SEARCH · Engineering Papers

Results for “learned priors”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 757 records · Page 42

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Autonomous extraction of millimeter-scale deformation in InSAR time series using deep learning

Systematically characterizing slip behaviours on active faults is key to unraveling the physics of tectonic faulting and the interplay between slow and fast earthquakes. Interferometric Synthetic Aperture Radar (InSAR), by enabling measurement of ground deformation at a global scale every few days, may hold the key to those interactions. However, atmospheric propagation delays often exceed ground deformation of interest despite state-of-the art processing, and thus InSAR analysis requires expert interpretation and a priori knowledge of fault systems, precluding global investigations of deformation dynamics. Here, we show that a deep auto-encoder architecture tailored to untangle ground deformation from noise in InSAR time series autonomously extracts deformation signals, without prior knowledge of a fault’s location or slip behaviour. Applied to InSAR data over the North Anatolian Fault, our method reaches 2 mm detection, revealing a slow earthquake twice as extensive as previously recognized. We further explore the generalization of our approach to inflation/deflation-induced deformation, applying the same methodology to the geothermal field of Coso, California.

58 GEOSCIENCES↗

NASA NTRS2023

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As the space economy continues to expand through increasingly easy access to advanced and inexpensive technology, space missions themselves have become more ambitious with exploration targets growing ever distant while simultaneously requiring larger guidance and communication budgets. These conflicting desires of distance and control drive the need for advanced on-board intelligent decision making to reduce communication and control limitations by automating as many mission functions as possible in-situ. While the amount of research on such Artificial Intelligence and Machine Learning (AI/ML) software modules has grown exponentially, the capacity to experimentally validate such software modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available bleeding-edge computational platforms via what is programmatically referred to as the BrainStack on the TechEdSat (TES-n) flight series. This on-orbit computational platform provides an evaluation laboratory where advanced software experiments are pre-loaded into memory prior to launch, then executed as payloads during mission operations with results reported back and program tweaks or new training sets uploaded as needed. Processors selected as part of the BrainStack are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and, more recently, neuromorphic processors, in LEO operations. Neuromorphic processors are of particular interest due to their superior power efficiency over GPUs in intelligent automation applications. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on TES-13, January 13, 2022, and continues to operate in orbit despite no significant modifications to harden the processor against the space environment. The Intel Loihi Gen-1 on TES-13 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. The processor is packaged in the Kapoho Bay USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by an Intel Pentium single-board computer to handle scheduling of the software application payloads and communications with the satellite’s primary computer. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the continually evolving BrainStack in the upcoming three TES-n/NOW flights. The Kapoho Point unit will incorporate eight Loihi-2 processors, enabling neural networks of up to one million neurons and one billion synapsis. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space automation applications may be initially tested.

Artificial Intelligence↗

DOE OSTI2022

Learning Grain-Boundary Segregation: From First Principles to Polycrystals

The segregation of solute atoms at grain boundaries (GBs) can strongly impact the structural and functional properties of polycrystals. Yet, due to the limited availability of simulation tools to study polycrystals at the atomistic scale (i.e., interatomic potentials), there is a minimal understanding of the variation of solute segregation tendencies across the very complex space of GB microenvironments and the large range of alloys in which it can occur. Here, we develop an algorithmic framework that can directly learn the full spectrum of segregation energies for a metal solute atom in a metal polycrystal from ab initio methods, bypassing the need for alloy interatomic potentials. This framework offers a pathway to a comprehensive catalog of GB solute segregation with quantum accuracy, for the entire alloy space. As an initial demonstration in this pursuit, we build an extensive GB segregation database for aluminum-based alloys across the periodic table, including dozens of alloys for which there are substantially no prior data.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2021

CAN-D: A Modular Four-Step Pipeline for Comprehensively Decoding Controller Area Network Data

Controller area networks (CANs) are a broadcast protocol for real-time communication of critical vehicle subsystems. Original equipment manufacturers of passenger vehicles hold secret their mappings of CAN data to vehicle signals, and these definitions vary according to make, model, and year. Without these mappings, the wealth of real-time vehicle information hidden in the CAN packets is uninterpretable, severely impeding vehicle-related research, including CAN cybersecurity and privacy studies, aftermarket tuning, efficiency and performance monitoring, and fault diagnosis to name a few. Guided by the four-part CAN signal definition, we present CAN-D (CAN-Decoder), a modular, four-step pipeline for identifying each signal's boundaries (start bit and length), endianness (byte ordering), signedness (bit-to-integer encoding), and by leveraging diagnostic standards, augmenting a subset of the extracted signals with meaningful, physical interpretation. En route to CAN-D, we provide a comprehensive review of the CAN signal reverse engineering research. All previous methods ignore endianness and signedness, rendering them incapable of decoding many standard CAN signal definitions. Incorporating endianness grows the search space from 128 to 4.72E21 signal tokenizations and introduces a web of changing dependencies. In response, we formulate, formally analyze, and provide an efficient solution to an optimization problem, allowing identification of the optimal set of signal boundaries and byte orderings. In addition, we provide two novel, state-of-the-art signal boundary classifiers—both of which are superior to previous approaches in precision and recall in three different test scenarios—and the first signedness classification algorithm, which exhibits a $>$ 97% F-score. Altogether, CAN-D is the only solution with the potential to extract any CAN signal that is also the state of the art. In evaluation on 10 vehicles of different makes, CAN-D's average $\ell ^1$ error is five times better (81% less) than all previous methods and exhibits lower average error, even when considering only signals that meet prior methods’ assumptions. Finally, CAN-D is implemented in lightweight hardware, allowing for an on-board diagnostic (OBD-II) plugin for real-time in-vehicle CAN decoding.

42 ENGINEERING↗

NASA NTRS1994

Operations automation

This is truly the era of 'faster-better-cheaper' at the National Aeronautics and Space Administration/Jet Propulsion Laboratory (NASA/JPL). To continue JPL's primary mission of building and operating interplanetary spacecraft, all possible avenues are being explored in the search for better value for each dollar spent. A significant cost factor in any mission is the amount of manpower required to receive, decode, decommutate, and distribute spacecraft engineering and experiment data. The replacement of the many mission-unique data systems with the single Advanced Multimission Operations System (AMMOS) has already allowed for some manpower reduction. Now, we find that further economies are made possible by drastically reducing the number of human interventions required to perform the setup, data saving, station handover, processed data loading, and tear down activities that are associated with each spacecraft tracking pass. We have recently adapted three public domain tools to the AMMOS system which allow common elements to be scheduled and initialized without the normal human intervention. This is accomplished with a stored weekly event schedule. The manual entries and specialized scripts which had to be provided just prior to and during a pass are now triggered by the schedule to perform the functions unique to the upcoming pass. This combination of public domain software and the AMMOS system has been run in parallel with the flight operation in an online testing phase for six months. With this methodology, a savings of 11 man-years per year is projected with no increase in data loss or project risk. There are even greater savings to be gained as we learn other uses for this configuration.

Boreham, Charles Thomas↗

NASA NTRS2012

Launch Pad Closeout Operations for the Mars Science Laboratory's Heat Rejection System

The Mars Science Laboratory (MSL) rover was launched on an Atlas V on November 26, 2011. Preparations were carried out prior to launch in order to closeout the spacecraft's complex heat rejection system (HRS), which consists of two mechanically pumped CFC-11 fluid loops. The first HRS loop, onboard the Curiosity rover, was fully integrated, filled with CFC-11, and successfully operated prior to launch pad operations; however, the second thermal loop, called the cruise HRS loop, required final mechanical and thermal integration activities to occur while on the launch pad in order to accommodate the last minute installation of the rover's Multi-Mission Radioisotope Thermoelectric Generator (MMRTG) power source. In order to prevent overheating of propellant tanks and critical avionics equipment buried deep within the spacecraft's aeroshell, the MMRTG needed to be pre-cooled using a separate non-flight mechanically pumped fluid loop prior to and during the final closeout and subsequent startup of the flight loop. This paper outlines the various steps that took place to safely install the MMRTG while carefully transitioning from the pre-cooling operation to the final startup and operation of the flight cruise HRS loop. Temperature data of the launch pad thermal transition from the ground support loop activity to the final flight loop operation is presented. Some background development of the ground support loop and lessons learned are also discussed. This successful launch pad integration activity required a close-knit coordination between NASA KSC, JPL, the Department of Energy, Idaho National Labs, Pratt and Whitney Rocketdyne Inc., Teledyne Technologies Inc., ULA, and Advanced Thermal Sciences Corp.

thermal↗

NASA NTRS2020

ZTF Early Observations of Type Ia Supernovae. II. First Light, the Initial Rise, and Time to Reach Maximum Brightness

While it is clear that Type Ia supernovae (SNe) are the result of thermonuclear explosions in C/O white dwarfs (WDs), a great deal remains uncertain about the binary companion that facilitates the explosive disruption of the WD. Here, we present a comprehensive analysis of a large, unique data set of 127 SNe Ia with exquisite coverage by the Zwicky Transient Facility (ZTF). High-cadence (six observations per night) ZTF observations allow us to measure the SN rise time and examine its initial evolution. We develop a Bayesian framework to model the early rise as a power law in time, which enables the inclusion of priors in our model. For a volume-limited subset of normal SNe Ia, we find that the mean power-law index is consistent with 2 in the r(ZTF)-band (a(r) = 2.01 ± 0.02), as expected in the expanding fireball model. There are, however, individual SNe that are clearly inconsistent with a(r) = 2. We estimate a mean rise time of 18.9 days (with a range extending from ∼15 to 22 days), though this is subject to the adopted prior. We identify an important, previously unknown, bias whereby the rise times for higher redshift SNe within a flux-limited survey are systematically underestimated. This effect can be partially alleviated if the power-law index is fixed to α = 2, in which case we estimate a mean rise time of 21.7 days (with a range from ∼18 to 23 days). The sample includes a handful of rare and peculiar SNe Ia. Finally, we conclude with a discussion of lessons learned from the ZTF sample that can eventually be applied to observations from the Vera C. Rubin Observatory.

A. A. Miller↗

DOE OSTI2025

Neural chaos: A spectral stochastic neural operator

Building surrogate models for operators with uncertainty quantification capabilities is essential for many engineering applications where randomness–such as variability in material properties, boundary conditions, and initial conditions–is unavoidable. Polynomial Chaos Expansion (PCE) is widely recognized as a go-to method for constructing stochastic surrogates in both intrusive and non-intrusive ways, and it has recently been used in the context of operator learning. However, its application becomes challenging for complex or high-dimensional processes, as achieving accuracy requires higher-order polynomials, which can increase computational demand and/or the risk of overfitting. Furthermore, PCE requires specialized treatments to manage random variables that are not independent, and these treatments may be problem-dependent or may fail with increasing complexity. Here, in this work, we adopt the same formalism as the spectral expansion used in PCE; however, we replace the classical polynomial basis functions with neural network (NN) basis functions to leverage their expressivity. To achieve this, we propose an algorithm that identifies NN-parameterized basis functions in a purely data-driven manner, without any prior assumptions about the joint distribution of the random variables involved, whether independent or dependent, or about their marginal distributions. The proposed algorithm identifies each NN-parameterized basis function sequentially, ensuring they are orthogonal with respect to the data distribution. The basis functions are constructed directly on the joint stochastic variables without requiring a tensor product structure or assuming independence of the random variables. This approach may offer greater flexibility for complex stochastic models, while simplifying implementation compared to the tensor product structures typically used in PCE to handle random vectors. This is particularly advantageous given the current state of open-source packages, where building and training neural networks can be done with just a few lines of code and extensive community support. We demonstrate the effectiveness of the proposed scheme through several numerical examples of varying complexity and provide comparisons with classical PCE.

Polynomial chaos expansion↗

NASA NTRS2020

Mars 2020 Center Differential Pivot Restraint: Flexurized Spring System Providing Compliance for Rover Mobility Deployment Prior to Landing

The Center Differential Pivot Restraint (CDPR) for the Mars 2020 mission is designed to constrain motion of the rover differential and to dampen out the load response of during rover’s mobility deployment event in Entry, Descent, and Landing (EDL) phase of the mission. For Mars 2020, it was required to redesign the mechanism to save minimum 33% of the mass from the previous Mars Science Laboratory (MSL) design. The new mechanism architecture used a monolithic spring-like flexure to act as the system compliance, resulting in 50% mass savings from the MSL design. Along the design and prototype testing process, several mechanism design principles were re-affirmed as well as lessons learned about potential race conditions.

Cameron, Matthew↗

DOE OSTI2026

Control Room of the Future Testbed Workshop – After-Action Report

The U.S. Department of Energy’s Office of Electricity is supporting a one-year, multi-laboratory effort to define the needs and requirements for a Control Room of the Future testbed, or CROFT. The effort responds to increasing grid complexity driven by large new loads, dynamic generation resources, and the growing adoption of advanced technologies and tools, including artificial intelligence (AI) and machine learning (ML). To support safe, secure, and effective grid modernization, CROFT will focus on how emerging technologies and tools can be rigorously evaluated in realistic operational settings, with attention to human-machine interaction, cognitive load, and workforce readiness. The project team includes Argonne National Laboratory, Idaho National Laboratory, National Laboratory of the Rockies, and Pacific Northwest National Laboratory. As part of the scoping effort, the team conducted two industry-focused workshops: one at DTECH on February 5, 2026, informed by prior industry interviews, and a second on May 4, 2026, adjacent to IEEE T&D. These engagements brought together utilities, vendors, consultants, national laboratories, academia, and government stakeholders to identify and prioritize use cases, barriers, validation needs, data-sharing constraints, and near- and longer-term requirements. This feedback will directly inform CROFT’s architecture and research focus areas, ensuring the testbed is grounded in real-world operational needs and designed to evaluate emerging technologies and tools in realistic control-room environments.

artificial intelligence↗

NASA NTRS1993

Entry Systems Panel deliberations

The Entry Systems Panel was chaired by Don Rummler, LaRC and Dan Rasky, ARC. As requested, each panel participant prior to the workshop prepared and delivered presentations to: (1) identify technology needs; (2) assess current programs; (3) identify technology gaps; and (4) identify highest payoff areas R&D. Participants presented background on the entry systems R&D efforts and operations experiences for the Space Shuttle Orbiter. These participants represented NASA Centers involved in research (Ames Research Center), development (Johnson Space Center) and operations (Kennedy Space Center) and the Shuttle Orbiter prime contractor. The presentations lead to the discovery of several lessons learned.

Rasky, Daniel J.↗

NASA NTRS2017

Hardware Assessment in Support of the Dynamic Power Convertor Development Effort

Stirling Radioisotope Power Systems (RPS) are being developed by NASA's RPS Program in collaboration with the U.S. Department of Energy (DOE). Efforts ranging from 2001 to 2015 enabled development of the Technology Demonstration Convertor (TDC) for use in the 110-watt Stirling Radioisotope Generator (SRG-110) and the Advanced Stirling Convertor (ASC) for use in the Advanced Stirling Radioisotope Generator (ASRG). The DOE selected Lockheed Martin Space Systems Company (LMSSC) as the system integration contractor for both flight development efforts. The SRG-110 housed two TDCs fabricated by Infinia and resulted in the production of 16x demonstration units and 2x engineering units. The project was redirected in 2006 to make use of a more efficient and lower mass ASCs under development by Sunpower Inc. The DOE managed the flight contract with LMSSC and subcontractor Sunpower Inc. from 2007 to 2013 to build the ASRG, with support from NASA Glenn Research Center (GRC). Sunpower Inc. held two parallel contracts to produce ASCs, one with Lockheed Martin to produce ASC-F flight units and one with GRC for the production of ASC-E3 engineering unit pathfinders that were used to refine the flight design and production processes. The DOE initiated termination of the ASRG contract in late 2013. After ASRG had ended, GRC completed characterization testing of the ASRG Engineering Unit #2 (EU2) and the GRC contract with Sunpower was also completed. The NASA RPS Program Office has recently initiated a new Dynamic Power Conversion development effort which includes the potential maturation of Stirling, Brayton, and Rankine power convertors for the next generation of RPS. The effort started with the request for proposal and review of submits. Contracts are anticipated for release in 2017 and will initially focus on a design phase prior to fabrication and testing. This new effort will focus on robustness in addition to high efficiency, specific power, and reliability. Also, some requirements introduced during the ASRG contract have also been included in the new effort, such as constant lateral loading. Due to the focus on robustness and new requirements relative to the older TDC design, the Stirling Cycle Development Project has initiated an assessment of government owned hardware to help inform requirements evolution and evaluation of future designs. While lessons learned from the ASRG flight development project have been taken into consideration, the evaluation of the TDC design had not been completed for some existing environments or relatively new requirements. To further assess the TDC design, a series of tasks were initiated to evaluate degradation for units that have operated unattended for over 105,000 hours, demonstrate robustness to a random vibration environment, characterize and evaluate performance for varying lateral load profiles. The status for each task are described.

Wilson, Scott D.↗

NASA NTRS2018

Hardware Assessment in Support of the Dynamic Power Convertor Development Effort

Stirling Radioisotope Power Systems (RPS) are being developed by NASAs RPS Program in collaboration with the U.S. Department of Energy (DOE). Efforts ranging from 2001 to 2015 enabled development of the Technology Demonstration Convertor (TDC) for use in the 110-watt Stirling Radioisotope Generator (SRG-110) and the Advanced Stirling Convertor (ASC) for use in the Advanced Stirling Radioisotope Generator (ASRG). The DOE selected Lockheed Martin Space Systems Company (LMSSC) as the system integration contractor for both flight development efforts. The SRG-110 housed two TDCs fabricated by Infinia and resulted in the production of 16x demonstration units and 2x engineering units. The project was redirected in 2006 to make use of a more efficient and lower mass ASCs under development by Sunpower Inc. The DOE managed the flight contract with LMSSC and subcontractor Sunpower Inc. from 2007 to 2013 to build the ASRG, with support from NASA Glenn Research Center (GRC). Sunpower Inc. held two parallel contracts to produce ASCs, one with Lockheed Martin to produce ASC-F flight units and one with GRC for the production of ASC-E3 engineering unit pathfinders that were used to refine the flight design and production processes. The DOE initiated termination of the ASRG contract in late 2013. After ASRG had ended, GRC completed characterization testing of the ASRG Engineering Unit 2 (EU2) and the GRC contract with Sunpower was also completed. The NASA RPS Program Office has recently initiated a new Dynamic Power Conversion development effort which includes the potential maturation of Stirling, Brayton, and Rankine power convertors for the next generation of RPS. The effort started with the request for proposal and review of submits. Contracts are anticipated for release in 2017 and will initially focus on a design phase prior to fabrication and testing. This new effort will focus on robustness in addition to high efficiency, specific power, and reliability. Also, some requirements introduced during the ASRG contract have also been included in the new effort, such as constant lateral loading. Due to the focus on robustness and new requirements relative to the older TDC design, the Stirling Cycle Development Project has initiated an assessment of government owned hardware to help inform requirements evolution and evaluation of future designs. While lessons learned from the ASRG flight development project have been taken into consideration, the evaluation of the TDC design had not been completed for some existing environments or relatively new requirements. To further assess the TDC design, a series of tasks were initiated to evaluate degradation for units that have operated unattended for over 105,000 hours, demonstrate robustness to a random vibration environment, characterize and evaluate performance for varying lateral load profiles. The status for each task are described.

Wilson, Scott D.↗

DOE OSTI2020

Reliable machine prognostic health management in the presence of missing data

Prognostics and health management enables the prediction of future degradation and remaining useful life (RUL) for in-service systems based on historical and contemporary data, showing promise for many practical applications. One major challenge for prognostics is the common occurrence of missing values in time-series data, often caused by disruptions in sensor communication or hardware/software failures. Another major concern is that the sufficient prior knowledge of critical component degradation with a clear failure threshold is often not readily available in practice. These issues can significantly hinder the application of advanced signal and data analysis methods and consequently degrade the health management performance. In this article, we propose a novel data-driven framework that is capable of providing accurate and reliable predictions of degradation and RUL. In this approach, one-hot health state indicators are appended to the historical time series so that the model learns end-of-life automatically. A modified gate recurrent unit based variational autoencoder is employed in generative adversarial networks to model the temporal irregularity of the incomplete time series. Furthermore, experiments on multivariate time-series datasets collected from real-world aeroengines verify that significant performance improvement can be achieved using the proposed model for robust long-term prognostics.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2023

Exploring the Relationship of Microstructure and Conductivity in Metal Halide Perovskites via Active Learning-Driven Automated Scanning Probe Microscopy

Electronic transport and hysteresis in metal halide perovskites (MHPs) are key to the applications in photovoltaics, light emitting devices, and light and chemical sensors. These phenomena are strongly affected by the materials microstructure including grain boundaries, ferroic domain walls, and secondary phase inclusions. Here, we demonstrate an active machine learning framework for “driving” an automated scanning probe microscope (SPM) to discover the microstructures responsible for specific aspects of transport behavior in MHPs. In our setup, the microscope can discover the microstructural elements that maximize the onset of conduction, hysteresis, or any other characteristic that can be derived from a set of current–voltage spectra. Furthermore, this approach opens new opportunities for exploring the origins of materials functionality in complex materials by SPM and can be integrated with other characterization techniques either before (prior knowledge) or after (identification of locations of interest for detail studies) functional probing.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Integrating Ultra-Coarse-Grained Protein Models into Accessible Workflows for Multiscale Molecular Dynamics

To capture protein conformational transitions using molecular dynamics (MD), several simulation resolutions covering different spatial and temporal scales are typically needed. All-atom (AA) simulations provide fine resolution, but are computationally infeasible for large systems over longer durations. Coarse-grained (CG) and ultra-coarse-grained (UCG) models have a lower resolution and computational cost while still being able to conserve essential protein features. Prior work on a Multiscale Machinelearned Modeling Infrastructure (MuMMI) combined both AA and CG simulations to study RAS-RAF protein interactions, leveraging CG models for longer time scales and using AA to investigate unusual conformations in greater detail. However, MuMMI is still resource-intensive, and this study aims to maximize exploration of the protein conformational space while reducing computational cost. In this paper, we build on prior work that integrates UCG models based on heterogeneous elastic network modeling (hENM) into the MuMMI workflow. We demonstrate that UCG models enable accurate sampling of protein conformations, focusing on simulating RAS-RAF protein interactions. Using higher-resolution CG Martini simulation data, we can automatically refine intramolecular interactions in UCG models. We present a scalable Python package that uses fluctuations observed in higher-resolution CG Martini simulations to estimate bond coefficients of the UCG model. We built novel machine learning-based backmapping methods to recover more detailed CG Martini structures from UCG structures, using diffusion models to learn the mapping between scales. Finally, we present UCG-mini-MuMMI, an accessible and less compute-intensive version of MuMMI as a resource for the scientific community. Incorporating UCG models into MD studies is applicable to a broad range of systems and proteins, and our study offers insights into the advantages and limitations of these methods.

Chemical structure↗

DOE OSTI2022

When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?

Physics-informed neural networks (PINNs) have become a popular choice for solving high-dimensional partial differential equations (PDEs) due to their excellent approximation power and generalization ability. Recently, extended PINNs (XPINNs) based on domain decomposition methods have attracted considerable attention due to their effectiveness in modeling multiscale and multiphysics problems and their parallelization. However, theoretical understanding of their convergence and generalization properties remains unexplored. In this study, we take an initial step towards understanding how and when XPINNs outperform PINNs. Specifically, for general multilayer PINNs and XPINNs, we first provide a prior generalization bound via the complexity of the target functions in the PDE problem and a posterior generalization bound via the posterior matrix norms of the networks after optimization. Moreover, based on our bounds, we analyze the conditions under which XPINNs improve generalization. Concretely, our theory shows that the key building block of XPINN, namely, the domain decomposition, introduces a tradeoff for generalization. On the one hand, XPINNs decompose the complex PDE solution into several simple parts, which decreases the complexity needed to learn each part and boosts generalization. On the other hand, decomposition leads to less training data being available in each subdomain, and hence such a model is typically prone to overfitting and may become less generalizable. Empirically, we choose five PDEs to show when XPINNs perform better than, similar to, or worse than PINNs, hence demonstrating and justifying our new theory.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2021

TLife-LSTM: Forecasting Future COVID-19 Progression with Topological Signatures of Atmospheric Conditions

Understanding the impact of atmospheric conditions on SARS-CoV2 is critical to model COVID-19 dynamics and sheds a light on the future spread around the world. Furthermore, geographic distri- butions of expected clinical severity of COVID-19 may be closely linked to prior history of respiratory diseases and changes in humidity, tem- perature, and air quality. In this context, we postulate that by tracking topological features of atmospheric conditions over time, we can provide a quanti?able structural distribution of atmospheric changes that are likely to be related to COVID-19 dynamics. As such, we apply the machinery of persistence homology on time series of graphs to extract topological signatures and to follow geographical changes in relative humidity and temperature. We develop an integrative machine learning framework named Topological Lifespan LSTM (TLife-LSTM) and test its predictive capabilities on forecasting the dynamics of SARS-CoV2 cases. We validate our framework using the number of con?rmed cases and hospitalization rates recorded in the states of Washington and California in the USA. Our results demonstrate the predictive potential of TLife-LSTM in forecasting the dynamics of COVID-19 and modeling its complex spatio-temporal spread dynamics.

Gel, Yulia R.↗