Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “TRAINING PLATFORMS”

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 613 records · Page 34

Predictive Interfaces for Long-Distance Tele-Operations

We address the development of predictive tele-operator interfaces for humanoid robots with respect to two basic challenges. Firstly, we address automating the transition from fully tele-operated systems towards degrees of autonomy. Secondly, we develop compensation for the time-delay that exists when sending telemetry data from a remote operation point to robots located at low earth orbit and beyond. Humanoid robots have a great advantage over other robotic platforms for use in space-based construction and maintenance because they can use the same tools as astronauts do. The major disadvantage is that they are difficult to control due to the large number of degrees of freedom, which makes it difficult to synthesize autonomous behaviors using conventional means. We are working with the NASA Johnson Space Center's Robonaut which is an anthropomorphic robot with fully articulated hands, arms, and neck. We have trained hidden Markov models that make use of the command data, sensory streams, and other relevant data sources to predict a tele-operator's intent. This allows us to achieve subgoal level commanding without the use of predefined command dictionaries, and to create sub-goal autonomy via sequence generation from generative models. Our method works as a means to incrementally transition from manual tele-operation to semi-autonomous, supervised operation. The multi-agent laboratory experiments conducted by Ambrose et. al. have shown that it is feasible to directly tele-operate multiple Robonauts with humans to perform complex tasks such as truss assembly. However, once a time-delay is introduced into the system, the rate of tele\ioperation slows down to mimic a bump and wait type of activity. We would like to maintain the same interface to the operator despite time-delays. To this end, we are developing an interface which will allow for us to predict the intentions of the operator while interacting with a 3D virtual representation of the expected state of the robot. The predictive interface anticipates the intention of the operator, and then uses this prediction to initiate appropriate sub-goal autonomy tasks.

Wheeler, Kevin R.↗

5G integrated edge computing platform for efficient component monitoring in coal-fired power plants

This project developed a cutting-edge 5G-integrated edge computing framework to enhance operational efficiency and reliability in coal-fired power plants through real-time component monitoring and anomaly detection. The initiative focused on leveraging distributed machine learning, federated learning, and 5G-based dynamic network slicing to support scalable, fault-tolerant monitoring environments to meet the operational requirements in industrial control systems. With a Distributed Edge Computing Service (DECS) orchestration, this project enabled federated learning at edge for condition monitoring and introduced adaptive client selection strategies to minimize communication overhead. Scalable distributed training was achieved using the Horovod framework, thus enhancing performance across edge nodes. In the realm of 5G networking, the project designed and deployed reconfigurable, QoS-aware network slicing tailored for operational technology (OT) environments, integrating software-defined networks to bolster cyber-resilience and enabling dynamic slicing for federated learning workloads. A significant milestone was the development of a virtualized ICS environment with 5G core integration—which allowed elastic and fault tolerant distributed training on real-world datasets such as NASA Bearings, Hydraulic Systems, and TEP. To broaden the impact of the project, a TRL-3 virtualized ICS testbed for research and education was designed. This project engaged several graduate and undergraduate students to conduct research on the cutting-edge technology, and it resulted in one PhD dissertation, one MS thesis, and over 14 peer-reviewed publications. With the support of this project students also participated in national cybersecurity competitions to improve their professional development skills.

20 FOSSIL-FUELED POWER PLANTS↗

Autonomous System Subversion Tactics: Prototypes and Recommended Countermeasures

One of the fielding requirements for Advanced and Small Modular Reactors (AR/SMR) is the ability to support remote and autonomous operations. Autonomous Control Systems (ACS) are found on platforms such as Autonomous Space Vehicles, Cruise Missiles, and advanced driver-assistance systems. Each of these ACS implementations depends upon a set of decision support subsystems responsible for supporting Autonomous Mission Managers (names vary based upon field and author preferences). These Autonomous Mission Managers receive inputs from system sensors (e.g., LIDAR collection from an automobile travelling down a street; transients from a nuclear reactor), and perform a set of classifications (e.g., Red Traffic Light; Small Pedestrian at 10m; Load Rejection; Single Coolant Pump Trip), and then use these classifications in combination with recommendation algorithms to achieve platform goals (e.g., Stop the Vehicle at the Traffic Light, Avoid the Small Pedestrian; Trip the Reactor to prevent a Safety Event). The design, implementation, and fielding of an ACS capability will alter the cyber-attack surface such that existing risk management plans will need to be updated to include how to protect and defend against data-science and decision-support-system attack classes. These attack classes would include protection of the design and training environments where algorithm selection and testing and training data would be obvious attack vectors. These attack classes would also require an informed set of detection and response procedures to identify anomalous behaviors and document best practices for anomaly assessment and vulnerability mitigation and remediation. Last year we published a Cyber Threat Assessment Methodology for Autonomous and Remote Operations for AR/SMRs along with a companion publication on Cyber Attack and Defense Use Cases. The focus of the methodology was on describing and enumerating ACS processes, components, and functions such that security engineers could: evaluate subversion options against the target; identify threat actor attributes and capabilities derived from each subversion option; and identify security controls and response countermeasures. The Use Cases document offered detailed methodology examples including an assessment of a Military Base SMR, an Autonomous System Decision Loop, and implementation of AR/SMR Machine Learning algorithms. Our proposal at the end of last year was to focus on implementation of subversion prototypes related to the last Use Case area: AR/SMR Machine Learning (ML) Algorithms. We included six attack scenarios in our Use Cases paper: a Poisoning Attack against ML functions implemented using an FPGA; a Trojaning Attack against ML classifiers exploiting the excitability of Nuclear Engineers; a Backdooring Attack against ML Training environments to ensure persistence of an attack vector; a False Positive Evasion Attack against multi-factor Access Control Systems using clever inputs; an Inference Attack against ML models by an Insider with access to the Operational environment; and an Adversarial Reprogramming Attack against a Material Access Control Video Surveillance System. At the beginning of this year these six attack scenarios were provided to our research teams at Georgia Tech and Idaho State University and each team successfully implemented a subversion attack against a ML implementation to include transient misclassifications. While this is a notable outcome from this type of research, this paper offers the reader insight into not only how to structure and execute these types of attacks, but into the thought process behind how the researcher investigated the problem space, performed initial algorithm implementation, and the trial-and-error behind arriving at the successful subversion prototypes. We include in this paper a set of associated Scenarios on how these subversion prototypes could be implemented and an initial set of guidance for AR/SMR architects, Nuclear Regulators, and Cyber Defenders to implement awareness and defense capabilities into their current operational portfolios.

42 ENGINEERING↗

Designing Antifouling and Antimicrobial Interfaces: Structural Characterization using CryoEM, Automated Microscopy, and AI Image Segmentation

The design of functionalized surfaces for interactions with biological systems is critical across sectors such as healthcare, energy, and agriculture. Tailoring materials for specific applications, such as antifouling and antimicrobial surfaces, demands a comprehensive understanding of topology and chemistry across multiple length and time scales on both biological and materials systems. This work presents the development and characterization of nanostructured surfaces with controlled topographies and chemistries that enhance bacterial membrane disruption, reduce biofilm formation, and improve antimicrobial and antifouling capabilities. Two specific use cases will be presented - the use of cellulose nanocrystals (CNCs) for bacterial growth inhibition and the development of antifouling surfaces to prevent protein and bacterial adsorption [1-4]. By leveraging large language models (LLMs) for image segmentation and training [5], we enable automated analysis of terabyte-scale cryogenic electron microscopy (cryoEM) datasets. This analysis provides statistical insights into the biotic/abiotic interface and facilitates automated electron microscopy experiments to mitigate time and dose. The integration of cryogenic electron tomography (cryoET) and cryogenic focused ion beam (cryoFIB) milling enables high-resolution, near-native-state imaging and 3D reconstructions of bio/material interfaces [6]. Orthogonal characterization techniques and computational modeling further enhances our understanding, offering a robust platform for the design and optimization of next-generation functional surfaces [7].

Williams, Alexis [ORNL] (ORCID:0000000252835822)↗

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗

Multi‐Decadal Decarbonization Pathways for U.S. Freight Rail

A‐STEP is a first‐of‐its‐kind, integrated, open‐source software tool aimed at guiding freight rail decarbonization decision‐making. It has tools for studying energy use details for individual trains, networks of trains, battery and hydrogen charging stations, national energy sourcing and pricing, and overall decarbonization costs and environmental impacts. It gives analysts an ability to study the challenges of making such change happen. Completely amenable to analyst specified inputs and parameter values, it can be customized to provide outputs for a wide variety of assumptions about future energy conditions and technological advances. Written in Python, C++, and VB.Net, A‐STEP can be implemented on both Windows and Linux‐based platforms.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA POWER: Providing Analysis-Ready, Cloud-Optimized Data for AI /ML Training and Applications in Earth Science

As global demand for sustainable development grows, the integration of Earth Observation (EO) data into decision making frameworks has become a primary objective for the scientific community. The NASA Prediction of Worldwide Energy Resources (POWER) project serves as a bridge between NASA EO data and the specialized needs of the renewable energy, sustainable infrastructure and agroclimatology communities. In this poster presentation we will present an overview of POWER data products and services along with its use in diverse research to decision-making workflows. By providing over 40 years of high-resolution historical, hourly and daily solar and meteorological data, POWER transforms satellite observations and global model reanalysis into actionable, Analysis-Ready Dataset (ARD). Currently, the project delivers over 250 industry-friendly parameters to the users from different NASA datasets like CERES SYN1Deg, MERRA-2, and IMERG alongside downscaled CMIP6 climate model data, fulfilling over 16 million requests from 50,000 unique users monthly. To ensure data quality and traceability, these parameters are rigorously validated against the ground-based observations from the Baseline Surface Radiation Network (BSRN) and the Global Surface Summary of the Day (GSOD) – these results will be discussed in the presentation. A newly introduced web-based PaRameter Uncertainty ViEwer (PRUVE) tool will be presented that provides an online validation platform to the users that benchmarks satellite-based and assimilation data products against these surface measurements. To reduce technical barriers to data adoption, POWER data is accessible through RESTful APIs, ESRI ArcGIS Image Services, a web-based Data Access Viewer tool, allowing users to visualize, validate and apply the dataset. For efficient data delivery POWER data is cloud-optimized into Zarr datastore accessible through NASA managed Amazon S3 ensures high-performance allowing users to integrate EO directly into operational pipelines. These customized services will be presented. Use cases from application will be presented from the energy sector - such as for design of generation systems, performance monitoring of solar power plants, in infrastructure sector- optimizing building energy efficiency and thermal comfort, in agriculture – such as driving crop simulation and yield forecasting models to enable climate resilient farming. Furthermore, the shift toward machine learning (ML) in EO research that has positioned POWER as a key provider for training datasets which will be discussed. Use-cases will be presented to showcase how NASA data is enabling the development of predictive tools for climate variability and resource management. The poster will present POWER’s future plans including technology development to enhance data traceability and reproducibility and improving I/O performance to support the rapid integration of new EO products, ensuring that POWER remains a robust scalable backend for the evolving landscape of AI-driven Earth Science. Additionally, POWER is developing an AI Agent and an MCP-Server to enable industry AI-Agentic workflows.

Neha Khadka↗

A sorghum practical haplotype graph facilitates genome‐wide imputation and cost‐effective genomic prediction

Abstract Successful management and utilization of increasingly large genomic datasets is essential for breeding programs to accelerate cultivar development. To help with this, we developed a Sorghum bicolor Practical Haplotype Graph (PHG) pangenome database that stores haplotypes and variant information. We developed two PHGs in sorghum that were used to identify genome‐wide variants for 24 founders of the Chibas sorghum breeding program from 0.01x sequence coverage. The PHG called single nucleotide polymorphisms (SNPs) with 5.9% error at 0.01x coverage—only 3% higher than PHG error when calling SNPs from 8x coverage sequence. Additionally, 207 progenies from the Chibas genomic selection (GS) training population were sequenced and processed through the PHG. Missing genotypes were imputed from PHG parental haplotypes and used for genomic prediction. Mean prediction accuracies with PHG SNP calls range from .57–.73 and are similar to prediction accuracies obtained with genotyping‐by‐sequencing or targeted amplicon sequencing (rhAmpSeq) markers. This study demonstrates the use of a sorghum PHG to impute SNPs from low‐coverage sequence data and shows that the PHG can unify genotype calls across multiple sequencing platforms. By reducing input sequence requirements, the PHG can decrease the cost of genotyping, make GS more feasible, and facilitate larger breeding populations. Our results demonstrate that the PHG is a useful research and breeding tool that maintains variant information from a diverse group of taxa, stores sequence data in a condensed but readily accessible format, unifies genotypes across genotyping platforms, and provides a cost‐effective option for genomic selection.

Jensen, Sarah E.↗

Scalable and efficient learning from crowds with Gaussian processes

Over the last few years, multiply-annotated data has become a very popular source of information. Online platforms such as Amazon Mechanical Turk have revolutionized the labelling process needed for any classification task, sharing the effort between a number of annotators (instead of the classical single expert). This crowdsourcing approach has introduced new challenging problems, such as handling disagreements on the annotated samples or combining the unknown expertise of the annotators. Probabilistic methods, such as Gaussian Processes (GP), have proven successful to model this new crowdsourcing scenario. However, GPs do not scale up well with the training set size, which makes them prohibitive for medium-to-large datasets (beyond 10K training instances). This constitutes a serious limitation for current real-world applications. In this work, we introduce two scalable and efficient GP-based crowdsourcing methods that allow for processing previously-prohibitive datasets. The first one is an efficient and fast approximation to GP with squared exponential (SE) kernel. The second allows for learning a more flexible kernel at the expense of a heavier training (but still scalable to large datasets). Since the latter is not a GP-SE approximation, it can be also considered as a whole new scalable and efficient crowdsourcing method, useful for any dataset size. Both methods use Fourier features and variational inference, can predict the class of new samples, and estimate the expertise of the involved annotators. A complete experimentation compares them with state-of-the-art probabilistic approaches in synthetic and real crowdsourcing datasets of different sizes. Finally, they stand out as the best performing approach for large scale problems. Moreover, the second method is competitive with the current state-of-the-art for small datasets.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Rehabilitation Tool

Biotran, or Fastex as named by Cybex, the company that manufactures it, is a force sensing system that helps physicians and physical therapists treat people with movement deficiencies. Based on NASA sensor technology, it also has applications in sports training and evaluation. Biotran provides a means of testing weight-bearing capabilities that may have been compromised by injury or disease. It also assists in the rehabilitation process by putting patients through a course of computer-directed exercises designed to improve strength and balance reaction time. The system tests and documents progress until maximum medical improvement is achieved. Lewis Research Center also assisted the company in the selection of the material used in the Biotran force sensing platforms. Biotran is currently manufactured by Cybex under the name Fastex.

Source record↗

Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows

Reduced rank nonlinear filters are increasingly utilized in data assimilation of geophysical flows, but often require a set of ensemble forward simulations to estimate forecast covariance. On the other hand, predictor-corrector type nudging approaches are still attractive due to their simplicity of implementation when more complex methods need to be avoided. However, optimal estimate of nudging gain matrix might be cumbersome. In this paper, we put forth a fully nonintrusive recurrent neural network approach based on a long short-term memory (LSTM) embedding architecture to estimate the nudging term, which plays a role not only to force the state trajectories to the observations but also acts as a stabilizer. Furthermore, our approach relies on the power of archival data and the trained model can be retrained effectively due to power of transfer learning in any neural network applications. In order to verify the feasibility of the proposed approach, we perform twin experiments using Lorenz 96 system. Our results demonstrate that the proposed LSTM nudging approach yields more accurate estimates than both extended Kalman filter (EKF) and ensemble Kalman filter (EnKF) when only sparse observations are available. With the availability of emerging AI-friendly and modular hardware technologies and heterogeneous computing platforms, we articulate that our simplistic nudging framework turns out to be computationally more efficient than either the EKF or EnKF approaches.

42 ENGINEERING↗

Benchmarking for AI for Science

AI has been instrumental for recent developments in a number of domains of the sciences. With several hundred machine learning (ML) algorithms and models, and numerous AI-specific hardware platforms, a common quest for all scientists working on AI for Science is around the selection of machine learning algorithm(s) to solve their domain-specific scientific problems. A number of different initiatives around AI Benchmarking have been set up and have been useful in understanding the benefits of different ML algorithms for different tasks.However, with the majority of these AI Benchmarking initiatives focusing on the conventional notions of benchmarking, where the focus is purely runtime performance (such as training time or inference time), their suitability for benchmarking different ML algorithms for solving scientific problems has been viewed as a performance problem even though both are hardly the same. To make reasonable, explainable, and justifiable advancements in science using AI, it is critical to focus on the merits of these algorithms in handling different domain science problems. In other words, more emphasis must be given on Benchmarking for AI for Science than AI Benchmarking. The vision of the former is not only to assess the performance of ML algorithms, but also to assess, and understand the benefits and merits of different ML algorithms in handling scientific problems. Benchmarking for AI for Science, instead of pure performance focused AI Benchmarking, has several benefits: (i) it has the potential to offer advances in the sciences, much more rapidly than through pure performance-based AI methods, (ii) it will encourage the community to focus on developing better domain-specific AI techniques, particularly given the provision for being able to benchmark different techniques, and (iii) it will encourage hardware manufacturers to focus on developing science-specific hardware subsystems.

Thiyagalingam, Jeyan↗

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As space missions continue to become more ambitious, complex, and distant to Earth, the need for advanced on-board intelligent decision making to guide everything from mission operations to fault detection and recovery has become a major front of space research. While the prevalence of research on such Artificial Intelligence / Machine Learning (AI/ML) modules has exploded, the capacity to experimentally validate such modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available AI/ML computational platforms via the TechEdSat (TES-n) flight series as part of what is programmatically referred to as the BRAINSTACK. BRAINSTACK will provide an orbital AI/ML evaluation laboratory where computational experiments are pre-loaded into memory prior to launch, and then executed as desired during the mission, with results reported back and program tweaks or new data sets uploaded as needed. Processors selected as part of the BRAINSTACK are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and more recently, neuromorphic processors in LEO operations. Neuromorphic processors are of particular interest due to their superior computational power efficiency over GPUs. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on January 13, 2022 and continues to operate in orbit despite almost no space environment modifications. The Intel Loihi Gen-1 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. This experiment utilized a Loihi packaged in the ‘Kapoho Bay’ USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by a host Intel Pentium single-board computer to handle scheduling of the AI/ML application payloads, and communications with the satellite vehicle manager. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the basis of the evolving BRAINSTACK in the upcoming three TES-n/NOW flights. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space AI/ML applications may be initially tested.

Artificial Intelligence↗

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As space missions continue to become more ambitious, complex, and distant to Earth, the need for advanced on-board intelligent decision making to guide everything from mission operations to fault detection and recovery has become a major front of space research. While the prevalence of research on such Artificial Intelligence / Machine Learning (AI/ML) modules has exploded, the capacity to experimentally validate such modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available AI/ML computational platforms via the TechEdSat (TES-n) flight series as part of what is programmatically referred to as the BRAINSTACK. BRAINSTACK will provide an orbital AI/ML evaluation laboratory where computational experiments are pre-loaded into memory prior to launch, and then executed as desired during the mission, with results reported back and program tweaks or new data sets uploaded as needed. Processors selected as part of the BRAINSTACK are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and more recently, neuromorphic processors in LEO operations. Neuromorphic processors are of particular interest due to their superior computational power efficiency over GPUs. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on January 13, 2022 and continues to operate in orbit despite almost no space environment modifications. The Intel Loihi Gen-1 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. This experiment utilized a Loihi packaged in the ‘Kapoho Bay’ USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by a host Intel Pentium single-board computer to handle scheduling of the AI/ML application payloads, and communications with the satellite vehicle manager. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the basis of the evolving BRAINSTACK in the upcoming three TES-n/NOW flights. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space AI/ML applications may be initially tested.

Artificial Intelligence↗

Control and prevention measures for legionellosis in hospitals: A cross-sectional survey in Italy

Highlights: • Legionellosis risk is high in Italian hospitals with many hospitalizations. • Legionella contamination in the water system was assessed in 97% of hospitals. • Risk assessment was performed in 73% of hospitals but only 53% had a dedicated team. • Measures to reduce legionellosis risk were adopted in 93.3% of hospitals. • Training courses on Legionnaires’ disease were planned in 36.5% of hospitals. Risk assessment, environmental monitoring, and the disinfection of water systems are the key elements in preventing legionellosis risk. The Italian Study Group of Hospital Hygiene of the Italian Society of Hygiene, Preventive Medicine, and Public Health and the Italian Multidisciplinary Society for the Prevention of Health Care-Associated Infections carried out a national cross-sectional survey to investigate the measures taken to prevent and control legionellosis in Italian hospitals. A multiple-choice questionnaire was developed, comprising 71 questions regarding hospital location, general characteristics, clinical and environmental surveillance, and control and preventive measures for legionellosis in 2015. Overall, 739 hospitals were enrolled from February to June 2017, and 178 anonymous questionnaires were correctly completed and evaluated (response rate: 24.1%). The survey was conducted using the SurveyMonkey® platform, and the data were analyzed using Stata 12 software. Of the participating hospitals, 63.2% reported at least one case of legionellosis, of which 28.2% were of proven nosocomial origin. The highest case numbers were reported in the Northern Italy, in hospitals with a pavilion structure or cooling towers, and in hospitals with higher numbers of beds, wards and operating theaters. Laboratory diagnosis was performed using urinary antigen testing alone (31.9%), both urinary antigen testing and single antibody titer (17.8%), or with seroconversion also added (21.5%). Culture-based or molecular investigations were performed in 28.8% and 22.1% of the clinical specimens, respectively. The water systems were routinely tested for Legionella in 97.4% of the hospitals, 62% of which detected a positive result (> 1000 cfu/L). Legionella pneumophila serogroup 2–15 was the most frequently isolated species (58.4%). The most common control measures were the disinfection of the water system (73.7%), mostly through thermal shock (37.4%) and chlorine dioxide (34.4%), and the replacement (69.7%) or cleaning (70.4%) of faucets and showerheads. A dedicated multidisciplinary team was present in 52.8% of the hospitals, and 73% of the hospitals performed risk assessment. Targeted training courses were organized in 36.5% of the hospitals, involving nurses (30.7%), physicians (28.8%), biologists (21.5%), technicians (26.4%), and cleaners (11%). Control and prevention measures for legionellosis are present in Italian hospitals, but some critical aspects should be improved. More appropriate risk assessment is necessary, especially in large facilities with a high number of hospitalizations. Moreover, more sensitive diagnostic tests should be used, and dedicated training courses should be implemented.

54 ENVIRONMENTAL SCIENCES↗

Improved spatial resolution for spot sampling in thermal desorption atomic force microscopy – mass spectrometry via rapid heating functions

The key to advancing materials is to understand and control their structure and chemistry. However, thorough chemical characterization is challenging since existing techniques characterize only a few properties of the specimen, thereby necessitating multiple measurement platforms to acquire the necessary information. The multimodal combination of atomic force microscopy (AFM) and mass spectrometry (MS) transcends existing analytical capabilities for nanometer scale spatially resolved correlation of the chemical and physical properties of a sample surface. One such hybrid system employs heated AFM cantilevers for thermal desorption (TD) sampling of molecules from a surface and subsequent gas phase ionization and detection of the liberated species by MS. Here in this paper, we report on the use of voltage pulse trains to tailor cantilever heating such that spot sampling size was reduced and mass spectral signal was improved compared to constant voltage, static heating of the cantilever. Desorption efficiency (DE), defined as the quotient of the mass spectral signal intensity and the volume of the desorption crater, was used to judge the effectiveness of a particular tailored heating function. To guide the development and optimization of the heating functions and aid in interpreting experimental results, a 1D finite element model was developed that predicted the cantilever response to different heating functions. Three tailored heating functions that used different combinations, magnitudes, and durations of rectangular voltage pulses, were used for surface spot sampling. The resultant sampling spot size and DE were compared to the same metrics obtained with the conventional method that uses a single voltage pulse. Using a model system composed of a thin film of ink containing pigment yellow 74 as a model system, desorption craters shrunk from 2 μm, using the conventional approach, to 310 nm using the optimum tailored heating function. This same pulsed heating function produced a 381× improvement in the DE and an 8× improvement in spatial resolution compared to the conventional heating approach showing that signal/amount of material sampled was improved significantly by this new cantilever heating strategy.

36 MATERIALS SCIENCE↗

HAPPA: A Modular Platform for HPC Application Resilience Analysis with LLMs Embedded

High-performance computing (HPC) systems are increasingly vulnerable to soft errors, which pose significant challenges in maintaining computational accuracy and reliability. Predicting the resilience of HPC applications to these errors is crucial for robust code protection and detailed resilience analysis. In this study, we present HAppA, a modular platform designed for HPC Application Resilience Analysis. Embedding Large Language Models (LLMs), HAppA addresses understanding the context information of long code sequences typical in HPC applications. HAppA implements a novel code representation module that chunks the code into fixed-size segments and aggregates the embeddings of these segments. Three aggregation methods have been explored: MeanPooling, MaxPooling, and LSTM-based techniques. We built a DAtaset for REsilience analysis using Fault Injection (FI), named DARE. Using our DARE dataset, HAppA is trained for regression prediction tasks. Our evaluation results demonstrate the predictive accuracy of HAppA compared to other models, particularly noting that the LSTM-based aggregation method -- HAppA-LSTM -- achieves a mean squared error (MSE) of 0.078 for SDC prediction, surpassing the existing state-of-the-art PARIS model, which recorded an MSE of 0.1172. Additionally, HAppA with the KeyBERT model extracts a list of keywords representing the source code. A comprehensive importance analysis of these keywords further elucidates the code patterns contributing to the error rate. These findings highlight the effectiveness of HAppA in analyzing the resilience of HPC applications and establish a new benchmark for predictive accuracy in resilience.

Jiang, Hailong [Kent State University]↗

Online Power System Event Detection via Bidirectional Generative Adversarial Networks

Accurate and speedy detection of power system events is critical to enhancing the reliability and resiliency of power systems. Although supervised deep learning algorithms show great promise in identifying power system events, they require a large volume of high-quality event labels for training. This paper develops a bidirectional anomaly generative adversarial network (GAN)-based algorithm to detect power system events using streaming PMU data, which does not rely on a huge amount of event labels. By introducing conditional entropy constraint in the objective function of GAN and graph signal processing-based PMU sorting technique, our proposed algorithm significantly outperforms state-of-the-art event detection algorithms in terms of accuracy. To facilitate the adoption of the proposed algorithm, a prototype online platform is also developed using Apache Hadoop, Kafka, and Spark to enable real-time event detection. Here, the accuracy and computational efficiency of the proposed algorithm are validated using a large-scale real-world PMU dataset from the Eastern Interconnection of the United States.

24 POWER TRANSMISSION AND DISTRIBUTION↗