Search NASA⌕ Search

SEARCH · Search NASA

Results for “Task complexity”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Analog Testing of Operations Concepts for Mitigation of Communication Latency During Human Space Exploration

OBJECTIVES: NASA Extreme Environment Mission Operations (NEEMO) is an underwater spaceflight analog that allows a true mission‐like operational environment and uses buoyancy effects and added weight to simulate different gravity levels. Three missions were undertaken from 2014‐2015, NEEMO's 18‐20. All missions were performed at the Aquarius undersea research habitat. During each mission, the effects of varying operations concepts and tasks type and complexity on representative communication latencies associated with Mars missions were studied. METHODS: 12 subjects (4 per mission) were weighed out to simulate near‐zero or partial gravity extravehicular activity (EVA) and evaluated different operations concepts for integration and management of a simulated Earth‐based science backroom team (SBT) to provide input and direction during exploration activities. Exploration traverses were planned in advance based on precursor data collected. Subjects completed science‐related tasks including presampling surveys, geologic‐based sampling, and marine‐based sampling as a portion of their tasks on saturation dives up to 4 hours in duration that were to simulate extravehicular activity (EVA) on Mars or the moons of Mars. One‐way communication latencies, 5 and 10 minutes between space and mission control, were simulated throughout the missions. Objective data included task completion times, total EVA times, crew idle time, translation time, SBT assimilation time (defined as time available for SBT to discuss data/imagery after it has been collected, in addition to the time taken to watch imagery streaming over latency). Subjective data included acceptability, simulation quality, capability assessment ratings, and comments. RESULTS: Precursor data can be used effectively to plan and execute exploration traverse EVAs (plans included detailed location of science sites, high‐fidelity imagery of the sites, and directions to landmarks of interest within a site). Operations concepts that allow for presampling surveys enable efficient traverse execution and meaningful Mission Control Center (MCC) interaction across long communication latencies and can be done with minimal crew idle time. Imagery and information from the EVA crew that is transmitted real‐time to the intravehicular (IV) crewmember(s) can be used to verify that exploration traverse plans are being executed correctly. That same data can be effectively used by MCC (across comm latency) to provide further instructions to the crew from a SBT on sampling priorities, additional tasks, and changes to the plan. Text / data capabilities are preferred over voice capabilities between MCC and IV when executing exploration traverse plans over communication latency. Autonomous crew planning tools can be effective at modifying existing plans if the objectives and constraints are clearly defined.

Chappell, Steven P.↗
NASA NTRS2022

Balancing Predictive and Reactive Science Planning for Mars 2020 Perseverance

The design of the science planning process for a space science mission needs to find a balance between operational and resource constraints and scientific decision-making. Science planning has previously been characterized as either predictive or reactive. Predictive science planning is needed when constraints drive science activities to be planned far in advance. For example, a combination of long one-way light time plus high-stakes science decisions drove the Cassini-Huygens mission to Saturn to have an extremely predictive planning process. On the other extreme, reactive science planning is needed when constraints drive science activities to be planned based on the results of the previous plan. For example, the Mars Exploration Rover mission interacted with the surface of Mars, and so the planning team needed to know the state of the rover at the end of each planning cycle before starting the next cycle. Operational and resource constraints that require management on intermediate timescales has led to the development of a science planning process between these two extremes. For example, the Mars Science Laboratory is a technically complex rover and has a parallel predictive process that allows the operations team to manage engineering constraints several days in advance while maintaining the reactive tactical planning process similar to that of MER. The Mars 2020 Perseverance rover is a technically complex rover in the MSL style, but has an added layer of science complexity: it is tasked with collecting a returnable cache of scientifically valuable samples of Mars within prime mission. Thus, the science planning process also needs to accommodate high-stakes longer-term science decisions in the style of Cassini. In order to balance the push-pull of these constraints, we have developed a science campaign-focused operational paradigm for Mars 2020 Perseverance that allows for both predictive planning to accommodate technological complexity and high-stakes science decisions as well as reactive planning to accommodate the realities of interacting with the martian surface. This paradigm influenced the design of operational processes and operational tools.

Spanovich, Nicole↗
NASA NTRS1997

Using APEX to Model Anticipated Human Error: Analysis of a GPS Navigational Aid

The interface development process can be dramatically improved by predicting design facilitated human error at an early stage in the design process. The approach we advocate is to SIMULATE the behavior of a human agent carrying out tasks with a well-specified user interface, ANALYZE the simulation for instances of human error, and then REFINE the interface or protocol to minimize predicted error. This approach, incorporated into the APEX modeling architecture, differs from past approaches to human simulation in Its emphasis on error rather than e.g. learning rate or speed of response. The APEX model consists of two major components: (1) a powerful action selection component capable of simulating behavior in complex, multiple-task environments; and (2) a resource architecture which constrains cognitive, perceptual, and motor capabilities to within empirically demonstrated limits. The model mimics human errors arising from interactions between limited human resources and elements of the computer interface whose design falls to anticipate those limits. We analyze the design of a hand-held Global Positioning System (GPS) device used for radical and navigational decisions in small yacht recalls. The analysis demonstrates how human system modeling can be an effective design aid, helping to accelerate the process of refining a product (or procedure).

VanSelst, Mark↗
NASA NTRS2008

Cassini Information Management System in Distributed Operations Collaboration and Cassini Science Planning

Launched on October 15, 1997, the Cassini-Huygens spacecraft began its ambitious journey to the Saturnian system with a complex suite of 12 scientific instruments, and another 6 instruments aboard the European Space Agencies Huygens Probe. Over the next 6 1/2 years, Cassini would continue its relatively simplistic cruise phase operations, flying past Venus, Earth, and Jupiter. However, following Saturn Orbit Insertion (SOI), Cassini would become involved in a complex series of tasks that required detailed resource management, distributed operations collaboration, and a data base for capturing science objectives. Collectively, these needs were met through a web-based software tool designed to help with the Cassini uplink process and ultimately used to generate more robust sequences for spacecraft operations. In 2001, in conjunction with the Southwest Research Institute (SwRI) and later Venustar Software and Engineering Inc., the Cassini Information Management System (CIMS) was released which enabled the Cassini spacecraft and science planning teams to perform complex information management and team collaboration between scientists and engineers in 17 countries. Originally tailored to help manage the science planning uplink process, CIMS has been actively evolving since its inception to meet the changing and growing needs of the Cassini uplink team and effectively reduce mission risk through a series of resource management validation algorithms. These algorithms have been implemented in the web-based software tool to identify potential sequence conflicts early in the science planning process. CIMS mitigates these sequence conflicts through identification of timing incongruities, pointing inconsistencies, flight rule violations, data volume issues, and by assisting in Deep Space Network (DSN) coverage analysis. In preparation for extended mission operations, CIMS has also evolved further to assist in the planning and coordination of the dual playback redundancy of highvalue data from targets such as Titan and Enceladus. This paper will outline the critical role that CIMS has played for Cassini in the distributed ops paradigm throughout operations. This paper will also examine the evolution that CIMS has undergone in the face of new science discoveries and fluctuating operational needs. And finally, this paper will conclude with theoretical adaptation of CIMS for other projects and the potential savings in cost and risk reduction that could potentially be tapped into by future missions.

Equils, Douglas J.↗
NASA NTRS1960

Centrifuge Study of Pilot Tolerance to Acceleration and the Effects of Acceleration on Pilot Performance

A research program the general objective of which was to measure the effects of various sustained accelerations on the control performance of pilots, was carried out on the Aviation Medical Acceleration Laboratory centrifuge, U.S. Naval Air Development Center, Johnsville, PA. The experimental setup consisted of a flight simulator with the centrifuge in the control loop. The pilot performed his control tasks while being subjected to acceleration fields such as might be encountered by a forward-facing pilot flying an atmosphere entry vehicle. The study was divided into three phases. In one phase of the program, the pilots were subjected to a variety of sustained linear acceleration forces while controlling vehicles with several different sets of longitudinal dynamics. Here, a randomly moving target was displayed to the pilot on a cathode-ray tube. For each combination of acceleration field and vehicle dynamics, pilot tracking accuracy was measured and pilot opinion of the stability and control characteristics was recorded. Thus, information was obtained on the combined effects of complexity of control task and magnitude and direction of acceleration forces on pilot performance. These tests showed that the pilot's tracking performance deteriorated markedly at accelerations greater than about 4g when controlling a lightly damped vehicle. The tentative conclusion was also reached that regardless of the airframe dynamics involved, the pilot feels that in order to have the same level of control over the vehicle, an increase in the vehicle dynamic stability was required with increases in the magnitudes of the acceleration impressed upon the pilot. In another phase, boundaries of human tolerance of acceleration were established for acceleration fields such as might be encountered by a pilot flying an orbital vehicle. A special pilot restraint system was developed to increase human tolerance to longitudinal decelerations. The results of the tests showed that human tolerance of longitudinal deceleration forces was considerably improved through use of the special restraint system.

Creer, Brent Y.↗
DOE OSTI2023

DeepAstroUDA: semi-supervised universal domain adaptation for cross-survey galaxy morphology classification and anomaly detection

Abstract Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA , as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1993

Programmable display pushbuttons on the Space Station's telerobot control panel

The Man-Systems Telerobotics Laboratory at NASA's Johnson Space Center and supported by Lockheed, is working to ensure that the Flight Telerobotic Servicer (FTS) to be used on the Space Shuttle (Orbiter) and the Space Station has a well designed user interface from a Human Factors perspective. The FTS, which is a project led by NASA's Goddard Space Flight Center, will be a telerobot used for Space Station construction, maintenance, and satellite repair. It will be directly controlled from workstations on the Orbiter and the Space Station and monitored from a ground workstation. The FTS will eventually evolve into a more autonomous system, but in the short-term the system will be manually operated (teleoperated) for many tasks. This emphasizes the importance of the human/telerobot interface on this system. This phase of the FTS workstation evaluation covers a preliminary study of programmable display pushbuttons (PDP's). The PDP is constructed of a matrix of directly addressable electroluminescent (EL) pixels which can be used to form dot-matrix characters. PDP's can be used to display more than one message and to control more than one function. Since the PDP's have these features, then a single PDP may possibly replace the use of many single-function pushbuttons, rotary switches, and toggle switches, thus using less panel space. It is of interest to determine if PDP's can be used to adequately perform complex hierarchically structured task sequences. The objective of this investigation was to compare the performance of experienced and inexperienced Remote Manipulator System (RMS) operators while performing an RMS like task on simulated PDP and non-PDP computer prototypes so that guidelines governing the use of programmable display pushbuttons on the FTS workstation could be created. The functionality of the RMS on the Orbiter was used as a model for this evaluation since the functionality of the FTS at the time of this writing has not been solidified.

Stuart, Mark A.↗
NASA NTRS2017

Tracking Historical NASA EVA Training: Lifetime Surveillance of Astronaut Health (LSAH) Development of the EVA Suit Exposure Tracker (EVA SET)

During a spacewalk, designated as extravehicular activity (EVA), an astronaut ventures from the protective environment of the spacecraft into the vacuum of space. EVAs are among the most challenging tasks during a mission, as they are complex and place the astronaut in a highly stressful environment dependent on the spacesuit for survival. Due to the complexity of EVA, NASA has conducted various training programs on Earth to mimic the environment of space and to practice maneuvers in a more controlled and forgiving environment. However, rewards offset the risks of EVA, as some of the greatest accomplishments in the space program were accomplished during EVA, such as the Apollo moonwalks and the Hubble Space Telescope repair missions. Water has become the environment of choice for EVA training on Earth, using neutral buoyancy as a substitute for microgravity. During EVA training, an astronaut wears a modified version of the spacesuit adapted for working in water. This high fidelity suit allows the astronaut to move in the water while performing tasks on full-sized mockups of space vehicles, telescopes, and satellites. During the early Gemini missions, several EVA objectives were much more difficult than planned and required additional time. Later missions demonstrated that "complex (EVA) tasks were feasible when restraints maintained body position and underwater simulation training ensured a high success probability".1,2 EVA training has evolved from controlling body positioning to perform basic tasks to complex maintenance of the Hubble Space Telescope and construction of the International Space Station (ISS). Today, preparation is centered at special facilities built specifically for EVA training, such as the Neutral Buoyancy Laboratory (NBL) at NASA's Johnson Space Center ([JSC], Houston) and the Hydrolab at the Gagarin Cosmonaut Training Centre ([GCTC], Star City, outside Moscow). Underwater training for an EVA is also considered hazardous duty for NASA astronauts. This activity places astronauts at risk for decompression sickness and barotrauma as well as various musculoskeletal disorders from working in the spacesuit. The medical, operational and research communities over the years have requested access to EVA training data to better understand the risks. As a result of these requests, epidemiologists within the Lifetime Surveillance of Astronaut Health (LSAH) team have compiled records from numerous EVA training venues to quantify the exposure to EVA training. The EVA Suit Exposure Tracker (EVA SET) dataset is a compilation of ground-based training activities using the extravehicular mobility unit (EMU) in neutrally buoyant pools to enhance EVA performance on orbit. These data can be used by the current ISS program and future exploration missions by informing physicians, researchers, and operational personnel on the risks of EVA training in order that future suit and mission designs incorporate greater safety. The purpose of this technical report is to document briefly the various facilities where NASA astronauts have performed EVA training while describing in detail the EVA training records used to generate the EVA SET dataset.

Laughlin, Mitzi S.↗
DOE OSTI2023

Archeological wood conservation with selected organosilicon compounds studied by XFM and nanoindentation

Waterlogged wood conservation is a complex and challenging task. Detailed knowledge about the interactions between the applied chemicals and wood is necessary to ensure the effective and safe conservation of wooden artifacts. The present research aims to determine the mechanism of dimensional stabilization of archeological wood by organosilicon compounds using the combination of synchrotron-based X-ray fluorescence microscopy (XFM) and nanoindentation. Archeological oak wood was treated with methyltrimethoxysilane, (3-mercaptopropyl)trimethoxysilane, or 1,3-bis-[(diethylamino)-3-(propoxy)propan-2-ol]-1,1,3,3-tetramethyldisiloxane, which in previous studies were found to be more effective than other organosilicons in stabilizing wood dimensions. The XFM and nanoindentation results showed that all three organosilicons infiltrated wood cell walls and enhanced their mechanical properties. The XFM also showed that part of the chemicals filled some void spaces like cell lumina. Based on the results obtained here and in our previous research, it is determined that the mechanism of archeological wood dimensional stabilization by organosilicon treatment is complex and likely involves both filling cell lumina and infiltration into cell walls where organosilicons interact with wood polymers.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

DS-GL: Advancing Graph Learning via Harnessing the Power of Nature within Dynamic Systems

With the rapid digitization of the world, an increasing number of real-world applications are turning to nonEuclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamic systems composed of CMOS components, have emerged as a new approach that harnesses the inherent power of natural annealing within dynamic systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are inherently binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees effective natural annealing poses daunting scalability concerns. To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamic system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system’s original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamic system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and component structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamic system while maintaining high accuracy. Evaluations with three diverse GL applications across six real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 102× to 106× speedups and 500× energy reduction over Graph Neural Networks on GPUs, with 5% - 20% accuracy enhancement.

Song, Ruibing↗
NASA NTRS2018

Towards Design Principles for Visual Analytics in Operations Contexts

Operations engineering teams interact with complex data systems to make technical decisions that ensure the operational efficacy of their missions. To support these decision-making tasks, which may require elastic prioritization of goals dependent on changing conditions, custom analytics tools are often developed. We were asked to develop such a tool by a team at the NASA Jet Propulsion Laboratory, where rover telecom operators make decisions based on models predicting how much data rovers can transfer from the surface of Mars. Through research, design, implementation, and informal evaluation of our new tool, we developed principles to inform the design of visual analytics systems in operations contexts. We offer these principles as a step towards understanding the complex task of designing these systems. The principles we present are applicable to designers and developers tasked with building analytics systems in domains that face complex operations challenges such as scheduling, routing, and logistics.

Lombeyda, Santiago↗
DOE OSTI2025

Persistent Sampling: Enhancing the Efficiency of Sequential Monte Carlo

Sequential Monte Carlo (SMC) samplers are powerful tools for Bayesian inference but suffer from high computational costs due to their reliance on large particle ensembles for accurate estimates. We introduce persistent sampling (PS), an extension of SMC that systematically retains and reuses particles from all prior iterations to construct a growing, weighted ensemble. By leveraging multiple importance sampling and resampling from a mixture of historical distributions, PS mitigates the need for excessively large particle counts, directly addressing key limitations of SMC such as particle impoverishment and mode collapse. Crucially, PS achieves this without additional likelihood evaluations-weights for persistent particles are computed using cached likelihood values. This framework not only yields more accurate posterior approximations but also produces marginal likelihood estimates with significantly lower variance, enhancing reliability in model comparison. Furthermore, the persistent ensemble enables efficient adaptation of transition kernels by leveraging a larger, decorrelated particle pool. Experiments on high-dimensional Gaussian mixtures, hierarchical models, and non-convex targets demonstrate that PS consistently outperforms standard SMC and related variants, including recycled and waste-free SMC, achieving substantial reductions in mean squared error for posterior expectations and evidence estimates, all at reduced computational cost. PS thus establishes itself as a robust, scalable, and efficient alternative for complex Bayesian inference tasks.

Karamanis, Minas↗
DOE OSTI2026

Inverse design of hypoeutectoid pearlite steel microstructures using a deep learning and genetic algorithm optimization framework

Goal-oriented microstructure design in metallic materials is a challenging task due to complex structure-property relationships. Traditional experimental and computational approaches are time-intensive and economically inefficient, limiting their applicability for large-scale design space exploration. Here, in this work, we propose an end-to-end framework that integrates deep learning models with genetic optimization to design microstructures with targeted mechanical properties. Deep learning models enable accurate forward design, while their integration with genetic optimization enables efficient inverse design within a few hours, compared to days or weeks using conventional finite element simulations. The framework combines experimental characterization and finite element modeling to analyze the influence of microstructural features on the mechanical behavior of hypoeutectoid steels. Data from both experiments and simulations are used to train the deep learning models. To demonstrate its effectiveness, we apply the framework to 0.63% carbon steel with proeutectoid ferrite and pearlite phases, commonly used in industrial applications. In this study, 2D microstructures were used for modeling, selected primarily for computational efficiency and to establish proof of concept. The framework successfully optimizes microstructures for targeted yield strength, ultimate strength, and stress concentration factors while significantly reducing computational time. Beyond hypoeutectoid steels, this scalable framework can be extended to other material systems and integrated with additive manufacturing, offering an efficient approach for accelerating microstructure design for specific engineering applications.

ConvLSTM↗
DOE OSTI2024

Numerical modeling of Joule heated ceramic melter

Computational fluid dynamics and heat transfer models of waste glass melters are being developed to support the vitrification campaign at the Waste Treatment and Immobilization Plant (WTP) as part of the United States nuclear waste stewardship and environmental protection programs. The WTP mission aims to achieve the stable and durable processing of vitrified waste in the safest, most efficient, and economical manner possible. Hanford’s tank waste is far more complex and varied than the waste treated by other vitrification facilities and both startup and long-term operational challenges are likely to be even greater than prior experience has shown. There are thousands of different waste compositions, which makes processing the waste a complex and challenging task. Models of test melters, pilot-scale, and full-scale melters have been developed to provide understanding and insight into the various physical and chemical phenomena occurring during vitrification. So the results of these modeling activities will be used to support the WTP operations to process legacy nuclear waste into a stable form for disposal.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

Design-time performance modeling of compositional parallel programs

Performance models are powerful instruments for understanding the performance of parallel systems and uncovering their bottlenecks. Already during system design, performance models can help ponder alternative development options. However, creating a performance model – whether theoretically or empirically – for an entire application that does not exist yet is challenging. In this paper, we propose to generate performance models of full programs from performance models of their components using formal composition operators derived from parallel design patterns. As long as the design of the overall system follows such a pattern, its performance model can be predicted with reasonable accuracy without an actual implementation. In conclusion, we demonstrate our approach with design patterns of varying complexity, including pipeline, task pool, and eventually MapReduce, which is representative of a broad class of data-analytics applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A FAIR-compliant parts catalogue for genome engineering and expression control in Saccharomyces cerevisiae

The synthetic biology toolkit for baker's yeast, Saccharomyces cerevisiae, includes extensive genome engineering toolkits and parts repositories. However, with the increasing complexity of engineering tasks and versatile applications of this model eukaryote, there is a continued interest to expand and diversify the rational engineering capabilities in this chassis by FAIR (findable, accessible, interoperable, and reproducible) compliance. In this study, we designed and characterised 41 synthetic guide RNA sequences to expand the CRISPR-based genome engineering capabilities for easy and efficient replacement of genomically encoded elements. Moreover, we characterize in high temporal resolution 20 native promoters and 18 terminators using fluorescein and LUDOX CL-X as references for GFP expression and OD600 measurements, respectively. Additionally, all data and reported analysis is provided in a publicly accessible jupyter notebook providing a tool for researchers with low-coding skills to further explore the generated data as well as a template for researchers to write their own scripts. We expect the data, parts, and databases associated with this study to support a FAIR-compliant resource for further advancing the engineering of yeasts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Multioutput Convolutional Neural Network for Improved Parameter Extraction in Time-Resolved Electrostatic Force Microscopy Data

Time-resolved scanning probe microscopy methods, like time-resolved electrostatic force microscopy (trEFM), enable imaging of dynamic processes ranging from ion motion in batteries to electronic dynamics in microstructured thin film semiconductors for solar cells. Reconstructing the underlying physical dynamics from these techniques can be challenging due to the interplay of cantilever physics with the actual transient kinetics of interest in the resulting signal. Previously, quantitative trEFM used empirical calibration of the cantilever or feed-forward neural networks trained on simulated data to extract the physical dynamics of interest. Both these approaches are limited by interpreting the underlying signal as a single exponential function, which serves as an approximation but does not adequately reflect many realistic systems. Here, we present a multi-branched, multi-output convolutional neural network (CNN) that uses the trEFM signal in addition to the physical cantilever parameters as input. The trained CNN accurately extracts parameters describing both single-exponential and bi-exponential underlying functions, and more accurately reconstructs real experimental data in the presence of noise. This article demonstrates an application of physics-informed machine learning to complex signal processing tasks, enabling more efficient and accurate analysis of trEFM.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

A physics informed bayesian optimization approach for material design: application to NiTi shape memory alloys

Abstract The design of materials and identification of optimal processing parameters constitute a complex and challenging task, necessitating efficient utilization of available data. Bayesian Optimization (BO) has gained popularity in materials design due to its ability to work with minimal data. However, many BO-based frameworks predominantly rely on statistical information, in the form of input-output data, and assume black-box objective functions. In practice, designers often possess knowledge of the underlying physical laws governing a material system, rendering the objective function not entirely black-box, as some information is partially observable. In this study, we propose a physics-informed BO approach that integrates physics-infused kernels to effectively leverage both statistical and physical information in the decision-making process. We demonstrate that this method significantly improves decision-making efficiency and enables more data-efficient BO. The applicability of this approach is showcased through the design of NiTi shape memory alloys, where the optimal processing parameters are identified to maximize the transformation temperature.

Chemistry↗