Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Direct Use”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Market Survey 2020: Commercial Clinical Decision Support Systems and Wellness Tools

For long-duration, deep space exploration missions, current methods for managing and supporting crew health and medical conditions will be unsuitable. Communication and data transmission lags will necessitate the use of a sophisticated clinical decision support system (CDSS) that will tailor diagnosis and treatment guidance that is context-sensitive for anticipated astronaut health, wellness, and medical conditions. A variety of clinical decision support (CDS) and wellness tools (WT) are currently available in the commercial market and a broad-brush survey of this market can provide an initial impression of the current state of the art which, in turn, can inform the roadmap of NASA deep space CDSS development and associated requirements. Such a survey was undertaken during the first six months of 2020 using directed convenience sampling to obtain information provided by vendors on their websites; both commercially available CDS and WT (such as those used to track and monitor nutrition, exercise, and sleep) were included. Areas assessed were item type (e.g., software/application, device); primary purpose of the item (e.g., diagnostic support, nutrition tracking); additional purposes (if any); reported features, capabilities, and functionality; setting of use (e.g., inpatient, outpatient); intended user (e.g., clinician, patient); location and sources of data/information used or produced by the item; integration with patient electronic health record (EHR); compliance with interoperability ontologies and standards (e.g., Health Level 7 [HL7], Systematized Nomenclature of Medicine – Clinical Terminology [SNOMED-CT]); and whether the item is knowledge-based (derived from research findings) or non-knowledge-based (derived through artificial intelligence, machine learning, advanced probability and statistics), among others. Ninety-seven (97) vendor websites describing 196 CDS and 73 WT (269 total) were reviewed and coded. The primary purpose of the majority of CDS reviewed is diagnosis or diagnosis/treatment/drug decision support—targeted for clinician use— and the primary purpose of the majority of WT reviewed is the monitoring of different health metrics, most often through the use of a biosensor device (e.g., blood pressure)—targeted for patient use. Very few CDS or WT appear to comply with major international interoperability standards or can be integrated with a patient’s EHR data. None consider contextual factors, such as conditions of the physical environment (e.g., CO2 levels). The majority of CDS and WT reviewed are non-knowledge, cloud- or web-based applications or software. Forty-three (43) major findings were identified and the implications those findings have for NASA will be discussed. Example major findings include: CDS-WT capabilities range from diagnosis to treatment applications, CDS-WT may be wearable or non-wearable and are technologically advanced and only a few CDS-WT tools referenced compliance to ensure interoperability, among other findings. Recommendations will also be offered that will help to address ExMC Gap, Medical-701: Enhance medical capabilities within an exploration medical system.

market survey↗
DOE OSTI2022

Device-Centric Firmware Malware Detection for Smart Inverters using Deep Transfer Learning

Since future power grids are inverter-dominant grids and inverters are getting smarter by incorporating remote access and seamless firmware update, it is anticipated that malware attackers will directly target smart inverters. However, malware threats targeting smart inverters have been less studied yet. This paper explores potential malware attacks targeting smart inverters and proposes a deep transfer-learning (DTL)-based malware detection framework for smart inverters. The proposed DTL method can significantly reduce development time and efforts for an artificial intelligence-based malware detection algorithm while improving detection accuracy. The experimental result shows that the proposed method achieves 98% of firmware malware detection accuracy. Furthermore, this approach will be transformative to other smart grid devices enabling seamless firmware update.

artificial intelligence↗
NASA NTRS2008

Long-term Satellite Observations of Asian Dust Storm: Source, Pathway, and Interannual Variability

Among the many components that contribute to air pollution, airborne mineral dust plays an important role due to its biogeochemical impact on the ecosystem and its radiative-forcing effect on the climate system. In East Asia, dust storms frequently accompany the cold and dry air masses that occur as part of springtime cold front systems. Outbreaks of Asian dust storms occur often in the arid and semi-arid areas of northwestern China -about 1.6x10(exp 6) square kilometers including the Gobi and Taklimakan deserts- with continuous expanding of spatial coverage. These airborne dust particles, originating in desert areas far from polluted regions, interact with anthropogenic sulfate and soot aerosols emitted from Chinese megacities during their transport over the mainland. Adding the intricate effects of clouds and marine aerosols, dust particles reaching the marine environment can have drastically different properties than those from their sources. Furthermore, these aerosols, once generated over the source regions, can be transported out of the boundary layer into the free troposphere and can travel thousands of kilometers across the Pacific into the United States and beyond. In this paper, we will demonstrate the capability of a new satellite algorithm to retrieve aerosol properties (e.g., optical thickness, single scattering albedo) over bright-reflecting surfaces such as urban areas and deserts. Such retrievals have been difficult to perform using previously available algorithms that use wavelengths from the mid-visible to the near IR because they have trouble separating the aerosol signal from the contribution due to the bright surface reflectance. This new algorithm, called Deep Blue, utilizes blue-wavelength measurements from instruments such as SeaWiFS and MODIS to infer the properties of aerosols, since the surface reflectance over land in the blue part of the spectrum is much lower than for longer wavelength channels. Reasonable agreements have been achieved between Deep Blue retrievals of aerosol optical thickness and those directly from AERONET sunphotometers over desert and semi-desert regions. New Deep Blue products will allow scientists to determine quantitatively the aerosol properties near sources using high spatial resolution measurements from SeaWiFS and MODIS-like instruments. Long-term satellite measurements (1998 - 2007) from SeaWiFS will be utilized to investigate the interannual variability of source, pathway, and dust loading associated with the Asian dust storm outbreaks. In addition, monthly averaged aerosol optical thickness during the springtime from SeaWiFS will also be compared with the MODIS Deep Blue products.

Hsu, N. Christina↗
NASA NTRS2008

Recent Progress in Characterization of Dust over Land Surfaces with Space-borne Passive Remote Sensing

Among the many components that contribute to air pollution, airborne mineral dust plays an important role due to its biogeochemical impact on the ecosystem and its radiative-forcing effect on the climate system. In East Asia, dust storms frequently accompany the cold and dry air masses that occur as part of springtime cold front systems. Outbreaks of Asian dust storms occur often in the arid and semi-arid areas of northwestern China -about 1.6x10(exp 6) square kilometers including the Gobi and Taklimakan deserts- with continuous expanding of spatial coverage. These airborne dust particles, originating in desert areas far from polluted regions, interact with anthropogenic sulfate and soot aerosols emitted from Chinese mega-cities during their transport over the mainland. Adding the intricate effects of clouds and marine aerosols, dust particles reaching the marine environment can have drastically different properties than those from their sources. Furthermore, these aerosols, once generated over the source regions, can be transported out of the boundary layer into the free troposphere and can travel thousands of kilometers across the Pacific into the United States and beyond. In this paper, we will demonstrate the capability of a new satellite algorithm to retrieve aerosol properties (e.g., optical thickness, single scattering albedo) over bright-reflecting surfaces such as urban areas and deserts. Such retrievals have been difficult to perform using previously available algorithms that use wavelengths from the mid-visible to the near IR because they have trouble separating the aerosol signal from the contribution due to the bright surface reflectance. This new algorithm, called Deep Blue, utilizes blue-wavelength measurements from instruments such as SeaWiFS and MODIS to infer the properties of aerosols, since the surface reflectance over land in the blue part of the spectrum is much lower than for longer wavelength channels. Reasonable agreements have been achieved between Deep Blue retrievals of aerosol optical thickness and those directly from AERONET sunphotometers over desert and semi-desert regions. New Deep Blue products will allow scientists to determine quantitatively the aerosol properties near sources using high spatial resolution measurements from SeaWiFS and MODIS-like instruments. Long-term satellite measurements (1998 - 2007) from SeaWiFS will be utilized to investigate the interannual variability of source, pathway, and dust loading associated with the Asian dust storm outbreaks. In addition, monthly averaged aerosol optical thickness during the springtime from SeaWiFS will also be compared with the MODIS Deep Blue products.

Hsu, N. Christina↗
NASA NTRSDate not supplied

First N 2 Profile for Venus’ Deep Lower Atmosphere

We present the first N 2 profile for Venus’ deep lower atmosphere (<15 km) and a constrained isotopic composition for cloud N 2 [1]. This work directly addresses unresolved questions for Venus using legacy observations. Prior to this work, there were no reported measurements for N 2 abundances at <15 km and the isotopic composition remained unconstrained [2]. The N 2 parameters are critical to understanding the evolution and thermal properties of the atmosphere [3-7]. Our N 2 results were obtained by re-analysis of data acquired in 1978 by the Pioneer Venus Large Probe Neutral Mass Spectrometer (LNMS) [8]. The archived mass spectra from 64.2 to 0.2 km were treated using the analytical procedures specifically developed for the LNMS [9-11]. Judicious peak fitting permitted disambiguation of (A) N 2 + and CO + at 28 u and (B) 14 N 15 N+, 13 CO + , and C 2 H 5 + at 29 u. Quality controls included comparing the (A) LNMS CO + /CO 2 + ratios to the NIST database and literature and (B) fitted counts for CO + to the expected counts of CO + calculated from C 18 O + and 13 CO + using the LNMS 16 O/ 18 O and 12 C/ 13 C ratios (obtained from CO 2 ). Our results show that N 2 is uniformly mixed across the deep lower atmosphere between ~0.2 and 15 km (2.49 ± 0.10 v%). In contrast, N 2 is non-uniformly mixed across the sub-cloud atmosphere and clouds (~15–59 km), where N 2 abundances increase by ~ 2-fold between ~15 km (2.45 ± 0.32 v%) and ~59-51 km (5.21 ± 0.18 v%). Using the cloud data, we also obtained a constrained 15 N/ 14 N ratio (2.93×10 -3 ± 0.13×10 -3 ) and δ 15 N value (-204 ± 35‰). Thus, the LNMS results [1] suggest that (A) the atmosphere is unstable at <15 km, (B) N 2 is not well-mixed >15 km, and (C) the cloud δ 15 N falls between Earth and the solar wind [12, 13]. Comparisons of the N 2 abundances and isotopic compositions for nitrogen, carbon, and oxygen to other Venus measurements will be discussed.

deep lower atmosphere↗
DOE OSTI2022

Deep learning of dynamically responsive chemical Hamiltonians with semiempirical quantum mechanics

Conventional machine-learning (ML) models in computational chemistry learn to directly predict molecular properties using quantum chemistry only for reference data. While these heuristic ML methods show quantum-level accuracy with speeds several orders of magnitude faster than traditional quantum chemistry methods, they suffer from poor extensibility and transferability; i.e., their accuracy degrades on large or new chemical systems. Incorporating quantum chemistry frameworks into the ML models directly solves this problem. Here we take the structure of semiempirical quantum mechanics (SEQM) methods to construct dynamically responsive Hamiltonians. SEQM methods use empirical parameters fitted to experimental properties to construct reduced-order Hamiltonians, facilitating much faster calculations than ab initio methods but with compromised accuracy. By replacing these static parameters with machine-learned dynamic values inferred from the local environment, we greatly improve the accuracy of the SEQM methods. Trained on molecular energies and atomic forces, these dynamically generated Hamiltonian parameters show a strong correlation with atomic hybridization and bonding. Trained with only about 60,000 small organic molecular conformers, the resulting model retains interpretability, extensibility, and transferability when testing on much larger chemical systems and predicting various molecular properties. Overall, this work demonstrates the virtues of incorporating physics-based descriptions with ML to develop models that are simultaneously accurate, transferable, and interpretable.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Leveraging dendritic complexity for neuromorphic computing

Abstract Beyond-von Neumann computing approaches are necessary to sustain the growth of microelectronics and the increasing appetite for artificial intelligence/machine learning algorithms. Neuromorphic computing is an emerging paradigm that takes inspiration from the brain to provide a path forward to improve the computational efficiency and computational density of next-generation computing architectures. In nature, we observe brains performing complex computations with a much smaller energy footprint than conventional computing approaches. Current neuromorphic systems are focused primarily on scalability, namely, increasing the number of computational units (neurons) and connections between units (synapses). However, for brain-like cognition and efficiency in next-generation computing hardware, we need increased complexity in function, as well as improved connection density for scalability. Here, we present our work that aims to incorporate dendrites for ‘compute-on-wire’ in neuromorphic architectures to increase the computational complexity (e.g. number of programmable parameters, nonlinear dynamics) as well as computational efficiency (energy/compute) of artificial neural networks (ANNs). We do this by showcasing neuromorphic dendrite elements that can be leveraged for various applications. We will present examples of neuroscience-inspired direction-selective circuits and an ANN with active dendrites leveraging shunting inhibition. We also demonstrate the benefits of using dendrites in deep neural networks. To conclude, we discuss how we can utilize emerging hardware devices in these systems and design next-generation neuromorphic architectures with dendrites.

Cardwell, Suma G. (ORCID:0000000226575545)↗
DOE OSTI2022

Deep learning methods for obtaining photometric redshift estimations from images

ABSTRACT Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as it is impossible to perform spectroscopy for every galaxy being observed, photometric redshift (photo-z) estimations are still of particular interest. Here, we investigate different deep learning methods for obtaining photo-z estimates directly from images, comparing these with ‘traditional’ machine learning algorithms which make use of magnitudes retrieved through photometry. As well as testing a convolutional neural network (CNN) and inception-module CNN, we introduce a novel mixed-input model that allows for both images and magnitude data to be used in the same model as a way of further improving the estimated redshifts. We also perform benchmarking as a way of demonstrating the performance and scalability of the different algorithms. The data used in the study comes entirely from the Sloan Digital Sky Survey (SDSS) from which 1 million galaxies were used, each having 5-filtre (ugriz) images with complete photometry and a spectroscopic redshift which was taken as the ground truth. The mixed-input inception CNN achieved a mean squared error (MSE) =0.009, which was a significant improvement ($30{{\ \rm per\ cent}}$) over the traditional random forest (RF), and the model performed even better at lower redshifts achieving a MSE = 0.0007 (a $50{{\ \rm per\ cent}}$ improvement over the RF) in the range of z < 0.3. This method could be hugely beneficial to upcoming surveys, such as Euclid and the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), which will require vast numbers of photo-z estimates produced as quickly and accurately as possible.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Discovery and Timing of Three Millisecond Pulsars in Radio and Gamma-Rays with the Giant Metrewave Radio Telescope and Fermi Large Area Telescope

In this work, we performed deep observations to search for radio pulsations in the directions of 375 unassociated Fermi Large Area Telescope γ-ray sources using the Giant Metrewave Radio Telescope (GMRT) at 322 and 607 MHz. In this paper we report the discovery of three millisecond pulsars (MSPs), PSR J0248+4230, PSR J1207–5050, and PSR J1536–4948. We conducted follow-up timing observations for ~5 yr with the GMRT and derived phase-coherent timing models for these MSPs. PSR J0248+4230 and J1207–5050 are isolated MSPs having periodicities of 2.60 ms and 4.84 ms. PSR J1536–4948 is a 3.07 ms pulsar in a binary system with an orbital period of ~62 days about a companion of a minimum mass of 0.32 M⊙. We also present multifrequency pulse profiles of these MSPs from the GMRT observations. PSR J1536–4948 is an MSP with an extremely wide pulse profile having multiple components. Using the radio timing ephemeris we subsequently detected γ-ray pulsations from these three MSPs, confirming them as the sources powering the γ-ray emission. For PSR J1536–4948 we performed combined radio–γ-ray timing using ~11.6 yr of γ-ray pulse times of arrival (TOAs) along with the radio TOAs. PSR J1536–4948 also shows evidence for pulsed γ-ray emission out to above 25 GeV, confirming earlier associations of this MSP with a ≥10 GeV point source. The multiwavelength pulse profiles of all three MSPs offer challenges to models of radio and γ-ray emission in pulsar magnetospheres.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2001

Main-Reflector Manufacturing Technology for the Deep Space Optical Communications Ground Station

The Deep Space Network (DSN) has plans to develop a 10-m-diameter optical communications receiving station. The system uses the direct detection technique, which has much different requirements from a typical astronomical telescope. The receiver must operate in daylight and nighttime conditions. This imposes special requirements on the optical system to reject stray light from the Sun and other sources. One of the biggest challenges is designing a main-reflector surface that meets these requirements and can be produced at a reasonable cost. The requirements for the performance of the reflector are presented. To date, an aspherical primary reflector has been assumed. A reflector with a spherical reflector has a major cost advantage over an aspherical design, with no sacrifice in performance. A survey of current manufacturing techniques for optical mirrors of this type was performed. Techniques including solid glass, lightweight glass, diamond-turned aluminum, and composite mirrors were investigated.

Britcliffe, M. J.↗
NASA NTRS2021

Discovery and Timing of Three Millisecond Pulsars in Radio and Gamma-Rays with the Giant Metrewave Radio Telescope and Fermi Large Area Telescope

We performed deep observations to search for radio pulsations in the directions of 375 unassociated Fermi Large Area Telescope γ-ray sources using the Giant Metrewave Radio Telescope (GMRT) at 322 and 607 MHz. In this paper we report the discovery of three millisecond pulsars (MSPs), PSR J0248+4230, PSR J1207–5050, and PSR J1536–4948. We conducted follow-up timing observations for ∼5 yr with the GMRT and derived phase-coherent timing models for these MSPs. PSR J0248+4230 and J1207–5050 are isolated MSPs having periodicities of 2.60 ms and 4.84 ms. PSR J1536–4948 is a 3.07 ms pulsar in a binary system with an orbital period of ∼62 days about a companion of a minimum mass of 0.32 M⊙. We also present multifrequency pulse profiles of these MSPs from the GMRT observations. PSR J1536–4948 is an MSP with an extremely wide pulse profile having multiple components. Using the radio timing ephemeris we subsequently detected γ-ray pulsations from these three MSPs, confirming them as the sources powering the γ-ray emission. For PSR J1536–4948 we performed combined radio–γ-ray timing using ∼11.6 yr of γ-ray pulse times of arrival (TOAs) along with the radio TOAs. PSR J1536–4948 also shows evidence for pulsed γ-ray emission out to above 25 GeV, confirming earlier associations of this MSP with a ≥10 GeV point source. The multiwavelength pulse profiles of all three MSPs offer challenges to models of radio and γ-ray emission in pulsar magnetospheres.

High energy astrophysics↗
NASA NTRS1971

Development and testing of the S-band antenna subsystem for the Mariner Mars 1971 spacecraft

The Mariner Mars 1971 S-band antenna subsystem is used to transmit and receive S-band signals to and from the Deep Space Instrumentation Facility ground stations. The antenna subsystem consists of a low-gain antenna, a medium-gain antenna, a directional coupler, a high-gain antenna, and all transmission lines required to interconnect the antennas to the spacecraft radio frequency subsystem. The low-gain antenna is used to transmit signals during cruise and receive signals throughout the mission. The medium-gain antenna is coupled to the low-gain antenna via the directional coupler and is used to transmit and receive signals during Mars orbit insertion. The high-gain antenna is used to transmit high data rate signals primarily during Mars orbit.

Brejcha, A. G.↗
DOE OSTI2021

Learning viscoelasticity models from indirect data using deep neural networks

In this study, we propose a novel approach to model viscoelasticity materials, where rate-dependent and non-linear constitutive relationships are approximated with deep neural networks. We assume that inputs and outputs of the neural networks are not directly observable, and therefore common training techniques with input–output pairs for the neural networks are inapplicable. To that end, we develop a novel computational approach to both calibrate parametric and learn neural-network-based constitutive relations of viscoelasticity materials from indirect displacement data in the context of multiple-physics systems. We show that limited displacement data holds sufficient information to quantify the viscoelasticity behavior. We formulate the inverse computation – modeling viscoelasticity properties from observed displacement data – as a PDE-constrained optimization problem and minimize the error functional using a gradient-based optimization method. The gradients are computed by a combination of automatic differentiation and implicit function differentiation rules. The effectiveness of our method is demonstrated through numerous benchmark problems in geomechanics and porous media transport.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Deep-Learning based Reconstruction of the Shower Maximum $X_{\mathrm{max}}$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory

The atmospheric depth of the air shower maximum X max is an observable commonly used for the determination of the nuclear mass composition of ultra-high energy cosmic rays. Direct measurements of X max are performed using observations of the longitudinal shower development with fluorescence telescopes. At the same time, several methods have been proposed for an indirect estimation of X max from the characteristics of the shower particles registered with surface detector arrays. In this paper, we present a deep neural network (DNN) for the estimation of X max . The reconstruction relies on the signals induced by shower particles in the ground based water-Cherenkov detectors of the Pierre Auger Observatory. The network architecture features recurrent long short-term memory layers to process the temporal structure of signals and hexagonal convolutions to exploit the symmetry of the surface detector array. We evaluate the performance of the network using air showers simulated with three different hadronic interaction models. Thereafter, we account for long-term detector effects and calibrate the reconstructed X max using fluorescence measurements. Finally, we show that the event-by-event resolution in the reconstruction of the shower maximum improves with increasing shower energy and reaches less than 25 g/cm 2 at energies above 2 × 10 19 eV.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Variations in the Width, Density, and Direction of the Palomar 5 Tidal Tails

Stars that escape globular clusters form tidal tails that are predominantly shaped by the global distribution of mass in the Galaxy, but also preserve a historical record of small-scale perturbations. Using deep grz photometry from DECaLS, we present highly probable members of the tidal tails associated with the evaporating globular cluster Palomar 5. These data yield the cleanest view of a stellar stream beyond ≈20 kpc and reveal: (1) a wide, low surface-brightness extension of the leading tail; (2) significant density variations along the stream; and (3) sharp changes in the direction of both the leading and the trailing tail. In the fiducial Milky Way model, a rotating bar perturbs the Palomar 5 tails and can produce streams with similar width and density profiles to those observed. However, the deviations of the stream track in this simple model do not match those observed in the Palomar 5 trailing tail, indicating the need for an additional source of perturbation. These discoveries open up the possibility of measuring the population of perturbers in the Milky Way, including dark-matter subhalos, with an ensemble of stellar streams and deep photometry alone.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

DeepDist: real-value inter-residue distance prediction with deep residual convolutional network

Abstract Background Driven by deep learning, inter-residue contact/distance prediction has been significantly improved and substantially enhanced ab initio protein structure prediction. Currently, most of the distance prediction methods classify inter-residue distances into multiple distance intervals instead of directly predicting real-value distances. The output of the former has to be converted into real-value distances to be used in tertiary structure prediction. Results To explore the potentials of predicting real-value inter-residue distances, we develop a multi-task deep learning distance predictor (DeepDist) based on new residual convolutional network architectures to simultaneously predict real-value inter-residue distances and classify them into multiple distance intervals. Tested on 43 CASP13 hard domains, DeepDist achieves comparable performance in real-value distance prediction and multi-class distance prediction. The average mean square error (MSE) of DeepDist’s real-value distance prediction is 0.896 Å 2 when filtering out the predicted distance ≥ 16 Å, which is lower than 1.003 Å 2 of DeepDist’s multi-class distance prediction. When distance predictions are converted into contact predictions at 8 Å threshold (the standard threshold in the field), the precision of top L/5 and L/2 contact predictions of DeepDist’s multi-class distance prediction is 79.3% and 66.1%, respectively, higher than 78.6% and 64.5% of its real-value distance prediction and the best results in the CASP13 experiment. Conclusions DeepDist can predict inter-residue distances well and improve binary contact prediction over the existing state-of-the-art methods. Moreover, the predicted real-value distances can be directly used to reconstruct protein tertiary structures better than multi-class distance predictions due to the lower MSE. Finally, we demonstrate that predicting the real-value distance map and multi-class distance map at the same time performs better than predicting real-value distances alone.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction

Understanding protein structure-function relationships is a key challenge in computational biology, with applications across the biotechnology and pharmaceutical industries. While it is known that protein structure directly impacts protein function, many functional prediction tasks use only protein sequence. In this work, we isolate protein structure to make functional annotations for proteins in the Protein Data Bank in order to study the expressiveness of different structure-based prediction schemes. We present PersGNN - an end-to-end trainable deep learning model that combines graph representation learning with topological data analysis to capture a complex set of both local and global structural features. While variations of these techniques have been successfully applied to proteins before, we demonstrate that our hybridized approach, PersGNN, outperforms either method on its own as well as a baseline neural network that learns from the same information. PersGNN achieves a 9.3% boost in area under the precision recall curve (AUPR) compared to the best individual model, as well as high F1 scores across different gene ontology categories, indicating the transferability of this approach.

Swenson, Nicolas↗
DOE OSTI2023

Emulating aerosol optics with randomly generated neural networks

Abstract. Atmospheric aerosols have a substantial impact on climate and remain one of the largest sources of uncertainty in climate prediction. Accurate representation of their direct radiative effects is a crucial component of modern climate models. However, direct computation of the radiative properties of aerosol populations is far too computationally expensive to perform in a climate model, so optical properties are typically approximated using a parameterization. This work develops artificial neural networks (ANNs) capable of replacing the current aerosol optics parameterization used in the Energy Exascale Earth System Model (E3SM). A large training dataset is generated by using Mie code to directly compute the optical properties of a range of atmospheric aerosol populations given a large variety of particle sizes, wavelengths, and refractive indices. Optimal neural architectures for shortwave and longwave bands are identified by evaluating ANNs with randomly generated wirings. Randomly generated deep ANNs are able to outperform conventional multilayer-perceptron-style architectures with comparable parameter counts. Finally, the ANN-based parameterization produces significantly more accurate bulk aerosol optical properties than the current parameterization when compared with direct Mie calculations using mean absolute error. The success of this approach makes possible the future inclusion of much more sophisticated representations of aerosol optics in climate models that cannot be captured by extension of the existing parameterization scheme and also demonstrates the potential of random-wiring-based neural architecture search in future applications in the Earth sciences.

54 ENVIRONMENTAL SCIENCES↗