Search NASA⌕ Search

SEARCH · Search NASA

Results for “experimental 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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Impact of environmental backgrounds on atmospheric monitoring of nuclear explosions

Radionuclide monitoring for nuclear explosions includes measuring radioactive aerosol and noble gas concentrations in the atmosphere. The International Monitoring System (IMS) of the Comprehensive Nuclear Test Ban Treaty (CTBT) has made such measurements for decades, revealing much about how atmospheric radioactivity impacts the sensitivity of the network. For example, civilian emissions of radioiodine make a substantial regional impact, but a minor global impact, while civilian radioxenon emissions create major regional and complex global impacts. This example statement is strongly influenced by the minimum signal level anticipated to be interesting. The original design of the IMS anticipated relatively large signal levels, and the accomplished IMS network substantially meets or exceeds the sensitivity needed to detect those signal levels. Much lower signal levels can be motivated, which could require reconsideration of station sensitivity. Using measured and simulated background concentrations, various possible desired signal levels, and an innovative anomaly threshold, maps of sensitivity and a station ranking are developed for current and future stations. These provide a strong motivation for additional experimentation to learn about sources and the potential plusses of new technology.

Eslinger, Paul W.↗
DOE OSTI2022

Recent progress toward catalyst properties, performance, and prediction with data-driven methods

Herein, data-driven approaches are currently renovating the field of heterogenous catalysis and open a door to advance catalyst design. Their success depends heavily on the synergy among machine learning (ML), experimental data, and quantum mechanical (QM) calculations. In this brief survey of recent progress, we examine catalysis informatics in the context of (1) ML-aided catalyst characterizations, (2) knowledge extractions from experimental data, (3) predictions of catalytic properties and constructions of reaction networks, and (4) ML-enabled large-scale QM simulations. An outlook on the current challenges of this rapidly evolving field is also provided.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Autonomous and dynamic precursor selection for solid-state materials synthesis

Abstract Solid-state synthesis plays an important role in the development of new materials and technologies. While in situ characterization and ab-initio computations have advanced our understanding of materials synthesis, experiments targeting new compounds often still require many different precursors and conditions to be tested. Here we introduce an algorithm (ARROWS 3 ) designed to automate the selection of optimal precursors for solid-state materials synthesis. This algorithm actively learns from experimental outcomes to determine which precursors lead to unfavorable reactions that form highly stable intermediates, preventing the target material’s formation. Based on this information, ARROWS 3 proposes new experiments using precursors it predicts to avoid such intermediates, thereby retaining a larger thermodynamic driving force to form the target. We validate this approach on three experimental datasets, containing results from over 200 synthesis procedures. In comparison to black-box optimization, ARROWS 3 identifies effective precursor sets for each target while requiring substantially fewer experimental iterations. These findings highlight the importance of domain knowledge in optimization algorithms for materials synthesis, which are critical for the development of fully autonomous research platforms.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Using genetic algorithms to systematically improve the synthesis conditions of Al-PMOF

The synthesis of metal-organic frameworks (MOFs) is often complex and the desired structure is not always obtained. In this work, we report a methodology that uses a joint machine learning and experimental approach to optimize the synthesis conditions of Al-PMOF (Al 2 (OH) 2 TCPP) [H 2 TCPP = meso-tetra(4-carboxyphenyl)porphine], a promising material for carbon capture applications. Al-PMOF was previously synthesized using a hydrothermal reaction, which gave a low throughput yield due to its relatively long reaction time (16 hours). Here, we use a genetic algorithm to carry out a systematic search for the optimal synthesis conditions and a microwave-based high-throughput robotic platform for the syntheses. We show that, in just two generations, we could obtain excellent crystallinity and yield close to 80% in a much shorter reaction time (50 minutes). Moreover, by analyzing the failed and partially successful experiments, we could identify the most important experimental variables that determine the crystallinity and yield.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Combining the synergistic control capabilities of modeling and experiments: Illustration of finding a minimum-time quantum objective

A common way to manipulate a quantum system, for example spins or artificial atoms, is to use properly tailored control pulses. In order to accomplish quantum information tasks before coherence is lost, it is crucial to implement the control in the shortest possible time. Here we report the near time-optimal preparation of a Bell state with fidelity higher than 99% in an NMR experiment, which is feasible by combining the synergistic capabilities of modeling and experiments operating in tandem. In this work, the pulses preparing the Bell state are found by experiments that are recursively assisted with a gradient-based optimization algorithm working with a model. Thus, we exploit the interplay between model-based numerical optimal design and experimental-based learning control. Utilizing the balanced synergism between the dual approaches, as dictated by the case specific capabilities of each approach, should have broad applications for accelerating the search for optimal quantum controls.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Preemptive optimization of a clinical antibody for broad neutralization of SARS-CoV-2 variants and robustness against viral escape

Most previously authorized clinical antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have lost neutralizing activity to recent variants due to rapid viral evolution. To mitigate such escape, we preemptively enhance AZD3152, an antibody authorized for prophylaxis in immunocompromised individuals. Using deep mutational scanning (DMS) on the SARS-CoV-2 antigen, we identify AZD3152 vulnerabilities at antigen positions F456 and D420. Through two iterations of computational antibody design that integrates structure-based modeling, machine-learning, and experimental validation, we co-optimize AZD3152 against 24 contemporary and previous SARS-CoV-2 variants, as well as 20 potential future escape variants. Our top candidate, 3152-1142, restores full potency (100-fold improvement) against the more recently emerged XBB.1.5+F456L variant that escaped AZD3152, maintains potency against previous variants of concern, and shows no additional vulnerability as assessed by DMS. This preemptive mitigation demonstrates a generalizable approach for optimizing existing antibodies against potential future viral escape.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

AEOLUS: Advances in Experimental Design, Optimal Control, and Learning for Uncertain Complex Systems

The AEOLUS Center is dedicated to developing a unified optimization-under-uncertainty framework for (1) learning predictive models from data and (2) optimizing experiments, processes, and designs governed by these models, all driven by complex, uncertain energy systems. AEOLUS addressed the critical need for principled, rigorous, scalable, and structure-exploiting capabilities for exploring parameter and decision spaces of complex forward simulation models---the so-called outer loop. This report summarizes the work done under DE-SC0021077 on (1) nonlocal models for solidification problems, (2) a multifidelity method for a nonlocal diffusion model, and (3) multifidelity Monte Carlo methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Computational design of high entropy alloy coating for hydrogen turbine applications

This project aims to develop novel high entropy alloy (HEA)-based coatings to protect critical components in hydrogen-fueled turbine power system. The HEA-coatings will demonstrate superior performance in hydrogen combustion environment to commercial NiCoCrAlY coating in current natural gas turbine system. The HEA coating facilitates the formation of a protective scale of alpha-alumina to slow down the inward diffusion of oxidizing species and the outward diffusion of metal elements, and possesses ultrahigh corrosion and spallation resistance to prolong the service lifetime of critical components in hydrogen turbine power system. Aimed to accelerate the discovery of novel HEA coating compositions, high throughput computational modeling including CALPHAD and density functional theory and machine learning are performed to predict phase stability, oxygen permeability, oxidation rate constant, coefficient of thermal expansion, and mechanical properties. Based on the modeling and machine learning prediction, experimental validation is performed. Preliminary results will be presented and approaches to minimize oxidation will be discussed.

alloy design↗
DOE OSTI2024

Advances in Experimental Design, Optimal Control, and Learning for Uncertain Complex Systems (Final Report for AEOLUS)

The AEOLUS Center is dedicated to developing a unified optimization-under-uncertainty framework for: (1) learning predictive models from data; and (2) optimizing experiments, processes, and designs governed by these models, all driven by complex, uncertain energy systems. AEOLUS addresses the critical need for principled, rigorous, scalable, and structure-exploiting capabilities for exploring parameter and decision spaces of complex forward simulation models. This report summarizes the key highlights of our research during the period of performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Extending Power of Nature from Binary Problems to Real-Valued Graph Learning in Real World

Nature performs complex computations constantly at clearly lower cost and higher performance than digital computers. It is crucial to understand how to harness the unique computational power of nature in Machine Learning (ML). In the past decade, besides the development of Neural Networks (NNs), the community has also relentlessly explored nature-powered ML paradigms. Although most of them are still predominantly theoretical, a new practical paradigm enabled by the recent advent of CMOS-compatible room-temperature nature-based computers has emerged. By harnessing the nature's power of entropy increase, this paradigm can solve binary learning problems delivering immense speedup and energy savings compared with NNs, while maintaining comparable accuracy. Regrettably, its values to the real world are highly constrained by its binary nature. A clear pathway to its extension to real-valued problems remains elusive. This paper aims to unleash this pathway by proposing a novel end-to-end Nature-Powered Graph Learning (NP-GL) framework. Specifically, through a three-dimensional co-design, NP-GL can leverage the nature's power of entropy increase to efficiently solve real-valued graph learning problems. Experimental results across 4 real-world applications with 6 datasets demonstrate that NP-GL delivers, on average, 6970X speedup and 10^5x energy consumption reduction with comparable or even higher accuracy than Graph Neural Networks (GNNs).

artificial intelligence↗
DOE OSTI2025

Dial

A key step in almost all scientific endeavors is answering the question: Given this data I already collected, what new data do I expect will yield the most useful information toward my scientific objective? The area of (sequential) experimental design has long been investigating answers to this question, but in recent years techniques from the machine learning subfield of active learning are increasingly applied. Researchers need a simple software tool for active learning applied to experimental design that can easily integrate into their existing workflows. This computer code, Dial, provides a microservice in ORNL's INTERSECT ecosystem for active learning applied to experimental design. By being part of the INTERSECT ecosystem, Dial is simple to integrate into any INTERSECT-based workflow. Dial provides multiple backend options, where a backend is an implementation of a specific active learning method. Users can select the backend that performs best for their application. Developers can also add new backends as needed. At its core, Dial receives a set of pre-existing measurements and input parameter bounds and then recommends one or more new sets of parameters to measure. Dial also includes interfaces to other microservices in the INTERSECT ecosystem so that it can be incorporated into INTERSECT campaigns. Dial provides a simple, yet powerful interface to convert automated INTERSECT workflows into autonomous workflows that adapt based on the results that are obtained. A shared microservice for active learning prevents duplicated effort by each application team implementing its own adaptive design of experiments tool.

Drane, Lance [Oak Ridge National Laboratory (ORNL)↗
DOE OSTI2025

Designing reinforcement learning algorithms for building HVAC control: From experimental observation to simulation comparisons

Advanced supervisory-level control with reinforcement learning (RL) is regarded as a promising solution for HVAC systems to minimize energy consumption while maintaining thermal comfort and indoor air quality. However, most RL applications were conducted in the simulation environment rather than real-world HVAC systems. This paper developed a value-based RL controller termed Deep Q-Network (DQN) for a typical central HVAC system and evaluated its performance in a building test facility. By comparing DQN with a rule-based controller, the study not only demonstrated the cases where DQN could properly maintain indoor comfort but also discussed possible reasons why DQN failed in some other situations. Recognizing the limitations of value-based RL algorithms from the experimental tests, a simulation study was conducted to compare DQN with an alternative RL approach, an actor–critic algorithm termed Deep Deterministic Policy Gradient (DDPG). In scenarios with a relatively large action space, DDPG outperformed DQN by requiring fewer computational resources and achieving better thermal comfort, lower energy consumption, and more stable control actions. The findings suggest that the ability of DDPG to handle continuous control variables more effectively allows for faster convergence in training and more precise control in practice, which enhances the overall efficiency and reliability of the HVAC system.

Guo, Fangzhou↗