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 1,585 records · Page 88
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Symplectic machine learning model for fast simulation of space-charge effects

Symplectic simulation of space-charge effects is crucial for the design and operation of high-intensity particle accelerators. Traditional methods for simulating these effects are often computationally expensive, resulting in significant overhead. In this work, we introduce a generative model based on a U-Net architecture within a generative adversarial network framework to efficiently simulate space-charge effects. The model is trained to predict the transverse multiparticle space-charge Hamiltonian, which can be physically computed using a gridless spectral method. The one-step symplectic transverse transfer map for the particles is then obtained by differentiating the predicted Hamiltonian. Benchmarking results demonstrate that this generative model achieves an order of magnitude higher computational efficiency compared to the spectral method, providing a highly efficient alternative for simulating space-charge effects with a large number of particles. By maintaining symplecticity, the model effectively preserves the phase-space structure and mitigates nonphysical errors in long-term simulations. This model has been integrated into jutrack, a novel autodifferentiable accelerator modeling code developed in the julia programming language.

Beam code development & simulation techniques↗
DOE OSTI2018

The Operation of the Tevatron Vacuum System

Outline: Tevatron Overview and Some History; Vacuum Upgrades; Cryogenic Upgrades; Maintenance and Records; Vacuum Diagnostics; Failures; Lessons Learned

43 PARTICLE ACCELERATORS↗
DOE OSTI2019

System Deterioration Detection and Root Cause Learning on Time Series Graphs

System deterioration detection and root cause analysis is crucial for today's industrial society. However, the design and operation of mechanic system is getting more and more complex, which makes it hard at identifying deterioration with noisy data. Our research focus on solving such problem on time-evolving sensor graphs in a streaming setting. Given a sequence of graphs, the ability to identify 1) any gradual and stable structured change and 2) the root cause components is of importance for early warning and system diagnosis. Existing methods either raise too many false alerts on instant changes or are too sensitive to noise. To address these problems, we propose Robust Failure Detection and Diagnosis (RoFaD). RoFaD can capture failure propagation given a time series of graph. By optimizing a matrix based Taylor expansion, RoFaD can identify system deterioration in the presence of noise and immediate changes, and diagnose the root cause components. Experiments on both synthetic and real world datasets demonstrate that RoFaD is more effective than the popular baselines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Electric Power Generation from Low to Intermediate Temperature Resources

This project was designed to test the concept on the Eland-Lodgepole Field near Dickinson, North Dakota in the Williston Basin. The field is in secondary-recovery water-flood and consists of 12 producing oil wells, 5 water injection wells and one disposal well. Water production at the site averages approximately 320 gallons per minute (20.2 l s-1) and the temperature is 100 ⁰C. Engineers at Ormat estimated power production potential with the existing resource to be approximately 350 kWh. Unfortunately, ownership of the field was transferred from Encore, Inc., to Denbury, Inc., within the first week of the project. After two years of discussion and planning, Denbury decided not to pursue this project due to complications with the site location and its proximity to Patterson Lake. Attempts to find other partners operating in the Williston Basin were unsuccessful. Consequently, we were unable to pursue the primary objective of the project. However, during negations with Denbury and subsequent time spent contacting other potential partners, we focused on objectives 2 and 3 and developed a clear understanding of the potential for co-produced production in the Williston Basin and the best practices for developing similar projects. At least nine water bearing formations with temperatures greater than 90 ⁰C extend over areas of several 10s of km2. The total energy contained in the rock volume of those geothermal aquifers is 283.6 EJ (1 EJ = 1018 J). The total energy contained in the water volume, determined from porosities which range from 2 percent to 8 percent, is 6.8 EJ. The aquifers grouped by 10 ⁰C temperature bins (Table 1) include one or more formations due to the bowl-shape structure of the basin. Table 1. Summary of energy available in geothermal aquifers in the Williston Basin Analysis of overall fluid production from active wells, units, fields and formations in North Dakota showed that few sites co-produce sufficient fluid for significant power production with ORC technology. Average co-produced water for 10,480 wells is 3.2 gallons per minute (gpm). Even excluding the tight formations, Bakken and Three Forks, average co-produced water for the remaining 3,337 is only 5 gpm. The output of the highest producing well is 184 gpm and the average of the top 100 wells is 52 gpm. Due to the depth of the oil producing formations in the Williston Basin, typically 3 km or greater, pumps are operated slowly to prevent watering out thus total fluid production is purposefully maintained at low volumes. There remain potential possibilities for development of geothermal fluids in the Williston Basin. Unitized fields in which water production from several tens of wells is collected at a single site are good possibilities for development. Water production in the unitized fields is greater than 1000 gpm is several areas. A similar possibility occurs where infill-drilling between Bakken and Three Forks horizontal wells has created areas where large volumes of geothermal fluids are available on multi-well pads and in unitized fields. Although the Bakken produces small amounts of water, the water/oil ration is typically less than 1, the oil and water mix produced at the well head can be sent through the heat exchanger on an ORC. It is estimated that several tens of MWh of power could be generated by a distributed system of ORC engines in the areas of high-density drilling in the Bakken Formation. Finally, horizontal drilling in water bearing formations is the other possibility. Several secondary recovery water-flood projects in the basin are producing water above 100 ⁰C at rates of 300 gpm to 850 gpm. Those systems also could produce several tens of MWh of power with ORC technology. Objective 3 of the project was highly successful. The program has produced 5 PhDs, 7 MS, and 3 BS students with theses in geothermal energy. The team has involved 7 faculty in 4 different engineering and science disciplines, ChE, EE, GE, and Geol. The team has produced 26 peer-reviewed papers and 62 presentations at professional meetings. Faculty involved in the program developed five graduate level courses covering different elements in heat flow and geothermal energy that are now offered in the Harold Hamm School of Geology and Geological Engineering. Lessons learned – Keys to developing a successful project;1. Determine target formations; a. Data from oil and gas operators, state oil and gas regulatory agencies, and state geological surveys help to identify producing formations and their properties; 2. Determine the quantity of energy available in the target formations; a. A complete thermal analysis of the basin or region yields the most useful information; b. Critical data include: BHT, heat flow, stratigraphy, lithology, lithological properties, and thermal conductivity, subsurface structure; 3. Determine fluid production potential; a. State oil and gas regulatory agencies, and state geological surveys have data on oil, gas and water production. State Water Commission/Agencies have data on water quality, aquifers, and regulations; b. Consider single horizontal wells, multiple conventional wells, and unitized fields; 4. Calculate energy production capacity of each formation based on different well combination and power plant scenarios. This is a broad overview rather than a site specific analysis; 5. Research and understand the local electrical power industry. Obtain the PPA before committing to the project; 6. Work with the high-level personnel in the oil company partner. Obtain an MOU that addresses all issues in the project including what to expect if the company goes out of business, is bought out, changes management, etc; and 7. Be prepared for project delays.

15 GEOTHERMAL ENERGY↗
DOE OSTI2026

Generative AI for Grid Operations [Slides]

In the last few years, the development and use of generative artificial intelligence (AI) and large-language models (LLMs) have changed the landscape of how AI and machine learning (ML) are being used in power systems. LLMs are built on foundational models based on large data sets that can be trained to provide information rapidly and through simple natural language prompts. Generative AI can then perform human-like tasks using ML models to identify and mimic pattens in the data sets. This presentation explores how generative AI can enhance grid operations by improving forecasts, enabling rapid contingency analyses, and offering real-time operational suggestions. By providing grid operators with valuable insights, generative AI will empower them to manage power systems more effectively.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2014

Crystallization In High Level Waste (HLW) Glass Melters: Operational Experience From The Savannah River Site

processing strategy for the Hanford Tank Waste Treatment and Immobilization Plant (WTP). The basis of this alternative approach is an empirical model predicting the crystal accumulation in the WTP glass discharge riser and melter bottom as a function of glass composition, time, and temperature. When coupled with an associated operating limit (e.g., the maximum tolerable thickness of an accumulated layer of crystals), this model could then be integrated into the process control algorithms to formulate crystal tolerant high level waste (HLW) glasses targeting higher waste loadings while still meeting process related limits and melter lifetime expectancies. This report provides a review of the scaled melter testing that was completed in support of the Defense Waste Processing Facility (DWPF) melter. Testing with scaled melters provided the data to define the DWPF operating limits to avoid bulk (volume) crystallization in the un-agitated DWPF melter and provided the data to distinguish between spinels generated by K-3 refractory corrosion versus spinels that precipitated from the HLW glass melt pool. This report includes a review of the crystallization observed with the scaled melters and the full scale DWPF melters (DWPF Melter 1 and DWPF Melter 2). Examples of actual DWPF melter attainment with Melter 2 are given. The intent is to provide an overview of lessons learned, including some example data, that can be used to advance the development and implementation of an empirical model and operating limit for crystal accumulation for WTP. Operation of the first and second (current) DWPF melters has demonstrated that the strategy of using a liquidus temperature predictive model combined with a 100 °C offset from the normal melter operating temperature of 1150 °C (i.e., the predicted liquidus temperature (TL) of the glass must be 1050 °C or less) has been successful in preventing any detrimental accumulation of spinel in the DWPF melt pool, and spinel has not been observed in any of the pour stream glass samples. Spinel was observed at the bottom of DWPF Melter 1 as a result of K-3 refractory corrosion. Issues have occurred with accumulation of spinel in the pour spout during periods of operation at higher waste loadings. Given that both DWPF melters were or have been in operation for greater than 8 years, the service life of the melters has far exceeded design expectations. It is possible that the DWPF liquidus temperature approach is conservative, in that it may be possible to successfully operate the melter with a small degree of allowable crystallization in the glass. This could be a viable approach to increasing waste loading in the glass assuming that the crystals are suspended in the melt and swept out through the riser and pour spout. Additional study is needed, and development work for WTP might be leveraged to support a different operating limit for the DWPF. Several recommendations are made regarding considerations that need to be included as part of the WTP crystal tolerant strategy based on the DWPF development work and operational data reviewed here. These include: Identify and consider the impacts of potential heat sinks in the WTP melter and glass pouring system; Consider the contributions of refractory corrosion products, which may serve to nucleate additional crystals leading to further accumulation; Consider volatilization of components from the melt (e.g., boron, alkali, halides, etc.) and determine their impacts on glass crystallization behavior; Evaluate the impacts of glass REDuction/OXidation (REDOX) conditions and the distribution of temperature within the WTP melt pool and melter pour chamber on crystal accumulation rate; Consider the impact of precipitated crystals on glass viscosity; Consider the impact of an accumulated crystalline layer on thermal convection currents and bubbler effectiveness within the melt pool; Evaluate the impact of spinel accumulation on Joule heating of the WTP melt pool; and Include noble metals in glass melt experiments because of their potential to act as nucleation sites for spinel crystallization.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2019

Industrial Cavity Production: Lessons Learned to Push the Boundaries of Nitrogen-Doping

Nitrogen doping has been proven now in several labs to enhance Q0 values of 1.3 GHz cavities in the gradient domain favored by CW operation. The choice of doping for the LCLS-II project has given the community a wealth of statistics and experience on the challenge of transferring the doping technology to industry. Overall, industry-produced nitrogen-doped cavities have shown excellent performance, however some technical issues have arisen. This talk focuses on lessons learned from the production of over 300 nitrogen-doped cavities for LCLS-II and how issues were mitigated to further improve performance. Finally, I will discuss pushing the boundaries of nitrogen-doping further by exploring different doping regimes in order to maintain excellent Q0 performance, while reaching higher quench fields.

Gonnella, D.↗
DOE OSTI2025

Non-destructive evaluation and machine learning methods for inspection of spent nuclear fuel canisters: A state-of-the-art review

Nuclear energy is among the cleanest and most efficient energy sources currently available. The operation of nuclear power plants (NPPs) produces large amounts of high-level radioactive waste known as spent nuclear fuel (SNF). Currently, large amounts of SNF is stored in dry cask storage systems (DCSSs) for extended interim storage until a permanent disposal solution becomes available. During the extended interim storage, the DCSS, particularly the SNF canisters, may degrade and abnormal conditions may occur. Therefore, non-destructive evaluation (NDE) and machine learning (ML) approaches are necessary for inspection of SNF canisters. This paper presents a state-of-the-art review of literature by summarizing recent progress made on the applications of NDE and ML for inspection of SNF canisters. Sixteen NDE methods are examined and compared: visual inspection, ultrasonic guided waves (UGWs), laser-based approaches, acoustic emission (AE), eddy current testing (ECT), non-invasive acoustic sensing, dynamic modal testing, cosmic ray muons tomography, neutron imaging, gamma rays detection, fiber optical sensors, through-wall communications, X-ray computed tomography (CT), vibrothermography, monoenergetic photon sources, and surface acoustic wave (SAW) sensors. The technology readiness level (TRL) for each method is assessed and compared. Recent publications on ML-enhanced visual inspection, AE, non-invasive acoustic sensing, dynamic modal testing, and neutron imaging for SNF canisters are summarized and future research needs are identified. In conclusion, this review article provides a convenient reference on the state-of-the-art applications of NDE and ML methods for inspection of SNF canisters.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Efficient Super-Resolution of Near-Surface Climate Modeling Using the Fourier Neural Operator

Downscaling methods are critical in efficiently generating high-resolution atmospheric data. However, state-of-the-art statistical or dynamical downscaling techniques either suffer from the high computational cost of running a physical model or require high-resolution data to develop a downscaling tool. Here, we demonstrate a recently proposed zero-shot super-resolution method, the Fourier neural operator (FNO), to efficiently perform downscaling without the need for high-resolution data. Because the FNO learns dynamics in Fourier space, FNO is a resolution-invariant emulator; it can be trained at a coarse resolution and produces emulation at any high resolution. We applied FNO to downscale a 4-km resolution Weather Research and Forecasting (WRF) Model simulation of near-surface heat-related variables over the Great Lakes region. The FNO is driven by the atmospheric forcings, and topographic features used in the WRF model at the same resolution. We incorporated a physics-constrained loss in FNO by using the Clausius-Clapeyron relation to better constrain the relations among the emulated states. Trained on merely 600 WRF snapshots at 4-km resolution, the FNO shows comparable performance with a widely used convolutional network, U-Net, achieving averaged modified Kling-Gupta Efficiency of 0.88 and 0.94 on the test dataset for temperature and pressure, respectively. We then employed the FNO to produce 1-km emulations to reproduce the fine climate features. Further, by taking the WRF simulation as ground truth, we show consistent performances at the two resolutions, suggesting the reliability of FNO in producing high-resolution dynamics. Our study demonstrates the potential of using FNO for zero-shot super-resolution in generating first-order estimation on atmospheric modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Using machine learning to improve efficiency and accuracy of burnup measurements at PBR reactors [Slides]

The outline of the slides include: Motivations of the work; Modeling and simulation; Machine learning model; Results and comparison study with linear regression; and Conclusions. This work was done to help PBR designers and operators understand the burnup measurement better. We look forward to discussing the results in detail with industrial collaborators.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

Implications of stop-and-go traffic on training learning-based car-following control

Learning-based car-following control (LCC) of connected and autonomous vehicles (CAVs) is gaining significant attention with the advancement of computing power and data accessibility. While the flexibility and large model capacity of model-free architecture enable LCC to potentially outperform the model-based car-following (CF) model in improving traffic efficiency and mitigating congestion, the generalizability of LCC for traffic conditions different from the training environment/dataset is not well-understood. Herein, this study seeks to explore the impact of stop-and-go traffic in the training dataset on the generalizability of LCC. It uses the characteristics of lead vehicle trajectories to describe stop-and-go traffic, and links the theory of identifiability (i.e., obtaining a unique parameter estimation result using sensor measurements) to the generalizability of behavior cloning (BC) and policy-based deep reinforcement learning (DRL). Correspondingly, the study shows theoretically that: (i) stop-and-go traffic can enable the property of identifiability and enhance the control performance of BC-based LCC in different traffic conditions; (ii) stop-and-go traffic is not necessary for DRL-based LCC to generalize to different traffic conditions; (iii) DRL-based LCC trained with only constant-speed lead vehicle trajectories (not sufficient to ensure identifiability) can be generalized to different traffic conditions; and (iv) stop-and-go traffic increases variance in the training dataset, which improves the convergence of parameter estimation while negatively impacting the convergence of DRL to the optimal control policy. Numerical experiments validate the above findings, illustrating that BC-based LCC entails comprehensive training datasets for generalizing to different traffic conditions, while DRL-based LCC can achieve generalization with simple free-flow traffic training environments. This further suggests DRL as a more promising and cost-effective LCC approach to reduce operational costs, mitigate traffic congestion, and enhance safety and mobility, which can accelerate the deployment and acceptance of CAVs.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Online Dynamic Cyber-Attack Diagnosis in Power Electronics Systems Based on Few-Shot Learning

With increasing exposure to software-based sensing and control, power electronics systems are facing higher risks of cyber-physical attacks. To ensure system stability and minimize potential economic losses, it is critical to monitor the operating states and detect those attacks at the early stage. However, anomaly detection and diagnosis of attacks are still challenging, especially when labeled anomaly data is difficult or even infeasible to obtain. To overcome this problem, we propose a Few-Shot Learning (FSL) based approach for cyber-attack diagnosis leveraging the waveform data. To the best of our knowledge, this work is the first attempt at leveraging FSL for cyber-attack diagnosis in power electronics systems. Extensive experimental results demonstrate that our proposed approach can achieve comparable diagnosis accuracy with the state-of-the-art data-driven methods using less than 0.04% of the training samples.

Li, Qi↗
DOE OSTI2025

Huge ensembles – Part 1: Design of ensemble weather forecasts using spherical Fourier neural operators

Abstract. Simulating low-likelihood high-impact extreme weather events in a warming world is a significant and challenging task for current ensemble forecasting systems. While these systems presently use up to 100 members, larger ensembles could enrich the sampling of internal variability. They may capture the long tails associated with climate hazards better than traditional ensemble sizes. Due to computational constraints, it is infeasible to generate huge ensembles (comprised of 1000–10 000 members) with traditional, physics-based numerical models. In this two-part paper, we replace traditional numerical simulations with machine learning (ML) to generate hindcasts of huge ensembles. In Part 1, we construct an ensemble weather forecasting system based on spherical Fourier neural operators (SFNOs), and we discuss important design decisions for constructing such an ensemble. The ensemble represents model uncertainty through perturbed-parameter techniques, and it represents initial condition uncertainty through bred vectors, which sample the fastest-growing modes of the forecast. Using the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System (IFS) as a baseline, we develop an evaluation pipeline composed of mean, spectral, and extreme diagnostics. With large-scale, distributed SFNOs with 1.1 billion learned parameters, we achieve calibrated probabilistic forecasts. As the trajectories of the individual members diverge, the ML ensemble mean spectra degrade with lead time, consistent with physical expectations. However, the individual ensemble members' spectra stay constant with lead time. Therefore, these members simulate realistic weather states during the rollout, and the ML ensemble passes a crucial spectral test in the literature. The IFS and ML ensembles have similar extreme forecast indices, and we show that the ML extreme weather forecasts are reliable and discriminating. These diagnostics ensure that the ensemble can reliably simulate the time evolution of the atmosphere, including low-likelihood high-impact extremes. In Part 2, we generate a huge ensemble initialized each day in summer 2023, and we characterize the simulations of extremes.

Mahesh, Ankur↗
DOE OSTI2022

Correcting for filter-based aerosol light absorption biases at the Atmospheric Radiation Measurement program's Southern Great Plains site using photoacoustic measurements and machine learning

Abstract. Measurement of light absorption of solar radiation by aerosols is vital for assessing direct aerosol radiative forcing, which affects local and global climate. Low-cost and easy-to-operate filter-based instruments, such as the Particle Soot Absorption Photometer (PSAP), that collect aerosols on a filter and measure light attenuation through the filter are widely used to infer aerosol light absorption. However, filter-based absorption measurements are subject to artifacts that are difficult to quantify. These artifacts are associated with the presence of the filter medium and the complex interactions between the filter fibers and accumulated aerosols. Various correction algorithms have been introduced to correct for the filter-based absorption coefficient measurements toward predicting the particle-phase absorption coefficient (Babs). However, the inability of these algorithms to incorporate into their formulations the complex matrix of influencing parameters such as particle asymmetry parameter, particle size, and particle penetration depth results in prediction of particle-phase absorption coefficients with relatively low accuracy. The analytical forms of corrections also suffer from a lack of universal applicability: different corrections are required for rural and urban sites across the world. In this study, we analyzed and compared 3 months of high-time-resolution ambient aerosol absorption data collected synchronously using a three-wavelength photoacoustic absorption spectrometer (PASS) and PSAP. Both instruments were operated on the same sampling inlet at the Department of Energy's Atmospheric Radiation Measurement program's Southern Great Plains (SGP) user facility in Oklahoma. We implemented the two most commonly used analytical correction algorithms, namely, Virkkula (2010) and the average of Virkkula (2010) and Ogren (2010)–Bond et al. (1999) as well as a random forest regression (RFR) machine learning algorithm to predict Babs values from the PSAP's filter-based measurements. The predicted Babs was compared against the reference Babs measured by the PASS. The RFR algorithm performed the best by yielding the lowest root mean square error of prediction. The algorithm was trained using input datasets from the PSAP (transmission and uncorrected absorption coefficient), a co-located nephelometer (scattering coefficients), and the Aerosol Chemical Speciation Monitor (mass concentration of non-refractory aerosol particles). A revised form of the Virkkula (2010) algorithm suitable for the SGP site has been proposed; however, its performance yields approximately 2-fold errors when compared to the RFR algorithm. To generalize the accuracy and applicability of our proposed RFR algorithm, we trained and tested it on a dataset of laboratory measurements of combustion aerosols. Input variables to the algorithm included the aerosol number size distribution from the Scanning Mobility Particle Sizer, absorption coefficients from the filter-based Tricolor Absorption Photometer, and scattering coefficients from a multiwavelength nephelometer. The RFR algorithm predicted Babs values within 5 % of the reference Babs measured by the multiwavelength PASS during the laboratory experiments. Thus, we show that machine learning approaches offer a promising path to correct for biases in long-term filter-based absorption datasets and accurately quantify their variability and trends needed for robust radiative forcing determination.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

A bi-level data-driven framework for fault-detection and diagnosis of HVAC systems

Long-term operation of heating, ventilation, and air conditioning (HVAC) systems will eventually lead to a range of HVAC system failures, resulting in excessive energy consumption and maintenance costs. Here, to avoid HVAC malfunctioning, fault detection diagnostic (FDD) is utilized as a common practice. Machine learning methods have lately received considerable interest for FDD analysis of HVAC systems due to their high detection accuracy. Meanwhile, HVAC malfunctions are regarded as rare occurrences, hence normal operating data samples are much more accessible than data samples in faulty and malfunctioning conditions. The dominating frequency of normal operation in HVAC datasets has also led to heavily biased classification algorithms within the literature. Moreover, the focus of previous literature has been on increasing the accuracy of the models which leads to a high number of false positives (misleading alarms) in the system. In order to enhance the performance of diagnostic procedures and fill the mentioned gaps, this study proposes a novel data-driven framework. A bi-level machine learning framework is developed for diagnosing faults in air handling units (AHUs) and rooftop units (RTUs) based on principal component analysis (PCA), time series anomaly detection, and random forest (RF). It is shown that PCA can reduce the dataset dimension with one principal component accounting for 95% of data variance. Also, the random forest could classify the faults with 89% precision for single-zone AHU, 85% precision for RTU, and 79% for multi-zone AHU. By proposing this framework, three persistent challenges are addressed: (I) minimizing false positives; (II) accounting for data imbalance; and (III) normal condition monitoring of equipment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Bioremediation of Chlorinated Volatile Organic Compounds: DOE Experiences and Lessons Learned

From the mid-1980s to the present, the Department of Energy (DOE) has developed, tested, and deployed diverse bioremediation strategies for chlorinated volatile organic compounds (cVOCs). A systematic review of these projects after decades of activity provides an opportunity to identify crosscutting themes and lessons learned. The knowledge provided by a DOE bioremediation retrospective represents a resource to support current and future bioremediation operations, and future decisions related to cVOC bioremediation. This systematic review examined the design, objectives, performance and outcomes for remediation projects at DOE sites including Savannah River, Hanford, Idaho, Mound and Pinellas. The results were used to identify emergent themes to provide actionable insights. The bioremediation retrospective technical team first developed standardized criteria to support the systematic review. Then, the evaluation was performed using a sequential process that was informed by local technical experts who identified and provided the structured information that served as the basis for the evaluation. The participation of these experts was invaluable to the effort. Importantly, DOE cVOC bioremediation efforts were implemented based on the foundational knowledge developed by U.S. Department of Defense (DoD) strategic and applied environmental technology development and certification programs, as well as technical, policy and regulatory guidance from the U.S. Environmental Protection Agency (EPA), Interstate Technology and Regulatory Council (ITRC), U.S. Geological Survey (USGS), industry, and universities. To maximize the value of the DOE cVOC bioremediation retrospective, the systematic review strategy focused on identifying important DOE-specific experiences, trends and lessons learned that would extend the knowledge available from these other key entities.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Active Learning for Rapid Targeted Synthesis of Compositionally Complex Alloys

The next generation of advanced materials is tending toward increasingly complex compositions. Synthesizing precise composition is time-consuming and becomes exponentially demanding with increasing compositional complexity. An experienced human operator does significantly better than a novice but still struggles to consistently achieve precision when synthesis parameters are coupled. The time to optimize synthesis becomes a barrier to exploring scientifically and technologically exciting compositionally complex materials. This investigation demonstrates an active learning (AL) approach for optimizing physical vapor deposition synthesis of thin-film alloys with up to five principal elements. We compared AL-based on Gaussian process (GP) and random forest (RF) models. The best performing models were able to discover synthesis parameters for a target quinary alloy in 14 iterations. We also demonstrate the capability of these models to be used in transfer learning tasks. RF and GP models trained on lower dimensional systems (i.e., ternary, quarternary) show an immediate improvement in prediction accuracy compared to models trained only on quinary samples. Furthermore, samples that only share a few elements in common with the target composition can be used for model pre-training. We believe that such AL approaches can be widely adapted to significantly accelerate the exploration of compositionally complex materials.

Chemistry↗
DOE OSTI2022

Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R 2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R 2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. Here we also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.

60 APPLIED LIFE SCIENCES↗