Search NASA⌕ Search

SEARCH · Search NASA

Results for “Continual 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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Projections of future climate for U.S. national assessments: past, present, future

Climate assessments consolidate our understanding of possible future climate conditions as represented by climate projections, which are largely based on the output of global climate models. Over the past 30 years, the scientific insights gained from climate projections have been refined through model structural improvements, emerging constraints on climate feedbacks, and increased computational efficiency. Within the same period, the process of assessing and evaluating information from climate projections has become more defined and targeted to inform users. As the size and audience of climate assessments has expanded, the framing, relevancy, and accessibility of projections has become increasingly important. This paper reviews the use of climate projections in national climate assessments (NCA) while highlighting challenges and opportunities that have emerged over time. Reflections and lessons learned address the continuous process to understand the broadening assessment audience and evolving user needs. Insights for future NCA development include (1) identifying benchmarks and standards for evaluating downscaled datasets, (2) expanding efforts to gather research gaps and user needs to inform how climate projections are presented in the assessment (3) providing practitioner guidance on the use, interpretation, and reporting of climate projections and uncertainty to better inform decision-making.

Assessment↗
DOE OSTI2024

Incentivizing and Supporting Early-Stage Solar Innovation in the United States

In 2018, the U.S. Department of Energy's Solar Energy Technologies Office and the National Renewable Energy Laboratory set out to develop a repeatable, predictable prize model (the American-Made Challenges) and an entrepreneurial innovation network (the American-Made Network) to support participants along their innovation journeys. This began with the launch of the Solar Prize. Five years and six rounds later, the Solar Prize is the longest-standing competition of the American-Made Challenges. It has awarded $\$20.1$ million in cash prizes and $\$5.5$ million in technical support vouchers to 140 teams across all aspects of the solar industry. By sharing the outputs of the prize, we hope that our lessons learned will help continue to build the clean tech entrepreneurship support ecosystem.

14 SOLAR ENERGY↗
DOE OSTI2025

Lessons Learned on Prize Design in the Perovskite Startup Prize

In 2018, the U.S. Department of Energy's Solar Energy Technologies Office and the National Renewable Energy Laboratory set out to develop a repeatable, predictable prize model with the American-Made Challenges. A new model launched by the Solar Energy Technologies Office in March 2021 was the American-Made Perovskite Startup Prize. This new prize aimed to accelerate the growth of the domestic perovskite industry and support the rapid development of solar cells and modules that use perovskite materials. By sharing the outputs of the prize, we hope that our lessons learned will help continue to build the clean tech entrepreneurship support ecosystem and influence how a successful prize design can be achieved.

14 SOLAR ENERGY↗
DOE OSTI2025

Tactical Analysis for Calculating Contextual Risk at Boundaries: Summary of Laboratory Directed Research & Development Effort

The Tactical Analysis for Calculating Contextual Risk at Boundaries (TACCRAB) tool is an innovative digital twin (DT) platform and automated risk algorithm designed to transform operational decision-making in structured screening environments, with an initial focus on Southern Border Land Ports of Entry (POEs). The invention provides integration points for advanced artificial intelligence, predictive modeling, and real-time data analysis to produce a comprehensive risk management tool that enables proactive, data-informed security strategies. The core inventive features of TACCRAB center on its unique risk algorithm, which dynamically calculates contextual risk by synthesizing historical data, near real-time streaming data from the checkpoints themselves, and AI-generated predictions. Unlike traditional risk assessment methods, TACCRAB utilizes a DT to provide comprehensive operational insights, allowing stakeholders to visualize, simulate, and optimize checkpoint configurations with unprecedented speed and contextual awareness. TACCRAB's key innovation lies in its ability to combine multiple complex inputs - including technology detection probabilities, resource availability, screening pathway characteristics, and threat actor behavioral patterns - into a unified risk calculation and update these inputs based on changing operational and environmental conditions. By leveraging a DT that continuously updates and learns from linked data, TACCRAB can suggest adaptive mitigation strategies that minimize risk while maintaining operational efficiency. Particularly novel is the platform's approach to decision support, which goes beyond static risk assessment. The DT provides dynamic metrics such as wait times, resource allocation effectiveness, and potential emerging threat scenarios, enabling users to view sophisticated, relevant what-if simulations and optimize checkpoint operations in near real-time. The system's architecture allows for generalized application across different screening environments, such as secure facilities, ports of entry, and soft targets, making it a versatile tool for security and operational management. The invention distinguishes itself through its comprehensive integration of predictive modeling, AI-driven pattern discovery, and user-friendly interface design. By combining these elements, TACCRAB transforms complex risk data into actionable insights, supporting decision-makers at various organizational levels - from booth agents making split-second screening decisions to checkpoint managers optimizing the day's resource allocation to strategic planners managing long-term investments.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2024

Controlling optical-cavity locking using reinforcement learning

Abstract This study applies an effective methodology based on Reinforcement Learning to a control system. Using the Pound–Drever–Hall locking scheme, we match the wavelength of a controlled laser to the length of a Fabry-Pérot cavity such that the cavity length is an exact integer multiple of the laser wavelength. Typically, long-term drift of the cavity length and laser wavelength exceeds the dynamic range of this control if only the laser’s piezoelectric transducer is actuated, so the same error signal also controls the temperature of the laser crystal. In this work, we instead implement this feedback control grounded on Q-Learning. Our system learns in real-time, eschewing reliance on historical data, and exhibits adaptability to system variations post-training. This adaptive quality ensures continuous updates to the learning agent. This innovative approach maintains lock for eight days on average.

47 OTHER INSTRUMENTATION↗
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 OSTI2025

Towards a Robust Adaptive Digital Twin for Fusion Applications

The development of a digital twin system for fusion applications is essential for enhancing the prediction, analysis, and optimization of complex plasma processes. Machine learning (ML), particularly deep learning has demonstrated strong capabilities in modeling such highly nonlinear and intricate systems. However, two critical challenges limit the deployment of deep learning-based digital twins: Uncertainty Quantification (UQ) and data drift. UQ is vital for ensuring trustworthy predictions, especially in decision-support scenarios. Additionally, data-driven models are often sensitive to changes in the underlying data distribution, such as shot-to-shot variations in fusion experiments, which can lead to performance degradation over time. To address these challenges, we are developing an uncertainty-aware, adaptive digital twin framework. Our approach incorporates deep learning models enhanced with Gaussian Process approximations for predictive uncertainty estimation, coupled with an online learning mechanism that enables continuous model adaptation to new experimental data. This adaptive capability allows the data driven models to respond effectively to evolving plasma behaviors and equipment conditions. Specifically, to mitigate the effects of shot-to-shot drift, our system updates itself incrementally as new data becomes available, improving both robustness and fidelity. Our vision is to evolve this data driven model into a self-sustaining digital twin system that leverages UQ based feedback to continuously refine itself and potentially support real-time decision making. This presentation will cover a brief background on uncertainty quantification for ML, our ongoing effort on development of UQ capabilities for ML, our data science pipeline from data collection to model development and analysis and online learning framework for modeling coil deflection at DIII-D. I will also briefly touch upon opportunities and challenges in development of digital twin framework.

Sammuli, Brian [General Atomics]↗
DOE OSTI2026

Structure-aware Initialization via Numerical Continuation and Informed Priors

Scientific machine learning (SciML) often operates in ill-conditioned, weakly identifiable regimes due to limited data or indirect observations. In such settings, optimization and inference are highly sensitive to the starting point, making initialization--often under-reported--a consequential degree of freedom. Random initialization is not a neutral default as it induces an implicit prior over candidate solutions and can systematically bias the result, producing large run-to-run variability. Here, we formalize this view by treating initialization as a hidden confounder in SciML and develop a unifying theory for structure-aware initialization via numerical continuation, constructing warm starts from related problem instances. Across representative tasks, including physics-informed neural networks, maximum likelihood estimation, and variational inference, warm starts have been shown to consistently reduce optimization effort and improve reliability.

Data integrity↗
DOE OSTI2025

An Experiment with LLMs as Database Design Tutors: Persistent Equity and Fairness Challenges in Online Learning

As large language models (LLMs) continue to evolve, their capacity to replace humans as their surrogates is also improving. As increasing numbers of intelligent tutoring systems (ITSs) are embracing the integration of LLMs for digital tutoring, questions are arising as to how effective they are and if their hallucinatory behaviors diminish their perceived advantages. One critical question that is seldom asked if the availability, plurality, and relative weaknesses in the reasoning process of LLMs are contributing to the much discussed digital divide and equity and fairness in online learning. In this paper, we present an experiment with database design theory assignments and demonstrate that while their capacity to reason logically is improving, LLMs are still prone to serious errors. We demonstrate that in online learning and in the absence of a human instructor, LLMs could introduce inequity in the form of “wrongful” tutoring that could be devastatingly harmful for learners, which we call ignorant bias, in increasingly popular digital learning. We also show that significant challenges remain for STEM subjects, especially for subjects for which sound and free online tutoring systems exist. Based on the set of use cases, we formulate a possible direction for an effective ITS for online database learning classes of the future.

Jamil, Hasan M. (ORCID:0000000231243780)↗
DOE OSTI2024

Calibrating Bayesian generative machine learning for Bayesiamplification

Recently, combinations of generative and Bayesian deep learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Advancing set-conditional set generation: Diffusion models for fast simulation of reconstructed particles

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve as efficient surrogate models. We propose a fast emulation approach that combines simulation and reconstruction. In other words, a neural network generates a set of reconstructed objects conditioned on input particle sets. To make this possible, we advance set-conditional set generation with diffusion models. Using a realistic, generic, and public detector simulation and reconstruction package (COCOA), we show how diffusion models can accurately model the complex spectrum of reconstructed particles inside jets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Deep Reinforcement Learning Based Control of Wind Turbines for Fast Frequency Response

In order to fulfill vital auxiliary grid services, such as load regulation, spin and non-spin reserve provision, and frequency support during emergencies, there is often a requirement for certain wind farms to operate in de-loaded modes. Leveraging the swift response capabilities of wind farms, this study demonstrates that reserving power in de-loaded modes can significantly enhance power grid stability and reliability during system contingencies. Controlling wind farms optimally for frequency support is intricate due to the nonlinearity of models and controllers and the complexity of wind farm interactions with power systems. Here, to address this challenge, this paper introduces a novel approach that integrates wind turbines into reinforcement learning-based solutions for frequency response. This innovative methodology utilizes the state-of-the-art reinforcement learning algorithm known as the surrogate-gradient-based evolutionary strategy. The proposed learning-based algorithm provides continuous control of wind farm output to rapidly stabilize system frequency and prevent unnecessary trips of under-frequency load shedding relays. To facilitate efficient training, parallel computing techniques are employed. The proposed methodology is evaluated on a modified IEEE-39 bus system, and simulation results reveal its efficacy in reliably supporting power system frequency and preventing the need for unnecessary load shedding.

Gao, Wei [Argonne National Laboratory (ANL), Argon↗
DOE OSTI2025

Mathematical Morphological Filtering with a Self-Adaptive Reconstruction Technique and Application to Local Seismic Data

Recorded seismic data are generally contaminated by noise from different sources, which masks the signals of interest. In the seismology community, frequency filtering (FF) is the standard method for noise suppression. However, when the signal of interest and noise share the same frequency band, the latter cannot be filtered out without infringing on the former. We implemented a noise suppression approach based on the mathematical morphology theorem. The method involves compound operations of dilation and erosion using structuring elements of varying lengths and decomposes an input noisy waveform into several time functions with differing characteristics. Further, the filtered waveform is constructed from the time functions using a self-adaptive reconstruction technique. Application to a data set of >4700 local waveforms suggests that the implemented mathematical morphological filtering (MMF) approach is efficient for data with low signal-to-noise ratio (SNR) and significantly outperforms FF in that SNR range. For most of the dataset, FF, machine learning (ML) denoising, and continuous wavelet transform (CWT) thresholding result in higher SNR values compared with the MMF method. However, for ~42% of the waveforms, MMF outperforms FF, and the SNR gain achieved with MMF is as large as ~23 dB. Compared to ML denoising and CWT thresholding, this proportion drops to only ~10%–14%. Our results suggests that in an operational setting, MMF cannot replace the other noise suppression methods; however, signal detection can be improved if MMF is used to supplement them in some scenarios. MMF could help detect signals in problematic low-SNR data, which are currently being missed particularly when using FF alone.

58 GEOSCIENCES↗
DOE OSTI2026

TANTE: Time-adaptive operator learning via neural Taylor expansion

Operator learning for time-dependent partial differential equations (PDEs) has seen rapid progress in recent years, enabling efficient approximation of complex spatiotemporal dynamics. However, most existing methods rely on fixed time step sizes during rollout, which limits their ability to adapt to varying temporal complexity and often leads to error accumulation. In this work, we propose the Time-Adaptive Transformer with Neural Taylor Expansion (TANTE), a novel operator-learning framework that produces continuous-time predictions with adaptive step sizes. TANTE predicts future states by performing a Taylor expansion at the current state, where neural networks learn both the higher-order temporal derivatives and the local radius of convergence. This allows the model to dynamically adjust its rollout based on the local behavior of the solution, thereby reducing cumulative error and improving computational efficiency. We demonstrate the effectiveness of TANTE across a wide range of PDE benchmarks, achieving superior accuracy and adaptability compared to fixed-step baselines, delivering accuracy gains of 60-80 % and speed-ups of 30-40 % at inference time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A resolution independent neural operator

The Deep operator network (DeepONet) is a powerful yet simple neural operator architecture that utilizes two deep neural networks to learn mappings between infinite-dimensional function spaces. This architecture is highly flexible, allowing the evaluation of the solution field at any location within the desired domain. However, it imposes a strict constraint on the input space, requiring all input functions to be discretized at the same locations; this limits its practical applications. Here, in this work, we introduce a general framework for operator learning from input–output data with arbitrary number and locations of sensors. This begins by introducing a resolution-independent DeepONet (RI-DeepONet), enabling it to handle input functions that are arbitrarily, but sufficiently finely, discretized. To this end, we propose two dictionary learning algorithms to adaptively learn a set of appropriate continuous basis functions, parameterized as implicit neural representations (INRs), from correlated signals defined on arbitrary point cloud data. These basis functions are then used to project arbitrary input function data as a point cloud onto an embedding space (i.e., a vector space of finite dimensions) with dimensionality equal to the dictionary size, which can be directly used by DeepONet without any architectural changes. In particular, we utilize sinusoidal representation networks (SIRENs) as trainable INR basis functions. The introduced dictionary learning algorithms are then used in a similar way to learn an appropriate dictionary of basis functions for the output function data, which defines a new neural operator architecture referred to as the R esolution I ndependent N eural O perator (RINO). In the RINO, the operator learning task simplifies to learning a mapping from the coefficients of input basis functions to the coefficients of output basis functions. We demonstrate the robustness and applicability of RINO in handling arbitrarily (but sufficiently richly) sampled input and output functions during both training and inference through several numerical examples.

Deep operator network (DeepONet)↗
DOE OSTI2026

Machine Learning an Ab-Initio Based Bond-Order Potential for Bismuthene

Bismuthene is a heavy 2D material whose strong spin–orbit coupling and recently observed single-element ferroelectricity have intensified interest in its structural, vibrational, and transport properties. Accurate modeling of these behaviors requires a short-range interatomic potential that can reproduce the underlying bonding physics at a fraction of the computational cost of first-principles methods. However, such a potential is currently unavailable. Here, in this work, we construct a Tersoff bond-order potential for β-bismuthene using a reinforcement-learning framework that integrates a continuous Monte Carlo Tree Search with a simplex-based local optimizer. The optimized parameter sets reproduce first-principles lattice constants, cohesive energy, the equation of state, elastic constants, and phonon dispersion. We validate the models by performing thermal-conductivity calculations and uniaxial fracture simulations our findings confirm the reliability of the resulting models across multiple thermomechanical regimes. Comparison of the three best solutions reveals how differences in pairwise interactions, angular terms, and bond-order behavior govern phonon features and mechanical responses. We demonstrate an interpretable and computationally efficient potential for bismuthene and demonstrate a general reinforcement-learning strategy for developing bond-order models in emerging 2D materials.

deformation↗
DOE OSTI2025

Machine Learning–Guided Boolean Matrix Inference for Real-Time O-RAN Conflict Detection

Open Radio Access Networks (O-RAN) are emerging, software-driven cellular architectures that promote flexibility by enabling components from different vendors to interoperate. Multiple control applications called xApps can independently adjust network parameters in near real time, often without awareness of each other's actions. This creates a system highly prone to unintended conflicts and performance degradation due to the inherent complexity of such openness. To model such systems and ultimately prevent or mitigate xApp conflicts, it is essential to understand the dynamic relationships between xApps (A), the control parameters they adjust (P), and the resulting KPI responses (K). While the mappings from A to P and from K to A can often be derived from xApp specifications, the relationship from P to K is typically hidden within the system’s dynamics and must be inferred from observed data. We propose a novel data-driven Boolean inference framework that uncovers the hidden P?K dependencies using machine learning and interpretable rule induction. Continuous parameters and KPIs are first binarized using decision tree classifiers, and a binary influence matrix L is then inferred by solving Boolean matrix equations over time. This compact representation improves interpretability and enables real-time tracking of dynamically evolving parameter-KPI dependencies. We demonstrate the effectiveness of our method in a realistic mobile handover scenario, where it accurately recovers the underlying logic and enables proactive conflict detection.

42 - ENGINEERING↗