Microstructure Quantification With Deep Learning Encoders Pre-Trained on a Massive Microscopy Dataset
Explore the source record for details and available documents.
machine learning↗
SEARCH · Engineering Papers
Results for “massive datasets”
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.
Picasso: Memory-Efficient Graph Coloring Using Palettes With Applications in Quantum Computing
A coloring of a graph is an assignment of colors to vertices such that no two neighboring vertices have the same color. The need for memory-efficient coloring algorithms is motivated by their application in computing clique partitions of graphs arising in quantum computations where the objective is to map a large set of Pauli strings into a compact set of unitaries. We present Picasso, a randomized memory-efficient iterative parallel graph coloring algorithm with theoretical sublinear space guarantees under practical assumptions. The parameters of our algorithm provide a trade-off between coloring quality and resource consumption. To assist the user, we also propose a machine learning model to predict the coloring algorithm’s parameters considering these trade-offs. We provide a sequential and a parallel implementation of the proposed algorithm. We perform an experimental evaluation on a 64-core AMD CPU equipped with 512 GB of memory and an Nvidia A100 GPU with 40GB of memory. For a small dataset where existing coloring algorithms can be executed within the 512 GB memory budget, we show up to 68× memory savings. On massive datasets we demonstrate that GPU-accelerated Picasso can process inputs with 49.5× more Pauli strings (vertex set in our graph) and 2,478× more edges than state-of-the-art parallel approaches.
artificial intelligence, quantum computing↗
Segmentation of Unstructured Datasets
Datasets generated by computer simulations and experiments in Computational Fluid Dynamics tend to be extremely large and complex. It is difficult to visualize these datasets using standard techniques like Volume Rendering and Ray Casting. Object Segmentation provides a technique to extract and quantify regions of interest within these massive datasets. This thesis explores basic algorithms to extract coherent amorphous regions from two-dimensional and three-dimensional scalar unstructured grids. The techniques are applied to datasets from Computational Fluid Dynamics and from Finite Element Analysis.
Bhat, Smitha↗
Frictionless knowledge injection for few-shot learning
Cutting-edge machine learning methods often require large volumes of curated training data, precluding their use in national security problems with rare events in massive datasets. We present a method for incorporating abstract knowledge into models tailored for sparse data. A subject matter expert defines salient concepts using data examples, which are encoded in the model’s embedding space. Models are then trained to respect these concepts. This method enables knowledge injection, yielding effective models with limited labeled data and the ability to assess model sensitivity for subject matter expertise across the nonproliferation mission space, as demonstrated with Raman spectra analysis.
Stomps, Jordan [ORNL] (ORCID:0000000178114479)↗
Scalable 3D reconstruction for X-ray single particle imaging with online machine learning
X-ray free-electron lasers offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate free-electron lasers enable single particle imaging, where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray single particle reconstruction algorithms, which estimate the particle orientation for each image independently, are slow and memory-intensive when handling the massive datasets generated by emerging free-electron lasers. Here, we introduce X-RAI (X-Ray single particle imaging with Amortized Inference), an online reconstruction framework that estimates the structure of 3D macromolecules from large X-ray single particle datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray single particle imaging towards real-time reconstruction.
Computer science↗
Foundation models for atomistic simulation of chemistry and materials
Conventional computational methods for modeling chemical and materials systems are limited by system size and timescale, forcing a trade-off between quantum-mechanical accuracy and the sampling needed for realistic observables. Large language and vision foundation models — pre-trained on massive datasets using transformer architectures — have revolutionized many fields. It is thus interesting to ask whether a foundation model — subject to suitable data, parameter scaling and training — could enable learned simulations of chemistry and materials. Here, in this study, we review the field of machine-learned interatomic potentials (MLIPs) and posit that scaling up large and diverse chemical and materials datasets and highly expressive architectures using advanced training strategies should result in models that are: more efficient, transferable, robust to out-of-distribution scenarios, and easier to fine-tune to a variety of downstream physical observables than models trained from scratch on small datasets corresponding to specific, targeted atomistic simulation tasks. We provide specific criteria for creating such large-scale MLIP foundation models, coordinated strategies for their development, evaluation and deployment, and highlight potential emergent capabilities that could transform predictive simulations in chemistry and materials science and accelerate discovery across multiple technological domains.
Yuan, Eric C.-Y. [University of California, Berkel↗
An AI-accelerated pathway for reproducible and stable halide perovskites
Halide perovskites (HPs) have remarkable optoelectronic properties, and in the last decade their photovoltaic power conversion efficiency and light-emitting diode efficiency have skyrocketed. Despite the surge in research on these burgeoning materials, two key challenges in the field remain: material irreproducibility and instability. Their behavior is especially dynamic in response to environmental stressors, due to complex interactions with the perovskite crystal lattice. Here, in this review, we survey the latest achievements in HP materials research accomplished with the assistance of artificial intelligence (AI), through the implementation of automated experimentation and machine learning (ML) data analysis. Automated synthesis and characterization tackle problems with material irreproducibility by systematically controlling parameters with very high precision, creating massive datasets, and allowing methodical comparisons from which unbiased conclusions can be drawn. AI can reveal otherwise unnoticed trends, inform future experiments with the highest potential information gain, and forecast future performance. The review concludes with a forward viewpoint of how human-assisted closed-loop laboratories and shared databases allow halide perovskite materials’ processing, properties, and performance to be potentially optimized with AI, accelerating the development of highly reproducible and stable optoelectronic devices.
Hering, Abigail R. [Univ. of California, Davis, CA↗
Using the optimal combined index weight ratio to improve the probability of anomaly detection in big area additive manufacturing
Big Area Additive Manufacturing (BAAM) of composites requires significant time, energy, and material, so it is critical to reduce production inefficiencies to make functional parts without multiple iterations. Statistical process control coupled with Principal Component Analysis (PCA) is a powerful technique that provides a quick, computationally inexpensive, and intuitive way for operators to detect defects that form in a manufacturing process without massive datasets. Recently, a combined index that is a weighted sum of the Hotelling's T 2 and squared residual error statistics has been proposed that can be monitored in one chart, improving interpretation accuracy and simplicity. However, the literature does not offer a formal method to optimise the weights. Here, we introduce two new approaches to the traditional weight selection approach using simulated and BAAM image data. Approach 1 uses a theoretically motivated optimum inspired by probabilistic principal component analysis. Approach 2 systematically varies the ratio of the weights to find the optimum. We show that approach 1 delivers optimal anomaly detection performance in select cases while approach 2 fares better in practice. Surprisingly, we also show that choosing a more complex PCA model has a minimal negative impact on anomaly detection performance compared to a more simplistic model.
3-dimensional printing↗
Design considerations for parallel graphics libraries
Applications which run on parallel supercomputers are often characterized by massive datasets. Converting these vast collections of numbers to visual form has proven to be a powerful aid to comprehension. For a variety of reasons, it may be desirable to provide this visual feedback at runtime. One way to accomplish this is to exploit the available parallelism to perform graphics operations in place. In order to do this, we need appropriate parallel rendering algorithms and library interfaces. This paper provides a tutorial introduction to some of the issues which arise in designing parallel graphics libraries and their underlying rendering algorithms. The focus is on polygon rendering for distributed memory message-passing systems. We illustrate our discussion with examples from PGL, a parallel graphics library which has been developed on the Intel family of parallel systems.
Crockett, Thomas W.↗
3D Feature Extraction for Unstructured Grids
Visualization techniques provide tools that help scientists identify observed phenomena in scientific simulation. To be useful, these tools must allow the user to extract regions, classify and visualize them, abstract them for simplified representations, and track their evolution. Object Segmentation provides a technique to extract and quantify regions of interest within these massive datasets. This article explores basic algorithms to extract coherent amorphous regions from two-dimensional and three-dimensional scalar unstructured grids. The techniques are applied to datasets from Computational Fluid Dynamics and those from Finite Element Analysis.
Silver, Deborah↗
Validating LES for Jet Aeroacoustics
Engineers charged with making jet aircraft quieter have long dreamed of being able to see exactly how turbulent eddies produce sound and this dream is now coming true with the advent of large eddy simulation (LES). Two obvious challenges remain: validating the LES codes at the resolution required to see the fluid-acoustic coupling, and the interpretation of the massive datasets that result in having dreams come true. This paper primarily addresses the former, the use of advanced experimental techniques such as particle image velocimetry (PIV) and Raman and Rayleigh scattering, to validate the computer codes and procedures used to create LES solutions. It also addresses the latter problem in discussing what are relevant measures critical for aeroacoustics that should be used in validating LES codes. These new diagnostic techniques deliver measurements and flow statistics of increasing sophistication and capability, but what of their accuracy? And what are the measures to be used in validation? This paper argues that the issue of accuracy be addressed by cross-facility and cross-disciplinary examination of modern datasets along with increased reporting of internal quality checks in PIV analysis. Further, it is argued that the appropriate validation metrics for aeroacoustic applications are increasingly complicated statistics that have been shown in aeroacoustic theory to be critical to flow-generated sound.
Bridges, James↗
Validating LES for Jet Aeroacoustics
Engineers charged with making jet aircraft quieter have long dreamed of being able to see exactly how turbulent eddies produce sound and this dream is now coming true with the advent of large eddy simulation (LES). Two obvious challenges remain: validating the LES codes at the resolution required to see the fluid-acoustic coupling, and the interpretation of the massive datasets that are produced. This paper addresses the former, the use of advanced experimental techniques such as particle image velocimetry (PIV) and Raman and Rayleigh scattering, to validate the computer codes and procedures used to create LES solutions. This paper argues that the issue of accuracy of the experimental measurements be addressed by cross-facility and cross-disciplinary examination of modern datasets along with increased reporting of internal quality checks in PIV analysis. Further, it argues that the appropriate validation metrics for aeroacoustic applications are increasingly complicated statistics that have been shown in aeroacoustic theory to be critical to flow-generated sound, such as two-point space-time velocity correlations. A brief review of data sources available is presented along with examples illustrating cross-facility and internal quality checks required of the data before it should be accepted for validation of LES.
Bridges, James↗
Dynamic Server-Based KML Code Generator Method for Level-of-Detail Traversal of Geospatial Data
Web-based geospatial client applications such as Google Earth and NASA World Wind must listen to data requests, access appropriate stored data, and compile a data response to the requesting client application. This process occurs repeatedly to support multiple client requests and application instances. Newer Web-based geospatial clients also provide user-interactive functionality that is dependent on fast and efficient server responses. With massively large datasets, server-client interaction can become severely impeded because the server must determine the best way to assemble data to meet the client applications request. In client applications such as Google Earth, the user interactively wanders through the data using visually guided panning and zooming actions. With these actions, the client application is continually issuing data requests to the server without knowledge of the server s data structure or extraction/assembly paradigm. A method for efficiently controlling the networked access of a Web-based geospatial browser to server-based datasets in particular, massively sized datasets has been developed. The method specifically uses the Keyhole Markup Language (KML), an Open Geospatial Consortium (OGS) standard used by Google Earth and other KML-compliant geospatial client applications. The innovation is based on establishing a dynamic cascading KML strategy that is initiated by a KML launch file provided by a data server host to a Google Earth or similar KMLcompliant geospatial client application user. Upon execution, the launch KML code issues a request for image data covering an initial geographic region. The server responds with the requested data along with subsequent dynamically generated KML code that directs the client application to make follow-on requests for higher level of detail (LOD) imagery to replace the initial imagery as the user navigates into the dataset. The approach provides an efficient data traversal path and mechanism that can be flexibly established for any dataset regardless of size or other characteristics. The method yields significant improvements in userinteractive geospatial client and data server interaction and associated network bandwidth requirements. The innovation uses a C- or PHP-code-like grammar that provides a high degree of processing flexibility. A set of language lexer and parser elements is provided that offers a complete language grammar for writing and executing language directives. A script is wrapped and passed to the geospatial data server by a client application as a component of a standard KML-compliant statement. The approach provides an efficient means for a geospatial client application to request server preprocessing of data prior to client delivery. Data is structured in a quadtree format. As the user zooms into the dataset, geographic regions are subdivided into four child regions. Conversely, as the user zooms out, four child regions collapse into a single, lower-LOD region. The approach provides an efficient data traversal path and mechanism that can be flexibly established for any dataset regardless of size or other characteristics.
Baxes, Gregory↗
Scalable edge clustering of dynamic graphs via weighted line graphs
Timestamped relational datasets consisting of records (or connections) between pairs of entities are ubiquitous in network science. For applications like peer-to-peer communication, email, various social network interactions, and computer network security, it is useful to organize these records into groups based on how and when they are occurring. Weighted line graphs offer a natural way to model how records are related in such datasets but for large real-world graph topologies, building and utilizing the line graph is prohibitively expensive. Here, we present the framework to cluster the edges of a dynamic graph via the associated line graph that contains two major contributions. The first is a method to work with the line graph implicitly and the second is a distributed scale implementation of an agglomerative hierarchical graph clustering algorithm. We outline a novel hierarchical dynamic graph edge clustering approach that efficiently breaks massive relational datasets into small sets of edges containing events at various timescales. This is in stark contrast to traditional graph clustering algorithms that prioritize highly connected (clique-like) community structures. Our approach relies on constructing a sufficient subgraph of a weighted line graph and applying a hierarchical agglomerative clustering. This approach is related to scalable techniques from spatial clustering, nonlinear-dimension reduction, topological data analysis, and draws particular inspiration from HDBSCAN. As an edge clustering, this method yields an overlapping node clustering. Our algorithm is parallelizable and we demonstrate efficient clustering of a billion-scale, real-world dynamic graph into small edge sets that correlate in topology and time. The entire clustering process for a graph with tens of billions of edges takes just a few minutes of run time on 256 nodes of a distributed compute environment. We argue how the output of the edge clustering is useful for a multitude of data visualization and powerful machine learning tasks, both involving the original massive dynamic graph data and metadata associated with the nodes and edges. Finally, we describe how this approach can be extended to dynamic hypergraphs and dynamic graphs/hypergraphs with unstructured data living on vertices and edges.
Data Analysis↗
The Montage architecture for grid-enabled science processing of large, distributed datasets
Montage is an Earth Science Technology Office (ESTO) Computational Technologies (CT) Round III Grand Challenge investigation to deploy a portable, compute-intensive, custom astronomical image mosaicking service for the National Virtual Observatory (NVO). Although Montage is developing a compute- and data-intensive service for the astronomy community, we are also helping to address a problem that spans both Earth and Space science, namely how to efficiently access and process multi-terabyte, distributed datasets. In both communities, the datasets are massive, and are stored in distributed archives that are, in most cases, remote from the available Computational resources. Therefore, state of the art computational grid technologies are a key element of the Montage portal architecture. This paper describes the aspects of the Montage design that are applicable to both the Earth and Space science communities.
virtual observatory↗
Robot Science Autonomy in the Atacama Desert and Beyond
Science-guided autonomy augments rovers with reasoning to make observations and take actions related to the objectives of scientific exploration. When rovers can directly interpret instrument measurements then scientific goals can inform and adapt ongoing navigation decisions. These autonomous explorers will make better scientific observations and collect massive, accurate datasets. In current astrobiology studies in the Atacama Desert we are applying algorithms for science autonomy to choose effective observations and measurements. Rovers are able to decide when and where to take follow-up actions that deepen scientific understanding. These techniques apply to planetary rovers, which we can illustrate with algorithms now used by Mars rovers and by discussing future missions.
robotic surface exploration↗
GC31G-1182: Opennex, a Private-Public Partnership in Support of the National Climate Assessment
The NASA Earth Exchange (NEX) is a collaborative computing platform that has been developed with the objective of bringing scientists together with the software tools, massive global datasets, and supercomputing resources necessary to accelerate research in Earth systems science and global change. NEX is funded as an enabling tool for sustaining the national climate assessment. Over the past five years, researchers have used the NEX platform and produced a number of data sets highly relevant to the National Climate Assessment. These include high-resolution climate projections using different downscaling techniques and trends in historical climate from satellite data. To enable a broader community in exploiting the above datasets, the NEX team partnered with public cloud providers to create the OpenNEX platform. OpenNEX provides ready access to NEX data holdings on a number of public cloud platforms along with pertinent analysis tools and workflows in the form of Machine Images and Docker Containers, lectures and tutorials by experts. We will showcase some of the applications of OpenNEX data and tools by the community on Amazon Web Services, Google Cloud and the NEX Sandbox.
datasets↗
AMAPS - A new paradigm for data distribution and analysis
Technological advancements in computing power and storage have made possible the collection and analysis of massive scientific datasets. Distribution has improved dramatically in recent years by making the data web-accessible.
Wilson, Brian↗