Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “short-term generation”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Accurately predicting stream temperature in ungauged basins remains a critical challenge for water resource management, thermoelectric power plant cooling, and ecosystem conservation. Large-sample machine learning models trained on hundreds of well-monitored river basins have shown remarkable performance; however, such models have yet to be developed solely using forcing data that can be readily extracted to simulate stream temperatures anywhere in the contiguous United States (CONUS). In this study, we present a scalable, large-sample deep learning framework using Long Short-Term Memory (LSTM) networks to simulate daily stream temperatures in ungauged basins across the CONUS. The framework leverages both modeled reanalysis of meteorological and streamflow inputs as well as static attributes available for all 2.7 million CONUS river reaches in the National Hydrography Dataset Plus (NHDPlusV2). By generating dynamical inputs from predefined thermally relevant upstream contributing areas, rather than the entire upstream basin, the model also offers improvements in very large basins where full-basin averaging can dilute the most important influences on stream temperature. Evaluated across 300 basins, the model achieves a median Mean Absolute Error (MAE) of 1.1 °C and a Nash-Sutcliffe Efficiency (NSE) of 0.95 on temporally and spatially distinct test folds—comparable to models trained exclusively using meteorological and streamflow observational data. The flexible, high-performing framework generalizes to any unmonitored river reach without significant regulation or unnatural thermal input immediately upstream, substantially expanding predictive capabilities in data-scarce regions.

Hydrology↗
DOE OSTI2025

A Comparative Study of Physics‐Informed and Data‐Driven Neural Networks for Compound Flood Simulation at River‐Ocean Interfaces: A Case Study of Hurricane Irene

Simulating compound flooding (CF) at the river-ocean interface within large-scale Earth System Models (ESMs) presents significant challenges due to complex interactions between river discharge, storm surge, and tides. This study assesses the comparative advantages of physics-informed and data-driven machine learning (ML) approaches for enhancing local ESM performance. We systematically compare data-driven neural network models (i.e., CNNs, U-Net, Long Short-Term Memory (LSTM), Gated Recurrent Unit), and physics-informed neural network (PINN) models, including vanilla PINN and a finite-difference-based PINN (FD-PINN). Specifically, FD-PINN is introduced to enhance computational efficiency, accelerating vanilla PINNs by ∼6.5 times while improving accuracy. To enhance data-driven model training, a new data-generation approach is developed to sample historical fluvial and coastal flood events, which ensures a robust data set for extreme event prediction. The models are evaluated using a realistic one-dimensional river domain extracted from an ESM's river mesh and the Hurricane Irene event as an independent test case. Results show that FD-PINN achieves accurate predictions with significantly reduced computational costs relative to vanilla PINNs. Among data-driven models, the best overall performance is achieved by a CNN-LSTM hybrid, which balances accuracy and efficiency. While a fully connected CNN (CNN-FC) provides the best accuracy, it incurs high computational cost. Architectures lacking strong temporal modeling tend to underperform on unseen events. These findings highlight the importance of sequence-aware designs for robust generalization. This study reveals the trade-offs between physics-informed and data-driven models and proposes an adaptive hybrid framework for integrating ML into ESMs to enhance local flood simulations.

Earth Systems Modeling↗
DOE OSTI2025

Surrogate models for development of unconventional shale reservoirs by an integrated numerical approach of hydraulic fracturing, flow and geomechanics, and machine learning

We develop well-completion surrogate models by taking an integrated workflow of hydraulic fracturing, flow, geomechanics, and machine learning simulation. There are three steps in the proposed workflow. First, history-matching processes are conducted with the field data including pumping and production data for characterization. Second, full-physics simulation is performed with various parameters of the field development (e.g., cluster spacing, clusters per stage, pumping rates and times, amount of proppant, and well spacing) to generate multiple simulation results by changing the parameters of the completion design with well-known hydraulic fracturing, reservoir, geomechanics simulators to calculate fracture geometry, reservoir depressurization, induced stress changes. The workflow is demonstrated over a field in the Southern Midland Basin. Here, we take two completion scenarios: a single well case followed by a multi-well case. Finally, a Long Short-Term Memory (LSTM) machine learning algorithm is employed to create surrogate models that can replicate the full-physics simulation results. Furthermore, results show that the trained models applied in the single well and multi-well cases for a particular geological system can provide good accuracy close to those provided by full-physics simulations. Specifically, the site-specific surrogate models can predict fracture parameters (length, height, and surface area) and cumulative production accurately with computational efficiency, suggesting our proposed workflow can be used as a pragmatic tool for expediting the well completion optimization process.

Geomechanics↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2026

Multispectral UAV imagery of experimental freshwater wetlands under 5 ppt saltwater intrusion, Louisiana, 2023 and 2024

Multispectral imagery was collected using an unmanned aerial vehicle (UAV) to evaluate how freshwater vegetation responds to short-term simulated saltwater intrusion events. The purpose of this data collection was to understand how plant health changes in response to acute salinity exposure, which is increasingly relevant in coastal wetland ecosystems facing sea level rise and storm surge events, such as in coastal Louisiana. Three experimental saltwater intrusions were conducted at a salinity of approximately 5 parts per thousand (ppt) for durations of 6-days, 10-days, and 17-days. UAV flights occurred both before and after each treatment. The resulting imagery was processed using Pix4DMapper software to georeference the images and generate orthomosaics. The multispectral sensor used in this study captures reflectance in five bands: blue, green, red, red-edge, and near-infrared. The uploaded data consist of georeferenced .tif orthomosaics for each spectral band, which are compatible with GIS software for vegetation analysis. This imagery can be utilized in investigations into vegetation stress, remote sensing of freshwater wetland ecosystems, and modeling of plant response to environmental changes.

EARTH SCIENCE > BIOSPHERE > ECOSYSTEMS↗
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
DOE OSTI2025

Persistent trade-offs balance competition and colonization across centuries

When a microbe colonizes a host, it must both establish infection and outcompete other organisms. Short-term experiments show that gains in competitive ability can reduce colonization, creating trade-offs, but whether microbes resolve these conflicts over long evolutionary timescales is unknown. We show that a trade-off between competitive killing and host colonization has been stably maintained for centuries in natural Pseudomonas populations infecting Arabidopsis thaliana. Tailocins—phage-derived weapons—provide strong competitive advantages, yet their production reduces colonization success, explaining why the most broadly lethal variants remain rare. Genomic surveys and historical genomes spanning two centuries reveal that the polymorphisms underlying this trade-off have persisted across 10⁵-10⁶ generations. Understanding such long-lived constraints can inform antimicrobial strategies that exploit evolutionary trade-offs.

Backman, Talia↗
DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗
DOE OSTI2025

Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models

Accurate solar Photovoltaic (PV) power forecasting is important for enhancing both the performance and economic feasibility of PV systems. This study evaluates several deep learning models, including Dense Neural Networks (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid LSTMCNN model, for predicting PV power production one day in advance. Prior to optimization, the models exhibited relatively high errors, with the best model (DNN) achieving a Root Mean Square Error (RMSE) of 31.13 kW and a coefficient of determination (R 2 ) of 62.15 %. After employing Bayesian optimization, the LSTM-CNN model demonstrated the best performance, with the RMSE reduced to 9.79 kW and R 2 improved to 97.62 %, showcasing significant enhancement in predictive accuracy. Here, the economic evaluation considered three cases: rewards for underestimation (0.08 USD/kWh), no rewards, and penalties for both over-and underestimation (120 % of the utility tariff). In the rewards scenario, the LSTM-CNN model reduced the Levelized Cost of Electricity (LCOE) by 4 %, while in the penalty scenario, a backup diesel generator would have increased the LCOE by 49 %. Additionally, the LSTM-CNN model minimized financial losses, achieving the lowest penalties and maximizing net cash flow compared to other models, demonstrating its overall technical and economic superiority.

Deep learning↗
NASA NTRS2026

Machine Learning for Predicting Team Functioning in HERA Missions

Team functioning is integral to success in future long term space exploration missions. Proactively detecting declines in team functioning can mitigate conflict and ensure mission success. This project developed a speech-based artificial intelligence (AI) system that unobtrusively predicts degradation in team functioning, including performance and cohesion, in the Human Exploration Research Analog (HERA) Campaigns 4 and 5. The AI system conducted automated analysis of the prosodic (tone of voice) and linguistic (language content) components of speech, modeling interpersonal dynamics at both the turn-taking and day-wide levels. We investigated team functioning via observing structured interactions (i.e., multi-mission space exploration vehicle-extra vehicular activity [MMSEV-EVA], team interaction battery [TIB]) and unstructured interactions before the MMSEV-EVA task. We developed machine learning models to predict team functioning (objective task accuracy, self reported team efficacy and self reported team cohesion) by analyzing OpenSmile acoustic features, linguistic descriptors extracted via the linguistic inquiry and word count (LIWC) dictionary, and semantic embeddings. In the TIB, static models using logistic regression and random forests were not able to predict task accuracy, but predicted team efficacy and cohesion during both the decision making and relational tasks to a moderate level (60-70%). Majority voting on the individual turns to predict day long team efficacy further increased accuracies (70-80%). Finally, long short-term memory (LSTM) models showed the best performance across all variables (80-91%), including task performance. In the MMSEV-EVA, static models achieved an accuracy of 60% with majority voting, which increased to 80% through the incorporation of mission day as a variable, accounting for the learning effect. A key finding across both tasks was the "team-dependent" nature of these interactions; models achieved much higher accuracy when trained on prior days of the same team's data rather than attempting to generalize across entirely different teams, with even 1-2 days of prior data per team achieving 5-15% improvement over team-independent models. In addition, the incorporation of pre-task data from the same team also improves model performance, e.g., incorporating data from the decision-making task of the TIB, which preceded the relational task, improved the prediction of team efficacy and cohesion during the latter. We compared model performance when trained on machine-generated data compared to data that had been further corrected by human annotators. Overall, models trained on human-corrected data exhibited a modest improvement in performance, particularly when acoustic features were used. We found no significant correlation between word error rate (WER) and model accuracy (r(55) = -0.08, p = 0.51), but model’s accuracy was significantly higher for medium/high quality transcription (0.74 (SD = 0.48)) compared to the low-quality group (0.64 (SD = 0.36)) (t(63)=2.82, p = 0.006). Based on these, several design recommendation emerge, that could inform Standards at NASA. Models predicting team functioning should incorporate at least one to two days of historical interaction data, include brief pre-task discussions, and explicitly model temporal learning effects, especially for longer operational tasks. Minimum quality standards for automated speech-processing pipelines are needed, given the performance gains observed with manually corrected acoustic data. Finally, systems should leverage both acoustic features and language embeddings in complementary ways, with modality choices and fusion strategies tailored to mission context, task demands, and data quality requirements.

Shrivatsa Mishra↗
DOE OSTI2025

Acute Exposure to Aerosolized Nanoplastics Modulates Redox-Linked Immune Responses in Human Airway Epithelium

Micro- and nanoplastics (MPs and NPs) are pervasive environmental pollutants detected in aquatic ecosystems, with emerging evidence suggesting their presence in airborne particles generated by water body motion. Inhalation exposure to airborne MPs and NPs remains understudied despite documented links between occupational exposure to these particles and adverse respiratory outcomes, including airway inflammation, oxidative stress, and chronic respiratory diseases. This study explored the effects of acute NP exposure on a fully differentiated 3D human airway epithelial model derived from 14 healthy donors. Airway epithelium was exposed to aerosolized 50 nm polystyrene NPs at concentrations ranging from 2.5 to 2500 µg/mL for three minutes per day over three days. Functional assays revealed no significant alterations in tissue integrity, cell survival, mucociliary clearance, or cilia beat frequency, suggesting intact epithelial function post-exposure. However, cytokine and chemokine profiling identified a significant five-fold increase in CCL3 (MIP-1α), a neutrophilic chemoattractant, in NP-exposed samples compared to controls. This was corroborated by increased neutrophil chemotaxis in response to conditioned media from NP-exposed tissues, indicating a pro-inflammatory neutrophilic response. Conversely, levels of interleukins (IL-21, IL-2, IL-15), CXCL10, and TGF-β were significantly reduced, suggesting immunomodulatory effects that may impair adaptive immune responses and tissue repair mechanisms. These findings demonstrate that short-term exposure to NP-containing aerosols induces a distinct pro-inflammatory response in airway epithelium, characterized by enhanced neutrophil recruitment and reduced secretion of key immune modulators. These findings underscore the potential for aerosolized NPs to induce oxidative and inflammatory stress, raising concerns about their long-term impact on respiratory health and redox regulation.

Biochemistry & Molecular Biology↗
DOE OSTI2025

Williston Basin Resource Study for Commercial-Scale Subsurface Hydrogen Storage

The Energy & Environmental Research Center (EERC), in partnership with the U.S. Department of Energy (DOE) National Energy Technology Laboratory (NETL), the EERC’s State Energy Research Center (SERC), MPLX Operations LLC, and TC Energy Development Holdings Inc. (a subsidiary of TC Energy Corporation), studied the potential for subsurface hydrogen storage and recovery in the Williston Basin of western North Dakota. The project’s goal was to evaluate the feasibility of large-scale, secure geologic H 2 storage to support future hydrogen generation, storage, and use. This work included laboratory testing, H 2 –rock–fluid exposure experiments, literature reviews on H 2 embrittlement, and reservoir modeling and simulations. The study included an assessment of storage potential across three types of storage reservoirs using both reservoir simulation and DOE’s web-based tool SHASTA-HELP (Subsurface Hydrogen Assessment, Storage, and Technology Acceleration – Hydrogen Estimator for Logistical Planning), as well as investigation of potential H 2 production and markets for commercial-scale deployment. Building on prior EERC gas storage research, three storage options were selected for detailed evaluation: the Broom Creek Formation (a clastic saline reservoir), the Dickinson Lodgepole Mounds (DLM) complex (carbonate mud mound structures) of the Lodgepole Formation (an active oil and gas producing reservoir), and the Dunham Salt Interval of the Piper Formation (to be used for engineered salt cavern development). These targets were prioritized based on prior EERC research using datasets related to seal capacity, reservoir quality, mechanical integrity, and injectivity. Exposure tests on Broom Creek and DLM samples showed mineral dissolution and precipitation that increased brine salinity and altered reservoir rock surfaces. Although these results provide useful insight, they are limited by small sample sizes and short-term (30-day) exposure, requiring further study to assess long-term storage integrity. Salt formations were not tested because of their known nonreactivity and established mechanical stability. Results of reservoir simulations performed for a single site demonstrated that the Broom Creek Formation may be capable of receiving up to 42,000 tonnes of injected H 2 over 7 months via one well. H 2 recovery took place over 5 months, resulting in approximately 26,000 tonnes (~62% without cushion gas [CG]). This work suggests water production may be important and subsequent cycles of injection and production may perform more efficiently; however, significant site-specific work in the future is needed to assess actual reservoir performance of injection and withdrawal of H 2 storage. For oil reservoir potential, a multiple-well model was used to simulate injection of approximately 32,000 tonnes of H 2 into a single wellbore while simultaneously producing in place reservoir fluids from four offset wells to maintain reservoir pressure. The simulation results suggested a high recovery (~98%); in addition, cost advantages through existing infrastructure could be realized. Challenges in this reservoir include vi managing gas purity and leakage risks. In both scenarios, production of H 2 takes place in a single-well scenario with 10 cycles (7 months of injection and 5 months of production) over 10 years. Finally, the use of engineered caverns in the Dunhan Salt was evaluated, and the results suggest that while they have a smaller capacity (<1000 tonnes per cavern), they exhibit nearly complete gas recovery (>99%), fast response times, and low purity risk. While caverns in North Dakota may be smaller in capacity, fields can be developed in galleries to accommodate the volumetric needs and rapid turnaround times necessary to meet market demands. Geographic limitations and thin salt intervals in North Dakota may represent less total storage potential than salt domes elsewhere, but significant opportunities exist to expand this market for gas storage in North Dakota. A basinwide assessment was performed to estimate a first-of-its-kind value for H 2 storage on a large scale. DOE’s SHASTA-HELP, combined with EERC simulation work, was used to perform the assessment. Estimated H 2 storage potential varied widely for each formation type. The Broom Creek saline formation was estimated to have a storage potential of approximately 1.7–90.5 million tonnes (MMt). The DLM oil reservoirs were estimated to have 0.07–0.19 MMt of capacity. Notably, each of these estimates relies on significant assumptions regarding reservoir thickness, porosity, permeability, and CG needed for operation. Much research is needed to understand the true site-specific storage resource potential of each formation. Using the Dunham Salt Interval for cavern development may result in as much as 4.79 MMt (up to 2.87 MMt working gas) of H 2 storage potential. An important note for consideration is that the values presented here need significantly more geological characterization and engineering assessments prior to gaining confidence in performance. This will be a focal point for future research and development needs. The basinwide evaluation also indicated that North Dakota has significant H 2 generation potential, with estimates up to a possible 13 MMt annually, suggesting a substantial opportunity for H 2 market development and thus the need for commercial-scale H 2 storage to facilitate growth and resilience. Key Recommendations 1. Conduct detailed site characterization (3D seismic, well logs, core sampling) to reduce geologic uncertainty. 2. Perform techno-economic analyses incorporating market, regulatory, and incentive frameworks. 3. Investigate long-term interactions among H 2 , CGs, well materials, and formations to assess risks. 4. Develop pilot- and field-scale demonstrations to validate models and establish best practices.

03 NATURAL GAS↗
DOE OSTI2025

Physics-Informed Recurrent Neural Networks to Predict Reactor Operations of the AGN-201 Nuclear Reactor

4 page paper submitted to ANS Student conference. Summary of paper similar to the following abstract: The ability to predict how a reactor will operate, understand when anomalous conditions arise, and ensure a reactor is being operated as expected is crucial for deploying new nuclear facilities. Digital twins serve as a unique solution to recognizing reactor behavior; however, they require data to be useful. For next-generation reactors, this data may not currently be available. To explore how synthetic physics-informed reactor data can be used to predict reactor operations, a recurrent neural network was implemented for the Idaho State University AGN-201 digital twin. The goal of this work is to determine how synthetic data can be used to train a recurrent neural network model for predicting the reactor power of the AGN-201. The recurrent neural network was validated using both synthetic and real operational data. We envision this approach will help bridge the gap between the virtual and physical sides of a digital twin, where reactor physics models based on as-built data can be corrected for actual operating parameters to ensure the virtual model mirrors reality.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2025

Subspace-Driven Learning for Anomaly Detection in Process Transients

Nuclear power plant (NPP) monitoring and diagnostic centers are actively investigating and implementing automated anomaly detection algorithms to help plants catch anomalies sooner, thereby preventing or reducing the duration of unexpected shutdowns. Current machine learning-based anomaly detection methods are expected to be highly effective during stable, full-power operations because NPPs typically operate as baseload power generators, meaning there are extensive operating data available from plant equipment. However, it is expected that anomaly detection methods will face significant challenges during transient conditions (i.e., when power output falls below full power) because plants only occasionally operate at these lower power levels, generating sparse transient operational data, and resulting in false alarms or missed detections. Here, to address this issue, transfer learning is used, which for this problem leverages knowledge (in the form of learned features) from stable, full-power operations to improve detection accuracy during transient conditions, even with limited data. In this effort, a novel subspace approach is developed to transfer a subset of the data features from full power operation to transients. This approach is validated through experiments using synthetic data and was found to outperform two baseline transfer learning approaches in anomaly detection performance across a range of amounts of transient data used in the training process.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2026

Governing in Time: Temporal Capacity and the Feasibility of Energy Transitions

Energy systems function as both technological systems and temporal institutions that shape how societies coordinate, justify, and support collective choices over time. This paper introduces the concept of governance horizons to explain why energy transitions can remain morally supported yet become institutionally weak under increasing pressure. We argue that governability depends on institutions' capacity to synchronize across multiple timeframes - aligning short-term decisions with intermediate coordination and long-term commitments. When this synchronization fails, transitions struggle not because their goals are dismissed, but because governance lacks sufficient time to justify, coordinate, and uphold decisions. Comparative analysis of San Antonio, Texas, and Interior Alaska reveals how energy system pressures generate distinct temporal configurations: San Antonio exhibits governance horizon stretching, where institutions must simultaneously meet near-term reliability demands and long-term transformation goals, while Interior Alaska exhibits horizon compression, where extreme environmental constraints force decision-making into short stabilization cycles. In both contexts, public support for sustainability goals coexists with institutional strain because evaluative judgments are unevenly distributed over time. A temporal configuration analysis is introduced as a diagnostic analytic stance for identifying these patterns. By treating temporal alignment as an explanatory variable rather than a background condition, this approach clarifies how feasibility, sequencing, and legitimacy are shaped by constraints on institutional time. The analysis demonstrates that successful energy transitions depend not only on technological innovation or institutional support, but on governance systems’ ability to sustain credible coordination across multiple time horizons.

Comparative case study↗
DOE OSTI2025

A Variational Autoencoder Model Toward Molecular Structure Representation Learning of Fuels

Here, in this work, a Variational Autoencoder (VAE)-based data-driven modeling framework is developed with the overarching goal of enabling fuel design. The VAE model is trained on a large dataset with several chemical species to learn a compressed latent space molecular representation. Chemical structure in the form of Simplified Molecular Input Line Entry System (SMILES) string is fed as input, encoded into the VAE latent space, and decoded back to the SMILES string using Long Short-Term Memory (LSTM) networks. Complexities of the VAE training loss function are thoroughly examined by varying the weightage (beta (𝜷) parameter) of the latent space regularization term, thereby assessing the balance between reconstruction accuracy and validity, and focusing on both accurate molecular structure reconstruction and latent space consistency. Two different strategies for 𝜷 variation are evaluated: linear annealing and cyclic annealing. In addition, the impact of total correlation adjustment and hierarchical priors is also studied with regard to the balance between reconstruction fidelity and latent space regularization, and potential issues such as posterior collapse, over-regularization, and poor disentanglement of latent variables. Overall, the best performance of the model is achieved with hierarchical priors and incrementally increasing 𝜷 from 0 to a threshold value of 0.25 over 75 epochs. The generative VAE model can be readily coupled with Quantitative Structure–Property Relationship (QSPR) analysis to develop an integrated end-to-end framework for fuel-property prediction and molecular design of novel promising fuels.

fuel design↗