Search NASA⌕ Search

SEARCH · Search NASA

Results for “Convolution”

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 1,423 records · Page 79

Is the surface oxygen exchange rate linked to bulk ion diffusivity in mixed conducting Ruddlesden–Popper phases?

There is a possible link between oxygen surface exchange rate and bulk oxygen anion diffusivity in mixed ionic and electronic conducting oxides; it is a topic of great interest and debate. While a large body of experimental evidence and theoretical analyses support a link, observed differences between bulk and surface composition of these materials are hard to reconcile with this observation. This is further compounded by potential problems with simultaneous measurement of both parameters. Here we utilize separate techniques, in situ neutron diffraction and pulsed isotopic surface exchange, to examine bulk ion mobility and surface oxygen exchange rates of three Ruddlesden-Popper phases, general form A n-1 A 2 'BnO 3n+1 , A n-1 A 2 'BnX 3n+1 ; LaSrCo 0.5 Fe 0.5 O 4-δ (n = 1), La 0.3 Sr 2.7 CoFeO 7-δ (n = 2) and LaSr 3 Co 1.5 Fe 1.5 O 10-δ (n = 3). These measurements are complemented by surface composition determination via high sensitivity-low energy ion scattering. We observe a correlation between bulk ion mobility and surface exchange rate between materials. The surface exchange rates vary by more than one order of magnitude with high anion mobility in the bulk of an oxygen vacancy-rich n = 2 Ruddlesden-Popper material correlating with rapid oxygen exchange. Furthermore this is in contrast with the similar surface exchange rates which we may expect due to similar surface compositions across all three samples. This paper conclude that experimental limitations lead to inherent convolution of surface and bulk rates, and that surface exchange steps are not likely to be rate limiting in oxygen incorporation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Dissolution kinetics of a sodium borosilicate glass in Tris buffer solutions: impact of Tris concentration and acid (HCl/HNO 3 ) identity

Here, understanding the corrosion behavior of glasses in near-neutral environments is crucial for many technologies including glasses for regenerative medicine and nuclear waste immobilization. To maintain consistent pH values throughout experiments in the pH = 7 to 9 regime, buffer solutions containing tris(hydroxymethyl)aminomethane (“Tris”, or sometimes called THAM) are recommended in ISO standards 10993-14 and 23317 for evaluating biomaterial degradation and utilized throughout glass dissolution behavior literature—a key advantage being the absence of dissolved alkali/alkaline earth cations (i.e. Na + or Ca 2+ ) that can convolute experimental results due to solution feedback effects. Although Tris is effective at maintaining the solution pH, it has presented concerns due to the adverse artificial effects it produces while studying glass corrosion, especially in borosilicate glasses. Therefore, many open questions still remain on the topic of borosilicate glass interaction with Tris-based solutions. We have approached this topic by studying the dissolution behavior of a sodium borosilicate glass in a wide range of Tris-based solutions at 65 °C with varied acid identity (Tris–HCl vs. Tris–HNO 3 ), buffer concentration (0.01 M to 0.5 M), and pH (7–9). The results have been discussed in reference to previous studies on this topic and the following conclusions have been made: (i) acid identity in Tris-based solutions does not exhibit a significant impact on the dissolution behavior of borosilicate glasses, (ii) ~0.1 M Tris-based solutions are ideal for maintaining solution pH in the absence of obvious undesirable solution chemistry effects, and (iii) Tris–boron complexes can form in solution as a result of glass dissolution processes. The complex formation, however, exhibits a distinct temperature-dependence, and requires further study to uncover the precise mechanisms by which Tris-based solutions impact borosilicate glass dissolution behavior.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ChemPix: automated recognition of hand-drawn hydrocarbon structures using deep learning

Inputting molecules into chemistry software, such as quantum chemistry packages, currently requires domain expertise, expensive software and/or cumbersome procedures. Leveraging recent breakthroughs in machine learning, we develop ChemPix: an offline, hand-drawn hydrocarbon structure recognition tool designed to remove these barriers. A neural image captioning approach consisting of a convolutional neural network (CNN) encoder and a long short-term memory (LSTM) decoder learned a mapping from photographs of hand-drawn hydrocarbon structures to machine-readable SMILES representations. We generated a large auxiliary training dataset, based on RDKit molecular images, by combining image augmentation, image degradation and background addition. Additionally, a small dataset of ~600 hand-drawn hydrocarbon chemical structures was crowd-sourced using a phone web application. These datasets were used to train the image-to-SMILES neural network with the goal of maximizing the hand-drawn hydrocarbon recognition accuracy. By forming a committee of the trained neural networks where each network casts one vote for the predicted molecule, we achieved a nearly 10 percentage point improvement of the molecule recognition accuracy and were able to assign a confidence value for the prediction based on the number of agreeing votes. The ensemble model achieved an accuracy of 76% on hand-drawn hydrocarbons, increasing to 86% if the top 3 predictions were considered.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Resolving buried optoelectronic features in metal halide perovskites via modulation spectroscopy studies

As research on both bulk and low dimensional metal halide perovskites (MHPs) continues to grow, the tools necessary to gain insights into their exotic and highly convoluted optoelectronic features must also expand. Electroabsorption (EA) is a modulation spectroscopy technique that is exceptionally valuable at deconvoluting overlapping spectral features as well as discerning between different electronic environments in semiconductors. This review outlines the critical shortcomings of traditional optical spectroscopy in determining essential properties such as the bandgap and exciton binding energy. In this report we provide a brief overview of the working principles of EA, focusing on the differences between bound and unbound charge carriers that result in unique behavior when interacting with an applied electric field. We discuss key studies highlighting the unique characterization available when coupling EA spectroscopy with traditional steady-state optical tools to investigate interesting and complex optical features in MHPs. We conclude that EA is a crucial tool for pushing the boundaries of our understanding of the optoelectronic properties of MHP thin films. When other optical characterization methods fall short in the richness of data provided, EA can bridge the knowledge gap to provide a complete optoelectronic characterization of novel MHPs and deepen the understanding of current structures and compositions as a function of their structural and morphological dimensionality.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Seeking regularity from irregularity: unveiling the synthesis–nanomorphology relationships of heterogeneous nanomaterials using unsupervised machine learning

Nanoscale morphology of functional materials determines their chemical and physical properties. However, despite increasing use of transmission electron microscopy (TEM) to directly image nanomorphology, it remains challenging to quantify the information embedded in TEM data sets, and to use nanomorphology to link synthesis and processing conditions to properties. We develop an automated, descriptor-free analysis workflow for TEM data that utilizes convolutional neural networks and unsupervised learning to quantify and classify nanomorphology, and thereby reveal synthesis–nanomorphology relationships in three different systems. While TEM records nanomorphology readily in two-dimensional (2D) images or three-dimensional (3D) tomograms, we advance the analysis of these images by identifying and applying a universal shape fingerprint function to characterize nanomorphology. After dimensionality reduction through principal component analysis, this function then serves as the input for morphology grouping through unsupervised learning. We demonstrate the wide applicability of our workflow to both 2D and 3D TEM data sets, and to both inorganic and organic nanomaterials, including tetrahedral gold nanoparticles mixed with irregularly shaped impurities, hybrid polymer-patched gold nanoprisms, and polyamide membranes with irregular and heterogeneous 3D crumple structures. In each of these systems, unsupervised nanomorphology grouping identifies both the diversity and the similarity of the nanomaterial across different synthesis conditions, revealing how synthetic parameters guide nanomorphology development. Our work opens possibilities for enhancing synthesis of nanomaterials through artificial intelligence and for understanding and controlling complex nanomorphology, both for 2D systems and in the far less explored case of 3D structures, such as those with embedded voids or hidden interfaces.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Creating ground truth for nanocrystal morphology: a fully automated pipeline for unbiased transmission electron microscopy analysis

Control over colloidal nanocrystal morphology (size, size distribution, and shape) is important for tailoring the functionality of individual nanocrystals and their ensemble behavior. Despite this, traditional methods to quantify nanocrystal morphology are laborious. New developments in automated morphology classification will accelerate these analyses but the assessment of machine learning models is limited by human accuracy for ground truth, causing even unsupervised machine learning models to have inherent bias. Herein, we introduce synthetic image rendering to solve the ground truth problem of nanocrystal morphology classification. By simulating 2D images of nanocrystal shapes via a function of high-dimensional parameter space, we trained a convolutional neural network to link unique morphologies to their simulated parameters, defining nanocrystal morphology quantitatively rather than qualitatively. An automated pipeline then processes, quantitatively defines, and classifies nanocrystal morphology from experimental transmission electron microscopy (TEM) images. Using improved computer vision techniques, 42,650 nanocrystals were identified, assessed, and labeled with quantitative parameters, offering a 600-fold improvement in efficiency over best-practice manual measurements. Further, a classification algorithm was trained with a prediction accuracy of 99.5%, which can successfully analyze a range of concave, convex, and irregular nanocrystal shapes. The resulting pipeline was applied to differentiating two syntheses of nominally cuboidal CsPbBr 3 nanocrystals and uniquely classifying binary nickel sulfide nanocrystal phase based on morphology. This pipeline provides a simple, efficient, and unbiased method to quantify nanocrystal morphology and represents a practical route to construct large datasets with an absolute ground truth for training unbiased morphology-based machine learning algorithms.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Deep‐learning‐based power distribution network switch action identification leveraging dynamic features of distributed energy resources

This study proposes a data‐driven approach for identifying switch actions in power distribution networks. Simulated micro‐phasor measurement unit data is utilised to train a convolutional neural network (CNN) model. The trained CNN model can identify multi‐phase multi‐switch actions. Instead of working as a blackbox, the proposed approach extracts the features from the hidden layers of the trained CNN for engineering interpretation and error check. In addition, a random‐forest‐based feature ranking algorithm is proposed to identify the most important features. The proposed approach is validated on the IEEE 123‐node feeder modelled in GridLAB‐D. The CNN model is built and trained using TensorFlow. The proposed approach achieves 96.57% identification accuracy.

42 ENGINEERING↗

Planck 2013 results. V. LFI calibration

We discuss the methods employed to photometrically calibrate the data acquired by the Low Frequency Instrument on Planck. Our calibration is based on a combination of the orbital dipole plus the solar dipole, caused respectively by the motion of the Planck spacecraft with respect to the Sun and by motion of the solar system with respect to the cosmic microwave background (CMB) rest frame. The latter provides a signal of a few mK with the same spectrum as the CMB anisotropies and is visible throughout the mission. In this data releasewe rely on the characterization of the solar dipole as measured by WMAP. We also present preliminary results (at 44 GHz only) on the study of the Orbital Dipole, which agree with the WMAP value of the solar system speed within our uncertainties. We compute the calibration constant for each radiometer roughly once per hour, in order to keep track of changes in the detectors’ gain. Since non-idealities in the optical response of the beams proved to be important, we implemented a fast convolution algorithm which considers the full beam response in estimating the signal generated by the dipole. Moreover, in order to further reduce the impact of residual systematics due to sidelobes, we estimated time variations in the calibration constant of the 30 GHz radiometers (the ones with the largest sidelobes) using the signal of an internal reference load at 4 K instead of the CMB dipole. We have estimated the accuracy of the LFI calibration following two strategies: (1) we have run a set of simulations to assess the impact of statistical errors and systematic effects in the instrument and in the calibration procedure; and (2) we have performed a number of internal consistency checks on the data and on the brightness temperature of Jupiter. Errors in the calibration of this Planck/LFI data release are expected to be about 0.6% at 44 and 70 GHz, and 0.8% at 30 GHz. Both these preliminary results at low and high ℓ are consistent with WMAP results within uncertainties and comparison of power spectra indicates good consistency in the absolute calibration with HFI (0.3%) and a 1.4σ discrepancy with WMAP (0.9%).

79 ASTRONOMY AND ASTROPHYSICS↗

Planck 2013 results. VII. HFI time response and beams

This paper characterizes the effective beams, the effective beam window functions and the associated errors for the Planck High Frequency Instrument (HFI) detectors. The effective beam is the angular response including the effect of the optics, detectors, data processing and the scan strategy. The window function is the representation of this beam in the harmonic domain which is required to recover an unbiased measurement of the cosmic microwave background angular power spectrum. The HFI is a scanning instrument and its effective beams are the convolution of: a) the optical response of the telescope and feeds; b) the processing of the time-ordered data and deconvolution of the bolometric and electronic transfer function; and c) the merging of several surveys to produce maps. The time response transfer functions are measured using observations of Jupiter and Saturn and by minimizing survey difference residuals. The scanning beam is the post-deconvolution angular response of the instrument, and is characterized with observations of Mars. The main beam solid angles are determined to better than 0.5% at each HFI frequency band. Observations of Jupiter and Saturn limit near sidelobes (within 5°) to about 0.1% of the total solid angle. Time response residuals remain as long tails in the scanning beams, but contribute less than 0.1% of the total solid angle. The bias and uncertainty in the beam products are estimated using ensembles of simulated planet observations that include the impact of instrumental noise and known systematic effects. Here, the correlation structure of these ensembles is well-described by five error eigenmodes that are sub-dominant to sample variance and instrumental noise in the harmonic domain. A suite of consistency tests provide confidence that the error model represents a sufficient description of the data. The total error in the effective beam window functions is below 1% at 100 GHz up to multipole ℓ ~ 1500, and below 0.5% at 143 and 217 GHz up to ℓ ~ 2000.

79 ASTRONOMY AND ASTROPHYSICS↗

An algorithm to locate the centers of baryon acoustic oscillations

The cosmic structure formed from baryon acoustic oscillations (BAO) in the early universe is imprinted in the galaxy distribution observable in large-scale surveys and is used as a standard ruler in contemporary cosmology. Typically, BAOs are detected as a preferential length scale in two-point statistics, which gives little information about the location of the BAO structures in real space. The aim of the algorithm described in this paper is to find probable centers of BAOs in the cosmic matter distribution. The algorithm convolves the three-dimensional distribution of matter density with a spherical shell kernel of variable radius placed at different locations. The locations that correspond to the highest values of the convolution correspond to the probable centers of BAOs. This method is realized in an open-source, computationally efficient algorithm. Here, we describe the algorithm and present the results of applying it to the SDSS DR9 CMASS survey and associated mock catalogs. A detailed performance study demonstrates the ability of the algorithm to locate BAO centers and in doing so presents a novel detection of the BAO scale in galaxy surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

ConKer: An algorithm for evaluating correlations of arbitrary order

Context. High order correlations in the cosmic matter density have become increasingly valuable in cosmological analyses. However, computing these correlation functions is computationally expensive. Aims. We aim to circumvent these challenges by developing a new algorithm called ConKer for estimating correlation functions. Methods. This algorithm performs convolutions of matter distributions with spherical kernels using FFT. Since matter distributions and kernels are defined on a grid, it results in some loss of accuracy in the distance and angle definitions. We study the algorithm setting at which these limitations become critical and suggest ways to minimize them. Results. ConKer is applied to the CMASS sample of the SDSS DR12 galaxy survey and corresponding mock catalogs, and is used to compute the correlation functions up to correlation order n = 5. We compare the n = 2 and n = 3 cases to traditional algorithms to verify the accuracy of the new algorithm. We perform a timing study of the algorithm and find that three of the four distinct processes within the algorithm are nearly independent of the catalog size N , while one subdominant component scales as O ( N ). The dominant portion of the calculation has complexity of O ( N c 4/3 log N c ), where N c is the of cells in a three-dimensional grid corresponding to the matter density. Conclusions. We find ConKer to be a fast and accurate method of probing high order correlations in the cosmic matter density, then discuss its application to upcoming surveys of large-scale structure.

79 ASTRONOMY AND ASTROPHYSICS↗

The discovery of a radio galaxy of at least 5 Mpc

Context. Giant radio galaxies (GRGs, or colloquially ‘giants’) are the Universe’s largest structures generated by individual galaxies. They comprise synchrotron-radiating active galactic nucleus ejecta and attain cosmological (megaparsec-scale) lengths. However, the main mechanisms that drive their exceptional growth remain poorly understood. Aims. To deduce the main mechanisms that drive a phenomenon, it is usually instructive to study extreme examples. If there exist host galaxy characteristics that are an important cause for GRG growth, then the hosts of the largest GRGs are likely to possess them. Similarly, if there exist particular large-scale environments that are highly conducive to GRG growth, then the largest GRGs are likely to reside in them. For these reasons, we aim to perform a case study of the largest GRG available. Methods. We reprocessed the LOFAR Two-Metre Sky Survey DR2 by subtracting compact sources and performing multi-scale CLEAN de-convolutions at 60" and 90" resolution. The resulting images constitute the most sensitive survey yet for radio galaxy lobes, whose diffuse nature and steep synchrotron spectra have allowed them to evade previous detection attempts at higher resolution and shorter wavelengths. We visually searched these images for GRGs. Results. We have discovered Alcyoneus, a low-excitation radio galaxy with a projected proper length l p = 4.99 ± 0.04 Mpc. Both its jets and lobes are detected at very high significance, and the SDSS-based identification of the host, at spectroscopic redshift z spec = 0.24674 ± 6 × 10 -5 , is unambiguous. The total luminosity density at ν = 144 MHz is L ν = 8 ± 1 × 10 25 W Hz -1 , which is below average, though near median (percentile 45 ± 3%) for GRGs. The host is an elliptical galaxy with a stellar mass M* = 2.4 ± 0.4 × 10 11 M ⊙ and a super-massive black hole mass M• = 4 ± 2 × 10 8 M ⊙ , both of which tend towards the lower end of their respective GRG distributions (percentiles 25 ± 9% and 23 ± 11%). The host resides in a filament of the Cosmic Web. Through a new Bayesian model for radio galaxy lobes in three dimensions, we estimate the pressures in the megaparsec-cubed-scale northern and southern lobes to be P min,1 = 4.8 ± 0.3 × 10 -16 Pa and P min,2 = 4.9 ± 0.6 × 10 -16 Pa, respectively. The corresponding magnetic field strengths are B min,1 = 46 ± 1 pT and B min,2 = 46 ± 3 pT. Conclusions. We have discovered what is in projection the largest known structure made by a single galaxy – a GRG with a projected proper length l p = 4.99 ± 0.04 Mpc. The true proper length is at least l min = 5.04 ± 0.05 Mpc. Beyond geometry, Alcyoneus and its host are suspiciously ordinary: the total low-frequency luminosity density, stellar mass, and super-massive black hole mass are all lower than, though similar to, those of the medial GRG. Thus, very massive galaxies or central black holes are not necessary to grow large giants, and, if the observed state is representative of the source over its lifetime, neither is high radio power. A low-density environment remains a possible explanation. The source resides in a filament of the Cosmic Web, with which it might have significant thermodynamic interaction. The pressures in the lobes are the lowest hitherto found, and Alcyoneus therefore represents the most promising radio galaxy yet to probe the warm–hot inter-galactic medium.

79 ASTRONOMY AND ASTROPHYSICS↗

HOLISMOKES IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images

Modeling of strong gravitational lenses is a necessity for further applications in astrophysics and cosmology. With the large number of detections in current and upcoming surveys, such as the Rubin Legacy Survey of Space and Time (LSST), it is pertinent to investigate automated and fast analysis techniques beyond the traditional and time-consuming Markov chain Monte Carlo sampling methods. Building upon our (simple) convolutional neural network (CNN), we present here another CNN, specifically a residual neural network (ResNet), that predicts the five mass parameters of a singular isothermal ellipsoid (SIE) profile (lens center x and y, ellipticity e x and e y , Einstein radius θ E ) and the external shear (γ ext, 1 , γ ext, 2 ) from ground-based imaging data. In contrast to our previous CNN, this ResNet further predicts the 1σ uncertainty for each parameter. To train our network, we use our improved pipeline to simulate lens images using real images of galaxies from the Hyper Suprime-Cam Survey (HSC) and from the Hubble Ultra Deep Field as lens galaxies and background sources, respectively. We find very good recoveries overall for the SIE parameters, especially for the lens center in comparison to our previous CNN, while significant differences remain in predicting the external shear. From our multiple tests, it appears that most likely the low ground-based image resolution is the limiting factor in predicting the external shear. Given the run time of milli-seconds per system, our network is perfectly suited to quickly predict the next appearing image and time delays of lensed transients. Therefore, we use the network-predicted mass model to estimate these quantities and compare to those values obtained from our simulations. Unfortunately, the achieved precision allows only a first-order estimate of time delays on real lens systems and requires further refinement through follow-up modeling. Nonetheless, our ResNet is able to predict the SIE and shear parameter values in fractions of a second on a single CPU, meaning that we are able to efficiently process the huge amount of galaxy-scale lenses expected in the near future.

79 ASTRONOMY AND ASTROPHYSICS↗

ZTF SN Ia DR2: An environmental study of Type Ia supernovae using host galaxy image decomposition

The second data release of Type Ia supernovae (SNe Ia) observed by the Zwicky Transient Facility has provided a homogeneous sample of 3628 SNe Ia with photometric and spectral information. This unprecedented sample size enables us to better explore our currently tentative understanding of the dependence of the host environment on SN Ia properties. In this paper, we make use of two-dimensional image decomposition to model the host galaxies of SNe Ia. We model elliptical galaxies as well as disc and spiral galaxies with or without central bulges and bars. This allows for the categorisation of SN Ia based on their morphological host environment, as well as the extraction of intrinsic galaxy properties corrected for both cosmological and atmospheric effects, through point-spread-function (PSF) convolution. We find that although this image decomposition technique leads to a significant bias towards elliptical galaxies in our final sample of processed galaxies, the overall results are still robust. By successfully modelling 728 host galaxies, we find that the photometric properties of SNe Ia found in discs and in elliptical galaxies correlate fundamentally differently with their host environment. We identified strong linear relations between light-curve stretch and our model-derived galaxy colour for both the elliptical (16.8σ) and disc (5.1σ) subpopulations of SNe Ia. Lower-stretch SNe Ia are found in redder environments, which we identify as an age and/or metallicity effect. Within the subpopulation of SNe Ia found in disc-containing galaxies, we find a significant linear trend (6.1σ) between light-curve stretch and model-derived local r-band surface brightness, which we link to the age and metallicity gradients found in disc galaxies. SN Ia colour shows little correlation with the host environment, as is seen in the literature. We do identify a possible dust effect in our model-derived surface brightness (3.3σ) for SNe Ia in disc galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗

Beyond the two-point correlation: Constraining primordial non-Gaussianity with density-perturbation moments

Constraining primordial non-Gaussianity (PNG) on the large-scale cosmic structure (LSS) is an important step in understanding properties of the early Universe, specifically in distinguishing between different inflationary models. Measuring PNG relies on evaluating the scale-dependent correlations in the density field. New summary statistics beyond the two- and three-point correlation functions in configuration space and their Fourier-space counterparts, the power- and bispectrum may provide increased sensitivity. We introduce a new method for extracting the PNG signal imprinted on the LSS by using the first three Gaussian moments of the normalized correlation in density perturbations, evaluated on varying distance scales. We aim to assess this method’s sensitivity to local PNG, parameterized by f NL . We performed spherical convolutions on a range of scales on dark-matter-halo simulations to measure the scale-dependent correlations in the density field. From these, we computed the first three moments and compared them to a model expectation vector, parameterized to the second power in f NL . Our method provides about 21% improvement in sensitivity to f NL with respect to using the two-point correlation function alone. Notably, we find that the second moment alone carries nearly as much constraining power as the mean, highlighting the potential of higher order statistics. Given its simplicity and efficiency, this framework is well suited for application to current and upcoming large-scale surveys such as the Dark Energy Spectroscopic Instrument (DESI).

early universe↗

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. Furthermore, we will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗