Search NASA⌕ Search

SEARCH · Search NASA

Results for “Constrained 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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Stability-Constrained Learning for Frequency Regulation in Power Grids With Variable Inertia

The increasing penetration of converter-based renewable generation has resulted in faster frequency dynamics, and low and variable inertia. As a result, there is a need for frequency control methods that are able to stabilize a disturbance in the power system at timescales comparable to the fast converter dynamics. This paper proposes a combined linear and neural network controller for inverter-based primary frequency control that is stable at time-varying levels of inertia. We model the time-variance in inertia via a switched affine hybrid system model. We derive stability certificates for the proposed controller via a quadratic candidate Lyapunov function. We test the proposed control on a 12-bus 3-area test network, and compare its performance with a base case linear controller, optimized linear controller, and finite-horizon Linear Quadratic Regulator (LQR). Our proposed controller achieves faster mean settling time and over 50% reduction in average control cost across 100 inertia scenarios compared to the optimized linear controller. Unlike LQR which requires complete knowledge of the inertia trajectories and system dynamics over the entire control time horizon, our proposed controller is real-time tractable, and achieves comparable performance to LQR.

data-driven control↗
NASA NTRS1989

Neural learning of constrained nonlinear transformations

Two issues that are fundamental to developing autonomous intelligent robots, namely, rudimentary learning capability and dexterous manipulation, are examined. A powerful neural learning formalism is introduced for addressing a large class of nonlinear mapping problems, including redundant manipulator inverse kinematics, commonly encountered during the design of real-time adaptive control mechanisms. Artificial neural networks with terminal attractor dynamics are used. The rapid network convergence resulting from the infinite local stability of these attractors allows the development of fast neural learning algorithms. Approaches to manipulator inverse kinematics are reviewed, the neurodynamics model is discussed, and the neural learning algorithm is presented.

Barhen, Jacob↗
DOE OSTI2024

Physics-constrained machine learning for electrodynamics without gauge ambiguity based on Fourier transformed Maxwell’s equations

We utilize a Fourier transformation-based representation of Maxwell’s equations to develop physics-constrained neural networks for electrodynamics without gauge ambiguity, which we label the Fourier–Helmholtz–Maxwell neural operator method. In this approach, both of Gauss’s laws and Faraday’s law are built in as hard constraints, as well as the longitudinal component of Ampère–Maxwell in Fourier space, assuming the continuity equation. An encoder–decoder network acts as a solution operator for the transverse components of the Fourier transformed vector potential, $\hat{A}_⟂(k,t)$, whose two degrees of freedom are used to predict the electromagnetic fields. This method was tested on two electron beam simulations. Among the models investigated, it was found that a U-Net architecture exhibited the best performance as it trained quicker, was more accurate and generalized better than the other architectures examined. We demonstrate that our approach is useful for solving Maxwell’s equations for the electromagnetic fields generated by intense relativistic charged particle beams and that it generalizes well to unseen test data, while being orders of magnitude quicker than conventional simulations. We show that the model can be re-trained to make highly accurate predictions in as few as 20 epochs on a previously unseen data set.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A physics-constrained deep learning surrogate model of the runaway electron avalanche growth rate

A surrogate model of the runaway electron avalanche growth rate in a magnetic fusion plasma is developed. This is accomplished by employing a physics-informed neural network (PINN) to learn the parametric solution of the adjoint to the relativistic Fokker–Planck equation. The resulting PINN is able to evaluate the runaway probability function across a broad range of parameters in the absence of any synthetic or experimental data. This surrogate of the adjoint relativistic Fokker–Planck equation is then used to infer the avalanche growth rate as a function of the electric field, synchrotron radiation and effective charge. Predictions of the avalanche PINN are compared against first principle calculations of the avalanche growth rate with excellent agreement observed across a broad range of parameters.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

A physics-constrained deep learning treatment of runaway electron dynamics

An adjoint formulation leveraging a physics-informed neural network (PINN) is employed to advance the density moment of a runaway electron (RE) distribution forward in time. A distinguishing feature of this approach is that once the adjoint problem is solved, its solution can be used to project the RE density forward in time for an arbitrary initial momentum space distribution of REs. Furthermore, by employing a PINN, a parametric solution to the adjoint problem can be learned. Thus, once trained, this adjoint-deep learning framework is able to efficiently project the RE density forward in time across various plasma conditions while still including a fully kinetic description of RE dynamics. As an example application, the temporal evolution of the density of primary electrons is studied, with particular emphasis on evaluating the decay of a RE population when below threshold. Predictions from the adjoint-deep learning framework are found to be in good agreement with a traditional relativistic electron Fokker–Planck solver, for several distinct initial conditions, and across an array of physics parameters. Once trained, the PINN thus provides a means of generating RE density time histories with exceptionally low online execution time.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Compressing Vision Transformers in Geospatial Transfer Learning with Manifold-Constrained Optimization

Deploying geospatial foundation models on resource-constrained edge devices demands compact architectures that maintain high downstream performance. However, their large parameter counts and the accuracy loss often induced by compression limit practical adoption.In this work, we leverage manifold-constrained optimization framework DLRT to compress large vision transformer–based geospatial foundation models during transfer learning. By enforcing structured low-dimensional parameterizations aligned with downstream objectives, this approach achieves strong compression while preserving task-specific accuracy. We show that the method outperforms of-the-shelf low-rank methods as LoRA. Experiments on diverse geospatial benchmarks confirm substantial parameter reduction with minimal accuracy loss, enabling high-performing, on-device geospatial models.

Snyder, Thomas [Yale University]↗
DOE OSTI2025

High‐Asymmetry Metasurface: A New Solution for Terahertz Resonance via Active Learning‐Augmented Diffusion Model

Terahertz (THz) metamaterials with high‐figure‐of‐merit (high‐FoM) performance resonance are essential for advancing sensors, detectors, and imagers. Conventional designs focus on symmetric or low‐asymmetry geometric structures, leaving high‐asymmetry designs largely unexplored due to the inefficiency of trial‐and‐error‐based rational design. Recent deep learning techniques offer automation and acceleration but are constrained by the need for large datasets inherent to their data‐driven nature. Here, a novel prior knowledge‐guided generative model augmented by a physics‐constrained active learning mechanism to design high‐asymmetry metamaterials. An advanced diffusion model learns features from a small set of classical structures with high‐FoM THz resonance and generates new high‐asymmetry structures. To mitigate the limited number of classical structures, the generated high‐asymmetry structures are actively selected and integrated into the initial training dataset based on their physical characteristics. Experimental results demonstrate the superior resonance performance of the generated high‐asymmetry metamaterials over classical designs, exhibiting improvements exceeding 30% in key resonance metrics. Remarkably, this performance is attained using only 68 classical structures as the initial training dataset, significantly reducing the data requirements for deep learning‐based metamaterial design. The proposed scheme for generating high‐asymmetry structures provides a new effective and efficient solution for high‐FoM resonance, expanding applications in high‐sensitivity THz metadevices.

diffusion model↗
DOE OSTI2025

Bayesian Entropy Neural Networks for physics-aware prediction

This article addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring flexible model behavior to incorporate non-data sample information. We introduce Bayesian Entropy Neural Networks (BENN), a framework grounded in Maximum Entropy (MaxEnt) principles, designed to impose constraints on Bayesian Neural Network (BNN) predictions. BENN is capable of constraining not only the predicted values but also their derivatives and variances, ensuring a more robust and reliable model output. To achieve simultaneous uncertainty quantification and constraint satisfaction, we employ the method of multipliers approach. This allows for the concurrent estimation of neural network parameters and the Lagrangian multipliers associated with the constraints. Our experiments, spanning diverse applications such as beam deflection modeling and microstructure generation, demonstrate the effectiveness of BENN. The results highlight significant improvements over traditional BNNs and showcase competitive performance relative to contemporary constrained deep learning methods.

14 SOLAR ENERGY↗
DOE OSTI2025

Machine learning models for PDE constrained optimization

Partial differential equation (PDE)-constrained optimization problems arise in a variety of scientific and engineering applications, such as topology optimization, electrodynamics, fluid dynamics, and structural dynamics. However, these problems are often challenging and computationally expensive to solve, due to the need to solve the PDEs within the optimization loop. One approach to reducing the computational cost of these methods while providing convergence guarantees is through inexact trust region methods; this method uses lower fidelity solutions of the PDE at early stages of the optimization and adjusts the required accuracy of inexact PDE solvers as the optimization progresses. In this work, we explore the use of machine learning based surrogate models with these inexact trust region methods. We first demonstrate the potential of this approach by using Gaussian processes as the surrogate model and test this on a simple PDE-constrained optimization problem. We then document explorations into improving the computational costs of evolutional deep neural network / neural Galerkin methods, with the eventual goal of using these methods with the inexact trust region algorithms. We are able to speed up these approaches, albeit at the cost of lower accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Learning broken symmetries with approximate invariance

Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized dataset, and is broken in actual data, due to asymmetries in the detector, or varying response resolution as a function of particle momentum. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry, effectively overconstraining the response of the neural network. We propose a learning model which balances the generality and asymptotic performance of unconstrained networks with the rapid learning of constrained networks. This is achieved through a dual-subnet structure, where one network is constrained by the symmetry and the other is not, along with a learned symmetry factor. In a simplified toy example that demonstrates violation of Lorentz invariance, our model learns as rapidly as symmetry constrained networks but escapes its performance limitations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Scientific machine learning for closure models in multiscale problems: A review

Here, closure problems are omnipresent when simulating multiscale systems, where some quantities and processes cannot be fully prescribed despite their effects on the simulation's accuracy. Recently, scientific machine learning approaches have been proposed as a way to tackle the closure problem, combining traditional (physics-based) modeling with data-driven (machine-learned) techniques, typically through enriching differential equations with neural networks. This paper reviews the different reduced model forms, distinguished by the degree to which they include known physics, and the different objectives of a priori and a posteriori learning. The importance of adhering to physical laws (such as symmetries and conservation laws) in choosing the reduced model form and choosing the learning method is discussed. The effect of spatial and temporal discretization and recent trends toward discretization-invariant models are reviewed. In addition, we make the connections between closure problems and several other research disciplines: inverse problems, Mori-Zwanzig theory, and multi-fidelity methods. In conclusion, much progress has been made with scientific machine learning approaches for solving closure problems, but many challenges remain. In particular, the generalizability and interpretability of learned models is a major issue that needs to be addressed further.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Critically assessing sodium-ion technology roadmaps and scenarios for techno-economic competitiveness against lithium-ion batteries

Sodium-ion batteries have garnered notable attention as a potentially low-cost alternative to lithium-ion batteries, which have experienced supply shortages and price volatility for key minerals. Here we assess their techno-economic competitiveness against incumbent lithium-ion batteries using a modelling framework incorporating componential learning curves constrained by minerals prices and engineering design floors. We compare projected sodium-ion and lithium-ion price trends across over 6,000 scenarios while varying Na-ion technology development roadmaps, supply chain scenarios, market penetration and learning rates. Assuming that substantial progress can be made along technology roadmaps via targeted research and development, we identify several sodium-ion pathways that might reach cost-competitiveness with low-cost lithium-ion variants in the 2030s. In addition, we show that timelines are highly sensitive to movements in critical minerals supply chains—namely that of lithium, graphite and nickel. Our modelled outcomes suggest that being price advantageous against low-cost lithium-ion variants in the near term is challenging and increasing sodium-ion energy densities to decrease materials intensity is among the most impactful ways to improve competitiveness.

25 ENERGY STORAGE↗
DOE OSTI2025

Improving Bond Dissociations of Reactive Machine Learning Potentials through Physics-Constrained Data Augmentation

In the field of computational chemistry, predicting bond dissociation energies (BDEs) presents well-known challenges, particularly due to the multireference character of reactive systems. Many chemical reactions involve configurations where single-reference methods fall short, as the electronic structure can significantly change during bond breaking. As generating training data for partially broken bonds is a challenging task, even state-of-the-art reactive machine learning interatomic potentials (MLIPs) often fail to predict reliable BDEs and smooth dissociation curves. By contrast, simple and inexpensive physics-based models, such as the well-established Morse potential, do not suffer from any such limitations. This work leverages the Morse potential to improve reactive MLIPs by augmenting the training data set with inexpensive Morse data along the dissociation pathways. Further, this physics-constrained data augmentation (PCDA) approach results in MLIPs with smooth bond dissociation curves as well as near coupled-cluster level BDEs, all without requiring any expensive multireference quantum mechanical calculations. A case study for methane combustion demonstrates how the PCDA approach can improve an existing reactive MLIP, namely, ANI-1xnr. In conclusion, not only are the BDEs and bond dissociation curves for all radicals and molecules significantly improved compared to ANI-1xnr but the PCDA-trained MLIP retains the reliability of ANI-1xnr when performing reactive molecular dynamics simulations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Optimal Control of Differentially Private EV Charging: A Scalable Learning Approach Under Uncertainty

Internet of Things (IoT)-enabled electric vehicles (IoEVs) enable intelligent charging coordination that accounts for grid congestion. However, increased data exchange raises privacy concerns, as charging patterns can reveal sensitive driver behavior to grid operators. Here, we propose a differentially private (DP) EV charging framework that enables coordinated control while protecting driver data with theoretical privacy guarantees. Nevertheless, integrating DP inevitably introduces uncertainty into the control strategy for EVs, which can lead to infeasible solutions. To tackle this challenge, we develop a feasible and scalable control algorithm based on constrained reinforcement learning (CRL) and convex hulls. While our framework is designed to handle the uncertainty introduced by DP, it is general and also applicable to other sources of uncertainty in EV charging, such as the stochastic nature of driver behavior and renewable variability. This ensures feasible and privacy-preserving coordination of EV charging at scale. Our method constructs convex hulls within the action space to guarantee feasibility under stochastic constraints and incorporates constraint reduction techniques to improve scalability. Case studies based on IEEE benchmark systems demonstrate that the proposed approach effectively balances feasibility under uncertainty, scalability, and privacy in large-scale EV charging control.

Engineering - Power transmission and distribution↗
DOE OSTI2026

Safe Deep Reinforcement Learning for Robust Frequency and Voltage-Constrained Networked Microgrid Restoration

Here, this paper proposes a safe soft actor-critic reinforcement learning (RL) algorithm–based controller for networked microgrid restoration. It formulates the post black-start start as a finite-horizon constrained Markov decision process. The RL agent co-optimizes real and reactive power set-points for both grid-forming and grid-following inverters under explicit voltage and frequency constraints, while enforcing proper power sharing via the Mean Active Power Sharing Index (MPSI) and Mean Reactive Power Sharing Index (MQSI). Numerical results obtained on the IEEE 123-bus distribution system show that the proposed method achieves a mean voltage build-up time of 0.01 s without breaching the 5% sharing-violation budget under various load scenarios, considering MPSI and MQSI indices. These findings demonstrate that the proposed method yields fast and safe black-start schedules without resorting to heuristic penalties.

Selim, Alaa [Dartmouth College, Hanover, NH (Unite↗
DOE OSTI2024

Constraining Galaxy-Halo connection using machine learning

We investigate the potential of machine learning (ML) methods to model small-scale galaxy clustering for constraining Halo Occupation Distribution (HOD) parameters. Our analysis reveals that while many ML algorithms report good statistical fits, they often yield likelihood contours that are significantly biased in both mean values and variances relative to the true model parameters. This highlights the importance of careful data processing and algorithm selection in ML applications for galaxy clustering, as even seemingly robust methods can lead to biased results if not applied correctly. ML tools offer a promising approach to exploring the HOD parameter space with significantly reduced computational costs compared to traditional brute-force methods if their robustness is established. Using our ANN-based pipeline, we successfully recreate some standard results from recent literature. Properly restricting the HOD parameter space, transforming the training data, and carefully selecting ML algorithms are essential for achieving unbiased and robust predictions. Among the methods tested, artificial neural networks (ANNs) outperform random forests (RF) and ridge regression in predicting clustering statistics, when the HOD prior space is appropriately restricted. We demonstrate these findings using the projected two-point correlation function (w p (r p )), angular multipoles of the correlation function (ξ ℓ (r)), and the void probability function (VPF) of Luminous Red Galaxies from Dark Energy Spectroscopic Instrument mocks. Our results show that while combining w p (r p ) and VPF improves parameter constraints, adding the multipoles ξ 0 , ξ 2 , and ξ 4 to w p (r p ) does not significantly improve the constraints.

cosmology↗
DOE OSTI2024

Reinforcement Learning for Distance Maximization in Energy-Constrained Robots

Our goal is to teach a robot to walk in an energy efficient way. Inspired by nature [1], we create a reinforcement learning method that balances distance traveled and energy consumption, which we call “utility.” Further, each step is symmetric to ensure equal strides while walking straight. We achieve our goal by rewarding decisions that lead to the best utility over several training iterations.

Pereira, Luiz Manella↗