SEARCH · Engineering Papers

Results for “machine reasoning”

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 559 records · Page 31

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability

Abstract Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of neural networks can enable the discovery of scientifically meaningful connections within geoscientific data. In particular, we use two methods for neural network interpretation called backward optimization and layerwise relevance propagation, both of which project the decision pathways of a network back onto the original input dimensions. To the best of our knowledge, LRP has not yet been applied to geoscientific research, and we believe it has great potential in this area. We show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network‐related geoscience research.

58 GEOSCIENCES↗

DOE OSTI2023

Barium stars as tracers of s -process nucleosynthesis in AGB stars: II. Using machine learning techniques on 169 stars

Barium (Ba) stars are characterised by an abundance of heavy elements made by the slow neutron capture process (s-process). This peculiar observed signature is due to the mass transfer from a stellar companion, bound in a binary stellar system, to the Ba star observed today. The signature is created when the stellar companion is an asymptotic giant branch (AGB) star. We aim to analyse the abundance pattern of 169 Ba stars using machine learning techniques and the AGB final surface abundances predicted by the FRUITY and Monash stellar models. We developed machine learning algorithms that use the abundance pattern of Ba stars as input to classify the initial mass and metallicity of each Ba star’s companion star using stellar model predictions. We used two algorithms. The first exploits neural networks to recognise patterns, and the second is a nearest-neighbour algorithm that focuses on finding the AGB model that predicts the final surface abundances closest to the observed Ba star values. In the second algorithm, we included the error bars and observational uncertainties in order to find the best-fit model. The classification process was based on the abundances of Fe, Rb, Sr, Zr, Ru, Nd, Ce, Sm, and Eu. We selected these elements by systematically removing s-process elements from our AGB model abundance distributions and identifying the elements whose removal had the biggest positive effect on the classification. We excluded Nb, Y, Mo, and La. Our final classification combined the output of both algorithms to identify an initial mass and metallicity range for each Ba star companion. With our analysis tools, we identified the main properties for 166 of the 169 Ba stars in the stellar sample. The classifications based on both stellar sets of AGB final abundances show similar distributions, with an average initial mass of M = 2.23 M ⊙ and 2.34 M ⊙ and an average [Fe/H] = –0.21 and –0.11, respectively. We investigated why the removal of Nb, Y, Mo, and La improves our classification and identified 43 stars for which the exclusion had the biggest effect. We found that these stars have statistically significant and different abundances for these elements compared to the other Ba stars in our sample. We discuss the possible reasons for these differences in the abundance patterns.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Diagnostics: Chapter 8 of the special issue: on the path to tokamak burning plasma operation

This chapter presents the activity conducted by the ITPA topical group (TG) on Diagnostics over about the last 15 years. Following a general introduction of the ITER Diagnostics led by their measurement roles, the document is organized in several subchapters detailing the design support, research and development activity conducted by each of the specialist working groups (WGs) of the TG. Please note that the magnetic diagnostics were supported at the TG without a specific WG. Their status is included in the general introduction. In the following some highlights of the subchapter’s contents are provided. Recent advances in ITER first wall (FW) diagnostics for the measurements of plasma-metallic wall interaction in support of the ITER research plan are reported. An InfraRed imaging Video Bolometer for ITER has been developed and tested on several tokamaks to measure the radiated power loss. A laser-induced breakdown spectroscopy (LIBS) technique which utilizes a pulsed laser beam to ablate locally by forming a crater, will measure local tritium inventory in the FW material. Real-time Residual Gas Analyzers will measure the neutral gas composition in a divertor port and an equatorial port during plasma operation. Due to the full metallic FW environment, the plasma-wall interaction in ITER will face several challenges such as the compromised radiated power and divertor heat flux measurements by reflection. Ray tracing and analysis codes have been developed to eliminate and correct the effects of reflection in the measurements. The characteristics of the reflecting surfaces depending on the roughness and angle of the incidence have been measured by dedicated experiments, and the results were applied to the reflection elimination. For the measurement of the metallic impurity radiation induced by eroded metallic atoms, a vacuum ultraviolet spectrometer has been developed and tested. An extensive thermonuclear diagnostic suite will be required to support the operation of ITER and the planned experimental program for future burning plasma experiments. Due to the harsh environmental conditions, the implementation of diagnostic systems in ITER is a major challenge. These conditions include high levels of neutron and gamma fluxes, neutron heating, particle bombardment. Therefore, the selection and design of diagnostic systems must take into account a number of phenomena previously unseen in diagnostic design. For this reason, the measurement of neutrons and confined or lost fast ions, with particular emphasis on alpha particles, is critical to ITER. The diagnostics associated with these measurements will be important for future plasma-burning experiments at ITER. The high neutron emission and very large plasma size in ITER make neutron diagnostics the main diagnostic method used to measure plasma parameters such as fusion power, fusion power density, ion temperature, energy of fast ions and their spatial distributions in the plasma core. Active spectroscopy techniques are methods where a neutral particle beam is injected into the plasma and information on plasma parameters is extracted from the measurement of line emission resulting from the beam-plasma interaction, either by plasma ions or by beam atoms. Spatial localization is achieved by crossing the beamline and multiple observation lines. The ITER plasma will be a high temperature, moderately dense, fully ionized collisional plasma. The plasma facing surfaces are principally metallic being fashioned from beryllium or tungsten but many other elements, arising from either structural or from operational needs, may enter this plasma. The energy range of the emitted photons range from meV (infra-red) to multi keV (x-rays) and originate from all areas of the plasma volume. The primary role of passive emission diagnostics is to identify what is in the plasma from spectral signatures. Extracting quantitative information from these measurements such as impurity content, ion temperature, rotation, degree of detachment and radiated power depends on calibrated instruments, a physics model of the atomic and molecular processes and plasma transport and an analysis workflow that takes into account environmental effects such as reflections. The particular needs for ITER have prompted a multi-machine, many-year effort to address all these aspects and this chapter reviews the work on diagnostic design, experiments and new analysis techniques. An overview of the laser diagnostics to be implemented on ITER is also provided in this paper. This includes descriptions of the Thomson scattering in the core, edge and divertor regions, polarimetry and interferometry diagnostics used for measuring plasma density and also measurements of helium density in the divertor using Laser Induced Flourescence. Techniques which can allow improvements on current measurements are also addressed in particular expanding poloidal polarimetry measurements to measure field fluctuations and proposed use of dispersion interferometery which has a number of advantages over existing methods. This paper identifies particular areas where further research and testing on existing tokamaks is useful even at this advanced stage to inform the design of diagnostics for ITER. Outstanding areas of concern for the implementation of laser diagnostics, in particular with a view to reliable operation are identified. An overview of the latest developments of microwave diagnostic systems and techniques is given. The primary focus is the contributions for ITER—the next step burning plasma experiment—which is supplemented by describing recent progress of techniques applicable for fusion experiments beyond ITER. The contributions are intentionally kept concise, and are being supplemented by a rich list of references for further studies. Radiation induced effects are receiving continuous and well-deserved attention of the ITER diagnostic community and they are in many cases one of the primary design drivers of the ITER diagnostic systems. The paper summarizes recent progress in this area focusing primarily on the ITER diagnostics but in some cases provides also outlook for the possible solutions for even more demanding radiation environment of fusion reactors beyond ITER. Despite advancements in the area of modeling and simulation of various radiation induced effects, experimental testing in a nuclear environment as close as possible to the target one is still seen as unavoidable for proper qualification of particular diagnostic functional elements. Recent advancement within three diagnostic areas: optical diagnostics, magnetics and bolometers is covered. Encouraging results on qualification of silica glass vacuum window assemblies are presented. In the area of magnetic sensors, progress of irradiation tests performed on ITER in-vessel LTCC inductive sensors is presented with outlook for novel technological approaches to inductive sensors utilizing thick printing and photolithography technologies being highlighted. Summary of advancements in the area of steady state magnetic field sensors based on Hall effect is given. New results of neutron irradiation test of the ITER borosilicate glass inserts for vacuum electrical feedthroughs are summarized finding negligible swelling at target level of neutron fluence. Off-line irradiation tests of fiber optic current sensors for plasma current measurement demonstrated that both for gamma doses up to 5 MGy and a total neutron fluence up to 10 15 cm −2 , radiation induced changes are still compatible with required measurement accuracy on ITER. The ITER bolometers are given as an example how considering radiation effects may influence the diagnostic design. Finally, outlook for future main R&D directions is outlined. All optical and laser-based diagnostics in ITER will be using mirrors to guide plasma radiation toward detectors, cameras and sensors. In the hostile plasma, radiation and particle environment the optical characteristics of diagnostic mirrors will degrade directly affecting the entire performance of involved diagnostic systems. An assessment of factors affecting mirror performance is provided. Among the prime adverse factors are deposition of plasma impurities, sputtering of mirror surface and steam ingress in the vicinity of mirrors. Within the International Tokamak Physics Activity with active support by ITER central team and domestic agencies, the structured research and development (R&D) program on mitigation of risks for diagnostic mirrors is underway. Within this program the mirror material development, the passive mitigation of mirror degradation by using diagnostic ducts and shutters along with an active mirror recovery program comprising the in-situ mirror cleaning and calibration is underway. Recent developments in diagnostic mirror R&D are described in this Chapter along with an example of their implementation of R&D solutions in ITER Infrared Thermography diagnostic. An assessment of still open engineering and physics questions, considerations on mirror risks during an early phase of ITER operation are given along with an overview of diagnostic mirror evolution in the late ITER operation stage toward the demonstration fusion power plant. Several crucial areas of diagnostic R&D outlined in ITER Research Plan are addressed. The basic control groups in a fusion reactor can be broken-down in five categories: (1) plasma position, magnetic configuration, and plasma current control, (2) profile control and confinement optimization, (3) MHD control and suppression, (4) edge dissipation control, radiation and plasma exhaust control and (5) break-down optimization. These categories are coupled via the physics (a control action in one domain will affect the other domains) and via shared actuators (e.g. ECRH for impurity accumulation avoidance, current density distribution control and MHD suppression). Consequently, a supervisory control system should determine the priority of the various control tasks, their couplings, and the interfaces with the safety and interlock system. For the systematic development of the various controllers taking the complexity of the plasma and the control system into account, a model-based approach is required. A short historical overview is given of the developments in systems and control theory and control engineering with special emphasis on those developments that are most relevant for Nuclear Fusion research and operation. An overview is given of the state of the field of fusion plasma control for the control categories. It will be shown how synthetic diagnostics are being developed in ITER and how they are used in diagnostic design and design validation and how they can be in model-based controller synthesis using relatively simple models. In modern control methods, multiple diagnostics are used to constrain relatively simple models. The constrained models provide an estimate for the state. This opens the route to state controllers, such as model predictive control. A major challenge in nuclear fusion research is the coherent combination of data from heterogeneous diagnostics and modeling codes for machine control and safety as well as physics studies. Measured data from different diagnostics often provide information about the same subset of physical parameters. Additionally, information provided by some diagnostics might be needed for the analysis of other diagnostics. A joint analysis of complementary and redundant data allows, e.g. to improve the reliability of parameter estimation, to increase the spatial and temporal resolution of profiles, to obtain synergistic effects, to consider diagnostics interdependencies and to find and resolve data inconsistencies. Physics-based modeling and parameter relationships provide additional information improving the treatment of ill-posed inversion problems. A coherent combination of all kind of available information within a probabilistic framework allows for improved data analysis results. The concept of integrated data analysis (IDA) in the framework of Bayesian probability theory is outlined and contrasted with conventional data analysis. Components of the probabilistic approach are summarized and specific ingredients beneficial for data analysis at fusion devices are discussed.

ITER↗

DOE OSTI2024

CACTUS: Chemistry Agent Connecting Tool Usage to Science

Large language models (LLMs) have shown remarkable potential in various domains but often lack the ability to access and reason over domain-specific knowledge and tools. In this article, we introduce Chemistry Agent Connecting Tool-Usage to Science (CACTUS), an LLM-based agent that integrates existing cheminformatics tools to enable accurate and advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama3-8b, and Mistral-7b, on a benchmark of thousands of chemistry questions. Our results demonstrate that CACTUS significantly outperforms baseline LLMs, with the Gemma-7b, Mistral-7b, and Llama3-8b models achieving the highest accuracy regardless of the prompting strategy used. Moreover, we explore the impact of domain-specific prompting and hardware configurations on model performance, highlighting the importance of prompt engineering and the potential for deploying smaller models on consumer-grade hardware without a significant loss in accuracy. By combining the cognitive capabilities of open-source LLMs with widely used domain-specific tools provided by RDKit, CACTUS can assist researchers in tasks such as molecular property prediction, similarity searching, and drug-likeness assessment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NASA NTRS1999

Modeling the Activity of Single Genes

The central dogma of molecular biology states that information is stored in DNA, transcribed to messenger RNA (mRNA) and then translated into proteins. This picture is significantly augmentated when we consider the action of certain proteins in regulating transcription. These transcription factors provide a feedback pathway by which genes can regulate one another's expression as mRNA and then as protein. To review: DNA, RNA and proteins have different functions. DNA is the molecular storehouse of genetic information. When cells divide, the DNA is replicated, so that each daughter cell maintains the same genetic information as the mother cell. RNA acts as a go-between from DNA to proteins. Only a single copy of DNA is present, but multiple copies of the same piece of RNA may be present, allowing cells to make huge amounts of protein. In eukaryotes (organisms with a nucleus), DNA is found in the nucleus only. RNA is copied in the nucleus then translocates(moves) outside the nucleus, where it is transcribed into proteins. Along the way, the RNA may be spliced, i.e., may have pieces cut out. RNA then attaches to ribosomes and is translated to proteins. Proteins are the machinery of the cell other than DNA and RNA, all the complex molecules of the cell are proteins. Proteins are specialized machines, each of which fulfills its own task, which may be transporting oxygen, catalyzing reactions, or responding to extracellular signals, just to name a few. One of the more interesting functions a protein may have is binding directly or indirectly to DNA to perform transcriptional regulation, thus forming a closed feedback loop of gene regulation. The structure of DNA and the central dogma were understood in the 50s; in the early 80s it became possible to make arbitrary modifications to DNA and use cellular machinery to transcribe and translate the resulting genes; more recently, genomes (i.e., the complete DNA sequence) of many organisms have been sequenced. This large-scale sequencing began with simple organisms, viruses and bacteria, progressed to eukaryotes such as yeast, and more recently (1998) progressed to a multi-cellular animal, the nematode Caenorhabditis elegans. Sequencers have now moved on to the fruit fly Drosophila melanogaster, whose sequence is slated for completion by the end of 1999. The human genome project is expected to determine the complete sequence of all 3 billion bases of human DNA within the next five years. In the wake of genome-scale sequencing, further instrumentation is being developed to assay gene expression and function on a comparably large scale. Much of the work in computational biology focuses on computational tools used in sequencing, finding genes that are related to a particular gene, finding which parts of the DNA code for proteins and which do not, understanding what proteins will be formed from a given length of DNA, predicting how the proteins will fold from a one-dimensional structure into a three dimensional structure, and so on. Much less computational work has been done regarding the function of proteins. One reason for this is that different proteins function very differently, and so work on protein function is very specific to certain classes of proteins. There are, for example, proteins such enzymes that catalyze various intracellular reactions, receptors that respond to extracellular signals and ion channels that regulate the flow of charged particles into and out of the cell. In this chapter, we will consider a particular class of proteins called transcription factors(TFs), which are responsible for regulating when a certain gene is expressed in a certain cell, which cells it is express in, and how much is expressed. Understanding these processes will involve developing a deeper understanding of transcription, translation, and the cellular processes that control those processes. All of these elements fall under the aegis of gene regulation or more narrowly transcriptional regulation. Some of the key questions in gene regulation are: What genes are expressed in a certain cell at a certain time? How does gene expression differ from cell to cell in a multicellular organism? Which proteins act as transcription factors, i.e., are important in regulating gene expression? From questions like these, we hope to understand which genes are important for various macroscopic processes. Nearly all of the cells of a multicellular organism contain the same DNA. Yet this same genetic information yields a large number of different cell types. The fundamental difference between a neuron and a liver cell, for example, is which genes are expressed. Thus understanding gene regulation is an important step in understanding development. Furthermore, understanding the usual genes that are expressed in cells may give important clues about various diseases. Some diseases, such as sickle cell anemia and cystic fibrosis, are caused by defects in single, non-regulatory genes; others, such as certain cancers, are caused when the cellular control circuitry malfunctions - an understanding of these diseases will involve pathways of multiple interacting gene products. There are numerous challenges in the area of understanding and modeling gene regulation. First and foremost, biologists would like to develop a deeper understanding of the processes involved, including which genes and families of genes are important, how they interact, etc. From a computation point of view, there has been embarrassingly little work done. In this chapter there are many areas in which we can phrase meaningful, non-trivial computational questions, but questions that have not been addressed. Some of these are purely computational (what is a good algorithm for dealing with a model of type X) and others are more mathematical (given a system with certain characteristics, what sort of model can one use? How does one find biochemical parameters from system-level behavior using as few experiments as possible?). In addition to biological and algorithmic problems, there is also the ever-present issue of theoretical biology - what general principles can be derived from these systems, what can one do with models other than just simulate time-courses, what can be deduced about a class of systems without knowing all the details? The fundamental challenge to computationalists and theorists is to add value to the biology - to use models, modeling techniques and algorithms to understand the biology in new ways.

Mjolsness, Eric↗

DOE OSTI2021

TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images

Abstract Atom segmentation and localization, noise reduction and deblurring of atomic-resolution scanning transmission electron microscopy (STEM) images with high precision and robustness is a challenging task. Although several conventional algorithms, such has thresholding, edge detection and clustering, can achieve reasonable performance in some predefined sceneries, they tend to fail when interferences from the background are strong and unpredictable. Particularly, for atomic-resolution STEM images, so far there is no well-established algorithm that is robust enough to segment or detect all atomic columns when there is large thickness variation in a recorded image. Herein, we report the development of a training library and a deep learning method that can perform robust and precise atom segmentation, localization, denoising, and super-resolution processing of experimental images. Despite using simulated images as training datasets, the deep-learning model can self-adapt to experimental STEM images and shows outstanding performance in atom detection and localization in challenging contrast conditions and the precision consistently outperforms the state-of-the-art two-dimensional Gaussian fit method. Taking a step further, we have deployed our deep-learning models to a desktop app with a graphical user interface and the app is free and open-source. We have also built a TEM ImageNet project website for easy browsing and downloading of the training data.

25 ENERGY STORAGE↗

DOE OSTI2021

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↗

NASA NTRS2004

Glenn Heat Transfer Simulation and Solver Graphical User Interface: Development and Testing

In the Tui ine Branch of the Turbomachinery and Propulsion Systems Division, researching and developing efficient turbine aerothermodynamics technologies is the main objective. Creating effective turbines for jet engines is a process which, if based purely on physical experimental testing, would be extremely expensive. It is for this reason, and also for the reasons of speed and ease, that the Turbine Branch spends a large amount of effort working with simulations of turbines. Specifically, they focus their work on two main fields: Computational Field Dynamics (CFD), and Experimental data analysis. The experimental field involves comparing experimental results to simulated results, whereas the CFD field involves running these simulations. The simulations are applied to aerodynamics and heat transfer cases, for both steady and unsteady flow conditions. By and large this work is applied to the domain of flow and heat transfer in axial turbines. The main application used to run these heat flow simulations is GlennHT. This program, recently rewritten in FORTRAN 90, allows the user to input a job file which specifies all the necessary parameters needed to simulate flow through a user-defined grid. There are several other executables used as well, ranging in application from converting grid files to and from particular formats, to merging blocks in a connectivity file, to converting connectivity files to a GlennHT compatible format. All of these executables are run from the command line in a terminal; some of them have interactive prompts where the user must specify the files to be manipulated after the program starts, while others take all of their parameters from the command line. With this amount of variation comes a good deal of commands and formats to memorize, which can cause slower and less efficient work, as users may forget how to execute a certain program, or not remember the pathnames of the files they wish to use. Two years ago, steps were made to expedite this process with a graphical user interface (GUI) that combines the functionality of all the executables along with adding some new functionality, such as residuals graphing and boundary conditions creation. Upon my beginning here at Glenn, many parts of the GUI, which was developed in Java, were nonfunctional. There were also issues with cross-platforming, as systems in the branch were transitioning from Silicon Graphics (SGI) machines to Linux machines. My goals this summer are to finish the parts of the GUI that are not yet completed, fix parts that did not work correctly, expand the functionality to include other useful features, such as grid surface highlighting, and make the system compatible with both Linux and SGI. I will also be heavily testing the system and providing sufficient documentation on how to use the GUI, as no such documentation existed previously.

Kardamis, Joseph R.↗

DOE OSTI2022

A Qualitative Strategy for Fusion of Physics into Empirical Models for Process Anomaly Detection

To facilitate the automated online monitoring of power plants, a systematic and qualitative strategy for anomaly detection is presented. This strategy is essential to provide credible reasoning on why and when an empirical versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. Empirical methods are usually based on pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The presented strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability, and suitability for training and testing, cause-effect, entropy inference, and model fitting. The strategy is demonstrated through a pilot use case for the application of anomaly detection to capture a valve packing leak at the high-pressure coolant injection system of a nuclear power plant.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

NASA NTRSDate not supplied

Monitoring Airspace Complexity and Determining Contributing Factors

The national airspace has evolved over many years to accommodate increased traffic demand [1] while simultaneously maintaining one of the safest forms of transportation [2], [3]. One of the reasons for this success is the ability of the system and the operators to adapt and accommodate to situations that routinely disrupt optimal operations. These situations may include: adverse weather, delays, early arrivals, equipment outages, and other factors that are outside the operators ability to control. These factors can lead to states where automation is unable to properly handle these issues and therefore air traffic controllers and pilots have to intervene, ultimately increasing communication between operators resulting in higher workload. As controller workload increases to handle sub-optimal operating conditions this can be viewed as an increase in complexity. The reasoning for this is because humans are now required to make tactical decisions in response to external factors, resulting in a departure from the strategic plan where operations would be more efficiently managed. Human operators control airspace complexity under rigid regulations that are constantly changing. The airspace is divided into sectors and the number of aircraft assigned to each controller is limited for safe handling. There has been past work that devised airspace complexity metrics in commercial aviation and related these metrics to controller workload (e.g., [4],[5]). The upper bounds on the system load are pre-determined. Such bounds on complexity make for a safe system, but the system cannot scale and adapt to autonomous, dense, and heterogeneous traffic, including the many types of Unmanned Aerial Vehicles (UAVs) envisioned to be added to the operations. We hypothesize that, as traffic density and heterogeneity grow, and other key metrics change, there will be phase transitions at which the way traffic should be managed changes significantly [6]. We offer a method for in-time detection of contributing factors that lead to phase transitions, characterized by increased complexity. To the best of our knowledge, there is no tool similar to our proposed effort that identifies such contributing factors or precursor patterns. To define the scope we are proposing to measure complexity from the viewpoint of the Terminal Radar Approach Control Facilities (TRACON) controller’s perspective. In particular we are analyzing arrivals into KSFO. With safety as the top concern for airspace operators, it is important to recognize that as density and heterogeneity grow, the focus of the system will change. Times of the day when the airspace has low density and heterogeneity, the flights will follow more efficient paths where the aircraft move on established routes that are more or less directly to the destination. However, when density and heterogeneity increases, the system will begin changing focus to avoiding conflicts and collisions and route the flights in a more flexible way. Higher flexibility requires more communication and coordination between controllers and pilots which the current automation is unable to handle. This paper proposes a novel approach that monitors airspace complexity at multiple scales, uses a Machine Learning-based tool that predicts when operations will transition to a regime of greater complexity, and identifies actions that can reduce the complexity while still maintaining efficient and safe operations. We demonstrate our proposed approach using data from multiple complementary sources. This includes, but is not limited to: historical aircraft surveillance data from NASA’s Sherlock Data Warehouse [7], METAR weather data, and airport configuration data from Aviation System Performance Metrics (ASPM). The surveillance data flight paths are sampled at a variable sample rate — increasing as the aircraft approaches the airport. This is due to how Sherlock manages flight track stitching between different radar facilities which have different sampling rates. The weather and performance data are logged at defined intervals throughout the day at a courser refresh rate. In addition to the logged data and metrics, we leverage pre-defined Standard Terminal Arrival Routes (STARs) procedures to characterize the path of each flight. Each flight files for one of these routes in the flight plan well before entering the terminal airspace, and approximately follows the route until it leaves the STAR, typically on the final fix of a runway transition. However, most flights do not always fly the full STAR procedure to completion [8], but the majority do adhere to the fixes within the common route of the procedure. Our approach leverages fixes in the common route of each of the STARs to build a reference path to the airport. This allows us to characterize the flight paths in what we are defining as the “maneuvering area” (the airspace between the STAR and before the flight is lined up on the runway’s final approach) to determine how off nominal the flights are to calculate its complexity score. Determining airspace complexity is a concept that does not have a concrete answer. In designing this metric, we consider what increases the workload for the air traffic controllers. Consequently more specialized vectoring maneuvers results in higher workload. Accordingly, we start with a theory: each flight has a direct path it takes from the STAR’s common route to the final approach’s outer marker fix for the flight’s landing runway. It is important to note that the direct path is only used as a reference. If the majority of the flights have a large consistent offset as compared to other routes it does not necessarily mean that those flights have higher complexity. We are merely building a distribution based on this direct path for that particular STAR and runway pair to determine the normal mode of operations for that route. Flights that are in the upper tail of these distributions will result in higher complexity scores and flights that fly in the median will represent the normal mode of operations and therefore will have lower complexity scores. Since flights following each STAR route take different paths to the airport, we have a different distribution for each STAR route and therefore can model these distributions to compute a complexity score from their respective normalized distributions. To evaluate the effectiveness of our proposed airspace complexity metric we will compare against an established approach based on trajectory clustering [9]. This unsupervised learning technique consists of the following steps: (1) identify the general maneuvering areas (waypoints) by performing $\kappa$-means or DBSCAN clustering on locations where aircraft frequently turn based on the surveillance radar track data, (2) map flight trajectories onto sequences of waypoints, and (3) cluster the sequences based on their common subsequences. From a high-level perspective, this baseline model learns nominal operations in the airspace through the sequence of waypoints that are representative of where aircraft change direction and defines deviations from the nominal operations as “complex.” Therefore, more deviations from the nominal operations correspond to higher complexity values. For our validation, we re-implemented this technique and tune model hyper-parameters to correctly detect waypoints for the arrival traffic into the San Francisco bay area. We will compute the complexity measure over a one-year period using our proposed technique as well as the baseline. Our validation will be based on each technique’s ability to detect a set of undesirable outcomes (e.g., go-arounds, holding patterns, average time in the airspace, etc.). Since our current complexity metric is derived from the offset from the direct reference path, it’s important to understand what causes these offsets. In many of the flights with high offset distance, flights performing holding patterns and S turns can be observed. These maneuvering tactics are utilized to add distance between the aircraft and the destination runway to prevent multiple flights from having conflicting arrival times. In order to predict a rise in complexity (or the precursor to complexity), it’s necessary to be able to identify these potential conflicts (which in turn, result in higher offsets). To do this, we define a “representative flight” for each STAR route and runway pair. This flight is approximately the path the flight would take if there was a clear path with no other flights in the airspace — including the time remaining to the airport. We first identify the flights for a given STAR runway pair using the offset to the reference path distributions that fall between the 44-55 percentiles. This yields the flights that conform to the most normal mode of operation. Each of these flights is partitioned based on the percent complete from the entry point into the maneuvering areas from 0\% – 100\% complete. Then for each percent “bin”, we take the median value of the flight’s latitude/longitude coordinates, airspeed, and (non causal) time remaining to the airport to construct a lookup table for each percent complete bin on a given route. As a flight enters the maneuvering area, we can find the estimated arrival time of a flight to the airport by finding the closest point to the representative path’s percent complete bin (relative to the flight’s current position at any snapshot in the airspace) and therefore retrieve the corresponding remaining time left on the “representative path”. We assume that the flight will follow the representative path to completion when deriving these estimates. We can then compare these estimated arrival times against other flights for the same snapshot in time to identify potential conflicts. If more flights are estimated to arrive within a tolerance window than there are runways available, then we have a potential conflict. We can use this derived measure along with other factors expected to add disruption to the operation such as weather and runway configuration changes as an input to machine learning tools to detect precursors that increases in our complexity measure. This novel method will assist in uncovering insights into the contributing factors that lead to increased complexity that may allow for in-time responses to avoid reaching a high complexity state in the airspace.

complexity↗

DOE OSTI2022

Application of Margin-Based Methods to Assess System Health

Health management of complex systems such as nuclear power plants is an essential task to guarantee system reliability. This task can be greatly enhanced by constantly monitoring asset status and performances and process such data (through anomaly detection, diagnostic, and prognostic computational algorithms) to identify asset degradation trends and faulty states. While such information and data are typically available for many of the assets, they are not propagated from the asset to the system level in order to identify the most critical assets and prioritize maintenance and surveillance activities. The main reason is driven by the fact that current reliability modeling techniques are inadequate to process such information/data. This is due to the nature of these techniques which are based on the concept of failure rate/probability that do not serve an operational context where quantitative asset health information is available. Simply stated, current reliability techniques serve a run-to-failure operational setting and not a predictive maintenance one where the goal is to perform maintenance and surveillance activities only when they are needed based on asset health. The risk informed asset management (RIAM) project is focusing on the development of a different kind of reliability modeling techniques designed to adequately serve a predictive operational setting. Such reliability techniques move aways from a failure rate/probability to a margin-based mindset where margin is here used as a metric to quantify asset health based only on current and past operational experience of the asset under consideration. In addition, margin-based reliability techniques are able to propagate asset health information from the component to system level and provide importance measure to each asset. This report summarizes a recent activity performed in collaboration with plant modernization pathway designed to integrate monitoring data into margin-based reliability models. Such activity focuses on a specific system of an existing nuclear power plant where large amount of historic monitoring data is used to monitor asset and system health.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2007

Launching to the Moon, Mars, and Beyond

Sumrall, John P.↗

DOE OSTI2021

Factors Governing Oxygen Vacancy Formation in Oxide Perovskites

The control of oxygen vacancy (V O ) formation is critical to advancing multiple metal-oxide-perovskite-based technologies. In this work, we report the construction of a compact linear model for the neutral V O formation energy in ABO 3 perovskites that reproduces, with reasonable fidelity, Hubbard-U-corrected density functional theory calculations based on the state-of-the-art, strongly constrained and appropriately normed exchange-correlation functional. We obtain a mean absolute error of 0.45 eV for perovskites stable at 298 K, an accuracy that holds across a large, electronically diverse set of ABO 3 perovskites. Our model considers perovskites containing alkaline-earth metals (Ca, Sr, and Ba) and lanthanides (La and Ce) on the A-site and 3d transition metals (Ti, V, Cr, Mn, Fe, Co, and Ni) on the B-site in six different crystal systems (cubic, tetragonal, orthorhombic, hexagonal, rhombohedral, and monoclinic) common to perovskites. Physically intuitive metrics easily extracted from existing experimental thermochemical data or via inexpensive quantum mechanical calculations, including crystal bond dissociation energies and (solid phase) reduction potentials, are key components of the model. Beyond validation of the model against known experimental trends in materials used in solid oxide fuel cells, the model yields new candidate perovskites not contained in our training data set, such as (Bi,Y)(Fe,Co)O 3 , which we predict may have favorable thermochemical water-splitting properties. The confluence of sufficient accuracy, efficiency, and interpretability afforded by our model not only facilitates high-throughput computational screening for any application that requires the precise control of V O concentrations but also provides a clear picture of the dominant physics governing V O formation in metal-oxide perovskites.

08 HYDROGEN↗

DOE OSTI2022

The 2021 room-temperature superconductivity roadmap

Designing materials with advanced functionalities is the main focus of contemporary solid-state physics and chemistry. Research efforts worldwide are funneled into a few high-end goals, one of the oldest, and most fascinating of which is the search for an ambient temperature superconductor (A-SC). The reason is clear: superconductivity at ambient conditions implies being able to handle, measure and access a single, coherent, macroscopic quantum mechanical state without the limitations associated with cryogenics and pressurization. This would not only open exciting avenues for fundamental research, but also pave the road for a wide range of technological applications, affecting strategic areas such as energy conservation and climate change. In this roadmap we have collected contributions from many of the main actors working on superconductivity, and asked them to share their personal viewpoint on the field. The hope is that this article will serve not only as an instantaneous picture of the status of research, but also as a true roadmap defining the main long-term theoretical and experimental challenges that lie ahead. Interestingly, although the current research in superconductor design is dominated by conventional (phonon-mediated) superconductors, there seems to be a widespread consensus that achieving A-SC may require different pairing mechanisms.

"Toward hot superconductivity"↗

NASA NTRS2007

Human Space Exploration: The Moon, Mars, and Beyond

America is returning to the Moon in preparation for the first human footprint on Mars, guided by the U.S. Vision for Space Exploration. This presentation will discuss NASA's mission, the reasons for returning to the Moon and going to Mars, and how NASA will accomplish that mission in ways that promote leadership in space and economic expansion on the new frontier. The primary goals of the Vision for Space Exploration are to finish the International Space Station, retire the Space Shuttle, and build the new spacecraft needed, to return people to the Moon and go to Mars. The Vision commits NASA and the nation to an agenda of exploration that also includes robotic exploration and technology development, while building on lessons learned over 50 years of hard-won experience. Why the Moon? Many questions about the Moon's potential resources and how its history is linked to that of Earth were spurred by the brief Apollo explorations of the 1960s and 1970s. This new venture will carry more explorers to more diverse landing sites with more capable tools and equipment for extended expeditions. The Moon also will serve as a training ground before embarking on the longer, more difficult trip to Mars. NASA plans to build a lunar outpost at one of the lunar poles, learn to live off the land, and reduce dePendence on Earth for longer missions. America needs to extend its ability to survive in hostile environments close to our home planet before astronauts will reach Mars, a planet very much like Earth. NASA has worked with scientists to define lunar exploration goals and is addressing the opportunities for a range of scientific study on Mars. In order to reach the Moon and Mars within a lifetime and within budget, NASA is building on common hardware, shared knowledge, and unique experience derived from the Apollo Saturn, Space Shuttle and contemporary commercial launch vehicle programs. The journeys to the Moon and Mars will require a variety of vehicles, including the Ares I Crew Launch Vehicle, which transports the Orion Crew Exploration Vehicle, and the Ares V Cargo Launch Vehicle, which transports the Lunar Surface Access Module. The architecture for the lunar missions will use one launch to ferry the crew into orbit, where it will rendezvous with the Lunar Module in the Earth Departure Stage, which will then propel the combination into lunar orbit. The imperative to explore space with the combination of astronauts and robots will be the impetus for inventions such as solar power and water and waste recycling. This next chapter in NASA's history promises to write the next chapter in American history, as well. It will require this nation to provide the talent to develop tools, machines, materials, processes, technologies, and capabilities that can benefit nearly all aspects of life on Earth. Roles and responsibilities are shared between a nationwide Government and industry team. The Exploration Launch Projects Office at the Marshall Space Flight Center manages the design, development, testing, and evaluation of both vehicles and serves as lead systems integrator. A little over a year after it was chartered, the Exploration Launch Projects team is testing engine components, refining vehicle designs, performing wind tunnel tests, and building hardware for the first flight test of Ares I-l, scheduled for spring 2009. The U.S. Vision for Space Exploration lays out a roadmap for a long-term venture of discovery. This endeavor will inspire and attract the best and brightest students to power this nation successfully to the Moon, Mars, and beyond. If one equates the value proposition for space with simple dollars and cents, the potential of the new space economy is tremendous, from orbital space delivery services for the International Space Station to mining and solar energy collection on the Moon and asteroids. The Vision for Space Exploration is fundamentally about bringing the resources of the solar system within the economic sphere of humaind. Given the immense size of our solar system, the amount of available material and energy within it present an enormous economic opportunity.

Sexton, Jeffrey D.↗

DOE OSTI2022

A computer vision algorithm for interpreting lacustrine carbonate textures at Searles Valley, USA

Investigations of the paleohydrologies of pluvial lake systems have often employed lake carbonate deposits called “tufa” that grow subaqueously and can be preserved long after the drying of the lake. For this reason, tufa have been used as a proxy for minimum lake level. However, they exhibit a variety of textures that hold the potential to reveal richer paleoclimatological information. With the goal of determining if tufa texture can be used as a proxy for lake environment, this study investigates the textures of tufa at Mono Lake, California in comparison to the fossil tufa in Searles Valley, California. While observations in the last century suggest that the tufa in the Mono basin grew in waters similar to the modern, the tufa at Searles formed during the last glacial period, when the Great Basin contained a system of pluvial lakes on the scale of the modern Great Lakes. The tufa at both basins have been observed to have a range of classifiable textures, and new methods of inspecting visual data could be informative about what factors control these textures. To this end, a t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm is used to project images of the tufa at Searles and Mono into a coordinate space, allowing for simple, quantitative comparisons of the visual similarity of textures. In this work, the textures of tufa at Searles are compared to each other, as well as to the tufa at Mono. This study performs a robust assessment of the feasibility of Mono Lake as a modern analogue for Searles Valley. It finds that there is a justifiable basis for the comparison of certain fossil facies at Searles to the tufa at Mono, significant progress towards the goal of using texture as a metric for the environment in which tufa formed.

58 GEOSCIENCES↗

DOE OSTI2022

Prediction of local concentration fields in porous media with chemical reaction using a multi scale convolutional neural network

The study of solute transport in porous media is of interest in many chemical engineering systems. Some example applications include packed bed catalytic reactors, filtration devices, and batteries. The pore scale modeling of these systems is time consuming and may require large computing resources, for this reason computational fluid dynamics (CFD) simulations are not practical if a large number of simulations is required, like in multiscale modeling, where a model at a large scale calls for pore scale simulations. It has been shown that neural networks can be trained with a dataset of flow simulations and then predict fields orders of magnitude faster, and with less computational resources, in new domains. However, it is crucial to provide the neural network with an effective description of the domain and the undergoing operating conditions to be able to train models that generalize accurately in unseen samples. Therefore, research is needed to employ neural networks in new complex systems. The appropriate training of a network for predicting coupled flow and solute transport processes is an outstanding problem due to the complex interplay between geometry and operating conditions. In this work, we train a multi scale convolutional neural network (MSNet) with a diverse dataset of simulations of transport and chemical reaction in porous media to predict the local concentration fields in images of porous media. Our dataset contains a wide diversity of sphere pack arrangements under different operating conditions (Péclet and Reynolds numbers). Further, we train a robust model by employing different input descriptors that represent the medium and the different operating conditions of each system. Our trained model is able to provide nearly instantaneous predictions, compared to around twenty hours of the CFD workflow, with less than 3.5% error on new geometries and transport conditions. Thus the model could be easily integrated in a multiscale workflow where fast response is needed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.

97 MATHEMATICS AND COMPUTING↗