accessible, Interoperable, and Reusable) data ecosystem for HPC application surrogate benchmarks. The SBI team comes from Argonne National Laboratory (ANL), Indiana University (IU), Rutgers University, the University of Tennessee, Knoxville (UTK), and the University of Virginia (UVA). SBI repositories include data, code, and all relevant collateral artifacts that the science and engineering community need to use and reuse these data sets and surrogates. SBI repositories generate active research from both the participants in SBI and the broad community of AI and domain scientists. This project develops surrogates that use several different neural nets to learn and quickly infer the results of simulations and data systems and captures them as surrogate benchmarks with a rich set of metadata covering: Data; Model; Metrics specification; Machine specification; and Science, Speed, and Power Results. We research FAIR metadata for these benchmarks. We develop application surrogate examples as benchmarks across many fields (ANL, UTK, IU, UVA). We also study non-Surrogate benchmarks that have many common features and similar issues as regards FAIRness. We work with MLCommons (UVA, UTK), which is a major machine learning benchmarking activity where we get metadata ontologies, software, and benchmarks, Benchmarks have datasets, models, and metadata and they need a technical framework developed by UTK and Rutgers and deployed by UVA. We study features of Surrogates including performance, training set size, and uncertainty quantification (Rutgers, UVA and IU).

97 MATHEMATICS AND COMPUTING↗

Induced seismicity in geothermal reservoirs: A review of forecasting approaches

In order to reach Europe's 2020 and 2050 targets in terms of greenhouse gas emissions, geothermal resources will have to contribute substantially to meeting carbon-free energy needs. However, public opinion may prevent future large-scale application of deep geothermal power plants, because induced seismicity is often perceived as an unsolicited and uncontrollable side effect of geothermal development. In the last decade, significant advances were made in the development of models to forecast induced seismicity, which are either based on catalogues of induced seismicity, on the underlying physical processes, or on a hybrid philosophy. In this paper, we provide a comprehensive overview of the existing approaches applied to geothermal contexts. This overview will outline the advantages and drawbacks of the different approaches, identify the gaps in our understanding, and describe the needs for geothermal observations. Most of the forecasting approaches focus on the stimulation phase of enhanced geothermal systems which are most prone to generate seismic events. Besides the statistical models suited for real-time applications during reservoir stimulation, the physics-based models have the advantage of considering sub-surface characteristics and estimating the impact of fluid circulation on the reservoir. Thus, to mitigate induced seismicity during major hydraulic stimulations, application of hybrid methods in a decision support system seems the best available solution. So far, however, little attention has been paid to geochemical effects on the failure process and to production periods. Quantitative modelling of induced seismicity still is a challenging and complex matter. Appropriate resources remain to be invested for the scientific community to continue its research and development efforts to successfully forecast induced seismicity in geothermal fields. This is a prerequisite for making this renewable energy resource sustainable and accessible worldwide.

58 GEOSCIENCES↗

Efficient Optimization of Energy Recovery From Geothermal Reservoirs With Recurrent Neural Network Predictive Models

Improving the long-term energy production performance of geothermal reservoirs can be accomplished by optimizing field development and management plans. Reliable prediction models, however, are needed to evaluate and optimize the performance of the underlying reservoirs under various operation and development strategies. In traditional frameworks, physics-based simulation models are used to predict the energy production performance of geothermal reservoirs. However, detailed simulation models are not trivial to construct, require a reliable description of the reservoir conditions and properties, and entail high computational complexity. Data-driven predictive models can offer an efficient alternative for use in optimization workflows. This paper presents an optimization framework for net power generation in geothermal reservoirs using a variant of the recurrent neural network (RNN) as a data-driven predictive model. The RNN architecture is developed and trained to replace the simulation model for computationally efficient prediction of the objective function and its gradients with respect to the well control variables. The net power generation performance of the field is optimized by automatically adjusting the mass flow rate of production and injection wells over 12 years, using a gradient-based local search algorithm. Two field-scale examples are presented to investigate the performance of the developed data-driven prediction and optimization framework. Furthermore, the prediction and optimization results from the RNN model are evaluated through comparison with the results obtained by using a numerical simulation model of a real geothermal reservoir.

15 GEOTHERMAL ENERGY↗