Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning operations”

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

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

At least 1,279 records · Page 71

Enhanced Precision in Geothermal Reservoir Characterization and Exploitation

The objective of this project is to demonstrate how enhanced analytical and artificial intelligence (AI) algorithms can play a critical role in all phases of geothermal resource development including 1) exploration, 2) exploitation, 3) maintenance, and 4) electric grid integration. A secondary goal, but one that in all likelihood will become more impactful, is to repurpose Introspective System's open source research and deployment architecture, xGraph™, so that is capable of significantly accelerating both the research as well as the deployment of operational systems for exploiting our nation’s vast geothermal resources. This development framework could be used to accelerate deployment by commercial operational enterprises.

15 GEOTHERMAL ENERGY↗

An On-Board Off-Board Framework for Online Replanning: Applied to UAVs in Urban Environments

Autonomous systems are being used in a multitude of areas at an increasing rate and require a high level of adaptivity and intelligence to operate safely, especially under faulty conditions. This paper introduces a novel genetic algorithm tailored for UAV trajectory replanning, with an improved execution time via search space reduction based on the operating conditions of the UAV and its remaining mission. A unique characteristic of the replanning agent is its fast-start and adaptive properties, pre-seeding candidates with partial solutions and dynamically tuning elitism, crossover, and mutation rates in correspondence to the average fitness and diversity of the population. A population restart mechanism and early stopping mechanism are evaluated as well to assess their effect on solution quality and runtime. Previous work on genetic algorithms for UAV replanning were conducted with short trajectories in a small state space. Our UAV operates in a 56,000 square meter simulated urban environment, with static obstacles and a total of 53 possible waypoints. The agent increases the safety and reliability of UAV autonomy when operating under faulty conditions and when replanning is required.

Machine Learning↗

Quality of Candidate Flights and Submission Prediction in Collaborative Digital Departure Reroute

Collaborative Digital Departure Reroute (CDDR) enables the reroute of flights using a flight operator proposed set of alternative route options, referred to as Trajectory Option Set (TOS), in order to reduce delay on the airport's surface and in the Metroplex environment. The reroute functionality is enabled through NASA's Digital Information Platform (DIP). TOS candidate flights are defined as flights with an alternative route with delay savings greater than the flight operator defined relative trajectory cost. This paper analyzes the TOS candidate flights at Dallas/Fort Worth International Airport (KDFW) in the North Texas Metroplex to gain insight into which candidate flights are higher quality through a scoring method. This insight will inform refinements to help CDDR focus on high quality reroute opportunities. Binary classification models for predicting the flight operator's submission of candidate flights are also explored in this paper.

Machine Learning↗

Quality of Candidate Flights and Submission Prediction in Collaborative Digital Departure Reroute

Collaborative Digital Departure Reroute (CDDR) enables the reroute of flights using a flight operator proposed set of alternative route options, referred to as Trajectory Option Set (TOS), in order to reduce delay on the airport's surface and in the Metroplex environment. The reroute functionality is enabled through NASA's Digital Information Platform (DIP). TOS candidate flights are defined as flights with an alternative route with delay savings greater than the flight operator defined relative trajectory cost. This paper analyzes the TOS candidate flights at Dallas/Fort Worth International Airport (KDFW) in the North Texas Metroplex to gain insight into which candidate flights are higher quality through a scoring method. This insight will inform refinements to help CDDR focus on high quality reroute opportunities. Binary classification models for predicting the flight operator's submission of candidate flights are also explored in this paper.

Machine Learning↗

System and Machine Learning-Guided Materials Design for High-Pressure Hydrogen Compression

Cost-effective and reliable hydrogen compression remains a challenging barrier in the widespread adoption of hydrogen as an energy carrier. The prevailing technology of mechanical compression suffers from several drawbacks, some of which can be addressed by nonmechanical compression strategies (e.g., electrochemical or metal hydride-based thermal compression). Thermally driven metal hydride compression strategies typically rely on multistage metal hydride-based compressors; however, discovering or optimizing low-stability metal hydrides that can pressurize hydrogen upward of 1000 bar is difficult, both with respect to computational predictions and experimental validation. Here, in this study, we (1) demonstrate that simple machine learning-derived design rules can inform the rational design of alloying strategies yielding low-stability hydrides, (2) validate their experimental pressure–composition–temperature (PCT) isotherms up to 875 bar, and (3) utilize a dynamic system-level model of a metal hydride compressor design to evaluate their performance under realistic operating conditions. Importantly, this analysis yields predicted operational efficiencies of both 2-stage (90–875 bar) and 3-stage (20–875 bar) metal hydride compressors to enable further evaluation of this technology and its techno-economic outlook.

alloy optimization↗

Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST

In this paper, we report on disruption prediction using a shallow machinelearning method known as Random Forests, trained on large databases containingonly plasma parameters that are available in real-time on Alcator C-Mod, DIII-D, and EAST. The database for each tokamak contains parameters sampled ~10 6 times throughout ~10 4 discharges (disruptive and non-disruptive) over the last 4years of operation. It is found that a number of parameters (e.g.P rad /P input ,l i ,n/n G ,B n=1 /B 0 ) exhibit changes in aggregate as a disruption is approached on one ormore of these tokamaks. However, for each machine, the most useful parameters,as well as the details of their precursor behaviors, are markedly different. When the prediction problem is framed using a binary classification scheme to discriminate between time slices "close to disruption" and "far from disruption," it is found that the prediction algorithms differ substantially in performance among the three machines ona time slice-by-time slice basis, but have similar disruption detection rates (~80-90%) on a shot-by-shot basis after appropriate optimisation. This could have important implications for disruption prediction and avoidance on ITER, for which developmentof a training database of disruptions may be infeasible. The algorithm's output is interpretable using a method that identifies the most strongly contributing inputsignals, which may have implications for avoiding disruptive scenarios. Lastly, to further support its real-time capability, successful applications in inter-shot and real-time environments on EAST and DIII-D are also discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Predicting U.S. federal fleet electric vehicle charging patterns using internal combustion engine vehicle fueling transaction statistics

Utilizing fueling transactions from internal combustion engine vehicles (ICEVs), the authors estimated how frequently midday public charging would be required for U.S. federal fleet battery electric vehicles (BEVs). Fueling transaction summary statistics are more widely available than trip-level telematics data, making this methodology more accessible and transferable to other researchers and fleet managers considering BEV replacements. For example, readers can easily apply a linear model using only the count of back-to-back fueling events at gas stations over 57 straight-line miles apart to predict days exceeding range. This linear regression predicted binned days exceeding 250 miles at 80% accuracy on a hold-out test set from the same fleet as the training data and 66 % accuracy on a new fleet displaying different driving behaviors. The authors additionally provide linear equations for days exceeding 200 and 300 miles as alternative range estimates to account for differences in BEV range and temperature impacts. Beyond the single-feature linear models which readers can apply, the authors tuned and trained other machine learning models on a variety of fueling transaction statistics including consecutive transaction distances, transaction distance from garage, estimated miles traveled from fuel economy and fuel quantity, and transaction periodicity. Utilizing a subset of 1678 light-duty federal fleet vehicles which contained daily vehicle miles traveled (VMT) in addition to fueling statistics, the authors determined which fueling transaction statistics were most relevant in predicting driving days exceeding 250 miles (an approximation of BEV rated driving range). In support of the U.S. federal fleet transition to zero-emission vehicles (ZEVs), the authors used these statistics and machine learning models to predict the frequency of BEV midday charging. After training models on the subset with VMT, the authors predicted days exceeding rated range for 112,902 light-duty vehicles operating in similar circumstances in the federal fleet using a Support Vector Regressor (SVR). In conclusion, they then used the projections as part of the ZEV Planning and Charging (ZPAC) tool to identify optimal candidates for BEVs for the federal fleet. An anonymized version of ZPAC is included in the supplementary materials.

25 ENERGY STORAGE↗

Digitalization of an experimental electrochemical reactor via the smart manufacturing innovation platform

The exponential increase in data produced over the last two decades has revolutionized the way we collect, store, process, analyze, model, and interpret information to improve profitability. Manufacturing is no exception. How- ever, Smart Manufacturing, the digital practice, organization, workforce, and infrastructure transformation for collection and deployment of data and models at scale and at all levels of manufacturing, is a complex, costly, and labor-intensive journey that is still seeing slow adoption. The Clean Energy Smart Manufacturing Innovation Institute (CESMII), a national Manufacturing USA public-private partnership sponsored by the Department of Energy, is addressing this scaled use of data and modeling in manufacturing. CESMII has focused on how to col- lect and use operating data for numerous applications that improve productivity, precision, and performance of manufacturing operations from factory floor to supply chain using process simulation, predictive analytics, mon- itoring and control, and real-time optimization. Because contextualized data are key, CESMII has developed the Smart Manufacturing Innovation Platform (SMIP) to lower the barriers to the data that are needed to accelerate data-based model building, improve data visualization, and more quickly gain insights. Reusable, standards-based ways of doing data collection, ingestion, and contextualization are particularly important for scaling access and use of data. The SMIP uses a standards-based definition and construct for reusable information models called an SM Profile. When an SM Profile is used in conjunction with the SMIP, the SMIP ensures the availability of contextualized, operational data for model building. The present work demonstrates Smart Manufacturing and the application of the SMIP for building several data-centered models for the operation and control of an ex- perimental electrochemical reactor that reduces carbon dioxide (CO 2 ) gas to valuable liquid and gas chemicals, such as alcohols, olefins, and syngas. We describe how the SMIP plays a central role in more effective model building and we demonstrate how the electochemical reactor can be controlled and optimized for the desired products. Use of the SMIP involves the transmission of real-time sensor measurements to a cloud resource so that the operating data are available to all model building experts. The data collection and transmission process is fully automated to greatly reduce the need for manual manipulation of the data. Data-driven machine learning models are used for advanced real-time state estimation, real-time optimization, and model-based feedback control for the reactor. The application models are implemented as a system to monitor the data flow and control the electrochemical reactor with a single visualization interface. SM Profiles are used to demonstrate reusability of the information models for the reactor and the instrumentation. The application packages, algorithms, and user interfaces developed are cast as Docker images in a library to facilitate reusability of the application models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Robust errant beam prognostics with conditional modeling for particle accelerators

Abstract Particle accelerators are complex and comprise thousands of components, with many pieces of equipment running at their peak power. Consequently, they can fault and abort operations for numerous reasons, lowering efficiency and science output. To avoid these faults, we apply anomaly detection techniques to predict unusual behavior and perform preemptive actions to improve the total availability. Supervised machine learning (ML) techniques such as siamese neural network models can outperform the often-used unsupervised or semi-supervised approaches for anomaly detection by leveraging the label information. One of the challenges specific to anomaly detection for particle accelerators is the data’s variability due to accelerator configuration changes within a production run of several months. ML models fail at providing accurate predictions when data changes due to changes in the configuration. To address this challenge, we include the configuration settings into our models and training to improve the results. Beam configurations are used as a conditional input for the model to learn any cross-correlation between the data from different conditions and retain its performance. We employ conditional siamese neural network (CSNN) models and conditional variational auto encoder (CVAE) models to predict errant beam pulses at the spallation neutron source under different system configurations and compare their performance. We demonstrate that CSNNs outperform CVAEs in our application.

43 PARTICLE ACCELERATORS↗

SU-C-BRD-03: Closing the Loop On Virtual IMRT QA

Purpose: To develop an algorithm that predicts a priori IMRT QA passing rates. Methods: 416 IMRT plans from all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam linacs (Varian Medical Systems, Palo Alto, CA). The 3%/3mm and 2%/2mm local distance to agreement (DTA) were recorded during clinical operations using a commercial 2D diode array (MapCHECK 2, Sun Nuclear, Melbourne, FL). Each plan was characterized by 37 metrics that describe different failure modes between the calculated and measured dose. Machine-learning algorithms (MLAs) were trained to learn the relation between the plan characteristics and each passing rate. Minimization of the cross validated error, together with maximum a posteriori estimation (MAP), were used to choose the model parameters. Results: 3%/3mm local DTA can be predicted with an error smaller than 3% for 98% of the plans. For the remaining 2% of plans, the residual error was within 5%. For 2%/2mm local DTA passing rates, 96% percent of the plans were successfully predicted with an error smaller than 5%. All high-risk plans that failed the 2%/2mm local criteria were correctly identified by the algorithm. The most important metric to describe the passing rates was determined to be the MU per Gray (modulation factor). Conclusions: Logs files and independent dose calculations have been suggested as possible substitutes for measurement based IMRT QA. However, none of these methods answer the fundamental question of whether a plan can be delivered with a clinically acceptable error given the limitations of the linacs and the treatment planning system. Predicting the IMRT QA passing rates a priori closes that loop. For additional robustness, virtual IMRT QA can be combined with Linac QA and log file analysis to confirm appropriate delivery.

60 APPLIED LIFE SCIENCES↗

Scanning Probe Microscopy in the Information Age

Scanning probe microscopy (SPM) has brought scientific exploration, visualization, and control to nanoscale. A plethora of measurement approaches and techniques devised around SPM enabled probing structure and functionalities crucial for virtually all areas of science. While high-resolution electron microscopy techniques preceded scanning probes, SPM effectively opened the door to probing the structure–property relationship on length scales spanning 100s of micrometers down to a single atom. As the complexity of the material systems and the scientific questions increased, so too did the SPM techniques. Substantial efforts have been dedicated toward the development of better instrumentation platforms, probes, and novel spectroscopic measurements; however, many opportunities related to data processing and acquisition in SPM are just being realized now. This chapter will describe the recent progress in data-driven SPM by giving a broad overview of the field, the foundation of the scanning tunneling microscope (STM) and the atomic force microscope (AFM), as well as a description behind the operating principles and dynamic modes. A comprehensive overview of the multi-frequency techniques, Band excitation, and general acquisition mode SPM is given, setting the context for the application of big data, machine learning, and artificial intelligence in the field of dynamic SPM.

Collins, Liam↗

Computational Exploration of High Entropy Alloys as Promising Materials for Future Beam Windows

With the ever-increasing demand for high beam power, the currently used beam-intercepting devices (BIDs) such as targets, and beam windows may not be able to handle the high power required for future accelerator complexes or the lifetime may be reduced drastically. As beam power increases, the damage incurred by BIDs, including thermal shock, fatigue, and irradiation damage, also rises. Therefore, it is imperative to design materials that can withstand high beam power for longer lifetimes. High entropy alloys (HEAs) have emerged as potential alternative materials for designing next-generation BIDs. In this study, we primarily focus on materials for developing beam windows for next-generation accelerator complexes. We propose an integrated approach that combines various computational techniques to study and design new materials. Specifically, we use CALPHAD, density functional theory (DFT), and molecular dynamics (MD) to comprehensively investigate the defect properties of suitable HEAs, offering potential alternatives for future beam windows. We begin by scanning the extensive phase space provided by Cr-Mn-V-Ti-Al-Co HEAs, selecting 8 compositions after evaluating approximately 120,000 unique compositions using CALPHAD. We, then employ DFT-informed machine learning techniques to develop force-field parameters. Finally, MD simulations using these developed force-field parameters will be used to study the effects of radiation damage on the defect and mechanical properties of the selected alloys. This research explains the use of the CALPHAD approach and shows how critical modeling (DFT and MD) is in developing novel material such as HEAs. It also highlights the promising role of machine learning in this field. The results from this study will greatly improve the novel materials development to be used in next-generation accelerator components, leading to higher beam power and longer operational times of BIDs.

43 PARTICLE ACCELERATORS↗

Overview of SMART Initiative

The objective of the SMART Initiative, i.e., Science-informed Machine Learning (ML) for Accelerating Real-Time Decisions in Subsurface Applications, is to show how the utilization of ML can significantly improve efficiency and effectiveness of field-scale commercial carbon storage operations in three main areas: real-time visualization, virtual learning, and real-time forecasting. This presentation reports the status of SMART initiative for demonstrating: (a) virtual learning during the pre-injection permitting phase, and (b) ML-assisted operational decision making and visualization.

Siriwardane, Hema↗

SMART – A Comprehensive Research and Development Program to Demonstrate Application of Machine Learning for Supporting CCS Deployment

Presentation material for a paper presented at the GHGT-17 conference, Calgary, Canada, October 20-24, 2024. The objective of the US Department of Energy’s SMART Initiative, i.e., Science-informed Machine Learning (ML) for Accelerating Real-Time Decisions in Subsurface Applications, is to showcase how the utilization of ML can significantly improve efficiency and effectiveness of field-scale commercial carbon storage operations. This paper will present the results from the current phase of SMART (field deployment) for demonstrating the applicability of ML-based tools and workflows for: (a) virtual learning during the pre-injection permitting phase, (b) advanced storage reservoir imaging to better characterize fractures and faults, and (c) dynamic storage reservoir modelling and optimization to inform operational decision making and visualization of system evolution.

CO2 geologic storage↗

Editorial: Predicting near-earth space environment: new perspective and capabilities in the AI age

Editorial on the Research Topic Predicting near-earth space environment: new perspective and capabilities in the AI age The near-Earth space environment is not only an operational hazard for space missions, but also a scientific laboratory for advancing our understanding and prediction of space plasma populations. This Research Topic is organized around three interconnected themes: observational datasets, machine-learning (ML) model development, and the discovery of new physical insights through those models. Its primary goal is to highlight the emerging capabilities in space environment prediction that are enabled, or will be enabled, by integrating advanced techniques—including AI/ML methods—with long-term curated datasets.

58 GEOSCIENCES↗

Uncertainty in counting ice nucleating particles with continuous flow diffusion chambers

Abstract. This study investigates the measurement of ice nucleating particle (INP) concentrations and sizing of crystals using continuous flow diffusion chambers (CFDCs). CFDCs have been deployed for decades to measure the formation of INPs under controlled humidity and temperature conditions in laboratory studies and by ambient aerosol populations. These measurements have, in turn, been used to construct parameterizations for use in models by relating the formation of ice crystals to state variables such as temperature and humidity as well as aerosol particle properties such as composition and number. We show here that assumptions of ideal instrument behavior are not supported by measurements made with a commercially available CFDC, the SPectrometer for Ice Nucleation (SPIN), and the instrument on which it is based, the Zurich Ice Nucleation Chamber (ZINC). Non-ideal instrument behavior, which is likely inherent to varying degrees in all CFDCs, is caused by exposure of particles to different humidities and/or temperatures than predicated from instrument theory of operation. This can result in a systematic, and variable, underestimation of reported INP concentrations. We find here variable correction factors from 1.5 to 9.5, consistent with previous literature values. We use a machine learning approach to show that non-ideality is most likely due to small-scale flow features where the aerosols are combined with sheath flows. Machine learning is also used to minimize the uncertainty in measured INP concentrations. We suggest that detailed measurement, on an instrument-by-instrument basis, be performed to characterize this uncertainty.

54 ENVIRONMENTAL SCIENCES↗

Marin County Wildland Fires: Examining Fuel Load and Land Cover Change to Inform Fire Prevention and Suppression Decisions in Marin County, CA

Heightened occurrence of severe wildfires in the Western United States is increasing the need to better understand regions of high potential wild fire severity and develop methodologies for identifying the best locations for fuels reduction and active wildfire suppression, especially in populated regions such as Marin County, California. Marin County, located in the San Francisco Bay Area, has had significant development in the wildland-urban interface and periods of highly wildfire-prone conditions. The NASA DEVELOP team collaborated with Fire Foundry, a Marin-based fire service work force development program, to develop new models to assist with fire management. Using data from Sentinel-2A, Planet Scope, ECOSTRESS, a county-wide LiDAR mapping effort, Landsat 7 Enhanced Thematic Mapper (ETM+), and Landsat 8 Operational Land Imager (OLI), the team developed several input data layers to three models evaluating wild fire severity. One model performed a suitability analysis with weights based on scientific literature, another utilized machine learning based on past fires in Marin and neighboring Sonoma County to predict the difference normalized burn ratio, and the third inputted data layers into the Flam Map tool, which outputs risk categories. The team compared model outputs and, using the best-fit model, performed fuzzy logic analysis to identify specific locations where a fire break could be constructed to interrupt the progress of an active fire. These tools were proven useful and will assist partners in preparing for and managing an active wildfire event.

Suhani Dalal↗

Probabilistic Forecasting of Generators Startups and Shutdowns in the MISO System Based on Random Forest

Solving security constrained unit commitment (SCUC) problems to plan an economical generation schedule for day-head electricity market has been an important research topic in recent years. Mixed integer programming method (MIP), the-state-of-art approach for solving SCUC problem, is known computationally hard when the number of binary status variables is large. In this paper, a machine learning-based algorithm - random forest (RF), was applied to forecast the startups (SU) and shutdowns (SD) hours of generators, based on historical hourly system condition observations in the Midcontinent Independent System Operator (MISO) system. The main purpose is to reduce the number of binary status variables, by fixing the SU/SD hours to a narrow range of high confidence. This would significantly reduce the size of the decision space, and therefore speed up SCUC solutions with reduced uncertainty.

Lin, Xinming↗