Search NASA⌕ Search

SEARCH · Search NASA

Results for “Operator learning”

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

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

At least 1,603 records · Page 89
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

Automated Mapping of Flood Events in the Mississippi River Basin Utilizing NASA Earth Observations

The Mississippi River Basin is the fourth largest drainage basin in the world, and is susceptible to multi-level flood events caused by heavy precipitation, snow melt, and changes in water table levels. Conducting flood analysis during periods of disaster is a challenging endeavor for NASA's Short-term Prediction Research and Transition Center (SPoRT), Federal Emergency Management Agency (FEMA), and the U.S. Geological Survey's Hazards Data Distribution Systems (USGS HDDS) due to heavily-involved research and lack of manpower. During this project, an automated script was generated that performs high-level flood analysis to relieve the workload for end-users. The script incorporated Landsat 8 Operational Land Imager (OLI) tiles and utilized computer-learning techniques to generate accurate water extent maps. The script referenced the Moderate Resolution Imaging Spectroradiometer (MODIS) land-water mask to isolate areas of flood induced waters. These areas were overlaid onto the National Land Cover Database's (NLCD) land cover data, the Oak Ridge National Laboratory's LandScan data, and Homeland Infrastructure Foundation-Level Data (HIFLD) to determine the classification of areas impacted and the population density affected by flooding. The automated algorithm was initially tested on the September 2016 flood event that occurred in Upper Mississippi River Basin, and was then further tested on multiple flood events within the Mississippi River Basin. This script allows end users to create their own flood probability and impact maps for disaster mitigation and recovery efforts.

Bartkovich, Mercedes↗
NASA NTRS2018

A Prognostic Launch Vehicle Probability of Failure Assessment Methodology for Conceptual Systems Predicated on Human Causal Factors

Lessons learned from past failures of launch vehicle developments and operations were used to create a new method to predict the probability of failure of conceptual systems. Existing methods such as Probabilistic Risk Assessments and Human Risk Assessments were considered but found to be too cumbersome for this type of system-wide application for yet-to-be-flown vehicles. The basis for this methodology were historic databases of past failures, where it was determined that various faulty human-interactions were the predominant root causes of failure rather than deficient component reliabilities evaluated through statistical analysis. This methodology contains an expert scoring part which can be used in either a qualitative or a quantitative mode. The method produces two products: a numerical score of the probability of failure and guidance to program management on critical areas in need of increased focus to improve the probability of success. In order to evaluate the effectiveness of this new method, data from a concluded vehicle program (USAF's Titan IV with the Centaur G-Prime upper stage) was used as a test case. The theoretical vs. actual probability of failure was found to be 4.46% vs. 6.67% respectively. Recommendations are made for future applications of this method to ongoing launch vehicle development programs.

Launch Vehicle↗
NASA NTRS2019

Maturation of Dynamic Power Convertors for Radioisotope Power Systems

Dynamic Radioisotope Power Systems (DRPS) are being developed by NASA’s Radioisotope Power Systems (RPS) Program in collaboration with the U.S. Department of Energy (DOE) for space science and exploration missions. A development effort is currently underway to mature dynamic power convertors for infusion into a potential future flight generator. This convertor maturation effort was formulated by the RPS Program at NASA Headquarters based on successful maturation models and utilizes expertise from agency’s technology and mission centers to support requirements development and technology assessments. The effort is being executed by Glenn Research Center’s (GRC) DRPS Project and the Thermal Energy Conversion Branch. The Dynamic Power Convertor (DPC) contracts consist of three phases to enable design, fabrication, and independent assessment of prototypes after delivery to the government. The contracts are intended to gather data on candidate dynamic conversion technologies to fill knowledge gaps, support assessments of dynamic conversion technologies, and elicit generator requirements. The 110-watt Stirling Radioisotope Generator (SRG-110) and Advanced Stirling Radioisotope Generator (ASRG) flight development projects provided Stirling convertor demonstration units and engineering models to verify and validate convertors against performance specifications and mission requirements. These units utilize temperature resistant materials and non-contacting bearings to demonstrate wear-free, long-life operation. This maturation effort builds on past lessons-learned and new requirements focused on demonstrating convertor robustness to critical environments meant to stress key aspects of each convertor within the margins of the design. This effort seeks to realize the full potential of dynamic power conversion technologies for NASA’s space science and exploration missions.

Wilson, Scott↗
NASA NTRS2017

Relay Communications Support to the ExoMars Schiaparelli Lander

The European Space Agency’s ExoMars Trace Gas Orbiter (TGO) arrived at Mars on October 19, 2016, three days after releasing the Schiaparelli Lander on a ballistic trajectory to Meridiani Planum. During the separation event, and subsequently during Schiaparelli’s Entry, Descent, and Landing (EDL), the NASA-provided Electra UHF payload onboard TGO was used to record signals from the Schiaparelli Lander for post-processing on the ground to recover both tracking of the lander’s carrier signal and reconstruction of the lander’s 8 kb/s telemetry. In addition, ESA’s Mars Express orbiter also recorded the Schiaparelli signal, with ground post-processing providing independent tracking of the lander carrier signal, and the Giant Metrewave Radio Telescope near Pune, India was configured to provide real-time detection of the lander carrier signal. While an anomaly in the latter stages of EDL led to loss of the lander, these critical event data sets, and in particular the telemetry reconstruction enabled by the TGO Electra recording, proved essential in enabling detailed diagnosis of the anomaly. And while the loss of the lander during EDL precluded the planned surface relay operations, the preparations for that activity provide important lessons learned for future Mars relay support scenarios.

Edwards, Charles D., Jr.↗
NASA NTRS2019

Prognostic Launch Vehicle Probability of Failure Assessment Methodology for Conceptual Systems Predicated on Human Causal Factors

Lessons learned from past failures of launch vehicle developments and operations were used to create a new method to predict the probability of failure of conceptual systems. Existing methods such as Probabilistic Risk Assessments and Human Risk Assessments were considered but found to be too cumbersome for this type of system-wide application for yet-to-be-flown vehicles. The basis for this methodology were historic databases of past failures, where it was determined that various faulty human-interactions were the predominant root causes of failure rather than deficient component reliabilities evaluated through statistical analysis. This methodology contains an expert scoring part which can be used in either a qualitative or a quantitative mode. The method produces two products: a numerical score of the probability of failure or guidance to program management on critical areas in need of increased focus to improve the probability of success. In order to evaluate the effectiveness of this new method, data from a concluded vehicle program (USAF's Titan IV with the Centaur G-Prime upper stage) was used as a test case. Although the theoretical vs. actual probability of failure was found to be in reasonable agreement (4.46% vs. 6.67% respectively) the underlying sub-root cause scoring had significant disparities attributable to significant organizational changes and acquisitions. Recommendations are made for future applications of this method to ongoing launch vehicle development programs.

Craig H Williams↗
NASA NTRSDate not supplied

Tours of High-containment and Pristine Facilities in Support of Mars Sample Return (MSR) Sample Receiving Facility (SRF) Definition Studies

During 2019 and 2020, the NASA Tiger Team RAMA (acronym of the authors) toured several high-containment biosafety laboratories and pristine space-mission facilities worldwide to better understand their practices, capabilities, and lessons-learned to aid in planning a Sample Receiving Facility (SRF) in support of Mars Sample Return (MSR). The team also included tours of a manufacturer of mobile and modular high-containment facilities as well as manufacturers of isolators and gloveboxes. In addition, the team visited the European Space Agency (ESA)ultraclean and sterile ISO 3 / airborne molecular contamination -9 (AMC-9) isolator line to clean and assemble the most critical hardware for ESA’s ExoMars Mars Lander System, and researchers developing a novel double-walled isolator (DWI) and robotic handling techniques in support of an MSR SRF. The RAMA team visits covered several construction modalities for an MSR SRF: (1) a new traditional fixed facility; (2) use of an existing fixed Biosafety Level 4(BSL-4) facility; (3) a novel modular BSL-4 approach; and (4) a hybrid combination of fixed, modular, and existing facilities. A new fixed facility approach can be tailored to MSR’s needs and is the approach used by all U.S. BSL-4 laboratories constructed to date. However, this approach could be the most expensive modality, take the longest to implement (8-12 years), and have significant programmatic risk of delay. The utilization of an existing BSL-4 facility may be possible depending on the final contamination control and science requirements for the MSR SRF. Due to the internal dimensions of the labs visited and facility structural requirements, it is unlikely that any modification can be made to the facility to meet cleanliness requirements. Furthermore, due to possible construction delays, possible capacity issues, and potential cross contamination vectors from in-house select agents, there may also be significant programmatic risks for sharing an existing facility. Another approach is building a contemporary modular facility. This is a novel approach that has recently been used for a BSL-3/3Ag facilities. The modular elements would be installed in a traditional building or shell structure. A modular facility has many advantages over a traditional fixed facility with lower costs, shorter design/construction/ commissioning schedule, and flexibility for easier retrofits and future expansion. Lastly, a hybrid approach of combining the use of either: (1) a modular facility inside a new fixed facility or (2) a modular and/or fixed BSL-4 annex in conjunction with an existing BSL-4 space should be considered. The advantage of a hybrid approach is that the facility could leverage the strengths of other approaches. Beyond facility construction approaches, the RAMA team investigated technologies and techniques for isolating and handling Martian samples in pristine environments. For example, ESA has been studying and developing a DWI breadboard along with other sample-handling technologies. The research and development investment for clean, remote manipulation and robotics at the start of the facility design phase would be beneficial to the SRF. Additionally, under-standing the lessons learned from Thales Alenia Space during the construction and operation of the most advanced state-of-the-art precision cleaning, sterilization, and assembly glovebox isolators ever developed for spacecraft hardware are also critical for the SRF. The RAMA team lays out a summary of the 18 facilities toured, and includes 43 observations,18 findings, and 22 areas of possible follow-up that the RAMA team and others could pursue to enable further findings. The observations and findings illustrate that constructing an MSR SRF would combine the complexity of both high-containment and pristine facilities, and merging these technologies would be challenging, but achievable.

Mars Sample Return↗
NASA NTRSDate not supplied

Leveraging VIPER Geotechnical and Mobility Insights for Endurance Rover and Traverse Development

A new generation of lunar surface rover exploration is rapidly approaching. This is evidenced by the rise of commercially developed rovers from private companies (e.g., Lunar Outpost’s MAPP) and government agencies, like NASA’s Volatiles Investigating Polar Exploration Rover (VIPER), the Lunar Terrain Vehicle (LTV), and the Endurance/Intrepid rover concepts, and the INSPIRE mission concept. The drive distance requirements for off-world vehicles are also rapidly increasing. For example, LTV driving requirements dictate a 20 km range on a single battery charge, with an overall lifetime requirement of 13,000 km over a minimum 10-year service life. Similarly, NASA's Endurance-A mission concept requires a 2000 km vehicle traverse distance, which is nearly 50 times further than the USSR's Lunokhod 2, the longest lunar rover mission to date. Previous planetary surface missions on the Moon and Mars have revealed harsh mobility conditions: aggressive rocky terrains on Mars severely damaged the Curiosity rover’s wheels, soft lunar regolith caused the Lunokhod 2 rover to sink and NASA’s Apollo 15 LRV (Lunar Roving Vehicle) spun out due to poor traction, which required manual correction. This demonstrates that mobility challenges like wheel degradation and soft soil driving performance must be accounted for in a mission’s design phase to meet increasingly aggressive mission durations and mobility goals. The success of these long duration missions requires highly reliable and durable mobility platforms in conjunction with a more developed understanding of the geotechnical properties of the lunar surface. The VIPER mission is uniquely posed to inform future missions about mobility performance, wheel durability, and lunar surface soil mechanics of sunlit and shadowed regions through use of data streams that already exist for other mission purposes. VIPER’s mission to the lunar south pole will provide a new perspective into off-world mobility challenges including traversal into permanently shadowed regions. Mobility data from VIPER’s mission will represent a first glimpse into the surface mobility challenges of the lunar South Pole. Utilization of VIPER’s existing capabilities including cameras, inertial measurement unit (IMU) data, motor currents/torque, drill data, and the rover’s suspension state and kinematics provide the opportunity to determine potentially useful information for future rover and traverse designs, as well as on-Earth testing practices. Data products collected during VIPER’s mission could inform design considerations for the Endurance rover much earlier than NASA’s standard “lessons learned” approach as VIPER has a highly tactical mission operations structure. This work outlines the specific links between possible data products from the VIPER mission and their potential impact on the Endurance/Intrepid mission concepts in their early design phases. From VIPER, we will also gain insights for future development of onboard mobility software as VIPER is a way-point driven rover which requires more constant human operation on Earth than some other rover missions (non-lunar surface). Primary VIPER data products and insights of interest include wheel sinkage, wheel slip, wheel degradation, surface soil shear strength, and terrain slope estimation. VIPER data products will be made available via the Planetary Data System’s Geosciences and Cartography and Imaging Sciences nodes, conforming to the PDS4 standard.

mobility↗
NASA NTRS2023

A Hyperspectral Inversion Framework for Estimating Absorbing Inherent Optical Properties and Biogeochemical Parameters in Inland and Coastal Waters

The simultaneous remote estimation of biogeochemical parameters (BPs) and inherent optical properties (IOPs) from hyperspectral satellite imagery of globally distributed optically distinct inland and coastal waters is a complex, unsolved, non-unique inverse problem. To tackle this problem, we leverage a machine-learning model termed Mixture Density Networks (MDNs). MDNs outperform operational algorithms by calculating the covariance between the simultaneously estimated products. We train the MDNs on a large ( N = 8237) dataset of co-aligned, in situ measured, hyperspectral remote sensing reflectance (R rs ), BPs, and absorbing IOPs from globally representative optically distinct inland and coastal waters. The estimated IOPs include absorption due to phytoplankton (a ph ), chromophoric dissolved organic matter (a cdom ), and non-algal particles (a nap ). The estimated BPs include chlorophyll-a, total suspended solids, and phycocyanin (PC). MDNs dramatically reduce uncertainty in the retrievals, relative to operational algorithms, when using a 50/50 dataset split, where the MDNs are trained on a randomly selected half of the in situ dataset and validated on the other half. Our model is shown to have higher, or equivalent, generalization performance than the calculated operational algorithms available for all BPs and IOPs (except PC) via a leave-one-out cross-validation assessment. The MDNs are sensitive to uncertainties in the hyperspectral satellite R rs , resulting from instrument noise and atmospheric correction; there is a difference of ~37.4–62.8% (using median symmetric accuracy) between the MDNs’ estimates derived from co-located satellite-derived R rs and in situ R rs . Of the IOPs, a cdom and a nap are less sensitive to uncertainties in hyperspectral satellite imagery relative to a ph , with remote estimates of a ph exhibiting incorrect spectral shape and magnitude relative to in situ measured IOPs. Despite the uncertainties in satellite derived R rs , the spatial distributions of BPs and IOPs in MDN-derived product maps of Lake Erie and the Curonian Lagoon, based on imagery taken with the Hyperspectral Imager for the Coastal Ocean (HICO) and PRecursore Iper-Spettrale della Missione Applicativa (PRISMA), are confirmed via co-aligned in situ measurements and agree with the literature’s understanding of these well-studied regions. The consistency and accuracy of the model on HICO and PRISMA imagery, despite radiometric uncertainties, demonstrate its applicability to future hyperspectral missions, such as the Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission, where the simultaneous estimation model will serve as a key part of phytoplankton community composition analysis.

Ryan E. O'Shea↗
DOE OSTI2020

AI-Science for Performance Optimization and Diagnosis of Science Instrument Federations

Next generation of science workflows are expected to be executed over complex federations composed of supercomputers, science instruments, storage systems and networks, with new additions of the edge and cloud systems and services. The sheer complexity of these multi-domain federations makes it hard to manage them and optimize their performance, as small impedance mismatches (that can dynamically develop between systems) could drastically degrade the entire federation performance. Recent proliferation of Software Defined Everything (SDX) technologies combined with containerization frameworks provide custom instruments that can monitor and collect critical measurements at various levels to support diagnoses and performance optimization; but their data too enormous for human operators and analysts to process and generate decisions. Machine Learning (ML) methods that extract critical parameters, relationships and trends from the data offer general solutions. Artificial Intelligence (AI) and ML methods must be custom-developed for these problems based on solid, rigorous foundations, since black-box approaches are often ineffective and unsound.We propose to develop comprehensive AI-Science for the performance of science federations to (i) monitor and control storage, networks, experiments, and computing systems across multiple domains via softwarization layers, at speeds and scales orders of magnitude superior to current practice, (ii) optimally realize and orchestrate complex workflows with high performance by using dynamic state and performance estimation methods, and (iii) aggregate measurements across sites and time to develop infrastructure-level profiles, optimizations and diagnoses using AI-Science based on foundational principles from ML, game theory, and information fusion areas.

Rao, Nageswara↗
DOE OSTI2021

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data (Final Report)

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components: (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2018

Replacement of Melter 2 at the Defense Waste Processing Facility (DWPF) - 18608

The original DWPF melter was replaced in 2002 with an identical unit, and radioactive operation of Melter 2 commenced in 2003. After nearly 14 years of service, a lower electrode failure of Melter 2 occurred in February 2017 which required its removal and replacement with Melter 3. The scope of the replacement outage involves several significant evolutions: - Shutdown of Melter 2 and placement into a safe state; - Remote external and internal inspection of Melter 2 to chronicle its condition prior to removal; - Disassembly and removal of Melter 2 from the process cell; - Placement of Melter 2 into a storage box and transport to a storage vault; - Preparation and initial testing of Melter 3 prior to transport to the DWPF; - Transport to the DWPF and installation of Melter 3 in the process cell; - Final startup testing and initiation of radioactive operation. Upon determination that repair of Melter 2 was not feasible, DWPF created an outage team to integrate schedules and resources needed to execute melter replacement as well as including maintenance scope for facility work that can only be performed when the melter is de-energized. The execution of this scope required integration with other mission critical outage activities already in progress, and planned to start, including initial facility tie-in scope for the new Salt Waste Processing Facility (SWPF). This unplanned addition of the melter replacement scope to the existing outage scope resulted in the longest facility outage period since the initiation of radioactive operations at the DWPF in 1996. Successful completion of this scope across all Liquid Waste facilities would require balance - for schedules, resources, priority, funding, etc. To overcome the significant challenges created by this additional scope, a WAR Room was established to ensure adequate integration and coordination of critical resources, and daily progress. The execution of this scope has required the integration of nearly two dozen work groups across multiple facilities at Savannah River Site (SRS), in addition to support from nearly a dozen vendors. The melter replacement outage was executed with a high degree of disciplined operation to ensure the facility was ready to resume glass pouring operation in time to support restart of the Liquid Waste program at the Savannah River Site (SRS). This paper will provide a brief overview of Melter 2 operational history. The execution of the removal and replacement operations will be described with a specific focus on lessons learned and opportunities where the outage execution diverged from the original Melter 1 replacement outage. It is expected to be of interest to vitrification facilities, as well as facilities, which require remote maintenance and replacement of large process equipment. (author)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS1993

The measurement and analysis of leaf spectral reflectance of two stands of loblolly pine populations

My research was conducted under the mentorship of Dr. Jeff Luvall. I worked at Marshall from June 1 through August 6, 1993. My proposal is titled 'The Measurement and Analysis of Leaf Spectral Reflectance of Two Stands of Loblolly Pine Populations.' The populations for this study were chosen from a larger population of 31 families managed by the International Forest Seed Company, Odenville, Alabama. The technology for mobile ground base spectral detecting is new and therefore the majority of time, June 2 through July 9, was spent on learning the techniques of the Spectrometer 2 spectroradiometer used in the gathering of spectra information. The activities included in the learning process were as follows: calibration of the equipment, programming the associated computer for data management, operation of the spectral devices, and input and output of data. From July 12 through August 3 the time was spent on learning the 'STATGRAP' computer software. This software will be used in the analysis of the data retrieved by the Spectrometer 2 spectroradiometer. Dr. Greg Carter, at Stennis, a colleague of Dr. Luvall, has been conducting similar work with different instruments and procedures and has agreed to host us for a training session on data gathering and analysis. This visit, which has previously planned for July 9, 1993, but had to be postponed because of schedule conflicts, is now confirmed for August 18-22, 1993. This trip to Stennis will provide the knowledge for conducting the field operations in my study, i.e., gathering of data and file conversions.

Paul, Anthony D.↗
DOE OSTI2021

High-dimensional Data-driven Energy optimization for Multi-Modal Transit Agencies (HD-EMMA) (Final Technical Report)

Public bus transit services in the U.S. are responsible for at least 19.7 million metric tons of CO 2 emission annually. Electric vehicles (EVs) can have a much lower environmental impact than comparable internal combustion engine vehicles (ICEVs), especially in urban areas. Unfortunately, EVs are also much more expensive than ICEVs. As a result, many public transit agencies can afford only mixed fleets of transit vehicles, consisting of EVs, hybrids (HEVs), and ICEVs. Transit agencies that operate such mixed fleets of vehicles face a challenging optimization problem: these agencies need to decide which vehicles are assigned to serving which transit trips. Since the advantage of EVs over ICEVs varies depending on the route and time of day (e.g., the benefit of EVs is higher in slower traffic with frequent stops and lower on highways), the assignment can have a significant effect on energy use and, hence, environmental impact. Through this project, we have developed reference data about energy collections and constructed a set of machine learning models that can accurately predict the energy consumption for the whole fleet at the level of each trip. We have used these models to develop a scheduling and assignment strategy that can rotate the different vehicle types across the transit agencies’ routes. The optimization algorithm ensures that the vehicles are matched to trips considering weather patterns, expected congestion, and road gradients to minimize the overall energy usage. We list the key observations from our project for other practitioners below. Details are available in the report, and the list of source code and our publications are included in the appendix. 1. We have demonstrated the feasibility of collecting, merging and analyzing large volumes of high-resolution real-world telemetry data from a mixed vehicle fleet. To mitigate the inherent noise of the recorded GPS points, the team developed an algorithm that filters data and maps the points onto a street. The algorithm considers previous and subsequent location measurements and different characteristics of nearby streets to determine how likely the vehicle travels on them. Then, the team segmented the time series into disjoint contiguous samples based on adjacent road segments and repeated the outlier detection and removal. For each data point, the team added features corresponding to elevation changes within the samples, weather features, such as temperature, and traffic data, such as speed ratio between actual speed and free-flow speed. 2. We have developed two forms of machine learning models that be used to understand and analyze the energy operations of a mixed vehicle transit fleet. The micro prediction model provides estimates of instantaneous energy prediction for all types of buses (diesel, hybrid, and electric). Such a model is important in evaluating the energy impacts of real-time bus operation strategies, but it is challenging due to diversified driving cycles of transit buses. The model can help the drivers understand the impact of their driving behaviors and short-term congestions. The macro prediction models estimate average energy consumption across the whole trip considering the features: distance traveled, various road-type features, elevation change, day of the week, time of day, various weather features (temperature, humidity, etc.), and traffic features (speed ratio and jam factor). 3. We have demonstrated that it is possible to transfer the machine learning models we have developed in this project to other teams and cities by using inductive transfer learning. We also showed that the performance of the macro energy prediction models can be improved using a multi-task learning approach where the learning parameters are shared between the models being developed for different vehicle types. The advantage of this approach is improved learning performance as the models can exploit common spatio-temporal and environmental characteristics. 4. Finally, we have developed trip and vehicle assignment and scheduling algorithms that use the energy prediction models and develop a trip to vehicle type (diesel, electric, hybrid) assignment for the whole operation to reduce overall emissions and cost. We have shown through simulations that the proposed algorithms can save $\$$ 48,910 in energy costs and 175 metric tons of CO 2 emission annually for CARTA.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Post-2026 Environmental Impact Statement Rate Analysis for the Colorado River Storage Project

The Glen Canyon Dam (GCD) is a principal power-generating asset within the Colorado River Storage Project (CRSP), accounting for approximately 70–80% of CRSP power production over the past two decades. In June 2023, the U.S. Bureau of Reclamation (Reclamation) issued a Notice of Intent to prepare an Environmental Impact Statement (EIS) outlining operational guidelines and strategies for Colorado River Basin reservoirs after 2026 (Reclamation, 2023). Power generation is among CRSP’s statutory purposes under the Colorado River Storage Project Act of 1956 (U.S. Congress, 1956). Assessing how alternative policy frameworks affect CRSP power production and the resulting electricity rates for U.S. customers is therefore essential to inform decision-making. This report evaluates projected electricity rates and the market value of electricity from the Western Area Power Administration (WAPA) CRSP GCD under multiple post-2026 policy scenarios to support Reclamation’s EIS development. Results from advanced econometric and machine learning models indicate that the Enhanced Coordination alternative (EnhanCoor), Maximum Operational Flexibility alternative (CCA), and Supply Driven - 55 alternative (SD55) alternatives yield more favorable hydropower generation and capacity outcomes, which are objectives outlined in Reclamation’s documentations (Reclamation, 2007; Reclamation, 2016). Specifically, these scenarios are associated with higher electricity production, lower projected rate trajectories, and greater economic value to the U.S. power system from CRSP generation. The remaining five scenarios generally produce lower generation, higher rate trajectories, and reduced long-term market values.

13 HYDRO ENERGY↗
DOE OSTI2022

Koopman-based Differentiable Predictive Control for the Dynamics-Aware Economic Dispatch Problem

The dynamics-aware economic dispatch (DED) problem embeds low-level generator dynamics and operational constraints to enable near real-time scheduling of generation units in a power network. DED produces a more dynamic supervisory control policy than traditional economic dispatch (T-ED) that reduces overall generation costs. However, the incorporation of differential equations that govern the system dynamics makes DED an optimization problem that is computationally prohibitive to solve. In this work, we present a new data-driven approach based on differentiable programming to efficiently obtain offline parametric solutions to the underlying DED problem. In particular, we employ the recently proposed differentiable predictive control (DPC) for offline learning of explicit neural control policies based on identified Koopman operator (KO) model of the system dynamics. We demonstrate the high solution quality and five orders of magnitude computational-time savings of the DPC method over the original optimization-based DED approach on a 9-bus test power grid network.

King, Ethan↗
DOE OSTI2026

Transfer learning for analysis of collective and non-collective Thomson scattering spectra

Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density (⁠n e ) and electron temperature (⁠T e ⁠). Deep neural networks can provide accurate estimates of ⁠n e and T e when conventional fitting algorithms may fail, such as when TS spectra are dominated by noise, or when fast analysis is required for real-time operation. Although deep neural networks typically require large training sets, transfer learning can improve model performance on a target task with limited data by leveraging pre-trained models from related source tasks, where select hidden layers are further trained using target data. We present five architecturally diverse deep neural networks, pre-trained on synthetic TS data and adapted for experimentally measured TS data, to evaluate the efficacy of transfer learning in estimating n e and T e in both the collective and non-collective scattering regimes. We evaluate errors in n e and T e estimates as a function of training set size for models trained with and without transfer learning, and we observe decreases in model error from transfer learning when the training set contains ≲ 200 experimentally measured spectra.

Artificial neural networks↗
DOE OSTI2025

Accurate and rapid acoustic damage characterization in complex structures using sparse sensor networks and deep learning models

Damage diagnosis in critical components is essential for ensuring the safety and reliability of operations across industries, spanning manufacturing, aerospace, and energy. Traditional acoustic nondestructive testing methods primarily focus on detecting defects through the direct scattering of single-mode incident waves from the damage, which limit their applicability to simple structures and small inspection areas. Our earlier research demonstrated that machine learning algorithms combined with sparse sensor networks can identify critical defect signatures even from multiply scattered, multi-mode acoustic signals, indicating the potential for improved defect inspection in complex, real-world structures. In this work, we demonstrate the successful implementation of this approach in a fixed sensor configuration to rapidly and accurately detect simulated defects in a geometrically complex, real-world structure, a brake rotor hub. Three different types of defects were physically simulated on the surface of the hub, and the collected data were used to train an autoencoder-based deep learning model. Two models were tested, one using single measurements and the other using multiple measurements taking advantage of the spatial distribution of the sensor network. After training, the multi-measurement model achieved 100 % accuracy in identifying, classifying, and locating unseen, unique damages. This work illustrates the potential of the proposed method for a wide range of industrial applications.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Deep-Learning-Based Multi-Timescale Load Forecasting in Buildings: Opportunities and Challenges from Research to Deployment

Electricity load forecasting for buildings and campuses is becoming increasingly important as the penetration of distributed energy resources (DERs) grows. Efficient operation and dispatch of DERs require reasonably accurate predictions of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets. Electric utilities have traditionally performed load forecasting for load pockets spanning large geographic areas, and therefore, forecasting has not been a common practice by buildings and campus operators. Given the growing trends of research and prototyping in the grid-interactive efficient buildings domain, characteristics beyond simple algorithm forecast accuracy are important in determining the algorithm's true utility for smart buildings. Other characteristics include the overall design of the deployed architecture and the operational efficiency of the forecasting system. In this work, we present a deep-learning-based load forecasting system that predicts the building load at 1-hour intervals for 18 hours in the future. We also discuss challenges associated with the real-time deployment of such systems as well as the research opportunities presented by a fully functional forecasting system that has been developed within the National Renewable Energy Laboratory's Intelligent Campus program.

building load forecasting↗