SEARCH · Search NASA
Results for “Fast pattern recognition”
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.
A low-latency graph computer to identify metastable particles at the Large Hadron Collider for real-time analysis of potential dark matter signatures
Abstract Image recognition is a pervasive task in many information-processing environments. We present a solution to a difficult pattern recognition problem that lies at the heart of experimental particle physics. Future experiments with very high-intensity beams will produce a spray of thousands of particles in each beam-target or beam-beam collision. Recognizing the trajectories of these particles as they traverse layers of electronic sensors is a massive image recognition task that has never been accomplished in real time. We present a real-time processing solution that is implemented in a commercial field-programmable gate array using high-level synthesis. It is an unsupervised learning algorithm that uses techniques of graph computing. A prime application is the low-latency analysis of dark-matter signatures involving metastable charged particles that manifest as disappearing tracks.
Block segmentation in feature space for realtime object detection in high granularity images
Computer vision has applications in object detection, image recognition and classification, and object tracking. One of the challenges of computer vision is the presence of useful information at multiple distance scales. Filtering techniques may sacrifice details at small scales in order to prioritize the analysis of large-scale features of the image. We present a strategy for coarse-graining multidimensional data while maintaining fine-grained detail for subsequent analysis. The algorithm is based on fixed-size block segmentation in the feature space. We apply this strategy to solve the long-standing challenge of detecting particle trajectories at the Large Hadron Collider in real time.
Development, construction and qualification tests of the mechanical structures of the electromagnetic calorimeter of the Mu2e experiment at Fermilab
The “muon-to-electron conversion” (Mu2e) experiment at Fermilab will search for the Charged Lepton Flavour Violating neutrino-less coherent conversion of a muon into an electron in the field of an aluminum nucleus. The observation of this process would be the unambiguous evidence of physics beyond the Standard Model. Mu2e detectors comprise a straw-tracker, an electromagnetic calorimeter and an external veto for cosmic rays. The calorimeter provides excellent electron identification, complementary information to aid pattern recognition and track reconstruction, and a fast calorimetric online trigger. The detector has been designed as a state-of-the-art crystal calorimeter and employs 1340 pure Cesium Iodide (CsI) crystals readout by UV-extended silicon photosensors and fast front-end and digitization electronics. A design consisting of two identical annular matrices (named “disks”) positioned at the relative distance of 70 cm downstream the aluminum target along the muon beamline satisfies the Mu2e physics requirements.The hostile Mu2e operational conditions, in terms of radiation levels (total ionizing dose of 12 krad and a neutron fluence of 5x1010 n/cm2 @ 1 MeVeq (Si)/y), magnetic field intensity (1 T) and vacuum level (10$^{-4}$ Torr) have posed tight constraints on the design of the detector mechanical structures and materials choice. The support structure of the two 670 crystal matrices employs two aluminum hollow rings and parts made of open-cell vacuum-compatible carbon fiber. The photosensors and service front-end electronics for each crystal are assembled in a unique mechanical unit inserted in a machined copper holder. The 670 units are supported by a machined plate made of vacuum-compatible plastic material. The plate also integrates the cooling system made of a network of copper lines flowing a low temperature radiation-hard fluid and placed in thermal contact with the copper holders to constitute a low resistance thermal bridge. The data acquisition electronics is hosted in aluminum custom crates positioned on the external lateral surface of the two disks. The crates also integrate the electronics cooling system as lines running in parallel to the front-end system.The constraints on the calorimeter mechanical structures design, the development from the conceptual design to the specifications of all the structural components, the status of components production and the components quality assurance tests are presented.
Development, construction and tests of the Mu2e electromagnetic calorimeter mechanical structures
The “muon-to-electron conversion” (Mu2e) experiment at Fermilab will search for the charged lepton flavour violating neutrino-less coherent conversion of a muon into an electron in the field of an aluminum nucleus. The observation of this process would be the unambiguous evidence of the existence of physics beyond the standard model. Mu2e detectors comprise a straw-tracker, an electromagnetic calorimeter and an external veto for cosmic rays. In particular, the calorimeter provides excellent electron identification, a fast calorimetric online trigger, and complementary information to aid pattern recognition and track reconstruction. The detector has been designed as a state-of-the-art crystal calorimeter and employs 1348 pure Cesium Iodide (CsI) crystals readout by UV-extended silicon photosensors and fast front-end and digitization electronics. A design consisting of two identical annular matrices (named “disks”) positioned at the relative distance of 70 cm downstream the aluminum target along the muon beamline satisfies the Mu2e physics requirements. The hostile Mu2e operational conditions, in terms of radiation levels (total expected ionizing dose of 12 krad and a neutron fluence of 5 × 10$^{10}$ n/cm$^{2}$ @ 1 MeV$_{eq}$ (Si)/y), magnetic field intensity (1 T) and vacuum level (10$^{-4}$ Torr) have posed tight constraints on scintillating materials, sensors, electronics and on the design of the detector mechanical structures and material choice. The support structure of each 674 crystal matrix is composed of an aluminum hollow ring and parts made of open-cell vacuum-compatible carbon fiber. The photosensors and front-end electronics for the readout of each crystal are inserted in a machined copper holder and make a unique mechanical unit. The resulting 674 mechanical units are supported by a machined plate of vacuum-compatible plastic material. The plate also integrates the cooling system made of a network of copper lines flowing a low temperature radiation-hard fluid and placed in thermal contact with the copper holders to constitute a low resistance thermal bridge. The data acquisition electronics are hosted in aluminum custom crates positioned on the external lateral surface of the disks. The crates also integrate the electronics cooling system as lines running in parallel to the front-end system. In this paper we report on the calorimeter mechanical structure design, the mechanical and thermal simulations that have determined the design technological choices, and the status of component production, quality assurance tests and plans for assembly at Fermilab.
MPGD Trackers in the ePIC Detector at the EIC
The future Electron-Ion Collider (EIC) at Brookhaven National Laboratory will collide polarized electrons with polarized proton/ions. The electron ? Proton / Ion Collider (ePIC) Experiment is the EIC general-purpose detector aiming at delivering the full physics program of the EIC. This unique environment imposes stringent requirements on the tracking system needed for the measurement of the scattered electron and charged particles produced in the collisions at the EIC. The central tracker of the ePIC detector has silicon layers for tracking and vertexing based on MAPS technology, which are complemented by large Micro-Pattern Gaseous Detector (MPGD) trackers in the barrel and in both the electron and hadron end cap regions. The MPGD layers provide fast timing (10-20 ns) and additional hit points (150 µm) for pattern recognition during track finding. Two MPGD technologies are used in ePIC central trackers: cylindrical Micromegas for the barrel inner tracker and planar thin-gap GEM-µRWELL hybrid detector for the barrel outer tracker and the end cap disks. In this talk, we will introduce these two technologies in the context of ePIC and we will discuss the ongoing R&D efforts to address the requirements. Finally, we will discuss the plans and timeline for the production and testing and commissioning of the MPGD trackers for the installation in the ePIC detector.
The ATLAS Fast TracKer system
The ATLAS Fast TracKer (FTK) was designed to provide full tracking for the ATLAS high-level trigger by using pattern recognition based on Associative Memory (AM) chips and fitting in high-speed field programmable gate arrays. The tracks found by the FTK are based on inputs from all modules of the pixel and silicon microstrip trackers. The as-built FTK system and components are described, as is the online software used to control them while running in the ATLAS data acquisition system. Also described is the simulation of the FTK hardware and the optimization of the AM pattern banks. An optimization for long-lived particles with large impact parameter values is included. A test of the FTK system with the data playback facility that allowed the FTK to be commissioned during the shutdown between Run 2 and Run 3 of the LHC is reported. The resulting tracks from part of the FTK system covering a limited $\eta$-$\phi$ region of the detector are compared with the output from the FTK simulation. It is shown that FTK performance is in good agreement with the simulation.
Distributed non-negative matrix factorization with determination of the number of latent features
The holistic analysis and understanding of the latent (that is, not directly observable) variables and patterns buried in large datasets is crucial for data-driven science, decision making and emergency response. Such exploratory analyses require devising unsupervised learning methods for data mining and extraction of the latent features, and non-negative matrix factorization (NMF) is one of the prominent such methods. NMF is based on compute-intense non-convex constrained minimization, which, for large datasets requires fast and distributed algorithms. However, current parallel implementations of NMF fail to estimate the number of latent features. In practice, identifying these features is both difficult and significant for pattern recognition and latent feature analysis, especially for large dense matrices. Here, we introduce a distributed NMF algorithm coupled with distributed custom clustering followed by a stability analysis on dense data, which we call DnMFk, to determine the number of latent variables. The results on synthetic data and the classical Swimmer data set demonstrate the accuracy of model determination while scaling nearly linearly across multiple processors for large data. Further, we employ DnMFk to determine the number of hidden features from a terabyte matrix.
Feed status and skin injury modulate immunopathology, global gene expression, and survival in channel catfish during virulent Aeromonas hydrophila infection
Introduction VirulentAeromonas hydrophilais a major pathogen in channel catfish (Ictalurus punctatus), that causes motileAeromonassepticemia and significant economic losses. We investigated the effect of feeding status and skin integrity on the host immune response, disease survival, and gastrointestinal pathology following a vAh challenge. Methods Using a bath immersion model, channel catfish were divided into four treatment groups: fin clipped and fed (FCF), fin clipped but not fed (FCN), not fin clipped but fed (NCF), and not fin clipped nor fed (NCN) alongside non-challenged control groups The FCF and NCF groups were fed 2 h prior to the challenge, but the FCN and NCN groups were not. Survival analysis, histopathological assessment, and RNA sequencing were conducted across groups at different time intervals throughout the vAh challenge. Results Survival rates were lowest in the FCF and FCN groups (30% and 23% survival, respectively), suggesting that both feeding and skin damage contributed to disease severity. Histopathological analyses revealed more severe intestinal and gastric lesions in fed groups, characterized by epithelial necrosis, hemorrhage, and edema. Transcriptomic analysis among the groups identified significant differentially expressed genes associated with inflammation, apoptosis, and metabolic stress, with notable upregulation of interleukin 1-beta (il-1β), and complement C3 (c3). Gene ontology enrichment highlighted distinct immune activation patterns between fed and unfed groups, with enhanced pathogen recognition and pro-inflammatory responses in unfed fish. Discussion These findings suggest feeding prior to infection may exacerbate disease pathology, potentially by creating a physiological state conducive to facilitate pathogen proliferation and dampened early immune responses, whereas short-term fasting appears to promote early immune activation. This study provides novel insights into the complex interplay between feed status, physical injury, and immune response to vAh infection.
Integration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure
Quantum materials research requires co-design of theory with experiments and involves demanding simulations and the analysis of vast quantities of data, usually including pattern recognition and clustering. Artificial intelligence is a natural route to optimise these processes and bring theory and experiments together. Here, we propose a scheme that integrates machine learning with high-performance simulations and scattering measurements, covering the pipeline of typical neutron experiments. Our approach uses nonlinear autoencoders trained on realistic simulations along with a fast surrogate for the calculation of scattering in the form of a generative model. We demonstrate this approach in a highly frustrated magnet, Dy 2 Ti 2 O 7 , using machine learning predictions to guide the neutron scattering experiment under hydrostatic pressure, extract material parameters and construct a phase diagram. Our scheme provides a comprehensive set of capabilities that allows direct integration of theory along with automated data processing and provides on a rapid timescale direct insight into a challenging condensed matter system.
Validation of the Sentinel-5 Precursor TROPOMI cloud data with Cloudnet, Aura OMI O 2 –O 2 , MODIS, and Suomi-NPP VIIRS
Accurate knowledge of cloud properties is essential to the measurement of atmospheric composition from space. In this work we assess the quality of the cloud data from three Copernicus Sentinel-5 Precursor (S5P) TROPOMI cloud products: (i) S5P OCRA/ROCINN_CAL (Optical Cloud Recognition Algorithm/Retrieval of Cloud Information using Neural Networks;Clouds-As-Layers), (ii) S5P OCRA/ROCINN_CRB (Clouds-as-Reflecting Boundaries), and (iii) S5P FRESCO-S (Fast Retrieval Scheme for Clouds from Oxygen absorption bands – Sentinel). Target properties of this work are cloud-top height and cloud optical thickness (OCRA/ROCINN_CAL), cloud height (OCRA/ROCINN_CRB and FRESCO-S), and radiometric cloud fraction (all three algorithms). The analysis combines (i) the examination of cloud maps for artificial geographical patterns, (ii) the comparison to other satellite cloud data (MODIS, NPP-VIIRS, and OMI O2–O2), and (iii) ground-based validation with respect to correlative observations (30 April 2018 to 27 February 2020) from the Cloudnet network of ceilometers, lidars, and radars. Zonal mean latitudinal variation of S5P cloud properties is similar to that of other satellite data. S5P OCRA/ROCINN_CAL agrees well with NPP VIIRS cloud-top height and cloud optical thickness and with Cloudnet cloud-top height, especially for the low (mostly liquid) clouds. For the high clouds, S5P OCRA/ROCINN_CAL cloud-top height is below the cloud-top height of VIIRS and of Cloudnet, while its cloud optical thickness is higher than that of VIIRS. S5P OCRA/ROCINN_CRB and S5P FRESCO cloud height are well below the Cloudnet cloud mean height for the low clouds but match on average better with the Cloudnet cloud mean height for the higher clouds. As opposed to S5P OCRA/ROCINN_CRB and S5P FRESCO, S5P OCRA/ROCINN_CAL is well able to match the lowest CTH mode of the Cloudnet observations. Peculiar geographical patterns are identified in the cloud products and will be mitigated in future releases of the cloud data products.
Charged particle tracking with quantum annealing optimization
Abstract At the High Luminosity Large Hadron Collider (HL-LHC), traditional track reconstruction techniques that are critical for physics analysis will need to be upgraded to scale with track density. Quantum annealing has shown promise in its ability to solve combinatorial optimization problems amidst an ongoing effort to establish evidence of a quantum speedup. As a step towards exploiting such potential speedup, we investigate a track reconstruction approach by adapting the existing geometric Denby-Peterson (Hopfield) network method to the quantum annealing framework for HL-LHC conditions. We develop additional techniques to embed the problem onto existing and near-term quantum annealing hardware. Results using simulated annealing and quantum annealing with the D-Wave 2X system on the TrackML open dataset are presented, demonstrating the successful application of a quantum annealing algorithm to the track reconstruction challenge. We find that combinatorial optimization problems can effectively reconstruct tracks, suggesting possible applications for fast hardware-specific implementations at the HL-LHC while leaving open the possibility of a quantum speedup for tracking.
Comparison of measurement and simulation of ATLAS cavern radiation background
Sixteen Medipix2 pixel detector based (MPX) devices were operated at various positions within the ATLAS detector and cavern continuously from early 2008 up to 2013. In addition to photons, each MPX detector is capable to detect charged particles, and neutrons as it is covered with a mask of converter materials dividing its area into regions sensitive to thermal or fast neutrons. The MPX detector network was effectively used for real-time measurements of the spectral characteristics and composition of complex radiation fields in ATLAS. This article reports comparison of the results of measurements performed with MPX detectors during the LHC operation period in 2010 and 2011 with Monte Carlo simulations results from the FLUGG and GCALOR codes. For the purpose of this comparison, the MPX detectors were operated in tracking mode with low threshold (8–10 keV) allowing one to distinguish among particle categories based on the recognition of track patterns left by the particles in the MPX sensitive layer. The comparison of measurements with simulations shows that the agreement between measured and simulated data is satisfactory in most cases within a factor of two.
Power quality disturbances diagnosis: A 2D densely connected convolutional network framework
The fast and accurate diagnosis of power quality disturbances (PQD) aids in avoiding shutdowns and unnecessary procedures, concerning electric energy distribution systems. As such, a number of techniques have been tested and applied in order to reach this objective. Majority of the techniques applied are two-step based. On the first step, power quality disturbances features are extracted. Second step, considering features extracted, disturbance classification is implemented. Recently, relevant literature has presented data-driven signal processing-based approaches, as deep convolutional neural networks (DCNN), which can implement both processing steps while providing automated recognition of patterns and outliers in data. However, not considered by state-of-art, power quality disturbances are evolving in nature, while all possible regularities might not be represented in the dataset. In this work a 2 Dimension Densely Connected Convolutional Network (2D-DenseNet) framework is presented. Further, a case study with synthetic disturbance events are analyzed. Easy-to-implement formulation, built on the 2D-DenseNet, without hard-to-design parameters, highlight potential aspects for real-life implementation.
A Deep Learning Modeling Framework to Capture Mixing Patterns in Reactive-Transport Systems
Prediction and control of chemical mixing are vital for many scientific areas such as subsurface reactive transport, climate modeling, combustion, epidemiology, and pharmacology. Due to the complex nature of mixing in heterogeneous and anisotropic media, the mathematical models related to this phenomenon are not analytically tractable. Numerical simulations often provide a viable route to predict chemical mixing accurately. However, contemporary modeling approaches for mixing cannot utilize available spatial-temporal data to improve the accuracy of the future prediction and can be compute-intensive, especially when the spatial domain is large and for long-term temporal predictions. To address this knowledge gap, in this work we will present in this paper a deep learning (DL) modeling framework applied to predict the progress of chemical mixing under fast bimolecular reactions. This framework uses convolutional neural networks (CNN) for capturing spatial patterns and long short-term memory (LSTM) networks for forecasting temporal variations in mixing. By careful design of the framework—placement of non-negative constraint on the weights of the CNN and the selection of activation function, the framework ensures non-negativity of the chemical species at all spatial points and for all times. Our DL-based framework is fast, accurate, and requires minimal data for training. The time needed to obtain a forecast using the model is a fraction (≈ O(-6)) of the time needed to obtain the result using a high-fidelity simulation. To achieve an error of 10% (measured using the infinity norm) for capturing local-scale mixing features such as interfacial mixing, only 24% to 32% of the sequence data for model training is required. To achieve the same level of accuracy for capturing global-scale mixing features, the sequence data required for model training is 64% to 70% of the total spatial-temporal data. Hence, the proposed approach—a fast and accurate way to forecast long-time spatial-temporal mixing patterns in heterogeneous and anisotropic media—will be a valuable tool for modeling reactive-transport in a wide range of applications.
Stabilization of the 81-channel coherent beam combination using machine learning
We develop a rapidly converging algorithm for stabilizing a large channel-count diffractive optical coherent beam combination. An 81-beam combiner is controlled by a novel, machine-learning based, iterative method to correct the optical phases, operating on an experimentally calibrated numerical model. A neural-network is trained to detect phase errors based on interference pattern recognition of uncombined beams adjacent to the combined one. Due to the non-uniqueness of solutions in the full space of possible phases, the network is trained within a limited phase perturbation/error range. This also reduces the number of samples needed for training. Simulations have proven that the network can converge in one step for small phase perturbations. When the trained neural-network is applied to a realistic case of 360 degree full range, an iterative scheme exploits random walking at the beginning, with the accuracy of prediction on phase feedback direction, to allow the neural-network to step into the training range for fast convergence. This neural-network-based iterative method of phase detection works tens of times faster than the commonly used stochastic parallel gradient descent approach (SPGD) using a single-detector and random dither when both are tested with random phase perturbations.
Distilling particle knowledge for fast reconstruction at high-energy physics experiments
Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. Its main application is the compactification of large deep neural networks to free up computational resources, in particular on edge devices. In this article, we consider proton-proton collisions at the High-Luminosity Large Hadron Collider (HL-LHC) and demonstrate a successful knowledge transfer from an event-level graph neural network (GNN) to a particle-level small deep neural network (DNN). Our algorithm, DistillNet, is a DNN that is trained to learn about the provenance of particles, as provided by the soft labels that are the GNN outputs, to predict whether or not a particle originates from the primary interaction vertex. The results indicate that for this problem, which is one of the main challenges at the HL-LHC, there is minimal loss during the transfer of knowledge to the small student network, while improving significantly the computational resource needs compared to the teacher. This is demonstrated for the distilled student network on a CPU, as well as for a quantized and pruned student network deployed on a field programmable gate array. Our study proves that knowledge transfer between networks of different complexity can be used for fast artificial intelligence (AI) in high-energy physics that improves the expressiveness of observables over non-AI-based reconstruction algorithms. Such an approach can become essential at the HL-LHC experiments, e.g. to comply with the resource budget of their trigger stages.
Artifact identification in X-ray diffraction data using machine learning methods
In situ synchrotron high-energy X-ray powder diffraction (XRD) is highly utilized by researchers to analyze the crystallographic structures of materials in functional devices ( e.g. battery materials) or in complex sample environments ( e.g. diamond anvil cells or syntheses reactors). An atomic structure of a material can be identified by its diffraction pattern along with a detailed analysis of the Rietveld refinement which yields rich information on the structure and the material, such as crystallite size, microstrain and defects. For in situ experiments, a series of XRD images is usually collected on the same sample under different conditions ( e.g. adiabatic conditions) yielding different states of matter, or is simply collected continuously as a function of time to track the change of a sample during a chemical or physical process. In situ experiments are usually performed with area detectors and collect images composed of diffraction patterns. For an ideal powder, the diffraction pattern should be a series of concentric Debye–Scherrer rings with evenly distributed intensities in each ring. For a realistic sample, one may observe different characteristics other than the typical ring pattern, such as textures or preferred orientations and single-crystal diffraction spots. Textures or preferred orientations usually have several parts of a ring that are more intense than the rest, whereas single-crystal diffraction spots are localized intense spots owing to diffraction of large crystals, typically >10 µm. In this work, an investigation of machine learning methods is presented for fast and reliable identification and separation of the single-crystal diffraction spots in XRD images. The exclusion of artifacts during an XRD image integration process allows a precise analysis of the powder diffraction rings of interest. When it is trained with small subsets of highly diverse datasets, the gradient boosting method can consistently produce high-accuracy results. The method dramatically decreases the amount of time spent identifying and separating single-crystal diffraction spots in comparison with the conventional method.