Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep neural network”

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 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

The optimal use of segmentation for sampling calorimeters

One of the key design choices of any sampling calorimeter is how fine to make the longitudinal and transverse segmentation. Here, to inform this choice, we study the impact of calorimeter segmentation on energy reconstruction. To ensure that the trends are due entirely to hardware and not to a sub-optimal use of segmentation, we deploy deep neural networks to perform the reconstruction. These networks make use of all available information by representing the calorimeter as a point cloud. To demonstrate our approach, we simulate a detector similar to the forward calorimeter system intended for use in the ePIC detector, which will operate at the upcoming Electron Ion Collider. We find that for the energy estimation of isolated charged pion showers, relatively fine longitudinal segmentation is key to achieving an energy resolution that is better than 10% across the full phase space. These results provide a valuable benchmark for ongoing EIC detector optimizations and may also inform future studies involving high-granularity calorimeters in other experiments at various facilities.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Distributed deep reinforcement learning for simulation control

Abstract Several applications in the scientific simulation of physical systems can be formulated as control/optimization problems. The computational models for such systems generally contain hyperparameters, which control solution fidelity and computational expense. The tuning of these parameters is non-trivial and the general approach is to manually ‘spot-check’ for good combinations. This is because optimal hyperparameter configuration search becomes intractable when the parameter space is large and when they may vary dynamically. To address this issue, we present a framework based on deep reinforcement learning (RL) to train a deep neural network agent that controls a model solve by varying parameters dynamically. First, we validate our RL framework for the problem of controlling chaos in chaotic systems by dynamically changing the parameters of the system. Subsequently, we illustrate the capabilities of our framework for accelerating the convergence of a steady-state computational fluid dynamics solver by automatically adjusting the relaxation factors of the discretized Navier–Stokes equations during run-time. The results indicate that the run-time control of the relaxation factors by the learned policy leads to a significant reduction in the number of iterations for convergence compared to the random selection of the relaxation factors. Our results point to potential benefits for learning adaptive hyperparameter learning strategies across different geometries and boundary conditions with implications for reduced computational campaign expenses 4 4 Data and codes available at https://github.com/Romit-Maulik/PAR-RL . .

42 ENGINEERING↗
DOE OSTI2022

Pile-up mitigation using attention

Abstract Particle production from secondary proton-proton collisions, commonly referred to as pile-up, impair the sensitivity of both new physics searches and precision measurements at large hadron collider (LHC) experiments. We propose a novel algorithm, Puma , for modeling pile-up with the help of deep neural networks based on sparse transformers. These attention mechanisms were developed for natural language processing but have become popular in other applications. In a realistic detector simulation, our method outperforms classical benchmark algorithms for pile-up mitigation in key observables. It provides a perspective for mitigating the effects of pile-up in the high luminosity era of the LHC, where up to 200 proton-proton collisions are expected to occur simultaneously.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Deep probabilistic direction prediction in 3D with applications to directional dark matter detectors

Abstract We present the first method to probabilistically predict 3D direction in a deep neural network model. The probabilistic predictions are modeled as a heteroscedastic von Mises-Fisher distribution on the sphere S 2 , giving a simple way to quantify aleatoric uncertainty. This approach generalizes the cosine distance loss which is a special case of our loss function when the uncertainty is assumed to be uniform across samples. We develop approximations required to make the likelihood function and gradient calculations stable. The method is applied to the task of predicting the 3D directions of electrons, the most complex signal in a class of experimental particle physics detectors designed to demonstrate the particle nature of dark matter and study solar neutrinos. Using simulated Monte Carlo data, the initial direction of recoiling electrons is inferred from their tortuous trajectories, as captured by the 3D detectors. For 40 keV electrons in a 70% He 30% CO 2 gas mixture at STP, the new approach achieves a mean cosine distance of 0.104 (26 ∘ ) compared to 0.556 (64 ∘ ) achieved by a non-machine learning algorithm. We show that the model is well-calibrated and accuracy can be increased further by removing samples with high predicted uncertainty. This advancement in probabilistic 3D directional learning could increase the sensitivity of directional dark matter detectors.

Computer Science↗
DOE OSTI2023

Multimodal representation learning for predicting molecule–disease relations

Motivation: Predicting molecule–disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule–molecule, molecule–disease and disease–disease semantic dependencies can potentially improve prediction performance. Methods: We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule–disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects. Results: We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens. Availability and implementation: The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer

Abstract Leaf-level hyperspectral reflectance has become an effective tool for high-throughput phenotyping of plant leaf traits due to its rapid, low-cost, multi-sensing, and non-destructive nature. However, collecting samples for model calibration can still be expensive, and models show poor transferability among different datasets. This study had three specific objectives: first, to assemble a large library of leaf hyperspectral data (n=2460) from maize and sorghum; second, to evaluate two machine-learning approaches to estimate nine leaf properties (chlorophyll, thickness, water content, nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur); and third, to investigate the usefulness of this spectral library for predicting external datasets (n=445) including soybean and camelina using extra-weighted spiking. Internal cross-validation showed satisfactory performance of the spectral library to estimate all nine traits (mean R2=0.688), with partial least-squares regression outperforming deep neural network models. Models calibrated solely using the spectral library showed degraded performance on external datasets (mean R2=0.159 for camelina, 0.337 for soybean). Models improved significantly when a small portion of external samples (n=20) was added to the library via extra-weighted spiking (mean R2=0.574 for camelina, 0.536 for soybean). The leaf-level spectral library greatly benefits plant physiological and biochemical phenotyping, whilst extra-weight spiking improves model transferability and extends its utility.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Deblending galaxies with variational autoencoders: A joint multiband, multi-instrument approach

ABSTRACT Blending of galaxies has a major contribution in the systematic error budget of weak-lensing studies, affecting photometric and shape measurements, particularly for ground-based, deep, photometric galaxy surveys, such as the Rubin Observatory Legacy Survey of Space and Time (LSST). Existing deblenders mostly rely on analytic modelling of galaxy profiles and suffer from the lack of flexible yet accurate models. We propose to use generative models based on deep neural networks, namely variational autoencoders (VAE), to learn probabilistic models directly from data. We train a VAE on images of centred, isolated galaxies, which we reuse, as a prior, in a second VAE-like neural network in charge of deblending galaxies. We train our networks on simulated images including six LSST bandpass filters and the visible and near-infrared bands of the Euclid satellite, as our method naturally generalizes to multiple bands and can incorporate data from multiple instruments. We obtain median reconstruction errors on ellipticities and r-band magnitude between ±0.01 and ±0.05, respectively, in most cases, and ellipticity multiplicative bias of 1.6 per cent for blended objects in the optimal configuration. We also study the impact of decentring and prove the method to be robust. This method only requires the approximate centre of each target galaxy, but no assumptions about the number of surrounding objects, pointing to an iterative detection/deblending procedure we leave for future work. Finally, we discuss future challenges about training on real data and obtain encouraging results when applying transfer learning.

Arcelin, Bastien↗
DOE OSTI2024

LSBGnet: an improved detection model for low-surface brightness galaxies

ABSTRACT The Chinese Space Station Telescope (CSST) is scheduled to launch soon, which is expected to provide a vast amount of image potentially containing low-surface brightness galaxies (LSBGs). However, detecting and characterizing LSBGs is known to be challenging due to their faint surface brightness, posing a significant hurdle for traditional detection methods. In this paper, we propose LSBGnet, a deep neural network specifically designed for automatic detection of LSBGs. We established LSBGnet-SDSS model using data set from the Sloan Digital Sky Survey (SDSS). The results demonstrate a significant improvement compared to our previous work, achieving a recall of 97.22 per cent and a precision of 97.27 per cent on the SDSS test set. Furthermore, we use the LSBGnet-SDSS model as a pre-training model, employing transfer learning to retrain the model with LSBGs from Dark Energy Survey (DES), and establish the LSBGnet-DES model. Remarkably, after retraining the model on a small DES sample, it achieves over 90 per cent precision and recall. To validate the model’s capabilities, we utilize the trained LSBGnet-DES model to detect LSBG candidates within a selected 5 sq. deg area in the DES footprint. Our analysis reveals the detection of 204 LSBG candidates, characterized by a mean surface brightness range of $23.5\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}\le \bar{\mu }_{\text{eff}}(g)\le 26.8\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}$ and a half-light radius range of 1.4 arcsec ≤ r1/2 ≤ 8.3 arcsec. Notably, 116 LSBG candidates exhibit a half-light radius ≥2.5 arcsec. These results affirm the remarkable performance of our model in detecting LSBGs, making it a promising tool for the upcoming CSST.

Su, Hao (ORCID:0009000778888301)↗
DOE OSTI2024

Deep Learning and Likelihood Approaches for Viral Phylogeography Converge on the Same Answers Whether the Inference Model Is Right or Wrong

Abstract Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.

Evolutionary Biology↗
DOE OSTI2021

Deep learning of accurate force field of ferroelectric HfO 2

The discovery of ferroelectricity in HfO 2 -based thin films opens up new opportunities for using this silicon-compatible ferroelectric to realize low-power logic circuits and high-density nonvolatile memories. The functional performances of ferroelectrics are intimately related to their dynamic responses to external stimuli such as electric fields at finite temperatures. Molecular dynamics is an ideal technique for investigating dynamical processes on large length and time scales, though its applications to new materials are often hindered by the limited availability and accuracy of classical force fields. Here we present a deep neural network–based interatomic force field of HfO 2 learned from ab initio data using a concurrent learning procedure. The model potential is able to predict structural properties such as elastic constants, equation of states, phonon dispersion relationships, and phase transition barriers of various hafnia polymorphs with accuracy comparable with density functional theory calculations. Here, the validity of this model potential is further confirmed by the reproduction of experimental sequences of temperature-driven ferroelectric-paraelectric phase transitions of HfO 2 with isobaric-isothermal ensemble molecular dynamics simulations. We suggest a general approach to extend the model potential of HfO 2 to related material systems including dopants and defects.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

Deconvoluting experimental decay energy spectra: The O 26 case

In nuclear reaction experiments, the measured decay energy spectra can give insights into the shell structure of decaying systems. However, extracting the underlying physics from the measurements is challenging due to detector resolution and acceptance effects. The Richardson-Lucy (RL) algorithm, a deblurring method that is commonly used in optics and has proven to be a successful technique for restoring images, was applied to our experimental nuclear physics data. The only inputs to the method are the observed energy spectrum and the detector's response matrix also known as the transfer matrix. We demonstrate that the technique can help access information about the shell structure of particle-unbound systems from the measured decay energy spectrum that is not immediately accessible via traditional approaches such as χ-square fitting. For a similar purpose, we developed a machine learning model that uses a deep neural network (DNN) classifier to identify resonance states from the measured decay energy spectrum. We tested the performance of both methods on simulated data and experimental measurements. Then, we applied both algorithms to the decay energy spectrum of 26 O → 24 O + n + n measured via invariant mass spectroscopy. Here, the resonance states restored using the RL algorithm to deblur the measured decay energy spectrum agree with those found by the DNN classifier. Both deblurring and DNN approaches suggest that the raw decay energy spectrum of 26 O exhibits three peaks at approximately 0.15 MeV, 1.50 MeV, and 5.00 MeV, with half-widths of 0.29 MeV, 0.80 MeV, and 1.85 MeV, respectively.

Spectrometers & spectroscopic techniques↗
DOE OSTI2023

Search for narrow resonances in the b -tagged dijet mass spectrum in proton-proton collisions at s = 13 TeV

A search is performed for narrow resonances decaying to final states of two jets, with at least one jet originating from a b quark, in proton-proton collisions at s = 13 TeV . The data set corresponds to an integrated luminosity of 138 fb - 1 collected with the CMS detector at the LHC. Jets originating from energetic b hadrons are identified through a b -tagging algorithm that utilizes a deep neural network or the presence of a muon inside a jet. The invariant mass spectrum of jet pairs is well described by a smooth parametrization and no evidence for the production of new particles is observed. Upper limits on the production cross section are set for excited b quarks and other resonances decaying to dijet final states containing b quarks. These limits exclude at 95% confidence level models of Z ' bosons with masses from 1.8 TeV to 2.4 TeV and of excited b quarks with masses from 1.8 TeV to 4.0 TeV. This is the most stringent exclusion of excited b quarks to date.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Tree-based algorithms for weakly supervised anomaly detection

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as dijet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step toward a more model-agnostic search for new physics. Published by the American Physical Society 2024

Astronomy & Astrophysics↗
DOE OSTI2023

Group-equivariant autoencoder for identifying spontaneously broken symmetries

We introduce the group-equivariant autoencoder (GE autoencoder), a deep neural network (DNN) method that locates phase boundaries by determining which symmetries of the Hamiltonian have spontaneously broken at each temperature. We use group theory to deduce which symmetries of the system remain intact in all phases, and then use this information to constrain the parameters of the GE autoencoder such that the encoder learns an order parameter invariant to these “never-broken” symmetries. This procedure produces a dramatic reduction in the number of free parameters such that the GE-autoencoder size is independent of the system size. We include symmetry regularization terms in the loss function of the GE autoencoder so that the learned order parameter is also equivariant to the remaining symmetries of the system. By examining the group representation by which the learned order parameter transforms, we are then able to extract information about the associated spontaneous symmetry breaking. We test the GE autoencoder on the 2D classical ferromagnetic and antiferromagnetic Ising models, finding that the GE autoencoder (1) accurately determines which symmetries have spontaneously broken at each temperature; (2) estimates the critical temperature in the thermodynamic limit with greater accuracy, robustness, and time efficiency than a symmetry-agnostic baseline autoencoder; and (3) detects the presence of an external symmetry-breaking magnetic field with greater sensitivity than the baseline method. Lastly, we describe various key implementation details, including a quadratic-programming-based method for extracting the critical temperature estimate from trained autoencoders and calculations of the DNN initialization and learning rate settings required for fair model comparisons.

42 ENGINEERING↗
DOE OSTI2023

Search for Higgs Boson and Observation of $Z$ Boson through Their Decay into a Charm Quark-Antiquark Pair in Boosted Topologies in Proton-Proton Collisions at $\sqrt{s}$ = 13 TeV

A search for the standard model (SM) Higgs boson ($H$) produced with transverse momentum ($p_T$) greater than 450 GeV and decaying to a charm quark-antiquark ($c\bar{c}$) pair is presented. The search is performed using proton-proton collision data collected at $\sqrt{s} = 13$ TeV by the CMS experiment at the LHC, corresponding to an integrated luminosity of 138 fb$^{-1}$. Boosted $H \to c\overline{c}$ decay products are reconstructed as a single large-radius jet and identified using a deep neural network charm tagging technique. The method is validated by measuring the $Z \to c\bar{c}$ decay process, which is observed in association with jets at high $p_T$ for the first time with a signal strength of $1.00^{+0.17}_{-0.14}$ (syst)$\pm 0.08$ (theo) $\pm 0.06$ (stat), defined as the ratio of the observed process rate to the SM expectation. The observed (expected) upper limit on $\sigma (H){\cal B}(H \to c\overline{c})$ is set at 47 (39) times the SM prediction at 95\%confidence level.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Why Dissolving Salt in Water Decreases Its Dielectric Permittivity

The dielectric permittivity of salt water decreases on dissolving more salt. For nearly a century, this phenomenon has been explained by invoking saturation in the dielectric response of the solvent water molecules. Herein, we employ an advanced deep neural network (DNN), built using data from density functional theory, to study the dielectric permittivity of sodium chloride solutions. Notably, the decrease in the dielectric permittivity as a function of concentration, computed using the DNN approach, agrees well with experiments. Detailed analysis of the computations reveals that the dominant effect, caused by the intrusion of ionic hydration shells into the solvent hydrogen-bond network, is the disruption of dipolar correlations among water molecules. Accordingly, the observed decrease in the dielectric permittivity is mostly due to increasing suppression of the collective response of solvent waters.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2022

Designing Monte Carlo Simulation and an Optimal Machine Learning to Optimize and Model Space Missions

This paper investigates applying artificial intelligence (AI) algorithms to attitude control system of satellites to optimally tune the controller using high performance computing. This methodology is applied to the Virtual Telescope for X-ray Observation mission, which is a precise formation of two separate spacecraft observing multiple objects in the space in the X-ray domain. The mission is divided into phases based on the instrumentation and the mission goal. To reach an stable precise formation robust to stochastic slew and slew rate (i.e., Euler angles and angular velocities) in a minimal constrained time T , consumed energy of the attitude control system, denoted as E, and root-mean-square state error of attitude control system, denoted as e, are minimized. Monte-Carlo simulation is used for the sensitivity analysis of optimization and designing a controller. Deep neural networks (DNN), Gaussian processes (GP), and support vector regression (SVR) learn this optimization as a surrogate model, while their hyperparameters are optimized in a novel approach. THETA supercomputer at Argonne Leadership Computing Facility (ALCF) is used for optimizing the hyperparameters of DNN. The surrogate model meets the requirements of the mission, and it shows a better performance over the optimization and Monte-Carlo. The optimal DNN can satisfy the mission requirements e and T while reducing E for 90% compared to the other given methods.

42 ENGINEERING↗
DOE OSTI2023

Neural Architecture Search Benchmarks: Insights and Survey

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.

97 MATHEMATICS AND COMPUTING↗