Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual learning”

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 1,171 records · Page 65

The Software Engineering Laboratory: An operational software experience factory

For 15 years, the Software Engineering Laboratory (SEL) has been carrying out studies and experiments for the purpose of understanding, assessing, and improving software and software processes within a production software development environment at NASA/GSFC. The SEL comprises three major organizations: (1) NASA/GSFC, Flight Dynamics Division; (2) University of Maryland, Department of Computer Science; and (3) Computer Sciences Corporation, Flight Dynamics Technology Group. These organizations have jointly carried out several hundred software studies, producing hundreds of reports, papers, and documents, all of which describe some aspect of the software engineering technology that was analyzed in the flight dynamics environment at NASA. The studies range from small, controlled experiments (such as analyzing the effectiveness of code reading versus that of functional testing) to large, multiple project studies (such as assessing the impacts of Ada on a production environment). The organization's driving goal is to improve the software process continually, so that sustained improvement may be observed in the resulting products. This paper discusses the SEL as a functioning example of an operational software experience factory and summarizes the characteristics of and major lessons learned from 15 years of SEL operations.

Basili, Victor R.↗

XTE Observations of PSR 1259-63 and a Test of Spin Orbit Coupling in the 4U0115+63 System

During this report period, Mallory Roberts went to GSFC to analyze the data from two minor outbursts, which occurred from 4UO115+63. Unfortunately, the outbursts were not of sufficient duration to do a unique orbital determination (which was the scientific goal of the experiment). As this report is being written, 4UO115+63 is undergoing its first major outburst in four years. We are planning on adding our RXTE PCA data to any public ASM or PCA data that is obtained through the duration of this outburst, and combining it with our BATSE data from 1994 and 1995 outbursts in order to learn something about the orbital evolution in this system. We have formed a collaboration with colleagues at MIT who are working on the ASM data for this outburst. Thus, work on the original data will continue, with no further funding, and we are hopeful that some important questions with regard to the orbital timing will finally be resolved. The PSR 1259-63 data were originally analyzed by Barry Giles, who reported that no pulsations or flux were seen from this source near apastron. Recently, a new background model for low-count rate sources has been developed for the PCA. We intend to use this new background model to reanalyze these data to see if we can improve the upper limit to the flux. This work will also continue with no further funding.

Cominsky, Lynn R.↗

Transforming Satellite Data into Weather Forecasts

A NASA project spans the gap between research and operations, introducing new composites of satellite imagery to weather forecasters to prepare for the next generation of satellites. Satellite imagery has been an immense benefit to weather forecasters. With it, they can assess aviation hazards such as low clouds, monitor thunderstorms, and track the evolution of dust plumes. Satellite sensors are continually evolving to provide ever greater imaging capabilities, and researchers continue to develop advanced techniques to identify hazards in satellite imagery. However, barriers can prevent experimental products from reaching forecasters in the operational environment. A NASA project has developed an interactive process whereby weather forecasters learn to interpret the latest satellite imagery and apply it to their operations. Forecasters then provide feedback to the researchers who are developing algorithms and products to further improve future products. This effort has taken on greater importance with the anticipated launch of a new series of satellites that will provide substantially greater amounts of data than are currently available.

Emily Berndt↗

The Land Surface Data Toolkit (LDT v7.2) - A Data Fusion Environment for Land Data Assimilation Systems

The effective applications of land surface models (LSMs) and hydrologic models pose a varied set of data input and processing needs, ranging from ensuring consistency checks to more derived data processing and analytics. This article describes the development of the Land surface Data Toolkit (LDT), which is an integrated framework designed specifically for processing input data to execute LSMs and hydrological models. LDT not only serves as a preprocessor to the NASA Land Information System (LIS), which is an integrated framework designed for multi-model LSM simulations and data assimilation (DA) integrations, but also as a land-surface-based observation and DA input processor. It offers a variety of user options and inputs to processing datasets for use within LIS and stand-alone models. The LDT design facilitates the use of common data formats and conventions. LDT is also capable of processing LSM initial conditions and meteorological boundary conditions and ensuring data quality for inputs to LSMs and DA routines. The machine learning layer in LDT facilitates the use of modern data science algorithms for developing data-driven predictive models. Through the use of an object-oriented framework design, LDT provides extensible features for the continued development of support for different types of observational datasets and data analytics algorithms to aid land surface modeling and data assimilation.

droughts and floods↗

TMS 2014 143rd Annual Meeting & Exhibition, Annual Meeting Supplemental Proceedings (ISBN: 978-1-118-88972-5)

The Magnetic Materials for Energy Applications IV, held at the 2014, 143rd Annual Meeting of The Minerals, Metals, and Materials Society (TMS), brought together experts, young investigators, and students from this sub-discipline of materials science in order for them to share their latest discoveries and develop collaborations. This symposium, which is organized by The Minerals, Metals, and Materials Society, is an important event for this community of scientists. This year, over 50 high-level technical talks were planned over the course of the event. In addition, the students and young investigators in attendance ensured the maximum benefit to the next generation’s work force in this area of study. Meeting global energy needs in a clean, efficient, secure and sustainable manner is arguably the greatest challenge facing mankind today. Magnetic materials play a critical role in myriad devices for the collection, conversion, transmission and storage of energy. For example, high performance permanent magnets are currently in great demand for the generators in wind turbines and electric motors in hybrid vehicles. Other classes of advanced magnetic materials are essential for efficient inductors/transformers and motors. Energy efficient cooling based on the magnetocaloric effect is another exciting possibility which is rapidly becoming industrially viable. The potential energy savings related to refrigeration and air conditioning based on magnetocaloric materials are highly attractive. This symposium allowed experts in areas relating to the advanced characterization, simulation, and optimization of magnetic materials to convene and present their latest research. The types of interactions afforded by this event are beneficial to society at large primarily because they provide opportunities for the leaders within this field to learn from one another and thus improve the quality and productivity of their investigations. Additionally, the presence of young investigators and students with technical interests in this field provides promise that the United States will continue to be a leader in this area. The support provided by the Department of Energy for this event directly enhanced its impact on the field by helping a number of students, young investigators, and technical experts attend and participate in this event. This symposium brought together research experts and students in the field to present the latest developments on the science surrounding advanced characterization, simulation, and optimization of magnetic materials and their use in energy applications such as generation and magnetic cooling. A strong technical program, containing more than 50 presentations was developed and organized around the following technical sessions. A strong list of invited speakers contributed to the high quality of technical content. Rare Earth Permanent Magnets: Processing, Characterization and Modeling Rare Earth Free Permanent Magnets Fundamentals of the Magnetocaloric Effect and Current Status of Magnetic Cooling Technology Magnetocaloric Materials High Performance Soft Magnets I High Performance Soft Magnets II

36 MATERIALS SCIENCE↗

Getting Smart about Solar: How to Build a Strong Solar Market and Get National Recognition

As the cost of solar energy continues to decrease, the opportunity to harness the benefits of local renewable energy grows. Join your peers as they share their experiences eliminating red tape to improve local processes and employing other best practices, and learn how engagement and national recognition with SolSmart has benefited their communities and could help your own.

14 SOLAR ENERGY↗

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↗

Adaptive Stress Testing: Using Reinforcement Learning to Find Failures in Safety-Critical Systems

Emerging applications in artificial intelligence, such as driverless cars and autonomous aircraft promise to be more efficient, cheaper to operate, and always available. However, ensuring the safety of these systems remains a major challenge to their certification and adoption. These autonomous systems are expected to routinely make safety-critical decisions where failures can have serious consequences including loss of life and property. Testing and validation techniques aim to identify and diagnose potential failures before the system is deployed. However, finding failure scenarios in autonomous systems can be very challenging due to high-dimensional and continuous state spaces, interaction with large environments over many time steps, and the rarity of failures. This talk presents Adaptive Stress Testing (AST), a simulation-based testing framework for finding the most likely path to a failure event of a safety-critical system. The key idea of AST is that stress testing can be formulated as a Partially Observable Markov Decision Process (POMDP), which enables reinforcement learning techniques to be used for finding failure events. Reinforcement learning algorithms can efficiently explore the search space and have been shown to scale to very large systems. We present applications of AST to find failures in various safety-critical systems including the aircraft collision avoidance systems, autonomous cars, and small unmanned aerial vehicles.

autonomous vehicles↗

Improving Workplace Management and Performance - A Lost Art? - 16004

Undertaking projects on nuclear licensed sites or on sites with a radiological connotation will undoubtedly lead to a variety of challenges. In many instances these challenges will be slightly different to those affiliated with projects on sites which do not have a radiological concern. However, common approaches can still often be found and transferable learning from other industries can also be applied. The majority of these challenges relate to worker safety (both occupationally and radiologically), protection of the public and the environment, public communication, and the choice of technical and logistical approaches taken (e.g. for areas like decommissioning, waste management, environmental remediation). Notwithstanding these challenges the success of site-related projects also depends heavily on the functionality of the project team. The aim here is to highlight a number of logical approaches that are too often overlooked and which might often lead to improvements in workplace management and performance. A successful project team is rarely built overnight, as it relies on the establishment of a harmonious working atmosphere, and continuous communication as well as demonstrable recognition of the relevance of the role of the different team members. Improving workplace management and performance can be approached through a number of ways. First, there are clear benefits in developing an industry-specific culture, but of equal importance is the application of learning from other industries. Second, improving workplace performance often comes down to treating people in the right manner and showing them respect. A culture of competition and blame in the workplace often results in individuals being too defensive or withholding useful information. Creating a harmonious atmosphere can help to overcome some of these barriers. The third area of improving workplace management and performance is through developing and empowering personnel on a more formal basis. This can be achieved through initiatives like the Investors In People (IiP) National Standard, which many countries now support. Achieving this National Standard provides an opportunity to demonstrate to both your personnel and your clients that you are committed to this initiative and that you want to improve workplace performance. The IiP National Standard can lead to a range of benefits. A combination of formal initiatives, developing sector-specific approaches and applying learning from other industries can lead to noticeable improvements in workplace management and performance. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Lessons Learned In Technology Development for Supplemental Treatment of Low-Activity Waste at Hanford

Hanford needs supplemental technology treatment of low-activity waste (LAW) in addition to the Waste Treatment Plant (WTP). The Washington State Department of Ecology requires that supplemental technology provide the same protection to human health and the environment as WTP LAW glass. In 2002, the U.S. Department of Energy (US DOE) evaluated supplemental treatment technologies for LAW treatment and looked more closely at three: bulk vitrification (BV), steam reforming, and tailored cementitious stabilization. US DOE with Ecology's support chose to design and test BV because it believed BV would offer rapid deployment, low cost, and waste stream versatility. This paper will describe the path taken in choosing and developing technologies for additional LAW treatment capacity and, more importantly, the lessons learned along the way. In conclusion: Contractors' off-the-shelf vitrification technology that worked elsewhere may not apply easily to Hanford's waste challenges. The BV development process could have been improved by first identifying and then focusing on primary areas of concern. Continuing integrated tests at the Horn Rapids facility offers a convenient option to test both the dryer and the SMF. But the plan for development of the SMF must be short term with well defined success criteria. US DOE has the responsibility to carefully evaluate each proposal and make critical decisions that will make optimum use of limited funds. The ERP provided valuable technical guidance on improving BV's design. This must be complemented by a similar study of cost effectiveness of a process. We must have a better understanding of life cycle costs before a path for supplemental treatment is chosen. US DOE has now gained five years of experience in developing BV. It is time for US DOE to make defensible economic evaluations before further funding towards developing supplemental treatment. It must reevaluate if the projected advantages of rapid deployment, low cost, and waste stream versatility are still valid. The decision-making methodology US DOE uses to approve designs as part of its Critical Decision Process appears rigorous and useful. Looking ahead, Ecology expects US DOE will use lessons learned from BV and other testing in a concerted manner as part of their decision-making process. The success of Hanford's cleanup depends on it. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach

Physical and budget constraints often result in irregular sampling, which complicates accurate subsurface imaging. Preprocessing approaches, such as missing trace or shot interpolation, are typically employed to enhance seismic data in such cases. Recently, deep learning has been used to address the trace interpolation problem at the expense of large amounts of training data to adequately represent typical seismic events. Nonetheless, most research in this area has focused on trace reconstruction, with little attention having been devoted to shot interpolation. Furthermore, existing methods assume regularly spaced receivers/sources failing in approximating seismic data from real (irregular) surveys. This work presents a novel shot gather interpolation approach which uses a continuous coordinate-based representation of the acquired seismic wavefield parameterized by a neural network. The proposed unsupervised approach, which we call coordinate-based seismic interpolation (CoBSI), enables the prediction of specific seismic characteristics in irregular land surveys without using external data during neural network training. Importantly, experimental results on real and synthetic 3-D data validate the ability of the proposed method to estimate continuous smooth seismic events in the time-space and frequency-wavenumber domains, improving sparsity or low-rank-based interpolation methods.

58 GEOSCIENCES↗

GPS-supported smartphone app-based integrated travel diary and time-use data collection: challenges and lessons learned

Travel behaviour and time-use data are two vital data sources for travel demand modelling. Travel behaviour is traditionally collected through household travel surveys, enhanced by using GPS-supported smartphone apps for passive location data collection. However, recruiting individuals willing to install these apps with sustained motivation to continue participation has been a critical challenge. This paper shares insights from a travel and time-use data collection procedure in Chicago and Sydney using the Fourstep app. Social media platforms were utilised as a solution to recruit participants in Chicago, where an international market research company failed to accomplish the task. This paper also discusses the challenges we faced and suggests ways to overcome them, offering valuable guidance to researchers in recruiting participants for smartphone application-based data collection. It also offers an analysis of travel, time-use, and travel-based multitasking behaviours based on the data collected from the Chicago and Sydney samples.

GPS-supported smartphone apps↗

Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis

Motivation: Cell movement in the early phase of Caenorhabditis elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulatory networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse microscopy images. Results: We present a deep reinforcement learning approach within an agent-based modeling system to characterize cell movement in the embryonic development of C.elegans. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, agent-based modeling that uses greedy algorithms. Here, we tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the superficial left-right asymmetry. In the first case, the model results suggested that Cpaaa’s intercalation is an active directional cell movement caused by the continuous effects from a longer distance (farther than the length of two adjacent cells), as opposed to a passive movement caused by neighbor cell movements. In the second case, a leader-follower mechanism well explained the collective cell movement pattern in the asymmetry rearrangement. These results showed that our approach to introduce deep reinforcement learning into agent-based modeling can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. Lastly, this model opens new doors to explore the large datasets generated by live imaging. Availability and implementation: Source code is available at https://github.com/zwang84/drl4cellmovement.

59 BASIC BIOLOGICAL SCIENCES↗

SAGE III on ISS Lessons Learned on Thermal Interface Design

The Stratospheric Aerosol and Gas Experiment III (SAGE III) instrument - the fifth in a series of instruments developed for monitoring vertical distribution of aerosols, ozone, and other trace gases in the Earth's stratosphere and troposphere - is currently scheduled for delivery to the International Space Station (ISS) via the SpaceX Dragon vehicle in 2016. The Instrument Adapter Module (IAM), one of many SAGE III subsystems, continuously dissipates a considerable amount of thermal energy during mission operations. Although a portion of this energy is transferred via its large radiator surface area, the majority must be conductively transferred to the ExPRESS Payload Adapter (ExPA) to satisfy thermal mitigation requirements. The baseline IAM-ExPA mechanical interface did not afford the thermal conductance necessary to prevent the IAM from overheating in hot on-orbit cases, and high interfacial conductance was difficult to achieve given the large span between mechanical fasteners, less than stringent flatness specifications, and material usage constraints due to strict contamination requirements. This paper will examine the evolution of the IAM-ExPA thermal interface over the course of three design iterations and will include discussion on design challenges, material selection, testing successes and failures, and lessons learned.

Davis, Warren↗

Adversarial sampling of unknown and high-dimensional conditional distributions

Many engineering problems require the prediction of realization-to-realization variability or a refined description of modeled quantities. In that case, it is necessary to sample elements from unknown high-dimensional spaces with possibly millions of degrees of freedom. While there exist methods able to sample elements from probability density functions (PDF) with known shapes, several approximations need to be made when the distribution is unknown. In this paper the sampling method, as well as the inference of the underlying distribution, are both handled with a data-driven method known as generative adversarial networks (GAN), which trains two competing neural networks to produce a network that can effectively generate samples from the training set distribution. In practice, it is often necessary to draw samples from conditional distributions. When the conditional variables are continuous, only one (if any) data point corresponding to a particular value of a conditioning variable may be available, which is not sufficient to estimate the conditional distribution. This work handles this problem using an a priori estimation of the conditional moments of a PDF. Herein, two approaches, stochastic estimation, and an external neural network are compared for computing these moments; however, any preferred method can be used. The algorithm is demonstrated in the case of the deconvolution of a filtered turbulent flow field. It is shown that all the versions of the proposed algorithm effectively sample the target conditional distribution with minimal impact on the quality of the samples compared to state-of-the-art methods. Additionally, the procedure can be used as a metric for the diversity of samples generated by a conditional GAN (cGAN) conditioned with continuous variables.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

The expressivity of classical and quantum neural networks on entanglement entropy

Abstract Analytically continuing the von Neumann entropy from Rényi entropies is a challenging task in quantum field theory. While then-th Rényi entropy can be computed using the replica method in the path integral representation of quantum field theory, the analytic continuation can only be achieved for some simple systems on a case-by-case basis. In this work, we propose a general framework to tackle this problem using classical and quantum neural networks with supervised learning. We begin by studying several examples with known von Neumann entropy, where the input data is generated by representing$${\text {Tr}}\rho _A^n$$ Tr ρ A n with a generating function. We adopt KerasTuner to determine the optimal network architecture and hyperparameters with limited data. In addition, we frame a similar problem in terms of quantum machine learning models, where the expressivity of the quantum models for the entanglement entropy as a partial Fourier series is established. Our proposed methods can accurately predict the von Neumann and Rényi entropies numerically, highlighting the potential of deep learning techniques for solving problems in quantum information theory.

Physics↗

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗

AutoFocus: AI/ML-driven real-time wavefront diagnostics to autonomously align and optimize X-ray optics

We present an integrated system that combines advanced wavefront diagnostics with artificial intelligence (AI) to automate and optimize X-ray optics at synchrotron beamlines. This system couples real-time wavefront sensing with AI-driven control algorithms to achieve precise beam alignment, stabilization, and performance optimization. A key feature is the use of multi-fidelity transfer learning, which enables knowledge gained from both real-world beamline optimizations and ultra-realistic digital twin simulations to be effectively applied to in situ optimization. By leveraging multi-objective bayesian optimization, the system continuously refines its performance, reducing optimization time and minimizing the need for manual adjustments. Designed for seamless deployment, it operates with existing beamline hardware and provides an intuitive graphical interface. Initial deployments at the advanced photon source beamlines have demonstrated its ability to enhance beam stability, improve reproducibility, and significantly streamline alignment procedures. This AI-enhanced control framework represents a significant step toward fully autonomous beamline operation in next-generation synchrotron facilities.

Rebuffi, Luca [Argonne National Laboratory (ANL), ↗