Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed computing, machine learning”

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 775 records · Page 43

Streaming Matching and Edge Cover in Practice

Graph algorithms with polynomial space and time requirements often become infeasible for massive graphs with billions of edges or more. State-of-the-art approaches therefore employ approximate serial, parallel, and distributed algorithms to tackle these challenges. However, such approaches require storing the entire graph in memory and thus need access to costly computing resources such as clusters and supercomputers. In this paper, we present practical streaming approaches for solving massive graph problems using limited memory for two prototypical graph problems: maximum weighted matching and minimum weighted edge cover. For matching, we conduct a thorough computational study on two of the semi-streaming algorithms including a recent breakthrough result that achieves a $1/(2+\varepsilon)$-approximation of the weight while using $O( n \log W /\epsilon)$ memory (here $n$ is the number of vertices and $W$ is the maximum edge weight), designed by Paz and Schwartzman [SODA, 2017]. Empirically, we show that the semi-streaming algorithms produce matchings whose weight is close to the best $1/2$-approximate offline algorithm while requiring less time and an order-of-magnitude less memory. For minimum weighted edge cover, we develop three novel semi-streaming algorithms. Two of these algorithms require a single pass through the input graph, require $O(n \log n)$ memory, and provide a 2-approximation guarantee on the objective. We also leverage a relationship between approximate maximum weighted matching and approximate minimum weighted edge cover to develop a two-pass $3/2+\epsilon$-approximate algorithm with the memory requirement of Paz and Schwartzman's semi-streaming matching algorithm. These streaming approaches are compared against the state-of-the-art 3/2-approximate offline algorithm. The semi-streaming matching and the novel edge cover algorithms proposed in this paper can process graphs with several billions of edges in under 30 minutes using 6 GB of memory, which is at least an order of magnitude improvement from the offline (non-streaming) algorithms. For the largest graph, the best alternative offline parallel approximation algorithm (GPA+ROMA) could not finish in three hours even while employing hundreds of processors and 1 TB of memory. We also demonstrate an application of the semi-streaming algorithm by computing a matching using linearly bounded memory on item intersection graphs derived from three machine learning datasets, whereas the existing offline algorithms could not complete on one of these datasets since their memory requirements exceeded 1TB.

Ferdous, S M.↗

Coordinated Ramping Product and Regulation Reserve Procurements in CAISO and MISO using Multi-Scale Probabilistic Solar Power Forecasts (Pro2R)

How can probabilistic solar forecasts lower costs and improve reliability for independent system operator (ISO) markets? We tackle this question in three steps. First, we enhance an existing solar forecasting system to provide well-calibrated hours-ahead probabilistic forecasts. We then relate the degree of uncertainty in those forecasts to error distributions for net load ramps for the California ISO (CAISO) using statistical and machine learning methods. Projected net load errors conditioned on solar uncertainty are translated into flexible ramp requirements that therefore reflect real-time meteorological and solar conditions, improving on typical ISO procedures. Finally, a multi-period look-ahead production cost model quantifies how conditional ramp requirements can a) decrease operating costs by lowering requirements compared to often conservative unconditional methods, and b) reduce generation scarcity events and consequently improve reliability by increasing flexibility requirements at times when unconditional forecast-based requirements understate actual ramp uncertainty. In addition to the products just described (quantification of solar uncertainty, its translation into requirements for ramp capability product, and quantification of the benefits of more accurate ramp requirements), this project also developed a visualization system that alerts system operators of ramp and uncertainty conditions within the network based on solar forecasts. The system is called Resource Forecast and Ramp Visualization for Situational Awareness (RaVIS). These four products represent significant advances in the state-of-the-art of probabilistic solar forecasting, development of weather-informed reserve requirements, production costing methods for estimating the benefits of more accurate reserve requirements, and visualization of system status, respectively. Yet the products are also practical and can be immediately implemented, potentially enabling system operators to save millions of dollars in ramp product procurement costs per year.

14 SOLAR ENERGY↗

Affine Transformations to Correlate Experimental and Simulated EDS Spectra for Multi-Element Systems

Energy Dispersive X-ray Spectroscopy (EDS) is an essential technique for determining elemental concentrations and distributions within microstructures, critical for materials discovery, optimization, and qualification. However, most published EDS data is qualitative because current quantitative EDS analysis methods require extensive calibration and post-processing, limiting their practicality and widespread adoption. This work seeks to establish a framework for accelerated EDS characterization and spectrum analysis that can leverage ML to analyze correlations between various elemental compositions and resulting EDS spectra. The complex physics and data result in a high-dimensional problem that grows exponentially with the number of elements in the system and the complexity of the spectrum analysis. ML provides a way to compute and optimize the results of this highly dimensional problem in a flexible way to tailor it to the user’s specific needs and material system. However, the framework emphasizes transparency through a strictly mathematical affine transformation, so the analysis remains understandable and reviewable to facilitate adoption by the scientific community. While currently implemented methods are simplistic and unvalidated, further development and demonstration of this framework could enable high-throughput, accurate, and accessible EDS characterization.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Probabilistic Nanomagnetic Memories for Uncertain and Robust Machine Learning

This project evaluated the use of emerging spintronic memory devices for robust and efficient variational inference schemes. Variational inference (VI) schemes, which constrain the distribution for each weight to be a Gaussian distribution with a mean and standard deviation, are a tractable method for calculating posterior distributions of weights in a Bayesian neural network such that this neural network can also be trained using the powerful backpropagation algorithm. Our project focuses on domain-wall magnetic tunnel junctions (DW-MTJs), a powerful multi-functional spintronic synapse design that can achieve low power switching while also opening the pathway towards repeatable, analog operation using fabricated notches. Our initial efforts to employ DW-MTJs as an all-in-one stochastic synapse with both a mean and standard deviation didn’t end up meeting the quality metrics for hardware-friendly VI. In the future, new device stacks and methods for expressive anisotropy modification may make this idea still possible. However, as a fall back that immediately satisfies our requirements, we invented and detailed how the combination of a DW-MTJ synapse encoding the mean and a probabilistic Bayes-MTJ device, programmed via a ferroelectric or ionically modifiable layer, can robustly and expressively implement VI. This design includes a physics-informed small circuit model, that was scaled up to perform and demonstrate rigorous uncertainty quantification applications, up to and including small convolutional networks on a grayscale image classification task, and larger (Residual) networks implementing multi-channel image classification. Lastly, as these results and ideas all depend upon the idea of an inference application where weights (spintronic memory states) remain non-volatile, the retention of these synapses for the notched case was further interrogated. These investigations revealed and emphasized the importance of both notch geometry and anisotropy modification in order to further enhance the endurance of written spintronic states. In the near future, these results will be mapped to effective predictions for room temperature and elevated operation DW-MTJ memory retention, and experimentally verified when devices become available.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Improving Cyber Situational Understanding

Effective cybersecurity operations require the ability to analyze large amounts of information to assess security risks and formulate defensive strategies against adversaries. This has become more complex in recent years as the sprawl and interconnectivity of devices grows through implementation of virtualization, cloud computing, and Internet of Things (IoT). The amount of data and analysis required for effective cybersecurity command and control decisions far exceeds humans’ capacity to perform manually. We characterize the analysis problem as cyber situational understanding. The research presented to improve cyber situational understanding focuses on vulnerability analysis and threat intelligence. Regarding vulnerabilities, entities must analyze and plan work for between thousands and tens of thousands of software vulnerabilities annually. Entities heavily use network firewalls to limit vulnerability exposure. As a result, some of these vulnerabilities permit exposure to adversarial exploitation, whereas others are inaccessible and therefore present negligible risk of exploitation. Distinguishing between high and low risk software vulnerabilities requires a deep understanding of the vulnerability, network firewall protection, and characteristics of the targeted device. This problem is solved by extracting network service features from vulnerability data features using both machine-learning and natural language processing. Then, the network firewall topology is parsed to determine which vulnerabilities are reachable by adversaries. Ultimately, a state-based safety analysis ascertains which vulnerabilities are unsafe. A related vulnerability analysis problem occurs in cybersecurity operations when associating an entity’s hardware and software assets to public vulnerability databases. Assets often reveal hardware and software through installation artifacts and network service identification, and entities store these artifacts in inventory databases. However, software and hardware vendors apply a standard Common Platform Enumeration (CPE) naming convention when publicly reporting vulnerabilities. Associating these two datasets often requires many hours to days of manual inspection. The proposed solution automates the mapping approach of human analysts using fuzzy matching techniques, natural language processing, and, ultimately, machine learning to present a small set of recommendations for mapping the two datasets. The result significantly reduces human analysis time and reduces the occurrence of false positives in vulnerability notifications. Finally, cyber threat intelligence (CTI) requires associating cyber observable artifacts, such as IP addresses, URIs, and file hashes, with cyber threat tactics, techniques, and procedures. Unfortunately, most CTI data is compartmentalized across multiple organizations and cannot be shared due to the legal and reputational risk with cyber threat being associated with the entity. The approach to solving this problem inovlves using a distributed ledger with anonymous token spending and authentication. This allows a consortium of semi-trusted entities to share the workload of curating CTI for a threat sharing community’s cooperative benefit.

Huff, Philip↗

Automated detection and analysis of particle beams in laser-plasma accelerator simulations

Numerical simulations of laser-plasma wakefield (particle) accelerators model the acceleration of electrons trapped in plasma oscillations (wakes) left behind when an intense laser pulse propagates through the plasma. The goal of these simulations is to better understand the process involved in plasma wake generation and how electrons are trapped and accelerated by the wake. Understanding of such accelerators, and their development, offer high accelerating gradients, potentially reducing size and cost of new accelerators. One operating regime of interest is where a trapped subset of electrons loads the wake and forms an isolated group of accelerated particles with low spread in momentum and position, desirable characteristics for many applications. The electrons trapped in the wake may be accelerated to high energies, the plasma gradient in the wake reaching up to a gigaelectronvolt per centimeter. High-energy electron accelerators power intense X-ray radiation to terahertz sources, and are used in many applications including medical radiotherapy and imaging. To extract information from the simulation about the quality of the beam, a typical approach is to examine plots of the entire dataset, visually determining the adequate parameters necessary to select a subset of particles, which is then further analyzed. This procedure requires laborious examination of massive data sets over many time steps using several plots, a routine that is unfeasible for large data collections. Demand for automated analysis is growing along with the volume and size of simulations. Current 2D LWFA simulation datasets are typically between 1GB and 100GB in size, but simulations in 3D are of the order of TBs. The increase in the number of datasets and dataset sizes leads to a need for automatic routines to recognize particle patterns as particle bunches (beam of electrons) for subsequent analysis. Because of the growth in dataset size, the application of machine learning techniques for scientific data mining is increasingly considered. In plasma simulations, Bagherjeiran et al. presented a comprehensive report on applying graph-based techniques for orbit classification. They used the KAM classifier to label points and components in single and multiple orbits. Love et al. conducted an image space analysis of coherent structures in plasma simulations. They used a number of segmentation and region-growing techniques to isolate regions of interest in orbit plots. Both approaches analyzed particle accelerator data, targeting the system dynamics in terms of particle orbits. However, they did not address particle dynamics as a function of time or inspected the behavior of bunches of particles. Ruebel et al. addressed the visual analysis of massive laser wakefield acceleration (LWFA) simulation data using interactive procedures to query the data. Sophisticated visualization tools were provided to inspect the data manually. Ruebel et al. have integrated these tools to the visualization and analysis system VisIt, in addition to utilizing efficient data management based on HDF5, H5Part, and the index/query tool FastBit. In Ruebel et al. proposed automatic beam path analysis using a suite of methods to classify particles in simulation data and to analyze their temporal evolution. To enable researchers to accurately define particle beams, the method computes a set of measures based on the path of particles relative to the distance of the particles to a beam. To achieve good performance, this framework uses an analysis pipeline designed to quickly reduce the amount of data that needs to be considered in the actual path distance computation. As part of this process, region-growing methods are utilized to detect particle bunches at single time steps. Efficient data reduction is essential to enable automated analysis of large data sets as described in the next section, where data reduction methods are steered to the particular requirements of our clustering analysis. Previously, we have described the application of a set of algorithms to automate the data analysis and classification of particle beams in the LWFA simulation data, identifying locations with high density of high energy particles. These algorithms detected high density locations (nodes) in each time step, i.e. maximum points on the particle distribution for only one spatial variable. Each node was correlated to a node in previous or later time steps by linking these nodes according to a pruned minimum spanning tree (PMST). We call the PMST representation 'a lifetime diagram', which is a graphical tool to show temporal information of high dense groups of particles in the longitudinal direction for the time series. Electron bunch compactness was described by another step of the processing, designed to partition each time step, using fuzzy clustering, into a fixed number of clusters.

43 PARTICLE ACCELERATORS↗

HyMARC Seedling: Optimized Hydrogen Adsorbents via Machine Learning and Crystal Engineering

This final report is presented in two parts: In Part 1, the H 2 capacities of a diverse set of 918,734 metal-organic frameworks (MOFs) sourced from 19 databases is predicted via machine learning (ML). Using only 7 structural features as input, ML identifies 8,282 MOFs with the potential to exceed the capacities of state-of-the-art materials. The identified MOFs are predominantly hypothetical compounds having low densities (<0.31 g/cm3) in combination with high surface areas (>5,300 m2/g), void fractions ($0.90), and pore volumes (>3.3 cm3/g). The relative importance of the input features are characterized, and dependencies on the ML algorithm and training set size are quantified. The most important features for predicting H 2 uptake are pore volume (for gravimetric capacity) and void fraction (for volumetric capacity). The ML models are available on the web, allowing for rapid and accurate predictions of the hydrogen capacities of MOFs from limited structural data; the simplest models require only a single crystallographic feature. In part 2, ways to improve the poor powder packing density of MOFs is discussed. More specifically, a strategy that improves packing efficiency and volumetric hydrogen gas storage density dramatically through engineered morphologies and controlled-crystal size distributions is presented that holds promise for maximizing storage capacity for a given MOF. The packing density improvement, demonstrated for the benchmark sorbent MOF-5, leads to a significant enhancement of volumetric hydrogen storage performance relative to commercial MOF-5. System model projections demonstrate that engineering of crystal morphology/size or use of a bimodal distribution of cubic crystal sizes in tandem with system optimization can surpass the 25 g/L volumetric capacity of a typical 700 bar compressed storage system and exceed the DOE targets 2020 volumetric capacity (30 g/L). Finally, a critical link between improved powder packing density and reduced damage upon compaction is revealed leading to sorbents with both high surface area and high density.

08 HYDROGEN↗

Artificial Intelligence/Machine Learning Technology in Power System Applications

The primary purpose of this report is to provide an overview of the advancement in artificial intelligence and machine learning (AI/ML) technologies and their applications in power systems. It offers a foundation for understanding the transformative role of AI/ML in power systems and aims to stimulate further research and development in this area. This report begins with a historical perspective of AI/ML technologies, then explores their advancement to today’s prominence. The document highlights key contributors to the success of AI/ML technologies, including increased computational power, greater data availability, innovative algorithms, and advanced tools. It further introduces various AI/ML techniques, including supervised, unsupervised and reinforcement learning, graph neural networks, and generative AI. It also emphasizes the critical importance of ensuring the safety, security, and trustworthiness of these AI/ML techniques within this sector. The report reviews the recent representative advancements in various power system applications enhanced by AI/ML techniques, underscoring key developments and their transformative impact as evidenced by numerous studies. It also explores both the opportunities and challenges associated with the application of AI/ML technologies to improve power system applications. While the report extensively covers AI/ML applications in power systems, focusing primarily on the technical and operational aspects, it may not thoroughly explore the sociopolitical, economic, and broader regulatory implications of AI/ML integration in power systems. AI/ML techniques hold significant potential for enhancing power system applications; however, they are not omnipotent. It is crucial to acknowledge their limitations and understand that they may not be able to address all challenges in the power system domain. Various factors must be considered that influence the implementation, adoption, and effectiveness of AI/ML solutions, including but not limited to safety, security, transparency, and trustworthiness. Additionally, the incorporation of advanced human–machine interfaces is essential, as it enables humans to validate the effectiveness of AI/ML solutions while remaining actively engaged, fostering trust in AI/ML deployment. Finally, the report summarizes AI/ML research activities supported by the Department of Energy (DOE) Office of Electricity (OE) through the Advanced Grid Modeling (AGM) program. The work aligns with the interests and mission of DOE-OE AGM, with the report serving as a resource for identifying existing progress and for pinpointing future applications within AI/ML that need further exploration and support.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Unveiling and Mapping Polymorphs in Fluorite Y2TiO5 Using 4D-STEM and Unsupervised Machine Learning

Y2TiO5 belongs to the Ln2TiO5 (Ln = lanthanide or Y) family of ceramic materials and exhibits a range of desirable material properties such as radiation tolerance, frustrated magnetism, and large dielectric constant. However, understanding the complex crystal structure of Y2TiO5 remains elusive, given that Y2TiO5 can adopt multiple polymorphs such as cubic, orthorhombic, and hexagonal phases within the lattice. In this work, we report a detailed structural analysis of Y2TiO5 using four-dimensional scanning transmission electron microscopy coupled with unsupervised machine learning. The pyrochlore nanodomains, characterized by the ordered arrangement of yttrium cations on the A site of their A2BO5 structure, are present within the matrix of a predominantly fluorite-structured Y2TiO5 along with a third polymorph, the hexagonal phase. The pyrochlore phase is found to form 2 nm boundary regions around hexagonal phase stacking faults, highlighting the potential influence of the hexagonal phase on the occurrence and distribution of the pyrochlore phase. Lastly, we identify a unique pyrochlore phase with asymmetric arrangement of cation ordering along a single planar direction. Our findings provide invaluable insights into the possible mechanisms stabilizing pyrochlore nanodomains within the fluorite lattice of Y2TiO5.

36 MATERIALS SCIENCE↗

Generative modeling enables molecular structure retrieval from Coulomb explosion imaging

Capturing the structural changes that molecules undergo during chemical reactions in real space and time is a long-standing dream and an essential prerequisite for understanding and ultimately controlling femtochemistry. A key approach to tackle this challenging task is Coulomb explosion imaging, which benefited decisively from recently emerging high-repetition-rate X-ray free-electron laser sources. With this technique, information on the molecular structure is inferred from the momentum distributions of the ions produced by the rapid Coulomb explosion of molecules. Retrieving molecular structures from these distributions poses a highly non-linear inverse problem that remains unsolved for molecules consisting of more than a few atoms. Here, we address this challenge using a diffusion-based Transformer neural network. We show that the network reconstructs unknown molecular geometries from ion-momentum distributions with a mean absolute error below one Bohr radius, which is half the length of a typical chemical bond.

Artificial Intelligence (cs.AI)↗

Denoising Seismograms in the Time Domain Using a Deep Learning Model

Deep learning has emerged as a transformative tool for enhancing the extraction of reliable information from seismograms, addressing the increasing demand for precise and efficient seismic data analysis. We introduce an innovative encoder–decoder deep learning model, named WaveDenoiser, designed for noise reduction in the time domain, thereby eliminating the need for spectrogram computations that have been used for existing deep learning tools and significantly improving processing speed. Utilizing the benchmark dataset that is Stanford Earthquake Dataset, we developed three models of varying sizes: base, medium, and large. Notably, the large (referred to as WaveDenoiser) model demonstrated superior performance, achieving a median signal‐to‐noise ratio improvement of 8.8 dB on in‐distribution unseen data (in the same geographic region) and 7.7 dB on out‐distribution unseen data (in a new geographic region), outpacing both the base and medium models. Further evaluation of the WaveDenoiser model revealed a reduction in median arrival‐time errors by 0.02 s for P waves and 0.01 s for S waves when processing waveforms prior to phase picking using PhaseNet on in‐distribution unseen data. When tested on out‐distribution unseen data, the model also effectively reduced the P‐wave median arrival‐time error by 0.02 and 0.01 s in median arrival‐time error for S waves. Importantly, the application of WaveDenoiser resulted in a significant reduction of phase picking outliers by 1.1% to 3.6% for both P and S waves. In addition, we achieved over five times acceleration in processing speed compared with the seisBench implementation of DeepDenoiser. Our findings underscore the potential of WaveDenoiser as a powerful tool for improving seismic data analysis and processing efficiency.

P-waves↗

Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN

Physics-informed neural network (PINN) has been successfully applied in solving a variety of nonlinear non-convex forward and inverse problems. However, the training is challenging because of the non-convex loss functions and the multiple optima in the Bayesian inverse problem. In this work, we propose a multi-variance replica exchange stochastic gradient Langevin dynamics method to tackle the challenge of the multiple local optima in the optimization and the challenge of the multiple modal posterior distribution in the inverse problem. Replica exchange methods are capable of escaping from the local traps and accelerating the convergence; two chains with different temperatures are designed where the low temperature chain aims for the local convergence, and the target of the high temperature chain is to travel globally and explore the whole loss function entropy landscape. However, it may not be efficient to solve mathematical inversion problems by using the vanilla replica method directly since the method doubles the computational cost in evaluating the forward solvers (likelihood functions) in the two chains. To address this issue, we propose to make different assumptions on the energy function estimation and this facilities one to use solvers of different fidelities in the likelihood function evaluation. More precisely, one can use a solver with low fidelity in the high temperature chain while using a solver with high fidelity in the low temperature chain. Our proposed method significantly lowers the computational cost in the high temperature chain, meanwhile preserving the accuracy and converging very fast. Here we give an unbiased estimate of the swapping rate and give an estimation of the discretization error of the scheme. To verify our idea, we design and solve four inverse problems which have multiple modes. The proposed method is also employed to train the Bayesian PINN to solve the forward and inverse problems; faster and more accurate convergence has been observed when compared to the stochastic gradient Langevin dynamics (SGLD) method and vanilla replica exchange methods.

97 MATHEMATICS AND COMPUTING↗

SMC 2021 : Analyzing Resource Utilization and User Behavior on Titan Supercomputer

Resource utilization statistics of submitted jobs on a supercomputer can help us understand how users from various scientific domains use HPC platforms and better design a job scheduler. We explore to generate insight regarding workload distribution and usage pattern domains from job scheduler trace, GPU failure information, and project-specific information collected from Titan supercomputer. Furthermore, we want to know how the scheduler performance varies over time and how the users' scheduling behavior changes following a system failure. These observations have the potential to provide valuable insight, which is helpful to prepare for system failures. These practices will help us develop and apply novel machine learning algorithms in understanding system behavior, requirement, and better scheduling of HPC systems. There are two datasets, RUR and GPU. RUR: This dataset is the job scheduler traces collected from the Titan supercomputerfrom 01/01/2015 to 07/31/2019 (2015.csv - 2019.csv). These were collected usingResource Utilization Report (RUR), a Cray-developed resource-usage data collectionand reporting system. It contains the usage information of its critical resources (CPU,Memory, GPU, and I/O) of each running job on Titan during that period [2]. ProjectAreas: Every job is associated with a project ID. TheProjectAreas.csvdatasetprovides a mapping of the project ID to its domain science. GPU: There have been some hardware-related issues in the GPUs in Titan that caused some GPUs to fail, sometimes irrecoverably during some job runs. This dataset provides information regarding these failures during the execution of the submitted jobs. GPUs on Titan are uniquely identified by a serial number (SN), and they are installed in a location. A GPU can be installed in a location, then removed from that location following a failure, and then re-installed in a different location after fixing the problem. If the failure can't be recovered, the GPU might be removed entirely from Titan. There are two prominent types of failures that resulted in the removal of GPUs from Titan: Double Bit Error (DBE) and Out of the Bus (OTB). The dataset (gc_full.csv) has the following fields: 1. SN : Serial number of a GPU 2. location : The location where it is installed 3. insert : The time when it was inserted into that location 4. remove : The time when it was removed from that location 5. duration : Amount of time the GPU spent in this location 6. out : If the device was taken out entirely w/o a re-installment into a new location. 7. event : If the GPU was taken out entirely, the reason for its removal. To learn more about this dataset, please refer to the git repositoryhttps://github.com/olcf/TitanGPULifeand the related publication [1]. References [1] George Ostrouchov, Don Maxwell, Rizwan A Ashraf, Christian Engelmann, MallikarjunShankar, and James H Rogers. Gpu lifetimes on titan supercomputer: Survival analysisand reliability. InSC20: International Conference for High Performance Computing,Networking, Storage and Analysis, pages 1-14. IEEE, 2020. [2] Feiyi Wang, Sarp Oral, Satyabrata Sen, and Neena Imam. Learning from five-yearresource-utilization data of titan system. In2019 IEEE International Conference onCluster Computing (CLUSTER), pages 1-6. IEEE, 2019.

42 ENGINEERING↗

SMC 2021 Data Challenge: Analyzing Resource Utilization and User Behavior on Titan Supercomputer

Resource utilization statistics of submitted jobs on a supercomputer can help us understand how users from various scientific domains use HPC platforms and better design a job scheduler. We explore to generate insight regarding workload distribution and usage pattern domains from job scheduler trace, GPU failure information, and project-specific information collected from Titan supercomputer. Furthermore, we want to know how the scheduler performance varies over time and how the users' scheduling behavior changes following a system failure. These observations have the potential to provide valuable insight, which is helpful to prepare for system failures. These practices will help us develop and apply novel machine learning algorithms in understanding system behavior, requirement, and better scheduling of HPC systems. There are two datasets, RUR and GPU: RUR dataset is the job scheduler traces collected from the Titan supercomputer from 01/01/2015 to 07/31/2019 (2015.csv - 2019.csv). These were collected using resource Utilization Report (RUR), a Cray-developed resource-usage data collection and reporting system. It contains the usage information of its critical resources (CPU, Memory, GPU, and I/O) of each running job on Titan during that period (https://ieeexplore.ieee.org/abstract/document/8891001). It includes ProjectAreas as additional information, every job is associated with a project ID. TheProjectAreas.csv dataset provides a mapping of the project ID to its domain science. GPU dataset has information regarding GPU failure on Titan. There have been some hardware-related issues in the GPUs in Titan that caused some GPUs to fail, sometimes irrecoverably during some job runs. This dataset provides information regarding these failures during the execution of the submitted jobs. GPUs on Titan are uniquely identified by a serial number (SN), and they are installed in a location. A GPU can be installed in a location, then removed from that location following a failure, and then re-installed in a different location after fixing the problem. If the failure can't be recovered, the GPU might be removed entirely from Titan. There are two prominent types of failures that resulted in the removal of GPUs from Titan: Double Bit Error (DBE) and Out of the Bus (OTB). The dataset (gc_full.csv) has seven attributes, we provided a short description of these attributes in the ReadMe file. To learn more about this dataset, please refer to the git repository https://github.com/olcf/TitanGPULife and the related publication (https://ieeexplore.ieee.org/abstract/document/9355319).

42 ENGINEERING↗

Facility Cybersecurity Framework Best Practices

Federal facilities are increasingly adopting automation and connecting to the Internet creating an energy-internet-of-things environment that converges operational technology (OT) and information technology (IT). Today's buildings increasingly weave together networked sensors and cyber and physical systems that enable data to be collected, aggregated, exchanged, stored and monetized in new ways. Building technological advances have created new energy technology, services, markets and value creation opportunities (e.g. transactive energy, two-way grid communications, machine learning, and increased use of renewable and distributed energy resources). But as larger data sets are being exchanged at faster speeds between an increasing number of OT systems, it becomes more difficult to protect the security of the data lifecycle and the physical equipment it interacts with. These challenges are especially difficult to overcome because the economic and environmental gain (interoperability, big data, social networks and ubiquitous information sharing) are driving these prominent trends in the digital age. Often cybersecurity is an afterthought. The U.S. Department of Energy’s (DOE) Federal Energy Management Program (FEMP) funded the Pacific Northwest National Laboratory (PNNL) to develop various cybersecurity tools, trainings, and reports to aid federal facility managers – and other building owners and operators – in better applying frameworks and lessons learned from the National Institute of Standards and Technology (NIST) Cybersecurity Framework (CSF), risk management framework (RMF), DOE’s cybersecurity capability maturity model (C2M2), and a wide variety of industry best practices and guidance documents (i.e., NIST 800 series, Department of Defense United Facilities Criteria). This set of tools, collectively known as the FEMP Facility-Related Control System Cyber Toolkit (FRCS Cyber Toolkit)2, is focused on cybersecurity concerns from facility-related control systems and other operational technology (OT), such as industrial control systems (ICS). The FRCS Cyber Toolkit can be applied across six of the sixteen critical infrastructure sectors designated by the Department of Homeland Security, including government facilities, healthcare and public health, commercial facilities (e.g., public assembly, offices, lodging), financial services (e.g., banking and insurance), emergency services (e.g., fire and police stations), and information technology. With increasingly converged IT and OT systems, it is crucial to address OT cybersecurity considerations and assess how the seam of these two systems could impact the overall cybersecurity posture of a facility. The objective of this report is to provide an overview of the best possible method to use FRCS Cyber Toolkit (section 2.0) and distilled cybersecurity best practices for the federal facilities to address growing non-linear cyber threats (section 3.0). Recommendations in this document are aggregated from several NIST and other documents (see Appendix A for additional details).

97 MATHEMATICS AND COMPUTING↗

Subsurface Characterization and Machine Learning Predictions at Brady Hot Springs Results

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells - increasing or decreasing the fluid flow rates across the wells - and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. Data and supporting literature from a study describing a new approach combining reservoir modeling and machine learning to produce models that enable strategies for the mitigation of decreased heat and power production rates over time for geothermal power plants. The computational approach used enables translation of sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy and discovery of optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an "open-source" reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 hours, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 seconds. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs. Includes a synthetic, yet realistic, model of a geothermal reservoir, referred to as open-source reservoir (OSR). OSR is a 10-well (4 injection wells and 6 production wells) system that resembles Brady Hot Springs (a commercially operational geothermal field in Nevada, USA) at a high level but has a number of sufficiently modified characteristics (which renders any possible similarity between specific characteristics like temperatures and pressures as purely random). We study OSR through CMG simulations with a wide range of flow allocation scenarios. Includes a dataset with 101 simulated scenarios that cover the period of time between 2020 and 2040 and a link to the published paper about this project, where we focus on the Machine Learning work for predicting OSR's energy production based on the simulation data, as well as a link to the GitHub repository where we have published the code we have developed (please refer to the repository's readme file to see instructions on how to run the code). Additional links are included to associated work led by the USGS to identify geologic factors associated with well productivity in geothermal fields. Below are the high-level steps for applying the same modeling + ML process to other geothermal reservoirs: 1. Develop a geologic model of the geothermal field. The location of faults, upflow zones, aquifers, etc. need to be accounted for as accurately as possible 2. The geologic model needs to be converted to a reservoir model that can be used in a reservoir simulator, such as, for instance, CMG STARS, TETRAD, or FALCON 3. Using native state modeling, the initial temperature and pressure distributions are evaluated, and they become the initial conditions for dynamic reservoir simulations 4....

15 GEOTHERMAL ENERGY↗

Artificial Intelligence Medical Support for Long-Duration Space Missions

We envision an artificial intelligence (AI) based system that will provide support and recommendations to the crew medical officer (CMO) and ground flight surgeon during long-duration space missions. Such a system would be pretrained on the knowledgebase of clinical knowledge on Earth, minimizing the amount of Earth data that needs to be transferred into space. Then during deployment, the system would be constantly refined through active learning from diverse streams of data from sensors in the spacecraft, data collected daily from individual astronauts, and human-in-the-loop feedback from the crew. The model could be interrogated for predictions and recommendations on personalized crew health based on the overall status of the spacecraft, medicinal stores, and status of other crew members. Adaptation techniques would be used to incorporate spaceflight data that have very different distributions from the training data due to the extreme environment. Edge computing and the most advanced neuromorphic processing would enable computation in scenarios with low power and bandwidth, while dimensionality reduction would be employed to ensure that the input data streams from spaceflight are as small as possible. In order to realize this long-term vision, several hardware and software aspects need to be developed and assembled. First, models pretrained on Earth biomedical data would need to be evaluated for predictive accuracy, and the best one selected. That model would need to be adapted to learn from diverse, sparse, and inconsistently measured data streams, as well as human-in-the-loop feedback. A data integration, standardization, and dimensionality reduction methodology would need to be developed to handle all data types and feed them into the model. Once the software and data infrastructure is developed, it would need to be integrated with small footprint compute processors and tested in high-radiation, high-vibration, unregulated temperature situations. As a short-term goal, we recommend to focus on the development of the data and model software structure. Several large language models (LLM) already exist that have been trained on Earth biomedical and clinical knowledgebases, including BioMedLLM, Med-PaLM, SPOKE LLM, and Foresight. These models need to be evaluated for accuracy and the best one chosen for a proof-of-concept structure, while maintaining awareness of the accelerating AI field and incorporating any newly improved model architectures as needed. Then, we recommend to develop a database of synthetic data types to mimic the diverse data streams that are expected in a long-duration space mission. This should include environmental and microbial data from the spacecraft, non-invasive data from wearables and point-of-care devices employed by astronauts, and more invasive molecular and physiological monitoring of clinical and biomarker data from astronauts. The data standardization methodology should be developed, and these data streams used to refine the clinical LLM. Several scenarios should be developed that could plausibly come up in a long-duration space mission, and changes or aberrations introduced to the data at specific times to mimic these scenarios. Then, question and answer tasks should be designed to interrogate the model for predictions and recommendations, with acceptable answers already identified.

Artificial Intelligence↗

Nonnegative tensor factorization for contaminant source identification

Unsupervised Machine Learning (ML) is becoming increasingly popular for solving various types of data analytics problems including feature extraction, blind source separation, exploratory analyses, model diagnostics, etc. In this work, we have developed a new unsupervised ML method based on Nonnegative Tensor Factorization (NTF) for identification of the original groundwater types (including contaminant sources) present in geochemical mixtures observed in an aquifer. Frequently, groundwater types with different geochemical signatures are related to different background and/or contamination sources. The characterization of groundwater mixing processes is a challenging but very important task critical for any environmental management project aiming to characterize the fate and transport of contaminants in the subsurface and perform contaminant remediation. This task typically requires solving complex inverse models representing groundwater flow and geochemical transport in the aquifer, where the inverse analysis accounts for available site data. Usually, the model is calibrated against the available data characterizing the spatial and temporal distribution of the observed geochemical types. Numerous different geochemical constituents and processes may need to be simulated in these models which further complicates the analyses. Additionally, the application of inverse methods may introduce biases in the analyses through the assumptions made in the model development process. Here, we substitute the model inversion with unsupervised ML analysis. The ML analysis does not make any assumptions about underlying physical and geochemical processes occurring in the aquifer. Our ML methodology, called NTFk, is capable of identifying (1) the unknown number of groundwater types (contaminant sources) present in the aquifer, (2) the original geochemical concentrations (signatures) of these groundwater types and (3) spatial and temporal dynamics in the mixing of these groundwater types. These results are obtained only from the measured geochemical data without any additional site information. In general, the NTFk methodology allows for interpretation of large high-dimensional datasets representing diverse spatial and temporal components such as state variables and velocities. NTFk has been tested on synthetic and real-world site three-dimensional datasets. Finally, the NTFk algorithm is designed to work with geochemical data represented in the form of concentrations, ratios (of two constituents; for example, isotope ratios), and delta notations (standard normalized stable isotope ratios).

58 GEOSCIENCES↗