Next-generation machine-learning models for molecular dynamics of systems with charge
Explore the source record for details and available documents.
Goff, James Michael [Sandia National Laboratories ↗
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.
Learning from examples - Generation and evaluation of decision trees for software resource analysis
A general solution method for the automatic generation of decision (or classification) trees is investigated. The approach is to provide insights through in-depth empirical characterization and evaluation of decision trees for software resource data analysis. The trees identify classes of objects (software modules) that had high development effort. Sixteen software systems ranging from 3,000 to 112,000 source lines were selected for analysis from a NASA production environment. The collection and analysis of 74 attributes (or metrics), for over 4,700 objects, captured information about the development effort, faults, changes, design style, and implementation style. A total of 9,600 decision trees were automatically generated and evaluated. The trees correctly identified 79.3 percent of the software modules that had high development effort or faults, and the trees generated from the best parameter combinations correctly identified 88.4 percent of the modules on the average.
Selby, Richard W.↗
Learning turbulent flows with generative models for super resolution and sparse flow reconstruction
Neural operators are promising surrogates for dynamical systems but when trained with standard L 2 losses they tend to oversmooth fine-scale turbulent structures. Here, we show that combining operator learning with generative modeling overcomes this limitation. We consider three practical turbulent-flow challenges where conventional neural operators fail: spatio-temporal super-resolution, forecasting, and sparse flow reconstruction. For Schlieren jet super-resolution, an adversarially trained neural operator (adv-NO) reduces the energy-spectrum error by 15 × while preserving sharp gradients at neural operator-like inference cost. For 3D homogeneous isotropic turbulence, adv-NO trained on only 160 timesteps from a single trajectory forecasts accurately for five eddy-turnover times and offers 114 × wall-clock speed-up at inference than the baseline diffusion-based forecasters, enabling near-real-time rollouts. For reconstructing cylinder wake flows from highly sparse Particle Tracking Velocimetry-like inputs, a conditional generative model infers full 3D velocity and pressure fields with correct phase alignment and statistics. These advances enable accurate reconstruction and forecasting at low compute cost, bringing near-real-time analysis and control within reach in experimental and computational fluid mechanics.
Fluid dynamics↗
Reweighting configurations generated by transferable, machine learned models for protein sidechain backmapping
Multiscale modeling requires the linking of models at different levels of detail, with the goal of gaining accelerations from lower fidelity models while recovering fine details from higher resolution models. Communication across resolutions is particularly important in modeling soft matter, where tight couplings exist between molecular-level details and mesoscale structures. While multiscale modeling of biomolecules has become a critical component in exploring their structure and self-assembly, backmapping from coarse-grained to fine-grained, or atomistic, representations presents a challenge, despite recent advances through machine learning. A major hurdle, especially for strategies utilizing machine learning, is that backmappings can only approximately recover the atomistic ensemble of interest. We demonstrate conditions for which backmapped configurations may be reweighted to exactly recover the desired atomistic ensemble. By training separate decoding models for each sidechain type, we develop an algorithm based on normalizing flows and geometric algebra attention to autoregressively propose backmapped configurations for any protein sequence. Critical for reweighting with modern protein force fields, our trained models include all hydrogen atoms in the backmapping and make probabilities associated with atomistic configurations directly accessible. We also demonstrate, however, that reweighting is extremely challenging despite state-of-the-art performance on recently developed metrics and generation of configurations with low energies in atomistic protein force fields. Through detailed analysis of configurational weights, we show that machine-learned backmappings must not only generate configurations with reasonable energies, but also correctly assign relative probabilities under the generative model. These are broadly important considerations in generative modeling of atomistic molecular configurations.
Monroe, Jacob I. [Univ. of Arkansas, Fayetteville,↗
Large-Scale Alfvenic Impulses on the Sun: How They Are Generated and What We Learn From Them
NASA GSFC The Sun's atmosphere hosts a wide variety of magnetosonic disturbances. These wave modes are detected, almost exclusively, by examining images of the Sun's magnetic atmosphere and looking for propagating distortions. Although none of the Sun's plasma parameters are measured directly, we derive a great deal of information from these observations. In fact, by modeling these propagating disturbances, we may be able to derive the most accurate estimates plasma parameters. From observations absorption, refraction, reflection, and coupling of numerous wave modes, we advance our knowledge of the Sun's magnetic field, temperature, density, and current. The Sun's continuous oscillation, coronal mass ejections, flares, and other dynamic phenomena can produce wave disturbances which are observable from near-Earth space. Several of these disturbances have been traced from the inner corona out into the heliosphere. From the generation of these disturbances, we are able to learn about the phenomena which create them as well as the media through which they re-propagating. The presentation will include a discussion of the generation of Alfvenic disturbances on the Sun, ways we observe these disturbances, and how recent advances in modeling and analysis have brought us closer to determining solar in situ parameters.
Thompson, Barbara↗
Generative AI models for learning flow maps of stochastic dynamical systems in bounded domains
Simulating stochastic differential equations (SDEs) in bounded domains, presents significant computational challenges due to particle exit phenomena, which requires accurate modeling of interior stochastic dynamics and boundary interactions. Despite the success of machine learning-based methods in learning SDEs, existing learning methods are not applicable to SDEs in bounded domains because they cannot accurately capture the particle exit dynamics. We present a unified hybrid data-driven approach that combines a conditional diffusion model with an exit prediction neural network to capture both interior stochastic dynamics and boundary exit phenomena. Our ML model consists of two major components: a neural network that learns exit probabilities using binary cross-entropy loss with rigorous convergence guarantees, and a training-free diffusion model that generates state transitions for non-exiting particles using closed-form score functions. The two components are integrated through a probabilistic sampling algorithm that determines particle exit at each time step and generates appropriate state transitions. Here, the performance of the proposed approach is demonstrated via three test cases: a one-dimensional simplified problem for theoretical verification, a two-dimensional advection-diffusion problem in a bounded domain, and a three-dimensional problem of interest to magnetically confined fusion plasmas.
Bounded domains↗
Hierarchical screening for Li-based solid electrolytes using fast, interpretable machine-learned potentials
Li-based solid-state electrolyte materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. The prohibitive cost of high-throughput screening with DFT has lead to the development of surrogate models using geometric analysis, empirical potentials, and descriptors for ionic transport. Here, I will discuss a hierarchical screening approach for identifying promising materials using a combination of density functional theory, bond-valence methods, and machine learning potentials generated with the Ultra-Fast Force Fields (UF3) framework. We show how the inexpensive bond-valence method can be used to guide the generation of training samples for machine learning, in addition to filtering candidates. Finally, we apply the hierarchical workflow to screen for ionic conductivity across a database of Li-containing compounds.
Materials discovery↗
Hierarchical Screening for Li-Based Solid Electrolytes Using Fast, Interpretable Machine-Learned Potentials
Li-based solid-state electrolyte materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. The prohibitive cost of high-throughput screening with DFT has lead to the development of surrogate models using geometric analysis, empirical potentials, and descriptors for ionic transport. Here, I will discuss a hierarchical screening approach for identifying promising materials using a combination of density functional theory, bond-valence methods, and machine learning potentials generated with the Ultra-Fast Force Fields (UF3) framework. We show how the inexpensive bond-valence method can be used to guide the generation of training samples for machine learning, in addition to filtering candidates.
Materials discovery↗
Lessons Learned From Developing Three Generations of Remote Sensing Science Data Processing Systems
The Biospheric Information Systems Branch at NASA s Goddard Space Flight Center has developed three generations of Science Investigator-led Processing Systems for use with various remote sensing instruments. The first system is used for data from the MODIS instruments flown on NASA s Earth Observing Systems @OS) Terra and Aqua Spacecraft launched in 1999 and 2002 respectively. The second generation is for the Ozone Measuring Instrument flying on the EOS Aura spacecraft launched in 2004. We are now developing a third generation of the system for evaluation science data processing for the Ozone Mapping and Profiler Suite (OMPS) to be flown by the NPOESS Preparatory Project (NPP) in 2006. The initial system was based on large scale proprietary hardware, operating and database systems. The current OMI system and the OMPS system being developed are based on commodity hardware, the LINUX Operating System and on PostgreSQL, an Open Source RDBMS. The new system distributes its data archive across multiple server hosts and processes jobs on multiple processor boxes. We have created several instances of this system, including one for operational processing, one for testing and reprocessing and one for applications development and scientific analysis. Prior to receiving the first data from OMI we applied the system to reprocessing information from the Solar Backscatter Ultraviolet (SBUV) and Total Ozone Mapping Spectrometer (TOMS) instruments flown from 1978 until now. The system was able to process 25 years (108,000 orbits) of data and produce 800,000 files (400 GiB) of level 2 and level 3 products in less than a week. We will describe the lessons we have learned and tradeoffs between system design, hardware, operating systems, operational staffing, user support and operational procedures. During each generational phase, the system has become more generic and reusable. While the system is not currently shrink wrapped we believe it is to the point where it could be readily adopted, with substantial cost savings, for other similar tasks.
Tilmes, Curt↗
Augmented Reality Data Generation for Training Deep Learning Neural Network
One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a highquality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.
Torres, Gil↗
Neural network error correction for solving coupled ordinary differential equations
A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.
Shelton, R. O.↗
Learning Shock Hydrodynamics with Generative Models
Explore the source record for details and available documents.
Jekel, Charles [Lawrence Livermore National Labora↗
The X-ray properties of normal galaxies. What do we know and what can we learn with the next generation of X-ray telescopes?
Einstein Observatory results are used to assess the possibilities of spaceborne X-ray astronomy projects such as XMM (ESA) and AXAF (NASA). Einstein observations show that normal galaxies of all morphological types are spatially extended sources of X-ray emission with 0.5 to 3.0 keV X-ray luminosities of 10 to the 39th to 41st power erg/sec. X-ray telescopes can study the end products of stellar evolution in galaxies of different morphological types. Phenomena linked to starburst nuclear activity can best be detected and studied in X-ray. Hot coronae or a hot phase of the interstellar medium can only be studied through their X-ray emission. It is shown that high spatial resolution is essential for studying normal galaxies and identifying different emission regions. Good spectral sensitivity and spectral imaging capability are essential for gaining a deeper understanding of the phenomena at work.
Fabbiano, G.↗
Interstellar PAH in the Laboratory and in Space. What have we Learned from the New Generation of Laboratory and Observational Studies?
Polycyclic Aromatic Hydrocarbons (PAHs) are an important and ubiquitous component of carbon-bearing materials in space. PAHs are the best-known candidates to account for the IR emission bands (UIR bands) and PAH spectral features are now being used as new probes of the ISM. PAHs are also thought to be among the carriers of the diffuse interstellar absorption bands (DIBs). In the model dealing with the interstellar spectral features, PAHs are present as a mixture of radicals, ions and neutral species. PAH ionization states reflect the ionization balance of the medium while PAH size, composition, and structure reflect the energetic and chemical history of the medium. A major challenge for laboratory astrophysics is to reproduce (in a realistic way) the physical conditions that exist in the emission and/or absorption interstellar zones. An extensive laboratory program has been developed at NASA Ames to assess the physical and chemical properties of PAHs in such environments and to describe how they influence the radiation and energy balance in space and the interstellar chemistry. In particular, laboratory experiments provide measurements of the spectral characteristics of interstellar PAH analogs from the ultraviolet and visible range to the infrared range for comparison with astronomical data. This paper will focus on the recent progress made in the laboratory to measure the direct absorption spectra of neutral and ionized PAHs in the gas phase in the near-UV and visible range in astrophysically relevant environments. These measurements provide data on PAHs and nanometer-sized particles that can now be directly compared to astronomical observations. The harsh physical conditions of the IS medium - characterized by a low temperature, an absence of collisions and strong VUV radiation fields - are simulated in the laboratory by associating a molecular beam with an ionizing discharge to generate a cold plasma expansion. PAH ions are formed from the neutral precursors in an isolated environment at low temperature (of the order of 100 K). The spectra of neutral and ionized PAHs are measured using the high sensitivity methods of cavity ring down spectroscopy (CRDS). These experiments provide unique information on the spectra of free, cold large carbon molecules and ions in the gas phase. Intrinsic band profiles and band positions of cold gas-phase PAHs can now be measured with high-sensitivity spectroscopy and directly compared to the astronomical data. The electronic bands measured for ionized PAH are found to be intrinsically broad (about 20 cm(sup -1)) while the bands associated with the neutral precursors are narrower (of the order of 2 - 10 cm(sup -1)). The laboratory data are discussed and compared with recent astronomical spectra of large and narrow DIBs and with the spectra of circumstellar environments of selected carbon stars and the implications for the interstellar PAH population are derived. Preliminary results also show that carbon nanoparticles are formed during the short residence time of the precursors in the plasma.
Salama, Farid↗
PAHs and the Diffuse Interstellar Bands. What have we Learned from the New Generation of Laboratory and Observational Studies?
Polycyclic Aromatic Hydrocarbons (PAHs) are an important and ubiquitous component of carbon-bearing materials in space. PAHs are the best-known candidates to account for the IR emission bands (UIR bands) and PAH spectral features are now being used as new probes of the ISM. PAHs are also thought to be among the carriers of the diffuse interstellar absorption bands (DIBs). In the model dealing with the interstellar spectral features, PAHs are present as a mixture of radicals, ions and neutral species. PAH ionization states reflect the ionization balance of the medium while PAH size, composition, and structure reflect the energetic and chemical history of the medium. A major challenge for laboratory astrophysics is to reproduce (in a realistic way) the physical conditions that exist in the emission and/or absorption interstellar zones, An extensive laboratory program has been developed at NASA Ames to characterize the physical and chemical properties of PAHs in astrophysical environments and to describe how they influence the radiation and energy balance in space and the interstellar chemistry. In particular, laboratory experiments provide measurements of the spectral characteristics of interstellar PAH analogs from the ultraviolet and visible range to the infrared range for comparison with astronomical data. This paper will focus on the recent progress made in the laboratory to measure the direct absorption spectra of neutral and ionized PAHs in the gas phase in the near-W and visible range in astrophysically relevant environments. These measurements provide data on PAHs and nanometer-sized particles that can now be directly compared to astronomical observations. The harsh physical conditions of the IS medium - characterized by a low temperature, an absence of collisions and strong V W radiation fields - are simulated in the laboratory by associating a molecular beam with an ionizing discharge to generate a cold plasma expansion. PAH ions are formed from the neutral precursors in an isolated environment at low temperature (of the order of 100 K). The spectra of neutral and ionized PAHs are measured using the high sensitivity methods of cavity ring down spectroscopy (CRDS). These experiments provide unique information on the spectra of free, cold large carbon molecules and ions in the gas phase. Intrinsic band profiles and band positions of cold gas-phase PAHs can now be measured with high- sensitivity spectroscopy and directly compared to the astronomical data. The electronic bands measured for ionized PAH are found to be intrinsically broad (about 20/cm) while the bands associated with the neutral precursors are narrower (of the order of 2 - 10/cm).
Salama, Farid↗
Pixel-Based Smoke Detection Using Machine Learning for the Next Generation Geostationary Satellite Imagery
No abstract available
Kaulfus, Aaron↗
Small target detection for search and rescue operations using distributed deep learning and synthetic data generation
It is important to find the target as soon as possible for search and rescue operations. Surveillance camera systems and unmanned aerial vehicles (UAVs) are used to support search and rescue. Automatic object detection is important because a person cannot monitor multiple surveillance screens simultaneously for 24 hours. Also, the object is often too small to be recognized by the human eye on the surveillance screen. This study used UAVs around the Port of Houston and fixed surveillance cameras to build an automatic target detection system that supports the US Coast Guard (USCG) to help find targets (e.g., person overboard). We combined image segmentation, enhancement, and convolution neural networks to reduce detection time to detect small targets. We compared the performance between the auto-detection system and the human eye. Our system detected the target within 8 seconds, but the human eye detected the target within 25 seconds. Our systems also used synthetic data generation and data augmentation techniques to improve target detection accuracy. This solution may help the search and rescue operations of the first responders in a timely manner.
Chow, Edward↗
Downscaled Earth System Model Data for Resilient Energy System Planning
The second-generation Sup3rCC dataset provides high-resolution meteorological data generated through the downscaling of multiple earth system models (ESMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6). This downscaling is performed through application of a generative machine learning approach called Super-Resolution for Renewable Resource Data (sup3r). This dataset builds on the first-generation Sup3rCC data by applying improved bias correction methods and adding downscaled precipitation to the output variables. In this presentation, we explore the output characteristics of the dataset and various validation analyses. We also present and discuss plans for the integration of this data into power system planning models using a decision-making under deep uncertainty (DMDU) methodology.
97 MATHEMATICS AND COMPUTING↗