SEARCH · Engineering Papers

Results for “Learning Framework”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,099 records · Page 61

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Exploring the energy landscape of RBMs: reciprocal space insights into bosons, hierarchical learning and symmetry breaking

Deep generative models have become ubiquitous due to their ability to learn and sample from complex distributions. Despite the proliferation of various frameworks, the relationships among these models remain largely unexplored, a gap that hinders the development of a unified theory of AI learning. In this work, we address two central challenges: clarifying the connections between different deep generative models and deepening our understanding of their learning mechanisms. We focus on Restricted Boltzmann Machines (RBMs), a class of generative models known for their universal approximation capabilities for discrete distributions. By introducing a reciprocal space formulation for RBMs, we reveal a connection between these models, diffusion processes, and systems of coupled bosons. Our analysis shows that at initialization, the RBM operates at a saddle point, where the local curvature is determined by the singular values of the weight matrix, whose distribution follows the Marc̆enko-Pastur law and exhibits rotational symmetry. During training, this rotational symmetry is broken due to hierarchical learning, where different degrees of freedom progressively capture features at multiple levels of abstraction. This leads to a symmetry breaking in the energy landscape, reminiscent of Landau’s theory. This symmetry breaking in the energy landscape is characterized by the singular values and the weight matrix eigenvector matrix. We derive the corresponding free energy in a mean-field approximation. We show that in the limit of infinite size RBM, the reciprocal variables are Gaussian distributed. Our findings indicate that in this regime, there will be some modes for which the diffusion process will not converge to the Boltzmann distribution. To illustrate our results, we trained replicas of RBMs with different hidden layer sizes using the MNIST dataset. Our findings not only bridge the gap between disparate generative frameworks but also shed light on the fundamental processes underpinning learning in deep generative models.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Developing a simulator-based satellite dataset for using machine learning techniques to derive aerosol-cloud-precipitation interactions in models and observations in a consistent framework

Aerosol-cloud-precipitation interactions (ACPI) remain a major uncertainty in understanding the Earth’s radiation budget and water cycle (including extremes). After decades of active research, various observationally based metrics have been developed to constrain ACPI in Earth System Models (ESMs), but direct comparison of model and data estimates can confound scientific understanding because limitations and uncertainties in sampling and retrieval procedures may combine with model deficiencies in process representations of ACPI to obstruct understanding. Furthermore, conventional ACPI metrics often vary from one regime to another, and the ACPI process representation in ESMs is also typically derived based on only a limited area/regime (even though the parameterization applies globally). To bridge the gap between models and data and to correctly describe ACPI in all regimes, we propose to construct a new CALIPSO-CloudSat merged dataset that is produced by the same algorithms used in satellite simulators in ESMs, and to use machine learning techniques to derive new ACPI metrics that can be accurately estimated by satellites and can provide meaningful constraints on cloud microphysical process representations in ESMs. The dataset will include measured and retrieved variables for aerosol, cloud, and precipitation from CALIPSO and CloudSat, and environmental variables from meteorological reanalysis. The data will be used to train a neural network to construct the ACPI metrics as a function of environmental conditions. The new ACPI formula will be used to constrain the ACPI in the Energy Exascale Earth System Model (E3SM), and to augment/reformulate the ACPI process representation in the E3SM to improve the simulation of the evolution of the atmosphere under different environmental conditions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

A Data Library of Liquid Clouds Modelled With a Large Eddy Simulation Framework

We describe a library of atmospheric large eddy simulations (LES) of liquid-phase boundary layer clouds constructed to enable aerosol–cloud–turbulence interaction studies, support parameterization evaluation and development, and provide training data for machine learning applications. The simulations use a modern LES framework designed for high numerical accuracy, coupled to a detailed spectral bin microphysical scheme. Case studies are configured to represent observed conditions in four key global cloud regions—the Northeastern Atlantic, Northeastern Pacific, Continental United States and Southern Ocean—following a semi-idealised approach. The library also includes aerosol concentration halving and doubling experiments to expose the sensitivities of the case studies to aerosol perturbations. Simulation results are compared to observations on a case-by-case basis, then the library's coverage is evaluated in terms of spreads in meteorological factors and atmospheric boundary layer attributes.

aerosol↗

NASA NTRSDate not supplied

A Framework for Software Health Management Using Bayesian Statistics

Software Health Management (SWHM) must make sure that the software always remains in safe and healthy regions of the state space. Boundaries between healthy and unhealthy regions are important for the detection of violations and health management.In this position paper, we present a framework, which employs techniques from Bayesian statistical modeling and active learning to efficiently characterize health boundaries in high-dimensional spaces. We will discuss, how this framework supports SWHM during design time and during operation of learning/adapting software systems

software health management↗

DOE OSTI2020

A physics-informed operator regression framework for extracting data-driven continuum models

The application of deep learning toward discovery of data-driven models requires careful application of inductive biases to obtain a description of physics which is both accurate and robust. We present here a framework for discovering continuum models from high fidelity molecular simulation data. Our approach applies a neural network parameterization of governing physics in modal space, allowing a characterization of differential operators while providing structure which may be used to impose biases related to symmetry, isotropy, and conservation form. Here, we demonstrate the effectiveness of our framework for a variety of physics, including local and nonlocal diffusion processes and single and multiphase flows. For the flow physics we demonstrate this approach leads to a learned operator that generalizes to system characteristics not included in the training sets, such as variable particle sizes, densities, and concentration.

42 ENGINEERING↗

DOE OSTI2020

The Nature and State of Groundwater Contamination at the Nevada National Security Site: What Have We Learned from Decades of Groundwater Analysis? - 20337

The regulatory framework for remediating radionuclide contamination from underground nuclear testing at the Nevada National Security Site (NNSS) is based on a combination of characterization and modeling studies, monitoring, and institutional controls [1]. Currently, tritium is the largest contributor (∼90%) to the estimated 44.6 million-curie radionuclide inventory resulting from underground testing [2]. Because of its short half-life (12.32 years), its relative contribution reduces below 10% of the total radiologic inventory over the next 120 years as a result of radioactive decay. Although tritium levels are observed well above the Safe Drinking Water Act (SDWA) maximum contaminant levels (MCLs) in groundwater, other radionuclides are well below their MCLs except within the nuclear test near-field (nuclear test cavity and chimney) environment. In fact, most device-derived radionuclides are below their MCL in groundwater even in samples collected from this near-field environment. The distribution of radionuclides following the nuclear detonation greatly influences the availability of potential contaminants for groundwater transport. Tritium is initially distributed in the gas phase, later as tritiated water in steam, and finally as liquid water, and is available to groundwater transport away from the near-field environment. Other radionuclides that are mobile in groundwater are {sup 14}C, {sup 36}Cl, {sup 99}Tc, and {sup 129}I though their radiologic inventory is small when compared to tritium. Many radionuclides (e.g. U, Pu, Am) are incorporated to a significant extent into the melt glass at the bottom of the cavity and are accessible to groundwater primarily through the slow process of glass dissolution. These radionuclides are also adsorbed to the surfaces of the crushed rock within the cavity and chimney which limits their migration in groundwater. Although colloid facilitated transport of radionuclides at the NNSS has been observed [3], radionuclide concentrations decrease with time and migration distances due to desorption and colloid filtration processes. Current studies indicate that radionuclides associated with colloids are unlikely to migrate downgradient from NNSS underground nuclear tests at concentrations above the SDWA MCL [4][5]. The results of over 50 years of sampling, along with an understanding of these post detonation processes, indicate that tritium is the only contaminant of concern downgradient of testing and that even tritium will not exceed its MCL in groundwater after ∼120 years. Although other longer-lived radionuclides may continue to be released slowly from the near-field environment they will likely never reach levels exceeding their MCLs in groundwater downgradient of the NNSS. Groundwater monitoring will continue to verify these observations. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2025

Optimal Transport as a Tool for Scientific Discovery in Radiation Biology

This report summarizes findings from research conducted for the “Exploration of the Poten tial for Artificial Intelligence and Machine Learning to Advance Low-Dose Radiation Biology Re search” (RadBio-AI) program, supported by the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, under Awards KP1601011/FWP CC121 and KP1601017/FWP CC121. The research reported here was undertaken in an effort to assess the potential of optimal measure transport methods as components within the larger scope of a com putational framework envisioned to support research in the radiation biology domain. Within this effort, our interest centered on enabling a unified generic framework where probabilistic modeling, inference, and statistical learning can be carried out for a wide range of data distributions. As described next in Section 1 (and in more detail in our original publication), optimal measure transport offers the possibility of such unified approach.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2020

Prognostics for Systems Health Management - Model and Hybrid Based Approaches. Where are We Heading?

To facilitate and solve the prediction problem, awareness of the current state and health of the system is key, since it is necessary to perform condition-based system health predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditional. In case of next generation electric aircrafts, computing remaining flying time is safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. In order to tackle and solve the prediction problem, it is essential to have awareness of the current health state of the system, especially since it is necessary to perform condition-based predictions. To be able to predict the future state of the system, it is also required to possess knowledge of the current and future operational conditions and flight profiles for accurate estimation of end-of-discharge (EOD) for the batteries. Similar framework can be implemented to other complex systems and subsystems. Our research approach is to develop a system level health monitoring safety indicator which runs estimation and prediction algorithms to estimate remaining useful life predictions at system, subsystem swell as component levels. Given models of the current and future system behavior, a general approach of model-based prognostics is discussed as a solution to the prediction problem and further for decision making. Data driven prognostics approaches have been equally used with good results in the past, where respective approaches have their own challenges to tackle. This limits their applicability to complex real-world domains: (a) high complexity or incompleteness of physics-based models and (b) limited representativeness of the training dataset for data-driven models. With the advent of internet of things for data collection and increased use of ML algorithms, hybrid approaches are the next avenue to reduce the challenges and achieve better results. An hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, we use physics-based performance models to infer unobservable model parameters related to the system's components health solving a calibration problem.

Prognostics↗

DOE OSTI2020

C-SAW: a framework for graph sampling and random walk on GPUs

Many applications require to learn, mine, analyze and visualize large-scale graphs. These graphs are often too large to be addressed efficiently using conventional graph processing technologies. Fortunately, recent research efforts find out graph sampling and random walk, which significantly reduce the size of original graphs, can benefit the tasks of learning, mining, analyzing and visualizing large graphs by capturing the desirable graph properties. This paper introduces C-SAW, the first framework that accelerates Sampling and Random Walk framework on GPUs. Particularly, C-SAW makes three contributions: First, our framework provides a generic API which allows users to implement a wide range of sampling and random walk algorithms with ease. Second, offloading this framework on GPU, we introduce warp-centric parallel selection, and two novel optimizations for collision migration. Third, towards supporting graphs that exceed the GPU memory capacity, we introduce efficient data transfer optimizations for out-of-memory and multi-GPU sampling, such as workload-aware scheduling and batched multi-instance sampling. Taken together, our framework constantly outperforms the state of the art projects in addition to the capability of supporting a wide range of sampling and random walk algorithms.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Retrieve Methane from IR sounder measurements Using Machine Learning-Enhanced Physical Inversion

The sensitivity of IR sounder measurements to atmospheric CH 4 is often limited due to interferences from signals of other trace gases, insufficient thermal contrast, and cloud blockage. In order to resolve the geographical and vertical distribution of atmospheric CH 4 profiles, accurate scene-dependent a priori information is critically needed to support an optimal estimation method-based physical inversion scheme. Following the principles of indexing, representation, and retrieval, a spectral fingerprinting methodology is developed to address the needs for both accuracy and computational efficiency in sounder-based CH 4 retrieval. Within this framework, a clustering method based on machine learning is first employed to stratify and identify the a priori state within the pre-constructed database, using optimized spectral radiances as predictors. The corresponding radiative kernel is then used to establish the physical inversion scheme for finding the solution. High-quality data from CH 4 data assimilation systems like the Carbon-Tracker and the Copernicus Atmosphere Monitoring Service (CAMS) reanalysis, as well as the state-of-art sounder products are used to build the training database, including radiative kernels. We will demonstrate the results retrieved from CrIS observations and the associated validation work.

Wan Wu↗

DOE OSTI2024

Active learning for the design of polycrystalline textures using conditional normalizing flows

Generative modeling has opened new avenues for solving previously intractable materials design problems. However, these new opportunities are accompanied by a drastic increase in the required amount of training data. This is in stark juxtaposition to the high expense and difficulty in curating such large materials datasets. In this work, we propose a novel framework for integrating generative models within an active learning loop. Further, this enables the training of generative models with datasets significantly smaller than what has previously been demonstrated, providing a direct route for their application in data constrained environments. The functionality of this framework is then demonstrated by addressing the challenge of designing polycrystalline textures associated with target anisotropic mechanical properties. The developed protocol exhibited a cost reduction between 14 to 18 times over a randomly sampled experimental design.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗

DOE OSTI2026

A Decomposition-Based Learn-To-Optimize Approach with Feasibility Layer Assistance for Sub-Hourly Unit Commitment

Sub-hourly unit commitment (UC) with 15-min intervals is gaining significant attention as a way to respond rapidly to the fluctuations in electricity supply and demand introduced by renewable resources. However, the increased temporal resolution and complex inter-temporal dependencies pose substantial computational challenges for traditional optimization methods. To this end, this paper explores a decomposition-based learn-to-optimize approach. Building on recent advances in machine learning, our method revisits the long- overlooked Lagrangian relaxation framework, which is a classical decomposition technique that enables tractable subproblem solving. These smaller subproblems are inherently well-suited for machine learning, as their reduced dimensionality and structural regularity allow predictive models to efficiently learn and generalize solution patterns. We thus propose a generic predictive model, which embeds Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure, and integrate a rule-based feasibility layer to capture temporal dependencies, reduce training effort, and improve feasibility w.r.t. unit-level constraints. Our method has been validated on the IEEE 118-bus system, demonstrating promising performance in solving sub-hourly UC problems efficiently and feasibly.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2002

The Design of Collectives of Agents to Control Non-Markovian Systems

The 'Collective Intelligence' (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided 'world' utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional-'team games'. We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that 'learning' is a property only of high-enough dimensional systems.

Lawson, John W.↗

NASA NTRS2004

The Design of Collectives of Agents to Control Non-Markovian Systems

The Collective Intelligence (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided "world" utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional "team games". We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents ability to learn. The implication is that learning is a property only of high-enough dimensional systems.

Lawson, John W.↗

DOE OSTI2025

Python Library for Monte Carlo Simulations with Ab Initio and Machine-Learned Interatomic Potentials

There is a growing need in the simulation community for software that provides a transparent, reproducible, usable, and extensible (TRUE) Monte Carlo (MC) simulation framework employing energies from ab initio methods and machine-learning interatomic potentials (MLIPs). We introduce a Python library (ASE-MC) that adds Monte Carlo functionality to the Atomic Simulation Environment (ASE) package. Now, we can combine the powerful tools used to build systems and perform ab initio and MLIP in ASE with MC simulation algorithms to sample the configurational space with a concise Python script. After presenting the design philosophy, we demonstrate the flexibility of our approach using selected examples. These example simulations include liquid water described with a message-passing MLIP in the canonical and isothermal–isobaric ensembles, sampling the characteristic dihedral angle of biphenyl and comparing an MLIP to first-principles calculations, and a grand canonical Monte Carlo simulation of ammonia adsorption on Pt(111). These examples showcase the main features of the software, which include flexibility in the choice of ab initio or MLIP engine, ab initio or MLIP grand canonical MC with cavity bias insertions and deletions, the ability to add custom MC moves to the move set, and how users can condense complex MC workflows into a single Python script. Finally, this library serves as a framework for reproducible Monte Carlo simulations, facilitating easy reproduction of the work and application to new systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states

We report molecular-orbital-based machine learning (MOB-ML) provides a general framework for the prediction of accurate correlation energies at the cost of obtaining molecular orbitals. The application of Nesbet’s theorem makes it possible to recast a typical extrapolation task, training on correlation energies for small molecules and predicting correlation energies for large molecules, into an interpolation task based on the properties of orbital pairs. We demonstrate the importance of preserving physical constraints, including invariance conditions and size consistency, when generating the input for the machine learning model. Numerical improvements are demonstrated for different datasets covering total and relative energies for thermally accessible organic and transition-metal containing molecules, non-covalent interactions, and transition-state energies. MOB-ML requires training data from only 1% of the QM7b-T dataset (i.e., only 70 organic molecules with seven and fewer heavy atoms) to predict the total energy of the remaining 99% of this dataset with sub-kcal/mol accuracy. This MOB-ML model is significantly more accurate than other methods when transferred to a dataset comprising of 13 heavy atom molecules, exhibiting no loss of accuracy on a size intensive (i.e., per-electron) basis. It is shown that MOB-ML also works well for extrapolating to transition-state structures, predicting the barrier region for malonaldehyde intramolecular proton-transfer to within 0.35 kcal/mol when only trained on reactant/product-like structures. Finally, the use of the Gaussian process variance enables an active learning strategy for extending the MOB-ML model to new regions of chemical space with minimal effort. We demonstrate this active learning strategy by extending a QM7b-T model to describe non-covalent interactions in the protein backbone–backbone interaction dataset to an accuracy of 0.28 kcal/mol.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NASA NTRS2004

Perceptual learning through optimization of attentional weighting: human versus optimal Bayesian learner

Human performance in visual detection, discrimination, identification, and search tasks typically improves with practice. Psychophysical studies suggest that perceptual learning is mediated by an enhancement in the coding of the signal, and physiological studies suggest that it might be related to the plasticity in the weighting or selection of sensory units coding task relevant information (learning through attention optimization). We propose an experimental paradigm (optimal perceptual learning paradigm) to systematically study the dynamics of perceptual learning in humans by allowing comparisons to that of an optimal Bayesian algorithm and a number of suboptimal learning models. We measured improvement in human localization (eight-alternative forced-choice with feedback) performance of a target randomly sampled from four elongated Gaussian targets with different orientations and polarities and kept as a target for a block of four trials. The results suggest that the human perceptual learning can occur within a lapse of four trials (<1 min) but that human learning is slower and incomplete with respect to the optimal algorithm (23.3% reduction in human efficiency from the 1st-to-4th learning trials). The greatest improvement in human performance, occurring from the 1st-to-2nd learning trial, was also present in the optimal observer, and, thus reflects a property inherent to the visual task and not a property particular to the human perceptual learning mechanism. One notable source of human inefficiency is that, unlike the ideal observer, human learning relies more heavily on previous decisions than on the provided feedback, resulting in no human learning on trials following a previous incorrect localization decision. Finally, the proposed theory and paradigm provide a flexible framework for future studies to evaluate the optimality of human learning of other visual cues and/or sensory modalities.

Non-NASA Center↗