Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptive 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 811 records · Page 45

Domain Adaptation for Measurements of Strong Gravitational Lenses

Upcoming surveys are predicted to discover galaxy-scale strong lenses on the order of 10\textsuperscript{5}, making deep learning methods necessary in lensing data analysis. Currently, there is insufficient real lensing data to train deep learning algorithms, but the alternative of training only on simulated data results in poor performance on real data. Domain Adaptation may be able to bridge the gap between simulated and real datasets. We utilize domain adaptation for the estimation of Einstein radius ($\Theta_E$) in simulated galaxy-scale gravitational lensing images with different levels of observational realism. We evaluate two domain adaptation techniques - Domain Adversarial Neural Networks (DANN) and Maximum Mean Discrepancy (MMD). We train on a source domain of simulated lenses and apply it to a target domain of lenses simulated to emulate noise conditions in the Dark Energy Survey (DES). We show that both domain adaptation techniques can significantly improve the model performance on the more complex target domain dataset. This work is the first application of domain adaptation for a regression task in strong lensing imaging analysis. Our results show the potential of using domain adaptation to perform analysis of future survey data with a deep neural network trained on simulated data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Developing and Testing a Physics Guided Machine Learning NeuralNetwork to Predict Tonal Noise Emitted by a Propeller

Artificial neural networks offer a highly nonlinear and adaptive model for predicting complex interactions between input-output parameters. However, these networks require large datasets which often exceed practical considerations in modeling experimental results. To alleviate the dataset size requirement, a method known as physics guided machine learning has been applied to construct several neural networks for predicting propeller tonal noise in the time domain over a broad range of flight conditions. Three space-filling designs, namely, Latin-Hypercube, Sphere-Packing, and Grid-Space, were used to distribute points throughout the input parameter space encompassing nondimensional flight conditions and observer geometry. Each neural network’s performance was validated by conditions outside of the training set and compared to the Propeller Analysis System tool from the NASA Aircraft Noise Prediction Program. Compared to the Grid-Space input design, the Latin-Hypercube and the Sphere-Packing designs provided a better representation of the domain for training. Regarding the network archetype, a fully connected perceptron was found to outperform the partially connected perceptron in their ability to predict tonal noise for small datasets. The black-box nature of these neural networks was also explored to understand how the networks constructed the waveform and understand why some network designs produce better models.

Propeller noise↗

Transfer learning for analysis of collective and non-collective Thomson scattering spectra

Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density (⁠n e ) and electron temperature (⁠T e ⁠). Deep neural networks can provide accurate estimates of ⁠n e and T e when conventional fitting algorithms may fail, such as when TS spectra are dominated by noise, or when fast analysis is required for real-time operation. Although deep neural networks typically require large training sets, transfer learning can improve model performance on a target task with limited data by leveraging pre-trained models from related source tasks, where select hidden layers are further trained using target data. We present five architecturally diverse deep neural networks, pre-trained on synthetic TS data and adapted for experimentally measured TS data, to evaluate the efficacy of transfer learning in estimating n e and T e in both the collective and non-collective scattering regimes. We evaluate errors in n e and T e estimates as a function of training set size for models trained with and without transfer learning, and we observe decreases in model error from transfer learning when the training set contains ≲ 200 experimentally measured spectra.

Artificial neural networks↗

Safe Reinforcement Learning for Emergency Load Shedding of Power Systems

The paradigm shift in the electric power grid necessitates a revisit of existing control methods to ensure the grid’s security and resilience. In particular, the increased uncertainties and rapidly changing operational conditions in power systems have revealed outstanding issues in terms of either speed, adaptiveness, or scalability of the existing control methods for power systems. On the other hand, the availability of massive real-time data can provide a clearer picture of what is happening in the grid. Recently, deep reinforcement learning (RL) has been regarded and adopted as a promising approach leveraging massive data for fast and adaptive grid control. However, like most existing machine learning (ML)- based control techniques, RL control usually cannot guarantee the safety of the power systems. In this paper, we introduce a novel method for safe RL-based load shedding of power systems that can enhance the safe voltage recovery of the electric power grid after experiencing faults. Numerical simulation on the IEEE 39-bus testcase is performed to demonstrate the effectiveness of the proposed safe RL emergency control, as well as its adaptive capability to faults not seen in the training.

reinforcement learning, emergency control, power g↗

Object and Gas Source Detection with Robotic Platforms in Perceptually-Degraded Environments

In exploration-oriented robotic missions for disaster relief in unknown subterranean environments, it is of prime importance for a human supervisor to rapidly gain situational awareness of salient objects within the environment. In this paper we present an automated object detection pipeline that is adaptable to heterogeneous robots with arbitrary sensor configurations. It has been deployed in time-critical scenarios with multiple collaborative robots in a variety of demanding underground environments. For visually observable objects, detections are made in both the visible and thermal spectra using a state-of-the-art machine learning framework for object detection and classification. Our pipeline can be rapidly adapted to a specific task by using a small, structured dataset to fine-tune a pre-trained convolutional neural network (CNN). Relative localization is separated from the CNN for speed of operation. A robust architecture for localization is used with outlier rejection and a hierarchy of fall-back distance measurement methods. Point-source objects such as gas and WiFi hotspots can also be detected, by tracking signal strength over time and presenting an intuitive visualization on a map. Observations of each object types are presented to the operator in ranked confidence order for final evaluation.

Agha-mohammadi, Ali-akbar↗

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

State of the art astronomical simulations have provided datasets which enabled the training of novel deep learning techniques for constraining cosmological parameters. However, differences in subgrid physics implementation and numerical approximations among simulation suites lead to differences in simulated datasets, which pose a hard challenge when trying to generalize across diverse data domains and ultimately when applying models to observational data. Recent work reveals deep learning algorithms are able to extract more information from complex cosmological simulations than summary statistics like power spectra. We introduce Domain Adaptive Graph Neural Networks (DA-GNNs), trained on CAMELS data, inspired by CosmoGraphNet (Villanueva-Domingo et al 2023). By utilizing GNNs, we can capitalize on their capacity to capture both astrophysical and topological features of galaxy distributions. Mixing these capabilities with domain adaptation techniques such as Maximum Mean Discrepancy (MMD), which enable extraction of domain-invariant features, our framework demonstrates enhanced accuracy and robustness. We present experimental results, including the alignment of distributions across domains through data visualization. These findings suggest that DA-GNNs are an efficient way of extracting domain independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗

Self-adaptive weights based on balanced residual decay rate for physics-informed neural networks and deep operator networks

Physics-informed deep learning has emerged as a promising alternative for solving partial differential equations. However, for complex problems, training these networks can still be challenging, often resulting in unsatisfactory accuracy and efficiency. In this work, we demonstrate that the failure of plain physics-informed neural networks arises from the significant discrepancy in the convergence rate of residuals at different training points, where the slowest convergence rate dominates the overall solution convergence. Based on these observations, we propose a pointwise adaptive weighting method that balances the residual decay rate across different training points. The performance of our proposed adaptive weighting method is compared with current state-of-the-art adaptive weighting methods on benchmark problems for both physics-informed neural networks and physics-informed deep operator networks. In conclusion, through extensive numerical results we demonstrate that our proposed approach of balanced residual decay rates offers several advantages, including bounded weights, high prediction accuracy, fast convergence rate, low training uncertainty, low computational cost, and ease of hyperparameter tuning.

Balanced convergence rate↗

Enhancing Distribution System Resilience: A First-Order Meta-RL Algorithm for Critical Load Restoration

The increasing frequency of extreme events and the integration of distributed energy resources (DERs) into modern grids have elevated the need for resilient and efficient critical load restoration strategies in distribution systems. However, the stochastic nature of renewable DERs, limited energy resource availability and the intricate nonlinearities inherent in complex grid control problem make the problem challenging. Although reinforcement learning (RL) and warm-start RL methods have shown promising results, their performance often falls short in rapidly adapting to new, unseen situations and typically requires exhaustive problem-specific tuning. To address these gaps, we propose a First-Order Meta-based RL (FOM-RL) algorithm within an online framework for adaptive and robust critical load restoration. By harnessing local DERs as the enabling technology, FOM-RL allows the RL agent to swiftly adapt to new unseen scenarios by leveraging previously acquired knowledge of different tasks. Experimental results provide evidence that proposed algorithm learns more efficiently and showcases generalization capabilities across diverse set of operational scenarios. Moreover, a rigorous theoretical analysis yields a tight sublinear regret bound, sensitive to temporal variability, with a task-averaged optimality gap bounded by O(VM+D*/(Tsquare root(M))). These results suggest that optimality improves with task similarity and an increased number of tasks M, reaffirming the efficacy and scalability of the proposed approach in addressing the complexities of critical load restoration in distribution systems.

complexity theory↗

Global field reconstruction from sparse sensors with Veronoi tessellation-assisted deep learning

Achieving accurate and robust global situational awareness of a complex time-evolving field from a limited number of sensors has been a longstanding challenge. This reconstruction problem is especially difficult when sensors are sparsely positioned in a seemingly random or unorganized manner, which is often encountered in a range of scientific and engineering problems. Moreover, these sensors can be in motion and can become online or offline over time. The key leverage in addressing this scientific issue is the wealth of data accumulated from the sensors. As a solution to this problem, we propose a data-driven spatial field recovery technique founded on a structured grid-based deep-learning approach for arbitrary positioned sensors of any numbers. It should be noted that the naïve use of machine learning becomes prohibitively expensive for global field reconstruction and is furthermore not adaptable to an arbitrary number of sensors. In the present work, we consider the use of Voronoi tessellation to obtain a structured-grid representation from sensor locations enabling the computationally tractable use of convolutional neural networks. One of the central features of the present method is its compatibility with deep-learning based super-resolution reconstruction techniques for structured sensor data that are established for image processing. The proposed reconstruction technique is demonstrated for unsteady wake flow, geophysical data, and three-dimensional turbulence. The current framework is able to handle an arbitrary number of moving sensors, and thereby overcomes a major limitation with existing reconstruction methods. The presented technique opens a new pathway towards the practical use of neural networks for real-time global field estimation.

Fukami, Kai↗

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗

Acquisition of STEM Images by Adaptive Compressive Sensing

Compressive Sensing (CS) allows a signal to be sparsely measured first and accurately recovered later in software [1]. In scanning transmission electron microscopy (STEM), it is possible to compress an image spatially by reducing the number of measured pixels, which decreases electron dose and increases sensing speed [2,3,4]. The two requirements for CS to work are: (1) sparsity of basis coefficients and (2) incoherence of the sensing system and the representation system. However, when pixels are missing from the image, it is difficult to have an incoherent sensing matrix. Nevertheless, dictionary learning techniques such as Beta-Process Factor Analysis (BPFA) [5] are able to simultaneously discover a basis and the sparse coefficients in the case of missing pixels. On top of CS, we would like to apply active learning [6,7] to further reduce the proportion of pixels being measured, while maintaining image reconstruction quality. Suppose we initially sample 10% of random pixels. We wish to select the next 1% of pixels that are most useful in recovering the image. Now, we have 11% of pixels, and we want to decide the next 1% of “most informative” pixels. Active learning methods are online and sequential in nature. Our goal is to adaptively discover the best sensing mask during acquisition using feedback about the structures in the image. In the end, we hope to recover a high quality reconstruction with a dose reduction relative to the non-adaptive (random) sensing scheme. In doing this, we try three metrics applied to the partial reconstructions for selecting the new set of pixels: (1) variance, (2) Kullback-Leibler (KL) divergence using a Radial Basis Function (RBF) kernel, and (3) entropy. Figs. 1 and 2 display the comparison of Peak Signal-to-Noise (PSNR) using these three different active learning methods at different percentages of sampled pixels. At 20% level, all the three active learning methods underperform the original CS without active learning. However, they all beat the original CS as more of the “most informative” pixels are sampled. One can also argue that CS equipped with active learning requires less sampled pixels to achieve the same value of PSNR than CS with pixels randomly sampled, since all the three PSNR curves with active learning grow at a faster pace than that without active learning. For this particular STEM image, by observing the reconstructed images and the sensing masks, we find that while the method based on RBF kernel acquires samples more uniformly, the one on entropy samples more areas of significant change, thus less uniformly. The KL-divergence method performs the best in terms of reconstruction error (PSNR) for this example [8].

Xie, Weiyi↗

Genetic algorithms for adaptive real-time control in space systems

Genetic Algorithms that are used for learning as one way to control the combinational explosion associated with the generation of new rules are discussed. The Genetic Algorithm approach tends to work best when it can be applied to a domain independent knowledge representation. Applications to real time control in space systems are discussed.

Vanderzijp, J.↗

Context-specific adaptation of pursuit initiation in humans

PURPOSE: To determine if multiple states for the initiation of pursuit, as assessed by acceleration in the "open-loop" period, can be learned and gated by context. METHODS: Four normal subjects were studied. A modified step-ramp paradigm for horizontal pursuit was used to induce adaptation. In an increasing paradigm, target velocity doubled 230 msec after onset; in a decreasing paradigm, it was halved. In the first experiment, vertical eye position (+/-5 degrees ) was used as the context cue, and the training paradigm (increasing or decreasing) changed with vertical eye position. In the second experiment, with vertical position constant, when the target was red, training was decreasing, and when green, increasing. The average eye acceleration in the first 100 msec of tracking was the index of open-loop pursuit performance. RESULTS: With vertical position as the cue, pursuit adaptation differed between up and down gaze. In some cases, the direction of adaptation was in exact accord with the training stimuli. In others, acceleration increased or decreased for both up and down gaze but always in correct relative proportion to the training stimuli. In contrast, multiple adaptive states were not induced with color as the cue. CONCLUSIONS: Multiple values for the relationship between the average eye acceleration during the initiation of pursuit and target velocity could be learned and gated by context. Vertical position was an effective contextual cue but not target color, implying that useful contextual cues must be similar to those occurring naturally, for example, orbital position with eye muscle weakness.

NASA Discipline Neuroscience↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide performance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.

Whitbeck, A. [Fermilab] (ORCID:0000000342245164)↗

EdgeAI: Machine learning via direct attached accelerator for streaming data processing at high shot rate x-ray free-electron lasers

We present a case for low batch-size inference with the potential for adaptive training of a lean encoder model. We do so in the context of a paradigmatic example of machine learning as applied in data acquisition at high data velocity scientific user facilities such as the Linac Coherent Light Source-II x-ray Free-Electron Laser. We discuss how a low-latency inference model operating at the data acquisition edge can capitalize on the naturally stochastic nature of such sources. We simulate the method of attosecond angular streaking to produce representative results whereby simulated input data reproduce high-resolution ground truth probability distributions. By minimizing the mean-squared error between the decoded output of the latent representation and the ground truth distributions, we ensure that the encoding layers and resulting latent representation maintains full fidelity for any downstream task, be it classification or regression. We present throughput results for data-parallel inference of various batch sizes, some with throughput exceeding 100 k images per second. We also show in situ training below 10 s per epoch for the full encoder–decoder model as would be relevant for streaming and adaptive real-time data production at our nation’s scientific light sources.

97 MATHEMATICS AND COMPUTING↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide perfor- mance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.

Whitbeck, A. [Fermilab]↗

Learning Canonical Embeddings for Unsupervised Shape Correspondence With Locally Linear Transformations

We present a new approach to unsupervised shape correspondence learning between pairs of point clouds. We make the first attempt to adapt the classical locally linear embedding algorithm (LLE)-originally designed for nonlinear dimensionality reduction-for shape correspondence. The key idea is to find dense correspondences between shapes by first obtaining high-dimensional neighborhood-preserving embeddings of low-dimensional point clouds and subsequently aligning the source and target embeddings using locally linear transformations. We demonstrate that learning the embedding using a new LLE-inspired point cloud reconstruction objective results in accurate shape correspondences. More specifically, the approach comprises an end-to-end learnable framework of extracting high-dimensional neighborhood-preserving embeddings, estimating locally linear transformations in the embedding space, and reconstructing shapes via divergence measure-based alignment of probability density functions built over reconstructed and target shapes. Our approach enforces embeddings of shapes in correspondence to lie in the same universal/canonical embedding space, which eventually helps regularize the learning process and leads to a simple nearest neighbors approach between shape embeddings for finding reliable correspondences. Comprehensive experiments show that the new method makes noticeable improvements over state-of-the-art approaches on standard shape correspondence benchmark datasets covering both human and nonhuman shapes.

deformation↗

Do Research Software Engineers and Software Engineering Researchers Speak the Same Language?

Anecdotal evidence suggests that research software engineers (RSEs) and software engineering researchers (SERs) often use different terminologies for similar concepts, creating communication challenges. To better understand these divergences, we have started investigating how software engineering fundamentals from the SER community are interpreted within the RSE community, identifying aligned concepts, knowledge gaps, and areas for potential adaptation. In conclusion, our preliminary findings reveal opportunities for mutual learning and collaboration, and our systematic methodology for terminology mapping provides a foundation for a crowdsourced extension and validation in the future.

Kehrer, Timo [Univ. of Bern (Switzerland)] (ORCID:↗