Spatiotemporal upscaling of sparse air-sea pCO2 data via physics-informed transfer learning
Not provided.
SEARCH · Search NASA
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.
Not provided.
The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies.
Integrating artificial intelligence and machine learning tools into industry necessitates large-scale collaborative efforts that ensure the robust and accurate execution of downstream analytics such as time series prediction, uncertainty quantification, grid optimization, and condition monitoring. However, concerns related to data privacy pervade the nuclear industry due to the proprietary nature of its data and the possibility of data leakage. Legacy techniques such as encryption often require the explicit transmission of data to trustworthy parties, thereby inviting data leakage concerns. The ideal collaboration scenario avoids the explicit dissemination of data/code while maintaining experimental fidelity, which is currently accomplished using various techniques such as trusted execution environments, homomorphic encryption, differential privacy, and multimatrix masking. These techniques, however, often necessitate a trade-off between trust, efficiency, and utility. This article extends a previously proposed technique called the directed infusion of data (DIOD) that ensures data privacy, allows for scalable obfuscation, and combats the risk of data leakage without compromising utility. The experiments discussed in this article examine a regression-type scenario using DIOD with the goal of preserving the inferential link between two variables. Using the point-kinetics equations, regression experiments compare the performance of a model trained using the original data to that of a model trained using the obfuscated data, which produced identical results. Our claim is further strengthened by an information theoretic proof and experiment, which showed that the inferential content between variables remains the same after obfuscation, thereby avoiding the required communication of the proprietary data.
Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.
Phasor measurement units (PMUs) play a crucial role in real-time monitoring and control of power grids. They rely on a communication network to transfer measurement data to the phasor data concentrator (PDC) for further processing and analysis. In this paper, a resilient cross-domain PMU and communication link placement method for minimizing the overall installation cost of the wide-area measurement system (WAMS) is proposed. Here, the main idea is to break down the barrier between the power grid domain and the communication domain, and consider the impact of one when design the other. The PMU placement in the power grid domain takes into account the cost of communication links by generating multiple solutions with equally minimum PMU costs for communication link placement evaluation. On the other hand, the communication link placement problem reduces the cost by customizing the routing policies based on the different roles of PMUs in grid observability. The proposed WAMS design is capable of withstanding any single component failure in the power domain (PMU failure or power branch failure) or in the communication domain (communication link failure or PDC failure). Numerical study on the IEEE 57-bus system reveals that the developed cross-domain optimization framework can significantly reduce the overall installation cost of WAMS while attaining multi-domain resiliency.
Data-intensive knowledge discovery requires scientific applications to run concurrently with analytics and visualization codes executing in situ for timely output inspection and knowledge extraction. Consequently, I/O pipelines of scientific workflows can be long and complex because they comprise many stages of analytics across different layers of the I/O stack of high-performance computing systems. Performance limitations at any I/O layer or stage can cause an I/O bottleneck resulting in greater than expected end-to-end I/O latency. In this paper, we present the design and implementation of a novel data management infrastructure called Software-Defined Storage Resource Enclaves (SIREN) at system level to enforce end-to-end policies that dictate an I/O pipeline's performance. SIREN provides an I/O performance interface for users to specify the desired storage resources in the context of in-situ analytics. If suboptimal performance of analytics is caused by an I/O bottleneck when data are transferred between simulations and analytics, schedulers in different layers of the I/O stack automatically provide the guaranteed lower bounds on I/O throughput. Lastly, our experimental results demonstrate that SIREN provides performance isolation among scientific workflows sharing multiple storage servers across two I/O layers (burst buffer and parallel file systems) while maintaining high system scalability and resource utilization.
Purpose: Recent development of an MLC for robotic external beam radiotherapy has the potential of new clinical application in conventionally fractionated radiation therapy. This study offers a dosimetric comparison of IMRT plans using Cyberknife with MLC versus conventional linac plans. Methods: Ten prostate cancer patients treated on a traditional linac with IMRT to 7920cGy at 180cGy/fraction were randomly selected. GTVs were defined as prostate plus proximal seminal vesicles. PTVs were defined as GTV+8mm in all directions except 5mm posteriorly. Conventional IMRT planning was performed on Philips Pinnacle and delivered on a standard linac with CBCT and 10mm collimator leaf width. For each case a Cyberknife plan was created using Accuray Multiplan with same CT data set, contours, and dose constraints. All dosimetric data was transferred to third party software for independent computation of contour volumes and DVH. Delivery efficiency was evaluated using total MU, treatment time, number of beams, and number of segments. Results: Evaluation criteria including percent target coverage, homogeneity index, and conformity index were found to be comparable. All dose constraints from QUANTEC were found to be statistically similar except rectum V50Gy and bladder V65Gy. Average rectum V50Gy was lower for robotic IMRT (30.07%±6.57) versus traditional (34.73%±3.62, p=0.0130). Average bladder V65Gy was lower for robotic (17.87%±12.74) versus traditional (21.03%±11.93, p=0.0405). Linac plans utilized 9 coplanar beams, 48.9±3.8 segments, and 19381±2399MU. Robotic plans utilized 38.4±9.0 non-coplanar beams, 85.5±21.0 segments and 42554.71±16381.54 MU. The average treatment was 15.02±0.60 minutes for traditional versus 20.90±2.51 for robotic. Conclusion: The robotic IMRT plans were comparable to the traditional IMRT plans in meeting the target volume dose objectives. Critical structure dose constraints were largely comparable although statistically significant differences were found in favor of the robotic platform in terms of rectum V50Gy and bladder V65Gy at a cost of 25% longer treatment time.
Accurate and low-latency quantum state discrimination is essential for protocols involving mid-circuit measurement (MCM) and conditional feed-forward. In superconducting quantum systems, conventional readout pipelines transfer measurement data to host processors for post-processing, introducing millisecond-scale delays that far exceed qubit coherence times. To overcome this bottleneck, we present an in-situ machine learning (ML) inference engine implemented on an FPGA for real-time quantum state discrimination. Our design performs inference directly on digitized readout signals with 40 ns latency, supports both qubit and qutrit readout, and enables conditional operations without host-side intervention. This capability is critical for MCM and for feedback-driven protocols such as quantum error correction. We validate the system on superconducting transmon hardware, demonstrating robust discrimination fidelity across multiple qubit and qutrit channels. We further demonstrate conditional qutrit logic driven by FPGA-resident classification, highlighting the potential of low-latency ML-on-FPGA control for NISQ applications and scalable fault-tolerant quantum computing.
High-throughput data generation methods and machine learning (ML) algorithms have given rise to a new era of computational materials science by learning the relations between composition, structure, and properties and by exploiting such relations for design. However, to build these connections, materials data must be translated into a numerical form, called a representation, that can be processed by an ML model. Data sets in materials science vary in format (ranging from images to spectra), size, and fidelity. Predictive models vary in scope and properties of interest. Here, we review context-dependent strategies for constructing representations that enable the use of materials as inputs or outputs for ML models. Furthermore, we discuss how modern ML techniques can learn representations from data and transfer chemical and physical information between tasks. Finally, we outline high-impact questions that have not been fully resolved and thus require further investigation.
Mass spectrometry (MS) is an analytical technique that enables all chemical species within a complex mixture to be resolved and identified based on their mass:charge ratio. MS is an increasingly important tool in life science research and development because it can resolve or separate small molecules, peptides, lipids, proteins, biopolymers and fragments of all of these structures. Unfortunately, the use of MS has been limited for lack of software tools to visualize, manipulate, store and transfer MS data. Ben Bowen, Oliver Ruebel and colleagues made a huge advance on the resolution of these limitations with the invention of "OpenMSI" (#2013-004), a computational method that makes the handling of these very large files (up to 50 Tb) much easier, especially for scientists with limited background in bioinformatics or sophisticated software applications of the type needed to handle such data files. With the OpenMSI Arrayed Analysis Tool (OMAAT, #2016-188) invention, the authors take MS data analysis one step further by providing tolls for automatic sample position optimization and ion selection. Even though sample deposition technologies have improved greatly, there is always the chance of encountering outliers in a predefined roster, especially in very large sample sets. Manual curation of the data would be extremely time consuming, so the inventors have included an algorithm that automatically finds the outliers. OMAAT is written in Python with accompanying Jupyter (formerly iPython) notebook and is fully integrated with OpenMSI.
This project describes fundamental experimental and theoretical work that relates to charge separation and migration in the solid, heterogeneous or aggregated state. Marcus theory assumes a system in equilibrium with all possible solvent (dipolar) configurations, with rapid interconversion among these on the ET timescale. This project has addressed the more general situation where the medium is at least partially frozen on the ET timescale, i.e. under conditions of dynamical arrest. The approach combined theory and experiment and includes: (1) Computer simulations of model systems, (2) Development of analytical procedures consistent with computer experiment and (3) Experimental studies and testing of the formal theories on this data. Electron transfer processes are unique as a consequence of the close connection between kinetics, spectroscopy and theory, which is an essential component of this work.
There are many technologies available to the nuclear power industry to improve efficiency in plant work activities. These range from new control room technologies to those for mobile field workers. They can make a positive impact on a wide range of performance objectives – increase in productivity, human error reduction, validation of results, accurate transfer of data, and elimination of repetitive tasks. It is expected that the industry will more and more turn to these technologies to achieve these operational efficiencies to lower costs. At the same time, this will help utilities manage a looming staffing problem as the inevitable retirement wave of the more seasoned workers affects both staffing levels and knowledge retention. A barrier to this wide-scale implementation of new technologies for operational efficiency is the lack of a comprehensive digital architecture that can support the real-time information exchanges needed to achieve the desired operational efficiencies. This project will define an advanced digital architecture that will accommodate the entire range of system, process, and plant worker activity to enable the highest degree of integration, thereby creating maximum efficiency and productivity. This pilot project will consider a range of open standards that are suitable for the various data and communication requirements of a seamless digital environment. It will map these standards into an overall architecture to support the II&C developments of this research program.
This is a graphic chart/map of the Cielo-to-Trinity storage infrastructure at Los Alamos National Laboratory.
A number of Department of Energy (DOE) science applications, involving exascale computing systems and large experimental facilities, are expected to generate large volumes of data, in the range of petabytes to exabytes, which will be transported over wide-area networks for the purpose of storage, visualization, and analysis. The objectives of this proposal are to (1) develop and test the component technologies and their synthesis methods to achieve source-to-sink high-performance flows, and (2) develop tools that provide these capabilities through simple interfaces to users and applications. In terms of the former, we propose to develop (1) optimization methods that align and transition multiple storage flows to multiple network flows on multicore, multibus hosts; and (2) edge and long-haul network path realization and maintenance using advanced provisioning methods including OSCARS and OpenFlow. We also propose synthesis methods that combine these individual technologies to compose high-performance flows using a collection of constituent storage-network flows, and realize them across the storage and local network connections as well as long-haul connections. We propose to develop automated user tools that profile the hosts, storage systems, and network connections; compose the source-to-sink complex flows; and set up and maintain the needed network connections.
The Records API (application program interface) for Advanced Energy System Design (AESD) enables software that serves multidimensional record-oriented data to interoperate with software than uses such data. In the context of the Records API, multidimensional data records are simply tuples of real numbers, integers, and character strings, where each data value is tagged by a variable name, according to a pre-defined schema, and each record is assigned a unique integer identifier. Conceptually, these records are isomorphic to rows in a relational database, JSON objects, or key-value maps. Records servers might supply static datasets, sensor measurements that periodically update as new telemetry become available, or the results of simulations as the simulations generate new output. Records client software might display or analyze the data, but in the case of simulations the client request the creation of new ensembles for specified input parameters. It is also possible to chain records clients and servers together so that a client consuming data from a server might transform that data and serve it to further clients. This minimalist API avoids imposing burdensome metadata, structural, or implementation requirements on developers by relying on open-source technologies that is readily available for common programming languages. In particular, the API has been designed to place the smallest possible burden on services that provide data. This document defines the message format for the Records API, a transport mechanism for communicating the data, and semantics for interpreting it. The message format is specified as Google Protocol Buffers and the transport mechanism uses WebSockets. We discuss three major use cases for serving and consuming records data: (i) static data, (ii) dynamically augmented data, (iii) on-demand simulations, (iv) with filters, and (v) with bookmarks. Separate implementations of the API exist in C++, Haskell, JavaScript, Python, and R.
The DARMA many-task framework provides asynchronous communication and load balancing functionality. This functionality is embedded in standard , modern C++ through the use of the template wrapper classes similar to futures. DARMA codes previously could not interoperate with MPI. A new C++ interface and extended semantics now allow quiescence of DARMA kernels and transfer of data ownership back into MPI, allowing 1) isolated DARMA kernels to be inserted in a larger MPI code or 2) reuse of MPI libraries like solvers within a DARMA application.
Integration of advanced communication technologies into nuclear facility operation has the potential for enhancing safety and accident -resiliency of the existing fleet of aging light water reactors, as well those of future advanced reactors. Conventional wired and wireless communication systems face implementation challenges at nuclear facilities due to the presence of thick reinforced concrete walls with steel liners throughout much of nuclear facility, especially the containment building. In addition, concerns related to security gaps in conventional communication networks have to be addressed when developing communication systems for nuclear facilities. To address communication technology gaps for nuclear energy, we are currently developing the acoustic communication (AC) hardware and network protocols for efficient and secure transfer of data, and will provide a preliminary experimental demonstration of the AC system prototype in a representative environment.
The objective of this project is to develop and demonstrate methods for transmission of information in nuclear facilities across physical barriers as acoustic/elastic guided waves along existing in-place metal piping infrastructure. Acoustic communication (AC) system hardware and software layers for efficient and resilient transfer of data are being developed,with the goal of performing experimental demonstration of information transmission in a representative environment.