SEARCH · Engineering Papers

Results for “task tuning”

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 163 records · Page 9

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture Codesign Package (SNAC-Pack), an open-source AutoML framework for hardware-aware neural architecture codesign and end-to-end FPGA deployment. SNAC-Pack runs a multi-objective global search with Optuna and NSGA-II, loading trials to a shared SQLite store that enables parallel workers across compute nodes. A hardware surrogate model outputs per-trial resource and latency estimates, avoiding the synthesis cost that would otherwise dominate the search loop. A local search stage then applies quantization-aware training (QAT) together with iterative magnitude pruning in a combined compression loop, after which the final model is synthesized to FPGA firmware via the hls4ml Python library. A YAML configuration and an optional agentic frontend let users run the pipeline on new datasets without modifying the framework. We demonstrate SNAC-Pack on jet classification at the Large Hadron Collider and superconducting qubit readout, discovering compact architectures that match or exceed strong baselines on the task metric while reducing FPGA resource utilization and, in the qubit readout case, reducing the design space exploration process from months of manual fine-tuning to hours of automated search.

Weitz, Jason [UC, San Diego]↗

DOE OSTI2026

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗

DOE OSTI2022

KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N<sub>2</sub>O emission using data from mesocosm experiments

Abstract. Agricultural nitrous oxide (N2O) emission accounts for a non-trivial fraction of global greenhouse gas (GHG) budget. To date, estimating N2O fluxes from cropland remains a challenging task because the related microbial processes (e.g., nitrification and denitrification) are controlled by complex interactions among climate, soil, plant and human activities. Existing approaches such as process-based (PB) models have well-known limitations due to insufficient representations of the processes or uncertainties of model parameters, and due to leverage recent advances in machine learning (ML) a new method is needed to unlock the “black box” to overcome its limitations such as low interpretability, out-of-sample failure and massive data demand. In this study, we developed a first-of-its-kind knowledge-guided machine learning model for agroecosystems (KGML-ag) by incorporating biogeophysical and chemical domain knowledge from an advanced PB model, ecosys, and tested it by comparing simulating daily N2O fluxes with real observed data from mesocosm experiments. The gated recurrent unit (GRU) was used as the basis to build the model structure. To optimize the model performance, we have investigated a range of ideas, including (1) using initial values of intermediate variables (IMVs) instead of time series as model input to reduce data demand; (2) building hierarchical structures to explicitly estimate IMVs for further N2O prediction; (3) using multi-task learning to balance the simultaneous training on multiple variables; and (4) pre-training with millions of synthetic data generated from ecosys and fine-tuning with mesocosm observations. Six other pure ML models were developed using the same mesocosm data to serve as the benchmark for the KGML-ag model. Results show that KGML-ag did an excellent job in reproducing the mesocosm N2O fluxes (overall r2=0.81, and RMSE=3.6 mgNm-2d-1 from cross validation). Importantly, KGML-ag always outperforms the PB model and ML models in predicting N2O fluxes, especially for complex temporal dynamics and emission peaks. Besides, KGML-ag goes beyond the pure ML models by providing more interpretable predictions as well as pinpointing desired new knowledge and data to further empower the current KGML-ag. We believe the KGML-ag development in this study will stimulate a new body of research on interpretable ML for biogeochemistry and other related geoscience processes.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2004

An Enabling Technology for New Planning and Scheduling Paradigms

The Night Projects Directorate at NASA's Marshall Space Flight Center is developing a new planning and scheduling environment and a new scheduling algorithm to enable a paradigm shift in planning and scheduling concepts. Over the past 33 years Marshall has developed and evolved a paradigm for generating payload timelines for Skylab, Spacelab, various other Shuttle payloads, and the International Space Station. The current paradigm starts by collecting the requirements, called ?ask models," from the scientists and technologists for the tasks that are to be scheduled. Because of shortcomings in the current modeling schema, some requirements are entered as notes. Next, a cadre with knowledge of vehicle and hardware modifies these models to encompass and be compatible with the hardware model; again, notes are added when the modeling schema does not provide a better way to represent the requirements. Finally, the models are modified to be compatible with the scheduling engine. Then the models are submitted to the scheduling engine for automatic scheduling or, when requirements are expressed in notes, the timeline is built manually. A future paradigm would provide a scheduling engine that accepts separate science models and hardware models. The modeling schema would have the capability to represent all the requirements without resorting to notes. Furthermore, the scheduling engine would not require that the models be modified to account for the capabilities (limitations) of the scheduling engine. The enabling technology under development at Marshall has three major components: (1) A new modeling schema allows expressing all the requirements of the tasks without resorting to notes or awkward contrivances. The chosen modeling schema is both maximally expressive and easy to use. It utilizes graphical methods to show hierarchies of task constraints and networks of temporal relationships. (2) A new scheduling algorithm automatically schedules the models without the intervention of a scheduling expert. The algorithm is tuned for the constraint hierarchies and the complex temporal relationships provided by the modeling schema. It has an extensive search algorithm that can exploit timing flexibilities and constraint and relationship options. (3) An innovative architecture allows multiple remote users to simultaneously model science and technology requirements and other users to model vehicle and hardware characteristics. The architecture allows the remote users to submit scheduling requests directly to the scheduling engine and immediately see the results. These three components are integrated so that science and technology experts with no knowledge of the vehicle or hardware subsystems and no knowledge of the internal workings of the scheduling engine have the ability to build and submit scheduling requests and see the results. The immediate feedback will hone the users' modeling skills and ultimately enable them to produce the desired timeline. This paper summarizes the three components of the enabling technology and describes how this technology would make a new paradigm possible.

Jaap, John↗

NASA NTRS2004

Enabling a New Planning and Scheduling Paradigm

The Flight Projects Directorate at NASA's Marshall Space Flight Center is developing a new planning and scheduling environment and a new scheduling algorithm to enable a paradigm shift in planning and scheduling concepts. Over the past 33 years Marshall has developed and evolved a paradigm for generating payload timelines for Skylab, Spacelab, various other Shuttle payloads, and the International Space Station. The current paradigm starts by collecting the requirements, called "tasks models," from the scientists and technologists for the tasks that they want to be done. Because of shortcomings in the current modeling schema, some requirements are entered as notes. Next a cadre with knowledge of vehicle and hardware modifies these models to encompass and be compatible with the hardware model; again, notes are added when the modeling schema does not provide a better way to represent the requirements. Finally, another cadre further modifies the models to be compatible with the scheduling engine. This last cadre also submits the models to the scheduling engine or builds the timeline manually to accommodate requirements that are expressed in notes. A future paradigm would provide a scheduling engine that accepts separate science models and hardware models. The modeling schema would have the capability to represent all the requirements without resorting to notes. Furthermore, the scheduling engine would not require that the models be modified to account for the capabilities (limitations) of the scheduling engine. The enabling technology under development at Marshall has three major components. (1) A new modeling schema allows expressing all the requirements of the tasks without resorting to notes or awkward contrivances. The chosen modeling schema is both maximally expressive and easy to use. It utilizes graphics methods to show hierarchies of task constraints and networks of temporal relationships. (2) A new scheduling algorithm automatically schedules the models without the intervention of a scheduling expert. The algorithm is tuned for the constraint hierarchies and the complex temporal relationships provided by the modeling schema. It has an extensive search algorithm which can exploit timing flexibilities and constraint and relationship options. (3) A web-based architecture allows multiple remote users to simultaneously model science and technology requirements and other users to model vehicle and hardware characteristics. The architecture allows the users to submit scheduling requests directly to the scheduling engine and immediately see the results. These three components are integrated so that science and technology experts with no knowledge of the vehicle or hardware subsystems and no knowledge of the internal workings of the scheduling engine have the ability to build and submit scheduling requests and see the results. The immediate feedback will hone the users' modeling skills and ultimately enable them to produce the desired timeline. This paper summarizes the three components of the enabling technology and describes how this technology would make a new paradigm possible.

Jaap, John↗

DOE OSTI2020

Comparison of time-frequency-analysis techniques applied in building energy data noise cancellation for building load forecasting: A real-building case study

Time-frequency analysis that disaggregates a signal in both time and frequency domain is an important supporting technique for building energy analysis such as noise cancellation in data-driven building load forecasting. There is a gap in the literature related to comparing various time–frequency-analysis techniques, especially discrete wavelet transform (DWT) and empirical mode decomposition (EMD), to guide the selection and tuning of time–frequency-analysis techniques in data-driven building load forecasting. This article provides a framework to conduct a comprehensive comparison among thirteen DWT/EMD techniques with various parameters in a load forecasting modeling task. A real campus building is used as a case study for illustration. The DWT and EMD techniques are also compared under various data-driven modeling algorithms for building load forecasting. The results in the case study show that the load forecasting models trained with noise-cancelled energy data have increased their accuracy to 9.6% on average tested under unseen data. This study also shows that the effectiveness of DWT/EMD techniques depends on the data-driven algorithms used for load forecasting modeling and the training data. Hence, DWT/EMD-based noise cancellation needs customized selection and tuning to optimize their performance for data-driven building load forecasting modeling.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2021

Developing Accelerated Test Protocols and Tuning Microstructures of the Common Materials to Improve Robustness, Reliability, and Endurance of SOFC Cells

This work is built on our prior work where we found that phase transformation in praseodymium nickelates, e.g. Pr 2 NiO 4 (PNO) and (Pr 1-x Nd x ) 2 NiO 4 (PNNO), can be electrochemically driven, and is substantially faster when compared to thermal annealing studies. The first task aims at an attempt to further accelerate the phase transformation in the oxygen electrode by alternating the current input in the cells, which lead to the development of accelerated test protocols (ATPs). ATPs showed up to 60x faster phase transformation and up to 10x faster performance degradation in (Pr 0.50 Nd 0.50 ) 2 NiO 4 electrodes, when compared to long-term operation under constant current density. Furthermore, the phase stable Nd 2 NiO 4 and (La 0.6 Sr 0.4 )(Co 0.8 Fe 0.2 )O 3 (LSCF6482) electrodes were tested in full cells under ATPs, and showed up to 10x faster performance degradation within 1,100 hours in a comparison with long-term thermal annealing studies and electrochemical operation under constant current density. The second task aims at the quantification of the contributions of cell components to the total impedance of a solid oxide fuel cell (SOFC) using electrochemical impedance spectroscopy (EIS) and distribution of relaxation times (DRT). Specifically, the role of gas composition at both anode and cathode was systematically studied, aiming at deconvoluting, identifying and quantifying the contributions of different electrode processes. This was achieved by first tuning the partial pressure of H 2 at the anode and subsequently varying the partial pressure of O 2 at the cathode. The results suggest that, while DRT offers a viable way of deconvoluting different times distributions, additional attention is needed before assigning a peak to a specific electrode process due to the significant overlap of the contributions from the cathode and the anode. Density function theory studies show that both Pr-vacancies and O-defects play a key role on the activity and stability for nickelates towards oxygen reduction reaction. The resident O-interstitials and oxygen ions in the PrO layer form peroxide (O 2 2- ) nearby Pr vacancies. The O 2 2- limits oxygen-ion transport due to the required additional energy to break its O-O bond. We further calculated the formation and segregation energies for different Ln ions (La, Pr, Nd, Pm, Sm, Gd, Tb, Dy, and Ho) in PNO and CeO 2 (111) surfaces. In addition to Nd, Pm and La are suggested as potential dopants in PNO to enhance it stability without decomposition due to their more negative formation energies, lower diffusion energies, and positive separation energies.

01 COAL, LIGNITE, AND PEAT↗

NASA NTRSDate not supplied

Enhancements, Verification, and VMS Integration of VTOL Concept Vehicle Simulation Models

Advanced Rotorcraft Technology (ART) and the NASA Ames Aeromechanics branch have jointly developed FLIGHTLAB simulation models for Advanced Air Mobility (AAM) VTOL concept vehicles. The overarching purpose of the simulation model development is to establish a set of well defined reference vehicles for FLIGHTLAB users and the rotorcraft community. The ongoing research effort and enhancement of these AAM simulation models to fulfill the role of quality reference vehicles is this paper’s focus. The content of this paper expands on the established characteristics of these AAM models in three primary areas. First, enhancement of the lift+cruise and tiltwing models with elastic airframe properties is discussed. The process of setting up the elastic airframe model in FLIGHTLAB, as well as the impacts on flight characteristics are explained. The introduction of the elastic airframe modeling allows these models to be used in flight dynamics, loads, and vibration analysis of the configuration designs. Next, linear model generation from the enhanced simulation model is covered. Confirming the validity of the linearized models is of importance, as these linear models are utilized for flight control design and tuning for these experimental configurations. For the final focus, the progress towards implementation of these models into the NASA Ames Vertical Motion Simulator (VMS) is described. This task seeks to demonstrate the procedures of integrating a FLIGHTLAB flight simulation in the VMS environment, test fully integrated simulation with communication between flight dynamics, control, and propulsion models, and explore the essential aspects of simulation model integration in a full flight simulator environment. This includes I/O definition, initialization, trim, flying, etc. By expanding the capabilities of the AAM simulation models, they continue to develop as valuable and approachable modeling references.

VMS↗

DOE OSTI2024

Harnessing large language models’ zero-shot and few-shot learning capabilities for regulatory research

Abstract Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency’s local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Biochemistry & Molecular Biology↗

NASA NTRS1988

Defining and measuring pilot mental workload

A theory is sought that is general enough to help the researcher deal with a wide range of situations involving pilot mental stress. A limited capacity theory of attention forms the basis for the theory. Mental workload is then defined as an intervening variable, similar to attention, that modulates or indexes the tuning between the demands of the environment and the capacity of the organism. Two methods for measuring pilot mental workload are endorsed: (1) objective measures based on secondary tasks; and (2) psychophysiological measures, which have not yet been perfected but which will become more useful as theoretical models are refined. Secondary-task research is illustrated by simulator studies in which flying performance has been shown not to be adversely affected by adding a complex choice-reaction secondary task.

Kantowitz, Barry H.↗

NASA NTRS1992

A neural fuzzy controller learning by fuzzy error propagation

In this paper, we describe a procedure to integrate techniques for the adaptation of membership functions in a linguistic variable based fuzzy control environment by using neural network learning principles. This is an extension to our work. We solve this problem by defining a fuzzy error that is propagated back through the architecture of our fuzzy controller. According to this fuzzy error and the strength of its antecedent each fuzzy rule determines its amount of error. Depending on the current state of the controlled system and the control action derived from the conclusion, each rule tunes the membership functions of its antecedent and its conclusion. By this we get an unsupervised learning technique that enables a fuzzy controller to adapt to a control task by knowing just about the global state and the fuzzy error.

Nauck, Detlef↗

DOE OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Countermeasures for Mitigation of Sensorimotor Decrements Following Head-Down Bed Rest

BACKGROUND Decrements in functional performance of tasks requiring postural and locomotor control remain common among crewmembers returning to Earth after6months on the International Space Station (ISS). These impairments will presumably be exacerbated after longer exploration-class missions with fewer exercise hardware options. Our recent studies suggest that an in-flight proprioceptive countermeasure may keep the proprioceptive system tuned to respond to upright balance challenges in a gravitational environment. Before testing a proprioceptive countermeasure in-flight, we must conduct an initial proof-of-concept study to determine its potential efficacy in a controlled unloading analog setting. OBJECTIVES We will determine if proprioceptive training during 60 days of 6° head down bed rest (HDBR) mitigates declines in functional task performance. We consider it critical to characterize the interaction between proprioceptive training and exercise. Thus, we will compare 3groupsof subjects(N=12 each): a proprioceptive training group, an exercise plus proprioceptive training group, and a control group(i.e. no training or exercise).The primary outcome measure will be the well-established and operationally relevant seat egress and walk test (also referred to as the functional mobility test)performed before and after HDBR. Other functional tests will also represent high priority exploration mission tasks that require high demand for dynamic control of postural stability. Additional measures will be used to identify the key physiological factors contributing to countermeasure benefits. COUNTERMEASURE METHODS We will use a ground version of our countermeasure to test the efficacy of proprioceptive training while maintaining HDBR constraints. Subjects will remain in the horizontal supine position on a sled that moves freely on air-bearings, similar to a puck on an air hockey table. Subjects will be loaded axially up to one full body weight via lateral cable pulleys towards their feet on an instrumented tilt board using a harness and weights system. Visual feedback of board tilt will be used to guide subjects while they make active tilts. Exercise and proprioceptive training prescriptions will represent those expected to be implemented during exploration spaceflight missions(e.g.20-minute proprioceptive training sessions3 times per week). RELEVANCE The deliverable from this project will be a proof-of-concept countermeasure design that has been fully assessed for efficacy in a spaceflight analog. The findings and lessons learned from this study will be translated for validation of this countermeasure on the ISS. An effective countermeasure will be added to the suite of operationally implemented in-flight sensorimotor countermeasures.

T R Macaulay↗

DOE OSTI2022

Tackling the Challenges in Scene Graph Generation With Local-to-Global Interactions

In this work, we seek new insights into the underlying challenges of the scene graph generation (SGG) task. Quantitative and qualitative analysis of the visual genome (VG) dataset implies: 1) ambiguity: even if interobject relationship contains the same object (or predicate), they may not be visually or semantically similar; 2) asymmetry: despite the nature of the relationship that embodied the direction, it was not well addressed in previous studies; and 3) higher-order contexts: leveraging the identities of certain graph elements can help generate accurate scene graphs. Motivated by the analysis, we design a novel SGG framework, Local-to-global interaction networks (LOGINs). Locally, interactions extract the essence between three instances of subject, object, and background, while baking direction awareness into the network by explicitly constraining the input order of subject and object. Globally, interactions encode the contexts between every graph component (i.e., nodes and edges). Finally, Attract and Repel loss is utilized to fine-tune the distribution of predicate embeddings. By design, our framework enables predicting the scene graph in a bottom-up manner, leveraging the possible complementariness. To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed. Overall, experimental results demonstrate that LOGIN can successfully distinguish relational direction than existing methods (in BRC task), while showing state-of-the-art results on the VG benchmark (in SGG task).

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

CSPlib: A performance portable parallel software toolkit for analyzing complex kinetic mechanisms

Computational singular perturbation (CSP) is a method to analyze dynamical systems. It targets the decoupling of fast and slow dynamics using an alternate linear expansion of the right-hand side of the governing equations based on eigenanalysis of the associated Jacobian matrix. This representation facilitates diagnostic analysis, detection and control of stiffness, and the development of simplified models. For this work, we have implemented CSP in a C++ open-source library CSPlib using the Kokkos parallel programming model to address portability across diverse heterogeneous computing platforms, i.e., multi/many-core CPUs and GPUs. We describe the CSPlib implementation and present its computational performance across different computing platforms using several test problems. Specifically, we test the CSPlib performance for a constant pressure ignition reactor model on different architectures, including IBM Power 9, Intel Xeon Skylake, and NVIDIA V100 GPU. The size of the chemical kinetic mechanism is varied in these tests. As expected, the Jacobian matrix evaluation, the eigensolution of the Jacobian matrix, and matrix inversion are the most expensive computational tasks. When considering the higher throughput characteristic of GPUs, GPUs performs better for small matrices with higher occupancy rate. CPUs gain more advantages from the higher performance of well-tuned and optimized linear algebra libraries such as OpenBLAS.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1998

Data Understanding Applied to Optimization

The goal of this research is to explore and develop software for supporting visualization and data analysis of search and optimization. Optimization is an ever-present problem in science. The theory of NP-completeness implies that the problems can only be resolved by increasingly smarter problem specific knowledge, possibly for use in some general purpose algorithms. Visualization and data analysis offers an opportunity to accelerate our understanding of key computational bottlenecks in optimization and to automatically tune aspects of the computation for specific problems. We will prototype systems to demonstrate how data understanding can be successfully applied to problems characteristic of NASA's key science optimization tasks, such as central tasks for parallel processing, spacecraft scheduling, and data transmission from a remote satellite.

Buntine, Wray↗

NASA NTRS2018

Leverage Points for System Health Management of Autonomous Systems

Systems Health Management (SHM) is one of three basic functionalities that constitute an autonomous capability of a system. The other two functionalities are Planning & Scheduling, and Task Execution. In an autonomous system, variable autonomy is often distinct from variable authority to sense, decide, and act. There are quantifiable Levels of Autonomy that can be achieved by tuning different portions of the Observe-Orient-Decide-Act loop to provide flexibility and control. This approach is tabulated for multiple domains such as spacecraft and aerial vehicles. Examining SHM through a Systems Thinking lens helps us understand its stocks and flows, loops, and delays. Systems thinking, and modeling, is a useful way to understand change and complexity of systems of many types. There are certain archetypes that underlie well-known autonomy architectures. And there often are leverage points - best places to intervene in a system - that can resolve or mitigate some fundamental challenges in the design and deployment of autonomous systems. I identify these levers and present the ones that have been successfully used in NASA missions.

Systems Thinking↗

NASA NTRSDate not supplied

Semantic Search with Sentence-BERT for Design Information Retrieval

Managing and referencing design knowledge is a critical activity in the design process. However, reliably retrieving useful knowledge can be a frustrating experience for users of knowledge management systems due to inherent limitations of standard keyword-based searches. In this research, we consider the task of retrieving relevant lessons learned from the NASA Lessons Learned Information System (LLIS). To this end, we apply a state-of-the-art natural language processing (NLP) technique for information retrieval (IR): semantic search with sentence-BERT, which is a modification of a Bidirectional Encoder Representations from Transformers (BERT) model that uses siamese and triplet network architectures to obtain semantically meaningful sentence embeddings. While the pre-trained sBERT model performs well out-of-the-box, we further fine-tune the model on data from the LLIS so that it learns on design engineering-relevant vocabulary. We quantify the improvement in query results using both standard sBERT and fine-tuned sBERT over a keyword search. Our use case throughout the paper is to use queries related to specific requirements from a NASA project. Fine tuning the sBERT model on LLIS data yields a mean average precision (MAP) of 0.807 on queries based on information needs from a real NASA project. Results indicate that applying state-of-the-art natural language processing techniques, especially when finetuned using engineering data, to design information retrieval tasks shows significant promise in modernizing design knowledge management systems.

Hannah S. Walsh↗