Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “collective intelligence”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Comparison of plug flow and multi-node stratified tank modeling approaches regarding computational efficiency and accuracy

Residential water heaters contain water stratified by temperature-driven density differences. This implies that a water tank can reach a state in which the top and bottom sections have different temperatures, unless mixing happens. A high degree of thermal stratification can improve the efficiency of some water heaters, by saving the amount of energy required for the heat-up process. Studies of stratification became popular in the 1970s and it remains an active research topic today. The research has led to the development of different models and techniques to better predict and define a stratified tanks behavior. By comparing these models and techniques used previously to describe thermal stratification, the phenomenon could be better understood, exploited, and used to increase efficiency and thermal energy capacity in modern water tanks. From the existing models, we found the one-dimensional standard plug-flow and a multi node model to be appropriate for analyzing the processes of the heat up and cool-down in a water tank. These two models are based on energy balances. This work involved comparing the accuracy and computational effort needed to implement these models. To assess accuracy, we compared both types of existing models to experimental data (also collected in this work) which included a heat up process using an external heat pump. This external process included a layering process that has an eddy diffusivity at five times the rate of thermal diffusion. For this project, we implemented the models in MATLAB, the multi-paradigm numerical computing environment. We quantified model accuracy using the root mean squared error between modeled data and experimental data for six measured tank temperatures. Comparing the accuracy and the computational time taken to run the simulation provides a method to contrast the performance of each model and a way to rate it. The multi node model was run using from 6 to 96 spatial nodes; the plug flow model was run using 1 to 0.001 º C temperature bin sizes. Additionally, timesteps were varied from 4 to 236 s. The results quantify the tradeoff between accuracy and computational time, providing guidance for simulations to intelligently select the best model type and simulation parameters. This research can be used to validate the pre-existing models and possibly improve the modern water tank.

Bulnes, Fernando Karg↗
DOE OSTI2025

Accelerating GNNs on GPU Sparse Tensor Cores through N:M Sparsity-Oriented Graph Reordering

Recent advancements in GPU hardware support have introduced the capability to leverage N:M sparse patterns for substantial performance gains. Graphs in Graph Neural Networks (GNNs) are typically sparse, but the sparsity is often irregular, not conforming to such sparse patterns. In this paper, we propose a novel graph reordering algorithm, the first of its kind, to reshape irregular graph data into the N:M structured sparse pattern at the tile level, allowing linear-algebra-based graph operations in GNNs to benefit from the N:M sparse hardware. The optimization is lossless, maintaining the accuracy of GNN. It can remove 98-100\% violations of the N:M sparse patterns at the vector level, and increase the proportion of conforming graphs in SuiteSparse collection from 5-9\% to 88.7-93.5\%. On A100 GPUs, the optimization accelerates Sparse Matrix Matrix (SpMM) by up to 43X (2.3X -- 7.5X on average) and speeds up the key graph operations in GNNs on real graphs by as much as 8.6X (3.5X on average).

artificial intelligence, graph neural networks↗
DOE OSTI2024

Electrical Fault and Power Quality Detection Algorithms and Customer-Owned DERs Monitoring with a Cyber Grid Guard System and DLT

In this study, the electrical fault and power quality detection algorithms and customer-owned DERs monitoring use cases were implemented, with a Cyber Grid Guard system and DLT. Electrical utilities continue to deploy more intelligent electronic devices (IEDs) inside and outside electrical substations, and are associated with customer-owned distributed energy resources (DERs). Data from these IEDs, such as power meters and protection relays, must be kept confidential and of high integrity. Blockchain technology has the potential to increase microgrid resilience by enhancing data sharing security. The growing use of IEDs and customer-owned renewable energy sources (DERs) may make it necessary to connect Distributed Ledger Technology (DLT) with power system applications. We implemented the electrical faulted phase detection and power quality monitoring algorithms with a Cyber Grid Guard (CGG) system using DLT. In addition, the DERs (wind turbine farms) use case and protective relay cyber-event tests were assessed, by using the CGG system with DLT. In the experimental model, the testbed was created by using a real-time simulator and CGG system with power meters/ protective relays in the loop. The data collected from the CGG system and IEDs were compared with the same time stamp source. These results showed the successful assessment of protection, control and monitoring applications using a CGG system with DLT. In the future, power system applications for the ESGT with DERs and the CGG system will be based on executing smart contracts between electrical utilities and customer-owned DERs.

Piesciorovsky, Emilio↗
DOE OSTI2024

Identifying Controlling Variables for Mercury Vapors in Alpha-4 at Y-12: Two Year Data Collection Update

Multiple sensor packages were deployed at Alpha-4 by SRNL, in collaboration with United Cleanup Oak Ridge LLC (UCOR), to monitor mercury vapor concentrations and meteorological parameters. These sensors collected data, inside and outside of the legacy-use facility, for approximately two years. Though data gaps still exist, particularly in colder months, several controlling variables were identified that govern mercury vapor concentrations within Alpha-4. Temperature, barometric pressure gradients, humidity, and wind speed have been identified as controlling variables. A strong positive correlation was seen between mercury vapor concentrations and temperature which generally followed diurnal fluctuations. Temperatures below approximately 10 degrees Celsius did not show any spikes above the PEL, indicating more work can be performed at any time during the winter months – more data should be collected to confirm consistency in this finding. Additionally, spikes in mercury vapor concentrations above that of the permissible exposure limit (PEL; 100 µg/m 3 ) occurred primarily in late afternoon or evening/overnight hours (between 3 PM and 6 AM), which suggests D&D operations might be best scheduled during morning or daytime hours prior to the late afternoon. However, a limited number of spikes did occur outside of the identified window, although this may be attributed to disturbances in air flow and mercury vapor release from work activities performed inside of the Alpha-4 building. The analysis conducted allows for a strong predictive capability for estimating mercury vapor concentrations based upon accurate meteorological parameters. Still, additional data collection, particularly in the winter months, could help to strengthen the predictive power and validate the identified data trends. Further, increased temporal resolution could also help to better characterize the incipient stages of the increases and decreases in the mercury vapor concentration. Continued monitoring support by SRNL at Y-12 is underway at Alpha-4 to further close remaining data gaps and support deactivation and decommissioning work. Within a collaborative effort with UCOR, the SRNL team is collecting mercury vapor data to study the efficacy of a novel mercury suppressant, FerroBlack® which was recently deployed at Alpha-4. In addition, modifications to the current monitoring setup to increase measurement resolution is also being investigated.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Electrical substation grid testbed for DLT applications of electrical fault detection, power quality monitoring, DERs use cases and cyber-events

Electrical utilities continue to deploy more intelligent electronic devices (IEDs) inside and outside electrical substation, and are associated with customer-owned distributed energy resources (DERs). The integrity and confidentiality of data from these IEDs, like power meters and protective relays, is crucial. Blockchain technology could improve the resilience of microgrids by improving the security of data sharing. The penetration of customer-owned DERs (renewable energy sources) and the increasing deployment of IEDs can lead to integrate power system applications with Distributed Ledger Technology (DLT). In this study, we implemented the electrical faulted phase detection and power quality monitoring algorithms with a Cyber Grid Guard (CGG) system using DLT. In addition, the DERs (wind turbine farms) use case and protective relay cyber-event tests were assessed, by using the CGG system with DLT. In the experimental model, the testbed was created by using a real-time simulator and CGG system with power meters/ protective relays in-the-loop. The data collected from the CGG system and IEDs were compared with the same time stamp source. These results had shown the successful assessment of protection, control and monitoring applications using a CGG system with DLT. In the future, the ESGT with DERs and the CGG system will be used in other power system applications, based on implementing smart contracts between electrical utilities with customer-owned DERs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. Here this study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM, specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

An Intelligent Adaptable Monitoring Package. Final Report

The “Intelligent Adaptable Monitoring Package” project was a four-year effort that demonstrated the feasibility of integrated sensing packages at tidal and wave energy sites. Such integration is generally required by the breadth of sensors required to understand environmental effects at marine energy sites and the operational difficulty of deploying, maintaining, and recovering such sensors. Over the course of the project, the Adaptable Monitoring Package (AMP) was deployed in multiple settings, each corresponding to a project budget period: - Budget Period 1: Demonstration of cabled deployment at Pacific Northwest National Laboratory’s Marine Science Laboratory. The deployment highlighted AMP hardware endurance over a 4-month deployment in a tidally-dominated environment and laid the groundwork for machine learning algorithms to detect and classify targets present in active sonar data. - Budget Period 2: Demonstration of an autonomous deployment at PacWave South off the coast of Newport, Oregon. The deployment highlighted the stability of AMP hardware and software, with the autonomous package collecting data on a duty cycle over a 1.5-month deployment. - Budget Period 3: Demonstration of an autonomous deployment powered by a wave energy converter at the U.S. Navy’s Wave Energy Test Site. The deployment highlighted the potential of wave energy to power ocean observatories and led to the development of machine learning algorithms to detect and classify targets in optical camera data. In aggregate, this project’s greatest success was demonstrating the AMP’s flexibility in a range of deployment scenarios. Each budget period represented a “first of a kind” demonstration of integrated instrumentation – cabled AMP, autonomous AMP, wave-energy powered AMP – and each deployment helped to identify and set goals for the next. Further, despite the exploratory nature of these deployments, each one achieved high system up-time and proved that flexible integration of multiple sensors in a single package represents a viable strategy for marine energy environmental monitoring. The key lessons learned from the project are: - Without continuous power, either from a shore cable or in situ source, many of the benefits of integration are lost (If continuous power is not available, the ability to detect rare events is lost, as is the ability to minimize the risk of behavioral changes through adaptive sensing. However, even on a duty cycle, there is still value in being able to acquire synchronous data from multiple sensors.); and - Observations from a moving platform present substantially greater data processing challenges than those from stationary platforms. Finally, these deployments also demonstrate an important truth: successful integration alone does not guarantee that relevant data are collected. To grow the knowledge base about environmental interactions with marine energy converters, integrated systems, like the AMP, need to include the right sensor mix and connect the data pipelines to effective processing algorithms. These deployments establish a strong foundation for future collaborations with the environmental research community: not only to understand the environmental effects of marine energy, but also to improve our general ability to study life in the sea.

16 TIDAL AND WAVE POWER↗
DOE OSTI2024

Leverage modern artificial intelligence (AI) enabled systems for waste reduction

Manufacturing industries continue to face challenges in reducing waste, as upstream strategies such as source reduction and product redesign require a deeper understanding of processes compared to conventional recycling methods. Recent advancements in artificial intelligence (AI) and machine learning (ML) have opened new opportunities to integrate modern computational techniques with traditional waste minimization strategies. This paper explores AI-enabled approaches for product redesign, source reduction, and recycling that can significantly reduce waste generation while improving efficiency and sustainability. AI-driven material substitution and lightweighting in product design enable discovery of novel materials with optimized properties, reducing waste without compromising performance. Reinforcement learning models optimize process parameters, raw material specifications, and machine sequencing to minimize production losses, while Industrial Internet of Things (IIoT) systems paired with AI analytics enhance real-time waste tracking, predictive maintenance, and quality inspection. Furthermore, AI-based demand forecasting and production planning reduce overproduction and excess inventory, as demonstrated in industrial applications. In recycling, ML-powered pattern recognition and robotic sorting technologies achieve higher accuracy in waste segregation, directly improving recycling efficiency. Complementary solutions such as smart bins and AI-enabled waste pickup scheduling optimize collection logistics, reducing both costs and emissions. Although implementation requires upfront investment in infrastructure and training, the long-term benefits include higher material efficiency, reduced waste, improved product quality, and stronger sustainability outcomes across the supply chain. By leveraging AI-enabled systems, manufacturers can align waste minimization efforts with circular economy principles, creating scalable solutions for both industry and society.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Final report- UFL - RAPIDS2: A SciDAC Institute for Computer Science, Data, and Artificial Intelligence

The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A Demonstration of Intelligent Container Surveillance Using Stationary and Mobile Camera Platforms

Surveillance of nuclear material storage containers is required to ensure that the container safety boundary is maintained during the service life of the container. As many of these container types are the first and only containment barrier to release protecting the worker, public, and environment, it is imperative to develop robust surveillance tools to characterize container degradation. Machine learning (ML) techniques have matured quickly in the past decade and are slowly becoming a routine application in data analysis. While more popular architectures have been developed with different applications in mind, these can be easily translated to container surveillance requirements. In this study, we developed a ML model based on the Detectron2 framework to identify slip lid containers and common exterior container defects, primarily dents. Commercial-off-the-shelf cameras are combined into a stationary camera array or are mounted to a robotic arm to provide more mobility for positioning needs. Results from the model evaluations on the images indicate that the stationary camera arrays outperform the accuracy of the mobile camera systems for both individual camera and composite image detections. Overall, however, the detection accuracies of the systems fell short of 50% and were less than satisfactory. Future efforts to improve the system involve focusing on a single camera deployable solution that combines a controllable light source that eliminates one of the biggest environmental factors that influence ML model detection performance. Additional training set collection is planned to build a more robust model that enables accurate detection from a wider range of imaging conditions.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2024

Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy

Austenitic 347H stainless steel offers superior mechanical properties and corrosion resistance required for extreme operating conditions such as high temperature. The change in microstructure due to composition and process variations is expected to impact material properties. Identifying microstructural features such as grain boundaries thus becomes an important task in the process-microstructure-properties loop. Applying convolutional neural network (CNN)-based deep learning models is a powerful technique to detect features from material micrographs in an automated manner. In contrast to microstructural classification, supervised CNN models for segmentation tasks require pixel-wise annotation labels. However, manual labeling of the images for the segmentation task poses a major bottleneck for generating training data and labels in a reliable and reproducible way within a reasonable timeframe. Microstructural characterization especially needs to be expedited for faster material discovery by changing alloy compositions. Here, in this study, we attempt to overcome such limitations by utilizing multimodal microscopy to generate labels directly instead of manual labeling. We combine scanning electron microscopy images of 347H stainless steel as training data and electron backscatter diffraction micrographs as pixel-wise labels for grain boundary detection as a semantic segmentation task. The viability of our method is evaluated by considering a set of deep CNN architectures. We demonstrate that despite producing instrumentation drift during data collection between two modes of microscopy, this method performs comparably to similar segmentation tasks that used manual labeling. Additionally, we find that naïve pixel-wise segmentation results in small gaps and missing boundaries in the predicted grain boundary map. By incorporating topological information during model training, the connectivity of the grain boundary network and segmentation performance is improved. Finally, our approach is validated by accurate computation on downstream tasks of predicting the underlying grain morphology distributions which are the ultimate quantities of interest for microstructural characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Report for the ASCR Workshop on Visualization for Scientific Discovery, Decision-Making, and Communication

Visualization—the use of visual elements to explore data, form hypotheses, or convey conclusions—is an integral part of the scientific process. Starting from an initial exploration of new data to illustrating outcomes for the general public, visualization is one of the most intuitive and powerful modes of communication. With the explosion of new data sources and types, unprecedented volumes of data, and new technologies, such as virtual reality (VR) and artificial intelligence (AI), visualization has become increasingly essential but also ever more challenging. The Department of Energy’s (DOE) Office of Advanced Scientific Computing Research (ASCR) sponsored a Basic Research Needs workshop in January 2022 to understand the major opportunities and grand challenges in visualization tools and technologies for scientific computing as well as for DOE-relevant applications and goals in general. The workshop identified five priority research directions (PRDs) for visualization to support scientific discovery, decision making, and communication. The first three PRDs describe interconnected research themes addressing the need for new techniques to deal with complex data, uncertainty, and interpretability (PRD 1); the need for scalable and interoperable software stacks (PRD 2); and the challenges and opportunities inherent in new technologies, such as VR, cloud, or exascale computing (PRD 3). The remaining two PRDs describe foundational research themes that recognize the potential of visualizations to provide equitable access to information and to strengthen the scientific discourse (PRD 4); and the need to consider human factors when designing visualizations (PRD 5). Collectively, these PRDs form the pillars for a coherent, long-term research and development strategy in Visualization for Scientific Discovery, Decision-Making, and Communication in the context of the Office of Science’s mission scope.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

AI-Enabled Robots for Automated Nondestructive Evaluation and Repair of Power Plant Boilers. Final Report

Boiler failure could cause loss of life and safety issues, cost hundreds of thousands of dollars in equipment repairs, property damage and production losses, and drive up the cost of electric power. Boiler maintenance is challenging and risky for inspectors working on scaffolding in confined hazardous spaces inside of a boiler and sometimes the space is hard to access. The operation is also time-consuming due to the large area of vertical structures for inspection and the tremendous effort needed for scaffolding. Recently, the use of robotics (e.g., drones and crawlers) in power plants for maintenance is growing rapidly. However, the existing robotics solutions show two notable technological gaps: no live repair capability, and no Artificial Intelligence (AI) for smart autonomy. The objective of this project is to develop an integrated autonomous robotic platform that is equipped with compact non-destructive evaluation (NDE) sensors to perform live inspection, operates onboard repair devices to perform live repair, and uses AI for intelligent data fusion and predictive analysis for automated and smart spatiotemporal inspection, analysis and repair of the furnace walls in coal-fired boilers. The approach to achieve the objective includes developing NDE sensors with signal processing techniques, designing and evaluating repair devices for robots based on fusion and solid-state technologies, and an autonomous robotic platform that can attach to and navigate on boiler furnace walls using magnetic drive tracks. The robot is also powered by AI to automate data gathering (e.g., 3D mapping and damage localization) and predictive analysis. This project has advanced the state-of-the-art by providing technological breakthroughs including compact NDE and repair tools for robots, AI capabilities for smart autonomy, and a robotic platform for automated boiler maintenance. This project has great potential to result in significant benefits including limiting or eliminating the need to send operators to assess difficult-to-access or hazardous areas, enabling automated live inspection and repair, avoiding time consuming scaffolding (especially for partial maintenance during unplanned outage), collecting comprehensive and well-organized data smartly, and avoiding or limiting the need for onsite or remote piloting technicians. The impacts can be tremendous in terms of the time and cost savings, reducing the risk for human operators, and increasing boiler reliability, usability, and efficiency. In addition, by developing the new technologies on the autonomous inspection and repair robot, by involving multiple undergraduate and graduate students working together with the faculty members on this project, and by generating knowledge and building up collaborations with industrial partners, this effort will significantly update the education capabilities, support long-term fundamental research, and maintain the leadership of Colorado School of Mines and Michigan State University in energy fields.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗
DOE OSTI2022

Development of Training Materials for Pathologists to Provide Machine Learning Validation Data of Tumor-Infiltrating Lymphocytes in Breast Cancer

The High Throughput Truthing project aims to develop a dataset for validating artificial intelligence and machine learning models (AI/ML) fit for regulatory purposes. The context of this AI/ML validation dataset is the reporting of stromal tumor-infiltrating lymphocytes (sTILs) density evaluations in hematoxylin and eosin-stained invasive breast cancer biopsy specimens. After completing the pilot study, we found notable variability in the sTILs estimates as well as inconsistencies and gaps in the provided training to pathologists. Using the pilot study data and an expert panel, we created custom training materials to improve pathologist annotation quality for the pivotal study. We categorized regions of interest (ROIs) based on their mean sTILs density and selected ROIs with the highest and lowest sTILs variability. In a series of eight one-hour sessions, the expert panel reviewed each ROI and provided verbal density estimates and comments on features that confounded the sTILs evaluation. We aggregated and shaped the comments to identify pitfalls and instructions to improve our training materials. From these selected ROIs, we created a training set and proficiency test set to improve pathologist training with the goal to improve data collection for the pivotal study. We are not exploring AI/ML performance in this paper. Instead, we are creating materials that will train crowd-sourced pathologists to be the reference standard in a pivotal study to create an AI/ML model validation dataset. The issues discussed here are also important for clinicians to understand about the evaluation of sTILs in clinical practice and can provide insight to developers of AI/ML models.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Innovations in Sensors and Controls for Building Energy Management: Research and Development Opportunities Report for Emerging Technologies

Sensors, actuators, and controllers, which collectively serve as the backbone of cyberphysical systems for building energy management, are one of the core technical areas of investment for achieving the U.S. Department of Energy (DOE) Building Technologies Office's (BTO's) goals for energy affordability in the national building stock - both commercial and residential. In fact, an aggregated annual energy savings of 29% is estimated in the commercial sector alone through the implementation of efficiency measures using current state-of-the-art sensors and controls to retune buildings by optimizing programmable settings based on occupant schedules and comfort requirements, as well as detecting and diagnosing equipment operation and installation problems (Fernandez et al. 2017). Monitoring and control of building conditions and operations has advanced significantly, from the invention of the modern thermostat just before the start of the 20th century to the midcentury incorporation of direct digital control into devices, the introduction of open protocols and network communications at the end of the century, and finally the invention of cloud-based computing and additional advancements that have enabled remote operation and a proliferation of connected and intelligent devices in building automation. Despite this potential, however, two main challenges hinder widespread adoption of sensors and controls in building operations that can ensure savings for high-efficiency components and equipment (e.g., heat pumps, windows, and lighting devices), as well as additional savings from more sophisticated control architectures and algorithms. energy savings of 29% is estimated in the commercial sector alone through the implementation of efficiency measures using current state-of-the-art sensors and controls to retune buildings by optimizing programmable settings based on occupant schedules and comfort requirements, as well as detecting and diagnosing equipment operation and installation problems (Fernandez et al. 2017). Monitoring and control of building conditions and operations has advanced significantly, from the invention of the modern thermostat just before the start of the 20th century to the midcentury incorporation of direct digital control into devices, the introduction of open protocols and network communications at the end of the century, and finally the invention of cloud-based computing and additional advancements that have enabled remote operation and a proliferation of connected and intelligent devices in building automation. Despite this potential, however, two main challenges hinder widespread adoption of sensors and controls in building operations that can ensure savings for high-efficiency components and equipment (e.g., heat pumps, windows, and lighting devices), as well as additional savings from more sophisticated control architectures and algorithms.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Automated Integration of Continental-Scale Observations in Near-Real Time for Simulation and Analysis of Biosphere–Atmosphere Interactions

The National Ecological Observatory Network (NEON) is a continental-scale observatory with sites across the US collecting standardized ecological observations that will operate for multiple decades. To maximize the utility of NEON data, we envision edge computing systems that gather, calibrate, aggregate, and ingest measurements in an integrated fashion. Edge systems will employ machine learning methods to cross-calibrate, gap-fill and provision data in near-real time to the NEON Data Portal and to High Performance Computing (HPC) systems, running ensembles of Earth system models (ESMs) that assimilate the data. For the first time gridded EC data products and response functions promise to offset pervasive observational biases through evaluating, benchmarking, optimizing parameters, and training new machine learning parameterizations within ESMs all at the same model-grid scale. Leveraging open-source software for EC data analysis, we are already building software infrastructure for integration of near-real time data streams into the International Land Model Benchmarking (ILAMB) package for use by the wider research community. We will present a perspective on the design and integration of end-to-end infrastructure for data acquisition, edge computing, HPC simulation, analysis, and validation, where Artificial Intelligence (AI) approaches are used throughout the distributed workflow to improve accuracy and computational performance.

Durden, David J.↗
DOE OSTI2020

Learning to Count Grave Sites for Cemetery Observation Models With Satellite Imagery

Understanding how people occupy open spaces is important for research in support of population modeling, policy, national security, emergency response, and sustainability. For the past decade, there has been an increase in research toward capturing and reporting population dynamics and patterns of life at the building level and in some open public spaces such as cemeteries and parks. This is done through observation models developed from local sociocultural information acquired at various spatiotemporal scales to inform night, day, and episodic population occupancy estimates (people/1000 sq ft). Sociocultural information for cemeteries and parks is scarcely available and often collected manually. The process is not only marred by inconsistencies but is laborious and time consuming. In this study, we leverage convolutional neural networks (CNNs) and satellite imagery to derive grave site counts as proxy variables to support scalable and accurate sociocultural data required in a population observation model. Through a hybrid workflow (weak localization plus regression model), we characterize a large scale automation process to counting of grave sites. We evaluate and demonstrate the efficacy of proposed workflow using out-of-data set large satellite imagery and establish its broader impact on cemetery observation models.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗