SEARCH · Search NASA
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.
An adaptive neural network for auto-associative memories operating in continuous time is considered. A new learning algorithm for the weight matrix defined by explicit locations of desirable equilibrium points is introduced. The approach is based upon the minimum 'strength energy' of the weight matrix for each prescribed performance of the neural network.
This study aims to provide accurate information about changes in agricultural systems (AS) using phenological metrics derived from the NDVI time series. Use of such information could help land managers optimize land use choices and monitor the status of agricultural lands, under a variety of environmental and socioeconomic conditions. For this purpose, the Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI data were used to derive phenological metrics over the Oum Er-Rbia basin (central Morocco). Random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) classifiers were explored and compared on their ability to classify AS classes over the study area. Four main AS classes have been considered: (1) irrigated annual crop (IAC), (2) irrigated perennial crop (IPC), (3) rainfed area (RA), and (4) fallow (FA). By comparing the accuracy of the three classifiers, the RF method showed the best performance with an overall accuracy of 0.97 and kappa coefficient of 0.96.The RF method was then chosen to examine time variations in AS over a 16-year period (2000–2016). The AS main variations were detected and evaluated for the four AS classes. These variations have been found to be linked well with other indicators of local agricultural land management, as well as the historical agricultural drought changes over the study area. Overall, the results present a tool for decision makers to improve agricultural management and provide a different perspective in understanding the spatiotemporal dynamics of agricultural systems.
Explore the source record for details and available documents.
Polynomial chaos expansions (PCEs) are widely used for uncertainty quantification (UQ) tasks, particularly in the applied mathematics community. However, PCE has received comparatively less attention in the statistics literature, and fully Bayesian formulations remain rare—especially with implementations in R. Motivated by the success of adaptive Bayesian machine learning models such as BART, BASS and BPPR, we develop a new fully Bayesian adaptive PCE method with an efficient and accessible R implementation: khaos. Our approach includes a novel proposal distribution that enables data-driven interaction selection and supports a modified g-prior tailored to PCE structure. Through simulation studies and real-world UQ applications, we demonstrate that the Bayesian adaptive PCE provides competitive performance for surrogate modeling, global sensitivity analysis and ordinal regression tasks.
In this paper, we present a new, simple, and optimized hardware architecture sequential learning technique for adaptive Principle Component Analysis (PCA) which will help optimize the hardware implementation in VLSI and to overcome the difficulties of the traditional gradient descent in learning convergence and hardware implementation.
X-ray imaging is a powerful technique to scan samples in a variety of contexts including biological, environmental and materials science, but commonly requires a synchrotron light source to produce X-rays at sufficient intensity. As these facilities are expensive to operate, the available beam time is limited and always in high demand. Particularly if the illuminated samples are sparse, standard raster scanning methods can be time-consuming, with a majority of that time being spent on areas of the image that carry little information. To increase the efficiency and maximize the information gain for a given time budget, we split the scanning process into a series of steps where previous measurements are used to inform the decision making and adapt the exposure distribution at later stages of the sequence. We formulate this task as a reinforcement learning problem where the goal is to produce a sequence of exposure maps that maximize a predefined scalar metric. We demonstrate the potential of this approach in simulations where the adaptive illumination can accelerate the measurement process by up to an order of magnitude compared with standard raster scanning. Finally, we present the first results from deploying the trained agents on an X-ray fluorescence beamline at the Stanford Synchrotron Radiation Lightsource.
Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.
A viewgraph presentation on the lessons learned and flight results from the F15 Intelligent Flight Control System (IFCS) project is shown. The topics include: 1) F-15 IFCS Project Goals; 2) Motivation; 3) IFCS Approach; 4) NASA F-15 #837 Aircraft Description; 5) Flight Envelope; 6) Limited Authority System; 7) NN Floating Limiter; 8) Flight Experiment; 9) Adaptation Goals; 10) Handling Qualities Performance Metric; 11) Project Phases; 12) Indirect Adaptive Control Architecture; 13) Indirect Adaptive Experience and Lessons Learned; 14) Gen II Direct Adaptive Control Architecture; 15) Current Status; 16) Effect of Canard Multiplier; 17) Simulated Canard Failure Stab Open Loop; 18) Canard Multiplier Effect Closed Loop Freq. Resp.; 19) Simulated Canard Failure Stab Open Loop with Adaptation; 20) Canard Multiplier Effect Closed Loop with Adaptation; 21) Gen 2 NN Wts from Simulation; 22) Direct Adaptive Experience and Lessons Learned; and 23) Conclusions
We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer er al. to the realm of continuous signals. Given a set of labeled examples belonging to a 'source' domain, we select a set of unlabeled examples in a related 'target' domain that play similar roles in both domains. Using these 'pivot samples, we map both domains into a common feature space, allowing us to adapt a classifier trained on source examples to classify target examples. We show that when between-class distances are relatively preserved across domains, we can automatically select target pivots to bring the domains into correspondence.
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.
Learn-to-Fly (L2F) is a new framework that aims to replace the traditional iterative development paradigm for aerial vehicles with a combination of real-time aerodynamic modeling, guidance, and learning control. To ensure safe learning of the vehicle dynamics on the fly, this paper presents an L1 adaptive control (L1AC) based scheme, which actively estimates and compensates for the discrepancy between the intermediately learned dynamics and the actual dynamics. First, to incorporate the periodic update of the learned model within the L2F framework, this paper extends the L1AC architecture to handle a switched reference system subject to unknown time-varying parameters and disturbances. The paper also includes analysis of both transient and steady-state performance of the L1AC architecture in the presence of non-zero initialization error for the state predictor. Second, the paper presents how the proposed L1AC scheme is integrated into the L2F framework, including its interaction with the baseline controller and the real-time modeling module. Finally, flight tests on an unmanned aerial vehicle (UAV) validate the efficacy of the proposed control and learning scheme.
Urban pluvial flooding poses a growing threat to the city of Baltimore, driven by heavy rainfall, increased impervious area, and aging infrastructure. Adapting to the risks posed by pluvial flooding is critical for building greater climate resiliency in Baltimore's Inner Harbor Watershed. This study addresses these challenges through community-informed decision analysis, which uses hydrologic modeling and optimization tools to identify robust flooding adaptation pathways. We will collaborate with community partners to identify key concerns and objectives regarding flooding. These concerns have been purposefully built in to a combined surface-subsurface dynamic flow simulation model. Model outputs are used to identify flooding locations within the Inner Harbor, and to test adaptation methods. Machine learning will be used search for solutions which meet diverse environmental, financial, and social goals, and solution performance will be examined under a wide range of potential future climatic conditions and integrated with an adaptive planning approach. This novel set of adaptation pathways will enhance the City's capacity to respond to evolving pluvial flood risk.
Modern cyberattacks in cyber-physical systems (CPS) rapidly evolve and cannot be deterred effectively with most current methods, which focus on characterizing past threats. Adaptive anomaly detection (AAD) is among the most promising techniques to detect evolving cyberattacks, with an emphasis on fast data processing and model adaptation. AAD has been researched extensively; however, to the best of our knowledge, our work is the first systematic literature review (SLR) on current research in this field. We present a comprehensive SLR, gathering 397 relevant papers and systematically analyzing 65 of them (47 research and 18 survey papers) on AAD in CPS from 2013 to November 2023. We introduce a novel taxonomy considering attack types, CPS application, learning paradigm, data management, and algorithms. Our findings show that most studies addressed either model adaptation or data processing, but rarely both simultaneously. This indicates a research gap in fully adaptive solutions. We also categorize algorithms, datasets, and attack characteristics, and summarize strengths and weaknesses across the literature. Our review provides a structured and accessible reference for researchers and practitioners, offering insights into key trends and highlighting limitations in current approaches. Finally, we outline several future research directions, including the need for integrated real-time processing and adaptive learning, explainability, and uncertainty quantification in AAD for CPS.
The first inhabited outpost on the frontier of space will be a place to live, work, and discover. Experiments conducted on Freedom will advance scientific knowledge about our world, our environment, and ourselves. We will learn how to adapt to the space environment and to build and operate new spacecraft with destinations far beyond Earth, continuing the tradition of exploration that began with a journey to the Moon. What we learn from living and working on Freedom will strengthen our expertise in science and engineering, promote national research and development initiatives and inspire another generation of Americans to push forward and onward. On the eve of the 21st century, Space Station Freedom will be our gateway to the future. This material covers gateways to space, research, discovery, utilization, benefits, and NASA.
Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.
A method for the rapid learning of nonlinear mappings and topological transformations using a dynamically reconfigurable artificial neural network is presented. This fully-recurrent Adaptive Neuron Model (ANM) network was applied to the highly degenerate inverse kinematics problem in robotics, and its performance evaluation is bench-marked. Once trained, the resulting neuromorphic architecture was implemented in custom analog neural network hardware and the parameters capturing the functional transformation downloaded onto the system. This neuroprocessor, capable of 10(exp 9) ops/sec, was interfaced directly to a three degree of freedom Heathkit robotic manipulator. Calculation of the hardware feed-forward pass for this mapping was benchmarked at approximately 10 microsec.
Performance Seeking Control attempts to find the operating condition that will generate optimal performance and control the plant at that operating condition. In this paper a nonlinear multivariable Adaptive Performance Seeking Control (APSC) methodology will be developed and it will be demonstrated on a nonlinear system. The APSC is comprised of the Positive Gradient Control (PGC) and the Fuzzy Model Reference Learning Control (FMRLC). The PGC computes the positive gradients of the desired performance function with respect to the control inputs in order to drive the plant set points to the operating point that will produce optimal performance. The PGC approach will be derived in this paper. The feedback control of the plant is performed by the FMRLC. For the FMRLC, the conventional fuzzy model reference learning control methodology is utilized, with guidelines generated here for the effective tuning of the FMRLC controller.
The current research was motivated by the recommendation made by a joint Government/Industry committee to introduce a new traffic control system, referred to as the Free Flight. This system is designed to use recent new technology to facilitate efficient and safe air transportation. We addressed one of the major difficulties that arise in the design of this and similar multi-agent systems: the adaptive (and slippery) nature of human agents. To facilitate a safe and efficient design of this multi-agent system, designers have to rely on assessments of the expected behavior of the different agents under various scenarios. Whereas the behavior of the computerized agents is predictable, the behavior of the human agents (including air traffic controllers and pilots) is not. Experimental and empirical observations suggest that human agents are likely to adjust their behavior to the design of the system. To see the difficulty that the adaptive nature of human agents creates assume that a good approximation of the way operators currently behave is available. Given this information an optimal design can be performed. The problem arises as the human operator will learn to adjust their behavior to the new system. Following this adjustment process the assumptions made by the designer concerning the operators behavior will no longer be accurate and the system might reach a suboptimal state. In extreme situations these potential suboptimal states might involve unnecessary risk. That is, the fact that operators learn in an adaptive fashion does not imply that the system will become safer as they gain experience. At least in the context of Safety dilemmas, experience can lead to a pareto deficient risk taking behavior.