Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative 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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

DuraMAT: Building a Consortium to Accelerate the Photovoltaic Module Reliability Learning Cycle

Durable and reliable photovoltaic (PV) modules are critical to enabling an efficient transition to sustainable energy generation. The rate at which new module designs and materials are developed and deployed currently outpaces the rate at which we can identify failure mechanisms and understand degradation rates. Increasing the service life of PV modules, and our ability to predict performance over time, requires more durable materials and designs, better durability testing, more extensive material characterization, robust modeling, and methods to cross-examine historical performance data to extract meaningful results. This is a multidisciplinary challenge that requires expertise from a broad range of fields and, therefore, benefits significantly from a collaborative approach. In this Perspective, we outline the approach taken by the Durable Module Materials Consortium (DuraMAT), present a few case studies where our approach was successful, and provide an outlook on where this approach might be applied as the PV technology landscape continues to rapidly evolve. Published by the American Physical Society 2024

14 SOLAR ENERGY↗
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↗
DOE OSTI2026

A human-in-the-loop explanation framework for morphologically transparent AI predictions from whole-slide images

Deep learning models enable the prediction of clinical endpoints from whole-slide images (WSIs), but many such models function as “black boxes”, lacking transparency about whether and which histomorphological patterns drive their predictions, hindering interpretability and clinical adoption. Here we propose a human-in-the-loop explanation framework, MorphoXAI, which provides both local and global interpretability for deep learning models by incorporating human-expert interpretations. At the global level, it reveals the histomorphological patterns on which the model consistently relies to distinguish between classes of WSIs, as well as the patterns associated with confusion between classes. At the local level, it indicates which of these patterns are used in the prediction of an individual WSI and which regions within the slide correspond to such patterns. We validated our method across multiple deep learning–based WSI analysis tasks spanning different tissue types. The results show that our framework generates explanations that accurately reflect the histomorphology underlying the model’s predictions at both global and local levels. For interpretability and clinical utility in diagnostic contexts, human evaluation results showed that our explanations were easy to interpret, rich in diagnostic features, and directly helpful for diagnostic decision-making, thereby enhancing pathologist-AI collaboration. Our work highlights that unifying global and local explanations and grounding them in expert-interpreted morphology enhances the interpretability and verifiability of deep learning models, thereby facilitating the transparent deployment of such models in clinical practice.

Lou, Peiliang↗
DOE OSTI2024

RGM: Random Geological Model Generation Package

This Fortran code is to accompany a manuscript to be submitted to Computers & Geosciences, a high-impact, peer-reviewed journal in computer methods for geosciences research. This Fortran code focuses on generation of synthetic geological models using a multi-randomization strategy. Generating high-fidelity synthetic geological models, including realistic seismic reflector migration images, faults, salt bodies, and relative geological time images, is the key for many supervised machine learning methods that aim to delineate faults and other geological properties of interest from seismic migration images. Our package contains two major functionalities: generating 2D synthetic random geological models and generating 3D synthetic random geological models. In each step of the generation process, we set random values for key properties of a geological model to improve the fidelity of the resulting geological model. The package also includes example codes on how to use the random geological model generation subroutines. We name this package RGM – Random Geological Model generation package.

Gao, Kai↗
DOE OSTI2025

Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost

Machine-learned interatomic potentials (MLIPs) are revolutionizing computational materials science and chemistry by offering an efficient alternative to ab initio molecular dynamics (MD) simulations. However, fitting high-quality MLIPs remains a challenging, time-consuming, and computationally intensive task where numerous trade-offs have to be considered, e.g., How much and what kind of atomic configurations should be included in the training set? Which level of ab initio convergence should be used to generate the training set? Which loss function should be used for fitting the MLIP? Which machine learning architecture should be used to train the MLIP? The answers to these questions significantly impact both the computational cost of MLIP training and the accuracy and computational cost of subsequent MLIP MD simulations. In this study, we use a configurationally diverse beryllium dataset and quadratic spectral neighbor analysis potential. We demonstrate that joint optimization of energy versus force weights, training set selection strategies, and convergence settings of the ab initio reference simulations, as well as model complexity can lead to a significant reduction in the overall computational cost associated with training and evaluating MLIPs. This opens the door to computationally efficient generation of high-quality MLIPs for a range of applications which demand different accuracy versus training and evaluation cost trade-offs.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2024

Integrating an Ensemble Reward System into an Off-Policy Reinforcement Learning Algorithm for the Economic Dispatch of Small Modular Reactor-Based Energy Systems

Nuclear Integrated Energy Systems (NIES) have emerged as a comprehensive solution for navigating the changing energy landscape. They combine nuclear power plants with renewable energy sources, storage systems, and smart grid technologies to optimize energy production, distribution, and consumption across sectors, improving efficiency, reliability, and sustainability while addressing challenges associated with variability. The integration of Small Modular Reactors (SMRs) in NIES offers significant benefits over traditional nuclear facilities, although transferring involves overcoming legal and operational barriers, particularly in economic dispatch. This study proposes a novel off-policy Reinforcement Learning (RL) approach with an ensemble reward system to optimize economic dispatch for nuclear-powered generation companies equipped with an SMR, demonstrating superior accuracy and efficiency when compared to conventional methods and emphasizing RL’s potential to improve NIES profitability and sustainability. Finally, the research attempts to demonstrate the viability of implementing the proposed integrated RL approach in spot energy markets to maximize profits for nuclear-driven generation companies, establishing NIES’ profitability over competitors that rely on fossil fuel-based generation units to meet baseload requirements.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
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 OSTI2024

Machine learning-guided design of direct methanol fuel cells with a platinum group metal-free cathode

Direct methanol fuel cells (DMFCs) offer a promising solution for clean electricity generation, particularly in small electronics and remote auxiliary power units. However, optimizing their efficiency and performance is challenging due to the complex interactions between various factors. Here, we present a novel approach that integrates experiments with machine learning to model and predict the performance of these fuel cells using atomically dispersed platinum group metal (PGM)-free catalysts at the cathode. Further, our machine learning models, trained on diverse input parameters, allow for the comprehensive optimization of DMFC performance prior to fabrication and testing. Through extensive experimental validation, we demonstrate that this data-driven approach accurately predicts key performance metrics, such as maximum power output and polarization curves. By combining our models with interpretable game-theory methods, we provide deep insights into the factors governing fuel cell performance, ultimately paving the way for the design of scalable and efficient DMFC technologies.

25 ENERGY STORAGE↗
DOE OSTI2025

Moltensaltpropnet

MoltenSaltPropnet is a physics-informed machine learning framework that aims to predict the thermophysical properties of molten fluoride and chloride salt mixtures, which are crucial for the design and safety of Generation IV molten salt reactors. The code processes data from the Molten-Salt Thermal Properties Database (MSTDB-TP) and the Janz compendium, converting critically evaluated correlations into fast, differentiable surrogate models for density, viscosity, thermal conductivity, and heat capacity across 448 distinct salt systems. The implementation consists of several key components: 1. Data Curation: The code parses and cleans the raw data, normalizing elemental mole fractions and extracting relevant regression coefficients for various thermophysical properties. 2. Feature Engineering: It generates fixed-length numerical descriptors that encapsulate the composition and temperature, incorporating polynomial interaction terms and dimensionality-reduction techniques to optimize model performance. 3. Coefficient Learning: Four different machine learning architectures are employed: a deep residual network (ResNet), a Kolmogorov–Arnold network (KAN), a sparsity-inducing neural network (SNN), and classical regression models. Each model learns to predict coefficients that define the temperature-dependent correlations for the thermophysical properties. 4. Property Reconstruction: The predicted coefficients are used to compute temperature-dependent property values, ensuring positivity and monotonic trends through a composite loss function that enforces physical constraints. 5. User Interface: An open-source web application enables users to filter the database, train task-specific models, and visualize the results, allowing for rapid exploration of candidate salt mixtures. MoltenSaltPropnet bridges the gap between limited experimental data and high-fidelity reactor simulations, providing a powerful tool for researchers in the field of molten salt reactors and advanced nuclear energy systems.

Retamales, Mauricio Eduardo Tano [Idaho National L↗
DOE OSTI2024

Improving Low‐Cloud Fraction Prediction Through Machine Learning

Abstract In this study, we evaluated the performance of machine learning (ML) models (XGBoost) in predicting low‐cloud fraction (LCF), compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. ML models show a substantial enhancement in predicting LCF regarding root mean squared errors and correlation coefficients. The good performance is consistent across the full spectrums of atmospheric stability and large‐scale vertical velocity. Employing an explainable ML approach, we revealed the importance of including the amount of available moisture in ML models for representing spatiotemporal variations in LCF in the midlatitudes. Also, ML models demonstrated marked improvement in capturing the LCF variations during the stratocumulus‐to‐cumulus transition (SCT). This study suggests ML models' great potential to address the longstanding issues of “too few” low clouds and “too rapid” SCT in global climate models.

Geology↗
DOE OSTI2026

Finite-element-based simulations of electrodes for CO 2 cascade reduction reactions

The multielectron reduction of CO 2 to liquid fuels could be a path to scalable energy storage, but reaching this goal requires major advances in catalysis and systems engineering. Cascade catalysis, which couples sequential reactions without isolating intermediates, has emerged as a promising route to enhance selectivity and efficiency in CO 2 reduction (CO 2 R). In this review, we examine how finite-element-based simulations of continuum model [finite element method (FEM)] approaches are being used to analyze and guide CO 2 R cascade systems. We first outline the fundamentals of cascade catalysis and recent advances in catalytic materials (metallic, molecular, and hybrid architectures). We then focus on FEM developments at the electrode and device scales, emphasizing how these models capture transport phenomena, local microenvironments, and geometry-dependent effects. To clarify design principles, we present case studies of cascade electrodes organized in systems without and with integrated semiconductors. We further emphasize the integration of FEM with multiscale frameworks (density functional theory, molecular dynamics, kinetic Monte Carlo) and its role in bridging atomic-level insights with device-level performance. Finally, we identify current limitations and future prospects, including improved boundary conditions, coupling with operando experiments, and machine learning-accelerated model development. Together, these insights provide design principles for next-generation CO 2 R cascade systems for efficient solar fuel production.

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

WaveDenoiser

We developed a robust deep learning model to effectively reduce background noise in the time domain from seismic waveforms. The deep learning model processes a 57-second three-component seismogram to predict and generate a denoised seismogram. The training was conducted using the benchmark STEAD dataset, which comprises globally distributed earthquake signals recorded at local distances ranging from 0 to 350 kilometers.

Chai, Chengping [Oak Ridge National Laboratory (OR↗
DOE OSTI2025

Decayheatml

This code is designed to predict and analyze the decay heat generated in molten salt reactors (MSRs) using a hybrid approach that combines machine learning and segmented polynomial fitting. The accurate prediction of decay heat is essential for reactor safety and the optimization of spent fuel storage. The code operates through several key components: 1) Data Architecture: It incorporates a modular data architecture that handles various MSR-specific operational parameters such as power density, humidity content, and air ingress. These parameters are sampled using Sobol sequences to ensure comprehensive coverage of operational uncertainties. 2) Machine Learning Framework: The code employs a diverse set of machine learning models, including polynomial regression, decision trees, random forests, gradient boosting, support vector regression, k-nearest neighbors, multi-layer perceptrons, and symbolic regression. These models are trained to predict decay heat over a wide temporal range, from immediate shutdown up to 10,000 years. 3) Region-Optimized Training: The temporal domain is divided into multiple regions, each modeled separately to capture distinct decay heat characteristics across different time scales. This approach significantly improves the accuracy and interpretability of predictions. 4) Segmented Polynomial Interpretation (SPI): The SPI method translates machine learning predictions into piecewise polynomial equations. These equations are physically interpretable and can be directly integrated into existing engineering workflows and safety analyses. 5) Front-End Interfaces: The code includes both a Jupyter notebook interface for research development and a Streamlit web application for operational deployment. These interfaces allow users to interactively explore decay heat predictions, adjust operational parameters, and visualize results in real-time. 6) Applications: The framework supports various applications, including safety system validation and spent fuel container optimization. It enables real-time evaluation of worst-case decay heat scenarios, informing the design of passive safety systems and optimizing container designs for long-term storage. Overall, this code provides a robust, accurate, and user-friendly tool for predicting decay heat in MSRs, enhancing reactor safety, and optimizing spent fuel management.

Retamales, Mauricio Eduardo Tano [Idaho National L↗
DOE OSTI2025

Rapid Flux Phenotyping to Accelerate Metabolic Engineering of Cyanobacteria

This project established a rapid flux phenotyping platform to accelerate metabolic engineering of cyanobacterial hosts. As proof of principle, we applied this platform to optimize cyanobacterial production of isobutyraldehyde and ethylene in Synechococcus PCC 7942, as well as lysine and fatty acids in the fast-growing strain S ynechococcus PCC 7002. By matching the throughput of strain characterization to the rate of strain generation, this research provided the foundation for a rational “design-build-test-learn” cycle for metabolic engineering of cyanobacteria and other bioenergy-relevant microbes.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Livewire: Automatic Annotations

Diogenes processes datasets to provide data quality metrics for the Livewire platform and creates standardized data dictionaries from data annotations. Diogenes needs data annotations that clearly outline thenformat and organization of the data. It also relies on the type, class, and unit of each data piece for comprehensive analysis, which it cannot determine independently. The Annotation Tool significantly reduces the time needed to create annotations for Diogenes by generating data annotations with the correct formatting and content. It also employs machine learning and hard-coded models to automatically annotate data class, quality type, and data units.

33 - ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2026

A Measurement of the Pion-Energy Dependence of Muon Neutrino Charged-Current Scattering to Final States With One Charged Pion in NOvA

The study of neutrino oscillations is a main priority for particle physics as the most immediately tractable lever on physics beyond the Standard Model. In particular, more insight into violation of the combined symmetry of charge-conjugation plus parity could yield clues to the origin of matter-antimatter asymmetry, and in some theoretical frameworks the neutrino mass could give insights into dark matter. NOvA is a long-baseline accelerator neutrino experiment with both a near and far detector that seeks to measure several of the parameters of the neutrino mixing matrix, as well as carry out a broad program of additional physics. NOvA has innovated and developed a variety of techniques in the space of neutrino physics, including expanding the use of machine learning techniques in reconstruction. NOvA has also set the stage for the next generation US-based long baseline experiment, DUNE. This dissertation details the creation of a new neutrino interaction vertex reconstruction package for NOvA, which offers enormous improvements in accuracy above the previous vertexer it replaces. This is accomplished using a Convolutional Visual Network trained on large datasets of simulated events. The vertexer is validated thoroughly against data. This dissertation also presents a cross-section measurement for $\nu_\mu + N \rightarrow \mu^- + 1\pi^\pm + X$ (where X does not include additional charged pions) binned in pion kinetic energy, a challenging measurement in general and for NOvA in particular. Measurements like this provide crucial inputs for neutrino interaction models utilized by neutrino oscillation experiments. This measurement in particular is important to the energy ranges relevant for DUNE in a band not well-covered by any other experiment.

Ewart, Erin [Indiana U., Bloomington (main)]↗
DOE OSTI2025

Point cloud-based diffusion models for the Electron-Ion Collider

At high-energy collider experiments, generative models can be used for a wide range of tasks, including fast detector simulations, unfolding, searches of physics beyond the Standard Model, and inference tasks. In particular, it has been demonstrated that score-based diffusion models can generate high-fidelity and accurate samples of jets or collider events. This work expands on previous generative models in three distinct ways. First, our model is trained to generate entire collider events, including all particle species with complete kinematic information. We quantify how well the model learns event-wide constraints such as the conservation of momentum and discrete quantum numbers. We focus on the events at the future Electron-Ion Collider, but we expect that our results can be extended to proton-proton and heavy-ion collisions. Second, previous generative models often relied on image-based techniques. The sparsity of the data can negatively affect the fidelity and sampling time of the model. We address these issues using point clouds and a novel architecture combining edge creation with transformer modules called Point Edge Transformers. Third, we adapt the foundation model OmniLearn, to generate full collider events. This approach may indicate a transition toward adapting and fine-tuning foundation models for downstream tasks instead of training new models from scratch.

Araz, Jack Y. [Stony Brook Univ., NY (United State↗