Search NASA⌕ Search

SEARCH · Search NASA

Results for “compact data storage”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

A Comparative Study of Multi-material Data Structures for Computational Physics Applications

The data structures used to represent the multi-material state of a computational physics application can have a drastic impact on the performance of the application. We look at efficient data structures for sparse applications where there may be many materials, but only one or few in most computational cells. We develop simple performance models for use in selecting possible data structures and programming patterns. We verify the analytic models of performance through a small test program of the representative cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Optical Processes behind Plasmonic Applications

Plasmonics is a revolutionary concept in nanophotonics that combines the properties of both photonics and electronics by confining light energy to a nanometer-scale oscillating field of free electrons, known as a surface plasmon. Generation, processing, routing, and amplification of optical signals at the nanoscale hold promise for optical communications, biophotonics, sensing, chemistry, and medical applications. Surface plasmons manifest themselves as confined oscillations, allowing for optical nanoantennas, ultra-compact optical detectors, state-of-the-art sensors, data storage, and energy harvesting designs. Surface plasmons facilitate both resonant characteristics of nanostructures and guiding and controlling light at the nanoscale. Plasmonics and metamaterials enable the advancement of many photonic designs with unparalleled capabilities, including subwavelength waveguides, optical nanoresonators, super- and hyper-lenses, and light concentrators. Alternative plasmonic materials have been developed to be incorporated in the nanostructures for low losses and controlled optical characteristics along with semiconductor-process compatibility. This review describes optical processes behind a range of plasmonic applications. It pays special attention to the topics of field enhancement and collective effects in nanostructures. The advances in these research topics are expected to transform the domain of nanoscale photonics, optical metamaterials, and their various applications.

2D materials↗
DOE OSTI2024

Integration of RNTuple in ATLAS Athena

After using ROOT’s TTree I/O subsystem for over two decades and storing more than an exabyte of compressed High Energy Physics (HEP) data, advances in technology have motivated a complete redesign, RNTuple, which breaks backward-compatibility to take better advantage of these storage options. The RNTuple I/O subsystem has been designed to address performance bottlenecks and other shortcomings of TTree. Specifically, RNTuple comes with an updated, more compact binary data format that can be stored both in ROOT files and natively in object stores. It is designed for modern storage hardware (e.g. high-throughput low-latency NVMe SSDs), and provides robust and easy to use interfaces. The binary format of RNTuple is scheduled to become production grade in 2024, and recently has become mature enough to start exploring the integration into software used by HEP experiments. In this contribution, we discuss the developments to support the features as required by the ATLAS analysis Event Data Model (EDM) in RNTuple, which will enable its integration into the Athena software framework. With these developments in place, we evaluate the performance of the current most recent versions of RNTuple-based ATLAS data sets and compare this to that of TTree.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2015

Parallel log structured file system collective buffering to achieve a compact representation of scientific and/or dimensional data

Collective buffering and data pattern solutions are provided for storage, retrieval, and/or analysis of data in a collective parallel processing environment. For example, a method can be provided for data storage in a collective parallel processing environment. The method comprises receiving data to be written for a plurality of collective processes within a collective parallel processing environment, extracting a data pattern for the data to be written for the plurality of collective processes, generating a representation describing the data pattern, and saving the data and the representation.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2020

Fission Product Gas Monitoring During Fuel Drying Operations - 20094

The goal of the project was to devise and implement a method of accurately qualifying any noble gas emitted during fuel drying operations (part of the dry fuel storage process) in order to provide the data needed to validate the off-site dose calculations. The imputes of the project was the NRC publishing Information Notice 18-01, 'Noble Fission Gas Releases During Spent Fuel Cask Loading Operations' in February 2018. The information notice describes some industry events that occurred during vacuum drying operations as part of a dry fuel campaign. The solution was devised by Fort Calhoun Station staff in partnership with Mirion Technologies technical staff. The monitoring was accomplished by directing all the effluent from the fuel storage cask vacuum drying machine through a sample chamber containing a compact ISOCS characterized CZT based gamma spectrometer connected to a Mirion Data Analyst. This resulted near real-time quantification of the radionuclides of concern. (authors)

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2026

REV-INR: Regularized Evidential Implicit Neural Representation for Uncertainty-Aware Volume Visualization

Applications of Implicit Neural Representations (INRs) have emerged as a promising deep learning approach for compactly representing large volumetric datasets. These models can act as surrogates for volume data, enabling efficient storage and on-demand reconstruction via model predictions. However, conventional deterministic INRs only provide value predictions without insights into the model’s prediction uncertainty or the impact of inherent noisiness in the data. This limitation can lead to unreliable data interpretation and visualization due to prediction inaccuracies in the reconstructed volume. Identifying erroneous results extracted from model-predicted data may be infeasible, as raw data may be unavailable due to its large size. To address this challenge, we introduce REV-INR, Regularized Evidential Implicit Neural Representation, which learns to predict data values accurately along with the associated coordinate-level data uncertainty and model uncertainty using only a single forward pass of the trained REV-INR during inference. By comprehensively comparing and contrasting REV-INR with existing well-established deep uncertainty estimation methods, we show that REV-INR achieves the best volume reconstruction quality with robust data (aleatoric) and model (epistemic) uncertainty estimates using the fastest inference time. Consequently, we demonstrate that REV-INR facilitates assessment of the reliability and trustworthiness of the extracted isosurfaces and volume visualization results, enabling analyses to be solely driven by model-predicted data.

Saklani, Shanu [Indian Institute of Technology, Ka↗
DOE OSTI2023

Scalable Incremental Checkpointing using GPU-Accelerated De-Duplication

Writing large amounts of data concurrently to stable storage is a typical I/O pattern of many HPC workflows. This pattern introduces high I/O overheads and results in increased storage space utilization especially for workflows that need to capture the evolution of data structures with high frequency as checkpoints. In this context, many applications, such as graph pattern matching, perform sparse updates to large data structures between checkpoints. For these applications, incremental checkpointing techniques that save only the differences from one checkpoint to another can dramatically reduce the checkpoint sizes, I/O bottlenecks, and storage space utilization. However, such techniques are not without challenges: it is non-trivial to transparently determine what data has changed since a previous checkpoint and assemble the differences in a compact fashion that does not result in excessive metadata. State-of-art data reduction techniques (e.g., compression and de-duplication) have significant limitations when applied to modern HPC applications that leverage GPUs: slow at detecting the differences, generate a large amount of metadata to keep track of the differences, and ignore crucial spatiotemporal checkpoint data redundancy. This paper addresses these challenges by proposing a Merkle tree-based incremental checkpointing method to exploit GPUs' high memory bandwidth and massive parallelism. Experimental results at scale show a significant reduction of the I/O overhead and space utilization of checkpointing compared with state-of-the-art incremental checkpointing and compression techniques.

Tan, Nigel↗
DOE OSTI2013

Moisture Effects on Compaction of Fiberboard in a 9975 Shipping Package (Final Report)

Compaction of lower layers in the fiberboard assembly has been observed in 9975 packages that contain elevated moisture. Lab testing has resulted in a better understanding of the relationship between the fiberboard moisture level and compaction of the lower fiberboard assembly, and the behavior of the fiberboard during transport. In laboratory tests of cane fiberboard, higher moisture content has been shown to correspond to higher total compaction, greater rate of compaction, and continued compaction over a longer period of time. In addition, laboratory tests have shown that the application of a dynamic load results in higher fiberboard compaction compared to a static load. The test conditions and sample geometric/loading configurations were chosen to simulate the regulatory requirements for 9975 package input dynamic loading. Dynamic testing was conducted to acquire immediate and cumulative changes in geometric data for various moisture levels. Two sample sets have undergone a complete dynamic test regimen, one set for 27 weeks, and the second set for 47 weeks. The dynamic input, data acquisition, test effects on sample dynamic parameters, and results from this test program are summarized and compared to regulatory specifications for dynamic loading. Compaction of the bottom fiberboard layers due to the accumulation of moisture is one possible cause of an increase in the axial gap at the top of the package. The net compaction of the bottom layers will directly add to the axial gap. The moisture which caused this compaction migrated from the middle region of the fiberboard assembly (which is typically the hottest). This will cause the middle region to shrink axially, which will also contribute directly to the axial gap. Measurement of the axial gap provides a screening tool for identifying significant change in the fiberboard condition. The data in this report provide a basis to evaluate the impact of moisture and fiberboard compaction on 9975 package performance during storage at the Savannah River Site (SRS).

36 MATERIALS SCIENCE↗
DOE OSTI2025

Topology-imprinting in nonlinear metasurfaces

Flat optical components, or metasurfaces, have transformed optical imaging, data storage, information processing, and biomedical applications by providing unprecedented control over light-matter interactions. These nano-engineered structures enable compact, multidimensional manipulation of light’s amplitude, phase, polarization, and wavefront, producing scalar and vector beams with unique properties such as orbital angular momentum and knotted topologies. This flexibility has potential applications in optical communication and imaging, particularly in complex environments such as atmospheric turbulence and undersea scattering. However, designing metasurfaces for shorter wavelengths, such as visible and ultraviolet light, remains challenging due to fabrication limitations and material absorption. Here, we introduce an innovative concept called topology imprinting using judiciously designed all-dielectric nonlinear optical metasurfaces to replicate desired waveforms at fundamental and harmonic frequencies, opening promising avenues for advanced photonic applications.

42 ENGINEERING↗
DOE OSTI2025

Development and flight-testing of modular autonomous cultivation systems for biological plastics upcycling aboard the ISS

Cultivation of microorganisms in space has enormous potential to enable in-situ resource utilization (ISRU) Here, we develop an autonomous payload with fully programmable serial passaging and sample preservation, termed the Modular Open Biological Platform (MOBP), and flight-test the MOBP aboard the International Space Station (ISS) by conducting enzymatic and microbial plastics upcycling experiments. The MOBP is a compact, modular bioreactor system that allows for sustained microbial growth via automated media transfers, such as those for sample collection and storage for terrestrial analyses, and precise data monitoring from integrated sensors. The MOBP was flight-tested with two experiments designed to evaluate biological upcycling of the plastic poly(ethylene terephthalate) (PET). The bioproduct βKA can be polymerized into a nylon-6,6 analog with improved properties for use in the production of a variety of materials. We posit the MOBP will aid in democratizing the execution of synthetic biology in spaceflight towards enabling ISRU.

09 BIOMASS FUELS↗
DOE OSTI2019

SDN-NGenIA, a Software Defined Next Generation Integrated Architecture for HEP and Data Intensive Science

This project aims to enable the LHC and other leading programs in high energy physics and other global science domains funded by the DOE to operate with a new level of efficiency and control, through the development of a Next Generation Integrated Architecture (NGenIA) based on intelligent software defined network (SDN)-driven network systems coupled to high throughput applications. While the initial focus is on the challenging LHC use case, the systems and products being developed are general, and apply to many fields of data intensive science ranging from astrophysical sky surveys to bioinformatics and earth observation, as well as other organizations facing the challenges of extracting knowledge from distributed multi-petabyte data stores. A central concept in this development program is a new paradigm ‘consistent network operations’ among widely distributed computing and storage facilities, where stable high throughput flows, at set rates, cross load-balanced network paths, up to flexible high water marks that are adjusted in real time to accommodate other network traffic. The large smooth flows are launched and managed by SDN services that act in concert with the experiments’ site-resident data distribution and management systems, to meet the expanding needs of the science programs. The technical goals include the construction of autonomous, intelligent site-resident services that interact dynamically with network-resident services, and with the science programs’ principal data distribution and management tools, to request or command network resources in support of high throughput petascale to exascale workflow Specific work items include: 1. Developing compact Data Transfer Nodes (DTNs) with auto-tuning functions that support data transfer rates in the 100 Gbps to the 1 Tbps range when used with high throughput data transfer applications 2. Deep site orchestration among virtualized clusters, storage subsystems and subnets to successfully coschedule CPU, storage and network resources 3. Science-program designed site architectures, operational modes, and policy and resource usage priorities, adjudicated across multiple network domains and virtual organizations, using the orchestration functions and methods 4. Seamlessly extending end-to-end operation across both extra-site and intra-site boundaries through the use of Open vSwitch (OVS), FireQoS + next generation Science DMZs 5. Novel methods of system integration that enable granular control of extreme scale long distance transfers through flow matching of scattered source-destination address pairs to multi-domain dynamic circuits 6. Funneling massive sets of streams to DTNs at the site edge hosting petascale buffer pools configured for flows of 100 Gbps and up, exploiting state of the art data transfers 7. Adaptive scheduling based on pervasive end-to-end monitoring, including DTN or compute-node resident agents providing comprehensive end-system profiling 8. Developing unsupervised and supervised machine learning and modeling methods to optimize the workflow involving terabyte to multi-petabyte datasets.

47 OTHER INSTRUMENTATION↗
DOE OSTI2015

Pressure-induced localisation of the hydrogen-bond network in KOH-VI

Using a combination of ab initio crystal structure prediction and neutron diffraction techniques, we have solved the full structure of KOH-VI at 7 GPa. Rather than being orthorhombic and proton-ordered as had previously be proposed, we find that this high-pressure phase of potassium hydroxide is tetragonal (space group I4/mmm) and proton disordered. It has an unusual hydrogen bond topology, where the hydroxyl groups form isolated hydrogen-bonded square planar (OH){sub 4} units. This structure is stable above 6.5 GPa and, despite being macroscopically proton-disordered, local ice rules enforce microscopic order of the hydrogen bonds. We suggest the use of this novel type of structure to study concerted proton tunneling in the solid state, while the topology of the hydrogen bond network could conceivably be exploited in data storage applications based solely on the manipulations of hydrogen bonds. The unusual localisation of the hydrogen bond network under applied pressure is found to be favored by a more compact packing of the constituents in a distorted cesium chloride structure.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

Experience with dynamic resource provisioning of the CMS online cluster using a cloud overlay

The primary goal of the online cluster of the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) is to build event data from the detector and to select interesting collisions in the High Level Trigger (HLT) farm for offline storage. With more than 1500 nodes and a capacity of about 850 kHEPSpecInt06, the HLT machines represent similar computing capacity of all the CMS Tier1 Grid sites together. Moreover, it is currently connected to the CERN IT datacenter via a dedicated 160 Gbps network connection and hence can access the remote EOS based storage with a high bandwidth. In the last few years, a cloud overlay based on OpenStack has been commissioned to use these resources for the WLCG when they are not needed for data taking. This online cloud facility was designed for parasitic use of the HLT, which must never interfere with its primary function as part of the DAQ system. It also allows to abstract from the different types of machines and their underlying segmented networks. During the LHC technical stop periods, the HLT cloud is set to its static mode of operation where it acts like other grid facilities. The online cloud was also extended to make dynamic use of resources during periods between LHC fills. These periods are a-priori unscheduled and of undetermined length, typically of several hours, once or more a day. For that, it dynamically follows LHC beam states and hibernates Virtual Machines (VM) accordingly. Finally, this work presents the design and implementation of a mechanism to dynamically ramp up VMs when the DAQ load on the HLT reduces towards the end of the fill.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Optimizing Alabama’s CO 2 Storage in Shelby County (Project OASIS) - Deliverable Task 7: Risk Assessment

The “Optimizing Alabama’s CO 2 Storage in Shelby County: Project OASIS” CarbonSAFE Phase II Project seeks to build on regional data sets that demonstrate that the subsurface within Shelby County, Alabama has the potential to store commercial volumes of CO 2 safely, permanently, and economically. The primary target CO 2 Storage Complex is the deep Ketona Dolomite located within a 140 square mile area of the Valley and Ridge Region of Alabama. This deep saline reservoir is beneath a confining system encompassing at least 6,500 ft of shales and other low permeability sediments. Project OASIS drilled a deep stratigraphic test well to confirm the geological properties of the confining system and storage reservoir(s) within the Storage Complex. The geological data was incorporated into numerical models to establish the areal extent of the CO 2 plume and help design the storage site and its monitoring system. The project is managed by the Southern States Energy Board (SSEB), an interstate compact organization consisting of governors and state legislative leaders from sixteen southern states, Puerto Rico, and the U.S. Virgin Islands, as well as an appointee by the President of the United States. The organizational compact provides it with access to state government organizations and legislatures. The Board also maintains an Associate Members program comprised of energy resource companies, utilities, trade groups, academic R&D science and technology experts and energy consultants. Further, the SSEB staff is experienced in managing and coordinating complex energy and environmental programs, from research programs to full-scale design and demonstrations of new and innovative technologies. Project OASIS is a public-private partnership of six entities with multiple principal investigators (PIs). SSEB’s Lead PI and Co-PI are responsible for all aspects of project performance in accordance with the DOE-NETL Cooperative Agreement. SSEB has issued subgrants to Advanced Resources International, Inc., Alabama A&M University, Auburn University, Crescent Resource Innovation, and Oklahoma State University. Advanced Resources International, Inc., issued subgrants to Baker Hughes and Loudon Technical Services for field services

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2014

A New On-the-Fly Sampling Method for Incoherent Inelastic Thermal Neutron Scattering Data in MCNP6

At thermal energies, the scattering of neutrons in a system is complicated by the comparable velocities of the neutron and target, resulting in competing upscattering and downscattering events. The neutron wavelength is also similar in size to the target's interatomic spacing making the scattering process a quantum mechanical problem. Because of the complicated nature of scattering at low energies, the thermal data files in ACE format used in continuous-energy Monte Carlo codes are quite large { on the order of megabytes for a single temperature and material. In this paper, a new storage and sampling method is introduced that is orders of magnitude less in size and is used to sample scattering parameters at any temperature on-the-fly. In addition to the reduction in storage, the need to pre-generate thermal scattering data tables at fine temperatures has been eliminated. This is advantageous for multiphysics simulations which may involve temperatures not known in advance. A new module was written for MCNP6 that bypasses the current S(α,β) table lookup in favor of the new format. The new on-the-fly sampling method was tested for graphite for two benchmark problems at ten temperatures: 1) an eigenvalue test with a fuel compact of uranium oxycarbide fuel homogenized into a graphite matrix, 2) a surface current test with a \broomstick" problem with a monoenergetic point source. The largest eigenvalue difference was 152pcm for T= 1200K. For the temperatures and incident energies chosen for the broomstick problem, the secondary neutron spectrum showed good agreement with the traditional S(α,β) sampling method. These preliminary results show that sampling thermal scattering data on-the-fly is a viable option to eliminate both the storage burden of keeping thermal data at discrete temperatures and the need to know temperatures before simulation runtime.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2019

Crack Growth Rate and Large Plate Demonstration of Chloride-induced Stress Corrosion Cracking in Spent Nuclear Fuel Storage Canisters

This report describes the body of work involving testing and analyses performed in FY18 and FY19 at the Savannah River National Laboratory and at Korea University to determine chloride-induced stress corrosion crack (CISCC) growth rates in weldments of austenitic stainless steel plate material. The primary work involved: several separate crack growth rate test campaigns with new testing setups using laboratory-scale corrosion specimens; analyses to estimate the stress intensity factors for flaws postulated to be present in the residual stress fields of axial and circumferential weldments in a prototypic dry storage canister; and establishment of a “large plate” (approximately 51×46 cm with thickness 16 mm and weight about 30 kg) CISCC test that uses a plate with a circumferential weldment harvested from the Sandia National Laboratories’ full-size mockup dry storage canister. The tests for crack growth rate were conducted on ASTM E1861 bolt-load compact tension specimens in a setup designed to allow initially dried salt deposits to deliquesce and infuse the brine to the crack front under conditions relevant to the canister storage environments (e.g., temperature and humidity). The crack growth rate test results matched previous experimental data in the open literature. These literature data had been compiled by SNL and EPRI to develop a temperature-dependent (K-insensitive) crack growth rate model to support flaw disposition in the ASME Boiler and Pressure Vessel Section XI Code Case N-860, “Examination Requirements and Acceptance Standards for Spent Nuclear Fuel Storage and Transportation Containment Systems.” The knowledge of the salt, temperature, humidity conditions for CISCC including the threshold stress intensity factor, $K_{ISCC}$, were used to setup the large plate test in which a set of partthrough- wall and through-wall electrical discharge machined (EDM) defects were positioned in the weld residual stress field of the welded plate material from the mockup canister. A salt solution was applied to this plate specimen with an air-brush spray, then dried, and then exposed to a constant 75% RH condition at an ambient room temperature of 22 °C. The salt loading and environmental condition is expected to be aggressive to cause CISCC. The visual results at the surface of the plate show corrosion product staining (brown rust appearance) but with no CISCC emanating from the machined notches after approximately 5 months exposure to date. The plate test will continue in FY20 and phased-array ultrasonic testing and other NDE techniques will be applied to identify and characterize CISCC that may emanate from the machined defects. The notches and any CISCC from them will be sectioned at the conclusion of the test to verify NDE characterization, and to develop effective through-wall crack growth rates from cracks that would likely be branched.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2017

Grid site availability evaluation and monitoring at CMS

The Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) uses distributed grid computing to store, process, and analyse the vast quantity of scientific data recorded every year. The computing resources are grouped into sites and organized in a tiered structure. Each site provides computing and storage to the CMS computing grid. Over a hundred sites worldwide contribute with resources from hundred to well over ten thousand computing cores and storage from tens of TBytes to tens of PBytes. In such a large computing setup scheduled and unscheduled outages occur continually and are not allowed to significantly impact data handling, processing, and analysis. Unscheduled capacity and performance reductions need to be detected promptly and corrected. CMS developed a sophisticated site evaluation and monitoring system for Run 1 of the LHC based on tools of the Worldwide LHC Computing Grid. For Run 2 of the LHC the site evaluation and monitoring system is being overhauled to enable faster detection/reaction to failures and a more dynamic handling of computing resources. Furthermore, enhancements to better distinguish site from central service issues and to make evaluations more transparent and informative to site support staff are planned.

43 PARTICLE ACCELERATORS↗
DOE OSTI2019

Ultrafast processing of pixel detector data with machine learning frameworks

Modern photon science performed at high repetition rate free-electron laser (FEL) facilities and beyond relies on 2D pixel detectors operating at increasing frequencies (towards 100 kHz at LCLS-II) and producing rapidly increasing amounts of data (towards TB/s). This data must be rapidly stored for offline analysis and summarized in real time for online feedback to the scientists. While at LCLS all raw data has been stored, at LCLS-II this would lead to a prohibitive cost; instead, enabling real time processing of pixel detector data (dark, gain, common mode, background, charge summing, subpixel position, photon counting, data summarization) allows reducing the size and cost of online processing, offline processing and storage by orders of magnitude while preserving full photon information. This could be achieved by taking advantage of the compressibility of sparse data typical for LCLS-II applications. Faced with a similar big data challenge a decade ago, computer vision stimulated revolutionary advances in machine learning hardware and software. We investigated if these developments are useful in the field of data processing for high speed pixel detectors and found that typical deep learning models and autoencoder architectures failed to yield useful noise reduction while preserving full photon information, presumably because of the very different statistics and feature sets in computer vision and radiation imaging. However, the raw performance of modern frameworks like Tensorflow inspired us to redesign in Tensorflow mathematically equivalent versions of the state-of-the-art, “classical” algorithms used at LCLS. The novel Tensorflow models resulted in elegant, compact and hardware agnostic code, gaining 1 to 2 orders of magnitude faster processing on an inexpensive consumer GPU, reducing by 3 orders of magnitude the projected cost of online analysis and compression without photon loss at LCLS-II. The novel Tensorflow models also enabled ongoing development of a pipelined hardware system expected to yield an additional 3 to 4 orders of magnitude speedup, necessary for meeting the data acquisition and storage requirements at LCLS-II, potentially enabling acquiring every single FEL pulse at full speed. Computer vision a decade ago was dominated by hand-crafted filters; their structure inspired the deep learning revolution resulting in modern deep convolutional networks; similarly, our novel Tensorflow filters provide inspiration for designing future deep learning models for ultrafast and efficient processing and classification of pixel detector images at FEL facilities.

47 OTHER INSTRUMENTATION↗