Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Learning with errors”

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 1,783 records · Page 99
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Predicting Team Functioning in Long Term Space Missions Using Acoustic and Linguistic Measures

Maintaining optimal team functioning is critical for long-duration space exploration missions, yet traditional monitoring methods, such as self-reports and wearable sensors, often impose operational burdens or suffer from bias. This paper investigates a non-intrusive speech-based artificial intelligence (AI) framework to predict degradations in team functioning using data from the Human Exploration Research Analog (HERA) of the U.S. National Aeronautics and Space Administration (NASA). Using acoustic features, linguistic descriptors, and semantic embeddings, we evaluate static non-linear and temporal machine learning models to predict both objective (task accuracy) and subjective (self-reported efficacy and cohesion) team functioning outcomes. Results indicate that temporal models outperform static approaches, with prediction of objective task accuracy in Team Interaction Battery (TIB) improving from near chance to 71%. Self-reported outcomes, including team efficacy and cohesion, are predicted more reliably than task performance, achieving balanced accuracies of up to 85.56% and 78.12%, respectively, and are found to be most strongly associated with acoustic features. In a second interdependent task, the MMSEV–EVA, accuracies of up to 78% are achieved using temporal models with acoustic features. Furthermore, incorporating just 1–2 days of team-specific historical data systematically improved performance, and acoustic markers from informal pre-task interactions provided modest predictive gains. Finally, while automated preprocessing yielded viable accuracy, humancorrected data provided moderate performance gains, though transcription error rates did not significantly correlate with model performance. These findings highlight the potential of speech as a passive, high-fidelity monitoring tool for autonomous habitats.

Temporal modeling↗
DOE OSTI2022

Nonnegative canonical tensor decomposition with linear constraints: nnCANDELINC

Abstract There is an emerging interest for tensor factorization applications in big‐data analytics and machine learning. To speed up the factorization of extra‐large datasets, organized in multidimensional arrays (also known as tensors), easy to compute compression‐based tensor representations, such as, Tucker and tensor train formats, are used to approximate the initial large‐tensor. Further, tensor factorization is used to extract latent features that can facilitate discoveries of new mechanisms and signatures hidden in the data, where the explainability of the latent features is of principal importance. Nonnegative tensor factorization extracts latent features that are naturally sparse and parts of the data, which makes them easily interpretable. However, to take into account available domain knowledge and subject matter expertise, often additional constraints need to be imposed, which lead us to canonical decomposition with linear constraints (CANDELINC), a canonical polyadic decomposition with rank deficient factors. In CANDELINC, Tucker compression is used as a preprocessing step, which lead to a larger residual error but to more explainable latent features. Here, we propose a nonnegative CANDELINC (nnCANDELINC) accomplished via a specific nonnegative Tucker decomposition; we refer to as minimal or canonical nonnegative Tucker. We derive several results required to understand the specificity of nnCANDELINC, focusing on the difficulties of preserving the nonnegative rank of a tensor to its Tucker core and comparing the real valued to nonnegative case. Finally, we demonstrate nnCANDELINC performance on synthetic and real‐world examples.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

An Algebra of Machine Learners with Applications

Machine learning (ML) methods are increasingly being applied to solve complex, data-driven problems in diverse areas, by exploiting the physical laws derived from first principles such as thermal hydraulics and the abstract laws developed recently for data and computing infrastructures. These physical and abstract laws encapsulate, typically in compact algebraic forms, the critical knowledge that complements data-driven ML models. We present a unified perspective of these laws and ML methods using an abstract algebra (A;⊕,Ⓧ), wherein the performance estimation and classification tasks are characterized by the additive ⊕ operations, and the diagnosis, reconstruction, and optimization tasks are characterized by the difference Ⓧ operations. This abstraction provides ML codes and their performance characterizations that are transferable across different areas. We describe practical applications of these abstract operations using examples of throughput profile estimation tasks in data transport infrastructures, and power-level and sensor error estimation tasks in nuclear reactor systems.

Rao, Nageswara↗
NASA NTRS2016

Optical Testing and Verification Methods for the James Webb Space Telescope Integrated Science Instrument Module Element

NASA's James Webb Space Telescope (JWST) is a 6.6m diameter, segmented, deployable telescope for cryogenic IR space astronomy (~40K). The JWST Observatory includes the Optical Telescope Element (OTE) and the Integrated Science Instrument Module (ISIM) that contains four science instruments (SI) and the fine guider. The SIs are mounted to a composite metering structure. The SI and guider units were integrated to the ISIM structure and optically tested at the NASA Goddard Space Flight Center as a suite using the Optical Telescope Element SIMulator (OSIM). OSIM is a full field, cryogenic JWST telescope simulator. SI performance, including alignment and wave front error, were evaluated using OSIM. We describe test and analysis methods for optical performance verification of the ISIM Element, with an emphasis on the processes used to plan and execute the test. The complexity of ISIM and OSIM drove us to develop a software tool for test planning that allows for configuration control of observations, associated scripts, and management of hardware and software limits and constraints, as well as tools for rapid data evaluation, and flexible re-planning in response to the unexpected. As examples of our test and analysis approach, we discuss how factors such as the ground test thermal environment are compensated in alignment. We describe how these innovative methods for test planning and execution and post-test analysis were instrumental in the verification program for the ISIM element, with enough information to allow the reader to consider these innovations and lessons learned in this successful effort in their future testing for other programs.

spaceborne telescopes↗
NASA NTRS2019

A Communication Channel Density Estimating Generative Adversarial Network

Autoencoder-based communication systems use neural network channel models to backwardly propagate message reconstruction error gradients across an approximation of the physical communication channel. In this work, we develop and test a new generative adversarial network (GAN) architecture for the purpose of training a stochastic channel approximating neural network. In previous research, investigators have focused on additive white Gaussian noise (AWGN) channels and/or simplified Rayleigh fading channels, both of which are linear and have well defined analytic solutions. Given that training a neural network is computationally expensive, channel approximation networks— and more generally the autoencoder systems—should be evaluated in communication environments that are traditionally difficult. To that end, our investigation focuses on channels that contain a combination of non-linear amplifier distortion, pulse shape filtering, intersymbol interference, frequency-dependent group delay, multipath, and non-Gaussian statistics. Each of our models are trained without any prior knowledge of the channel. We show that the trained models have learned to generalize over an arbitrary amplifier drive level and constellation alphabet. We demonstrate the versatility of our GAN architecture by comparing the marginal probability density function of several channel simulations with that of their corresponding neural network approximations

Smith, Aaron↗
NASA NTRSDate not supplied

Establishing Trust in NASA’s Artemis Campaign Computer-Human Interface (CHI) Implementation

The NASA Artemis program will return humans to the Moon. This time, with the help of commercial and international partners, the program's objective is a permanent moon base. The moon base infrastructure, including an orbiting moon station and moon surface assets, will be developed for astronauts to stay for the long haul to learn to live and work on another planet in preparation for an eventual Humans-to-Mars mission. As the roundtrip communication delays increase in deep space exploration, the crew will need more onboard systems autonomy and functionality to maintain and control the vehicle or habitat. These mission constraints will change the current Earth-based spacecraft to ground control support approach that will demand more safe, efficient, and effective Computer-Human Interface (CHI) control. For Artemis, CHI is defined as the elements that the crew interfaces with: audio, video, lighting, and crew controls subsystems. Understanding how CHI will need to evolve to support deep space missions will be critical for the Artemis program--especially crew controls, which is the focus of this paper. How does NASA ensure crew controls are reliable enough to control complex systems and prevent a catastrophic event due to human error--especially when the astronauts could be physiologically and/or psychologically impaired? NASA's approach to mitigating catastrophic hazards in human spaceflight system development such as crew controls, is through a holistic system engineering and Human System Integration methodology that focuses on incorporating NASA's Human-Rating Requirements-that ensures human performance characteristics to control/safely recover the crew from hazardous situations within the human interface design are considered. This paper discusses, at a high level, CHI for the Artemis program. Next, a discussion of what it means to human-rate a space system crew controls and how trust in the human-computer interface begins with the NASA human rating requirements. Finally, a discussion on how systems engineering and the human system integration process ensures that crew control implementation incorporates the NASA human-rating requirements.

artemis↗
NASA NTRSDate not supplied

Establishing Trust in NASA’s Artemis Campaign Computer-Human Interface (CHI) Implementation

The NASA Artemis program will return humans to the Moon. This time, with the help of commercial and international partners, the program's objective is a permanent moon base. The moon base infrastructure, including an orbiting moon station and moon surface assets, will be developed for astronauts to stay for the long haul to learn to live and work on another planet in preparation for an eventual Humans-to-Mars mission. As the roundtrip communication delays increase in deep space exploration, the crew will need more onboard systems autonomy and functionality to maintain and control the vehicle or habitat. These mission constraints will change the current Earth-based spacecraft to ground control support approach that will demand more safe, efficient, and effective Computer-Human Interface (CHI) control. For Artemis, CHI is defined as the elements that the crew interfaces with: audio, video, lighting, and crew controls subsystems. Understanding how CHI will need to evolve to support deep space missions will be critical for the Artemis program--especially crew controls, which is the focus of this paper. How does NASA ensure crew controls are reliable enough to control complex systems and prevent a catastrophic event due to human error--especially when the astronauts could be physiologically and/or psychologically impaired? NASA's approach to mitigating catastrophic hazards in human spaceflight system development such as crew controls, is through a holistic system engineering and Human System Integration methodology that focuses on incorporating NASA's Human-Rating Requirements-that ensures human performance characteristics to control/safely recover the crew from hazardous situations within the human interface design are considered. This paper discusses, at a high level, CHI for the Artemis program. Next, a discussion of what it means to human-rate a space system crew controls and how trust in the human-computer interface begins with the NASA human rating requirements. Finally, a discussion on how systems engineering and the human system integration process ensures that crew control implementation incorporates the NASA human-rating requirements.

artemis↗
DOE OSTI2023

Investigation of 3D printed lightweight hybrid composites via theoretical modeling and machine learning

Hybrid composites combine two or more different fillers to achieve multifunctional or advanced material properties, such as lightweight and enhanced mechanical properties. The properties of the composites significantly depend on their microstructures, which can be tailored via advanced 3D printing processes. Understanding the process-structure-property relationships is critical to enable the design and engineering of novel hybrid composites for applications in aerospace, automotive, and protective coatings. Here, for this work, we develop 3D printable and lightweight hybrid composites and leverage the conventional design of experiments, a theoretical hybrid model, and an image-driven machine learning (ML) method to investigate their mechanical behaviors. The hybrid composites are formulated with elastomer matrix, microfillers, and thin-shell particles, enabling a significant degree of design freedom of microstructures with densities and mechanical properties varying up to 70% and 91%, respectively. Our statistical analysis indicates that the 3D printing path direction and the microfibers fraction are dominating process parameters with contribution percentages of 45.3% and 57.7% on the specific stiffness and strength, respectively. A hybrid mechanics model is developed based on a simple Weibull distribution function and classical single-filler models to effectively capture the variations in mechanical properties, however, it overestimates the values due to its statistical constraints and idealization of experimental uncertainty. The image-driven ML model leverages the microscale images directly without losing the structural details, shows more accurate predictions with experimental data, and has 48.6% lower root mean square error than the theoretical model.

3D printing↗
DOE OSTI2025

Rapid wavefield forecasting for earthquake early warning via deep sequence to sequence learning

We propose a deep learning model, WaveCastNet, to forecast high-dimensional wavefields. WaveCastNet integrates a convolutional long expressive memory architecture into a sequence-to-sequence forecasting framework, enabling it to model long-term dependencies and multiscale patterns in both space and time. By sharing weights across spatial and temporal dimensions, WaveCastNet requires significantly fewer parameters than more resource-intensive models such as transformers, resulting in faster inference times. Crucially, WaveCastNet also generalizes better than transformers to rare and critical seismic scenarios, such as high-magnitude earthquakes. Here, we show the ability of the model to predict the intensity and timing of destructive ground motions in real time, using simulated data from the San Francisco Bay Area. Furthermore, we demonstrate its zero-shot capabilities by evaluating WaveCastNet on real earthquake data. Our approach does not require estimating earthquake magnitudes and epicenters, steps that are prone to error in conventional methods, nor does it rely on empirical ground-motion models, which often fail to capture strongly heterogeneous wave propagation effects.

Geophysics↗
DOE OSTI2022

Data-driven model for divertor plasma detachment prediction

We present a fast and accurate data-driven surrogate model for divertor plasma detachment prediction leveraging the latent feature space concept in machine learning research. Our approach involves constructing and training two neural networks: an autoencoder that finds a proper latent space representation (LSR) of plasma state by compressing the multi-modal diagnostic measurements and a forward model using multi-layer perception (MLP) that projects a set of plasma control parameters to its corresponding LSR. By combining the forward model and the decoder network from autoencoder, this new data-driven surrogate model is able to predict a consistent set of diagnostic measurements based on a few plasma control parameters. In order to ensure that the crucial detachment physics is correctly captured, highly efficient 1D UEDGE model is used to generate training and validation data in this study. The benchmark between the data-driven surrogate model and UEDGE simulations shows that our surrogate model is capable of providing accurate detachment prediction (usually within a few per cent relative error margin) but with at least four orders of magnitude speed-up, indicating that performance-wise, it has the potential to facilitate integrated tokamak design and plasma control. Comparing with the widely used two-point model and/or two-point model formatting, the new data-driven model features additional detachment front prediction and can be easily extended to incorporate richer physics. This study demonstrates that the complicated divertor and scrape-off-layer plasma state has a low-dimensional representation in latent space. Understanding plasma dynamics in latent space and utilising this knowledge could open a new path for plasma control in magnetic fusion energy research.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

GraphAlign: Graph-Enabled Machine Learning for Seismic Event Filtering

This report summarizes results from a 2 year effort to improve the current automated seismic event processing system by leveraging machine learning models that can operated over the inherent graph data structure of a seismic sensor network. Specifically, the GraphAlign project seeks to utilize prior information on which stations are more likely to detect signals originating from particular geographic regions to inform event filtering. To date, the GraphAlign team has developed a Graphical Neural Network (GNN) model to filter out false events generated by the Global Associator (GA) algorithm. The algorithm operates directly on waveform data that has been associated to an event by building a variable sized graph of station waveforms nodes with edge relations to an event location node. This builds off of previous work where random forest models were used to do the same task using hand crafted features. The GNN model performance was analyzed using an 8 week IMS/IDC dataset, and it was demonstrated that the GNN outperforms the random forest baseline. We provide additional error analysis of which events the GNN model performs well and poorly against concluded by future directions for improvements.

58 GEOSCIENCES↗
DOE OSTI2021

AGGREGATE: dAta-driven modelinG preservinG contRollable dEr for outaGe mAnagemenT and rEsiliency (Final Report)

The AGGREGATE project team successfully developed and validated various modules for outage management. Brief summaries of each module are provided to showcase their strength for outage management and restoration for a distribution system with a high penetration of connected distribution energy resources (DERs). In recent years, inverter-based DERs have been widely deployed in distribution system. A most of behind-the-meter (BTM) solar power generation is not visible to the utility. The data-driven DER and load estimation modules are using machine learning (ML) and artificial intelligence (AI) to manage this issue, which provides an opportunity for distribution system operators (DSOs) to operate systems and make decisions in real-time for a distribution system with a high penetration of DERs deployed. Also, the estimated DER and true load can be further leveraged in network aggregation and cold-load pick up estimation for reducing the computing complexity and providing for fast restoration. After load demand and DER power generations have been estimated, the information will support topology and state estimation (SE). The topology estimation module demonstrated the viability of mixed integer linear programming (MILP) formulation to estimate the most likely operational radial topology and outage sections using power flow measurements, historical/estimated load and DERs data and smart meter ping measurements. Formulation includes continuous (power flow, load and DERs data) and binary measurements (smart meter ping measurements) in a single formulation. Errors in continuous data and binary data are modeled as normal distribution and Bernoulli distribution, respectively. In the future distribution grid, the power injection from controllable DERs will be essential for efficient and resilient grid operation. However, determining the optimal DER injections and restoration actions is dependent on knowledge of the system states. State estimation (SE), already the cornerstone of transmission energy management systems, will become commonplace in distribution management systems as more measurements become available from deployment of automated metering infrastructure (AMI). Observability analysis is the first step in SE, as it determines the sufficiency of the available measurements for accurately estimating the current system states. A new type of pseudo-measurement called a Correlational Measurement (CM) is introduced in this module, to enhance the observability of the system to enable more accurate SE. CMs encapsulate knowledge of correlation between demand patterns for similar classes of loads as well as injection patterns for same-technology renewable DERs. During grid contingency scenarios, DERs have been traditionally disconnected, without any fault ride-through capabilities. However, with new regulations and better technology, it is feasible for these resources to contribute to the grid’s restoration after an adverse event and hence enhance resilience. The controllability module proposes a two-step restoration scheme for the power system restoration process by leveraging additional degrees of freedom in power electronics interfaced DERs for mitigating voltage problems. In a resilience mode without the utility system, the distribution grid relies on DERs to serve critical load. In such a severe event with multiple faults on the distribution feeders, actuation of various protective devices (PDs) divides the distribution system into electrical islands. The undetected actuated PDs due to fault current contributions from DERs can delay the restoration process, thereby reducing the system resilience. The Advanced Outage Management (AOM) and the Advanced Feeder Restoration (AFR) modules developed in this project provide improved system resilience with multiple DERs. AOM identifies the faulted sections and actuated PDs in a distribution system with DERs by incorporating smart meter data. The most credible outage scenario including fault locations, PD actuations, and fault indicator (FI) failures is identified by a set of binary integer linear programming incorporating hypotheses. The AFR module serves to restore a distribution system with available energy resources taking into consideration the availability of utility sources and DERs. By partitioning the system into islands, critical load will be served with the available generation resources within islands based on the solution of a MILP. When the utility systems become available, the optimal path will be determined by a spanning tree search algorithm that reconnects these islands back to substations and restores the remaining load. The transmission and distribution (T&D) co-simulation module was used to validate the effect of a control action performed on the distribution side assets as it propagates to the transmission side. This ensures that the control action performed results in a feasible operating point on both the transmission and the distribution system. In addition to validation, the team used the T&D co-simulation module to demonstrate how distribution system assets can be used to mitigate issues on the transmission system. Specifically, the team demonstrated that appropriate switching operations on the distribution side can alleviate the line overload condition on the transmission side without causing new operational constraint violations.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Waveform processing using neural network algorithms on the front-end electronics

In a multi-channel radiation detector readout system, waveform sampling, digitization, and raw data transmission to the data acquisition system constitute a conventional processing chain. The deposited energy on the sensor is estimated by extracting peak amplitudes, area under pulse envelopes from the raw data, and starting times of signals or time of arrivals. However, such quantities can be estimated using machine learning algorithms on the front-end Application-Specific Integrated Circuits (ASICs), often termed as “edge computing”. Edge computation offers enormous benefits, especially when the analytical forms are not fully known or the registered waveform suffers from noise and imperfections of practical implementations. In this work, we aim to predict peak amplitude from a single waveform snippet whose rising and falling edges containing only 3 to 4 samples. We thoroughly studied two well-accepted neural network algorithms, Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN) by varying their model sizes. Further, to better fit front-end electronics, neural network model reduction techniques, such as network pruning methods and variable-bit quantization approaches, were also studied. By combining pruning and quantization, our best performing model has the size of 1.5 KB, reduced from 16.6 KB of its full model counterpart. It can reach mean absolute error of 0.034 comparing to that of a naive baseline of 0.135. Such parameter-efficient and predictive neural network models established feasibility and practicality of their deployment on front-end ASICs.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Divertor Plasma Detachment Control Neural Network

DivControlNN is a state-of-the-art software tool that leverages advanced machine learning techniques to predict and control divertor plasma behavior in fusion reactors. Plasma, a highly energetic and electrically charged gas, requires meticulous management to protect reactor components and maintain optimal energy production. Conventional simulation methods, although extremely detailed, typically demand extensive computational time-making them unsuitable for real-time control scenarios. DivControlNN addresses this challenge by learning from tens of thousands of high-fidelity simulations, thereby creating a rapid surrogate model that can deliver near-instantaneous predictions. At the core of its functionality is a sophisticated technique known as latent space mapping, which condenses complex, high-dimensional plasma data into a compact, lower-dimensional representation. This streamlined representation enables the system to quickly forecast essential plasma properties and determine the precise conditions required for effective detachment. Detachment is a crucial process in which the plasma is cooled before reaching the divertor plates, thereby reducing heat loads and mitigating material erosion. In recent experiments conducted on the KSTAR tokamak in South Korea, DivControlNN successfully guided the detachment process without any fine-tuning-even when applied to a new tungsten divertor configuration. By achieving a computational speed-up of over one hundred million times compared to traditional simulation methods while maintaining low prediction errors, DivControlNN stands to significantly enhance real-time control and diagnostic capabilities in future fusion reactors. This breakthrough paves the way for safer, more reliable reactor operation and represents a major advancement toward realizing fusion energy as a practical, sustainable, and clean power source.

Xu, Xueqiao [Lawrence Livermore National Laborator↗
DOE OSTI2024

Exploring 2D X-ray diffraction phase fraction analysis with convolutional neural networks: Insights from kinematic-diffraction simulations

Abstract Deep-learning models are effective for analyzing the complex information in 2D X-ray diffraction (XRD) patterns. Accurately collecting parameters of the material sample is crucial during model training, significantly impacting model performance. In this study, we employ a kinematic-diffraction simulator to generate simulated 2D XRD patterns for Ti–6Al–4V alloy, allowing precise control of sample parameters. These simulated patterns are used to train convolutional neural networks, predicting $$\upbeta$$ β -phase volume fractions. The training data set consists exclusively of 2D XRD patterns with pure $$\upalpha$$ α - or pure $$\upbeta$$ β -phase, while the testing set incorporates patterns with intermediate phase volume fraction. In particular, we investigate how the architectures of the model influence prediction reliability and computational performance. Experimental results reveal that, with appropriate training, the convolutional neural network accurately detects intermediate phase volume fractions even trained with only pure-phase patterns, achieving a mean square error accuracy of $$9.4 \times 10^{-4}$$ 9.4 × 10 - 4 . Graphical abstract

Yue, Weiqi↗
NASA NTRS2016

Laboratory Testing and Performance Verification of the CHARIS Integral Field Spectrograph

The Coronagraphic High Angular Resolution Imaging Spectrograph (CHARIS) is an integral field spectrograph (IFS) that has been built for the Subaru telescope. CHARIS has two imaging modes; the high-resolution mode is R82, R69, and R82 in J, H, and K bands respectively while the low-resolution discovery mode uses a second low-resolution prism with R19 spanning 1.15-2.37 microns (J+H+K bands). The discovery mode is meant to augment the low inner working angle of the Subaru Coronagraphic Extreme Adaptive Optics (SCExAO) adaptive optics system, which feeds CHARIS a coronagraphic image. The goal is to detect and characterize brown dwarfs and hot Jovian planets down to contrasts five orders of magnitude dimmer than their parent star at an inner working angle as low as 80 milliarcseconds. CHARIS constrains spectral crosstalk through several key aspects of the optical design. Additionally, the repeatability of alignment of certain optical components is critical to the calibrations required for the data pipeline. Specifically the relative alignment of the lens let array, prism, and detector must be highly stable and repeatable between imaging modes. We report on the measured repeatability and stability of these mechanisms, measurements of spectral crosstalk in the instrument, and the propagation of these errors through the data pipeline. Another key design feature of CHARIS is the prism, which pairs Barium Fluoride with Ohara L-BBH2 high index glass. The dispersion of the prism is significantly more uniform than other glass choices, and the CHARIS prisms represent the first NIR astronomical instrument that uses L-BBH2as the high index material. This material choice was key to the utility of the discovery mode, so significant efforts were put into cryogenic characterization of the material. The final performance of the prism assemblies in their operating environment is described in detail. The spectrograph is going through final alignment, cryogenic cycling, and is being delivered to the Subaru telescope in April 2016. This paper is a report on the laboratory performance of the spectrograph, and its current status in the commissioning process so that observers will better understand the instrument capabilities. We will also discuss the lessons learned during the testing process and their impact on future high-contrast imaging spectrographs for wavefront control.

Coronagraphic High Angular Resolution Imaging Spec↗
DOE OSTI2025

Forecasting Multi-Step-Ahead Street-Scale Nuisance Flooding using a seq2seq LSTM Surrogate Model for Real-Time Application in a Coastal-Urban City

In coastal-urban cities facing an elevated risk of nuisance flooding (by rain and tide) due to increased heavy rainfall, sea level rise, urbanization, and aging drainage systems, real-time flood forecasting at the street-scale can provide useful information to transportation decision-makers. Physics-Based Models (PBMs) that offer high accuracy come with high computational runtimes and costs that limit their application for real-time flood forecasting. To address this challenge, Machine Learning (ML) surrogate models trained from PBMs have been proposed to provide street-scale flood forecasts. Previous related studies have focused on using Long Short-Term Memory (LSTM) architectures to model hourly flood depth on streets. While LSTM models can capture input sequences effectively, they fall short in accurately preserving output sequences, limiting their suitability for multi-step-ahead forecasts. The seq2seq LSTM architecture offers a key advantage here by capturing the full sequence of input–output, making it potentially more suitable for multi-step-ahead flood forecasts compared to traditional LSTM models. However, seq2seq LSTM has not been tested for street-scale flood forecasting, particularly for rapidly fluctuating nuisance flooding events which require special attention to its temporal sequences. Hence, in this study, we applied the seq2seq LSTM model to explore multi-step-ahead street-scale nuisance flooding and compared its results to the traditional LSTM model as a benchmark model. LSTM and seq2seq LSTM surrogate models were applied to 22 flood-prone streets in Norfolk, Virginia, as a case study with a 4-hr (short-term) and 8-hr (long-term) lead time. The models were trained with environmental (rainfall and tide) and topographic (elevation, Topographic Wetness Index, and Depth-To-Water) features along with PBM-derived water depths for different storm events. The results demonstrated satisfactory performance of both LSTM and seq2seq LSTM surrogate models throughout the forecast period compared to the PBM. However, the seq2seq LSTM showed lower Mean Absolute Error (MAE)/ Root Mean Square Error (RMSE) and higher Nash–Sutcliffe Efficiency (NSE)/ correlation than the LSTM across most lead times, particularly for long-term forecasting due to its supremacy in handling both input–output sequences together, which is missing in the traditional LSTM. For example, in the long-term, the average RMSE ranges were 0.0268–0.0373 m for LSTM and 0.0226–0.0319 m for seq2seq LSTM, while in the short-term, they were 0.0263–0.0293 m and 0.0261–0.0283 m, respectively. Additionally, while both models exhibited similar performance in distinguishing flooded and non-flooded streets for flood depth ≥ 0.1 m, the seq2seq LSTM model demonstrated superior performance for higher flood depths (such as ≥ 0.2 m and ≥ 0.3 m). Once trained, inference took only 0.09 to 0.11 s (short-term) and 0.30 to 0.35 s (long-term) per storm event for the 22 streets, making the application highly suitable for real-time decision-making during nuisance flood events.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Local reduced-order modeling for electrostatic plasmas by physics-informed solution manifold decomposition

Despite advancements in high-performance computing and modern numerical algorithms, computational cost remains prohibitive for multi-query kinetic plasma simulations. Here, in this work, we develop data-driven reduced-order models (ROMs) for collisionless electrostatic plasma dynamics, based on the kinetic Vlasov-Poisson equation. Our ROM approach projects the equation onto a linear subspace defined by the proper orthogonal decomposition (POD) modes. We introduce an efficient tensorial method to update the nonlinear term using a precomputed third-order tensor. We capture multiscale behavior with a minimal number of POD modes by decomposing the solution manifold into multiple time windows and creating temporally local ROMs. We consider two strategies for decomposition: one based on the physical time and the other based on the electric field energy. Applied to the 1D1V Vlasov–Poisson simulations, that is, prescribed E-field, Landau damping, and two-stream instability, we demonstrate that our ROMs accurately capture the total energy of the system both for parametric and time extrapolation cases. The temporally local ROMs are more efficient and accurate than the single ROM. In addition, in the two-stream instability case, we show that the energy-windowing reduced-order model (EW-ROM) is more efficient and accurate than the time-windowing reduced-order model (TW-ROM). With the tensorial approach, EW-ROM solves the equation approximately 90 times faster than Eulerian simulations while maintaining a maximum relative error of 7.5% for the training data and 11% for the testing data.

Electrostatic plasmas↗