Results for “learning framework” — Page 31

NASA NTRS2020

Prognostics for Systems Health Management - Model and Hybrid Based Approaches. Where are We Heading?

To facilitate and solve the prediction problem, awareness of the current state and health of the system is key, since it is necessary to perform condition-based system health predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditional. In case of next generation electric aircrafts, computing remaining flying time is safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. In order to tackle and solve the prediction problem, it is essential to have awareness of the current health state of the system, especially since it is necessary to perform condition-based predictions. To be able to predict the future state of the system, it is also required to possess knowledge of the current and future operational conditions and flight profiles for accurate estimation of end-of-discharge (EOD) for the batteries. Similar framework can be implemented to other complex systems and subsystems. Our research approach is to develop a system level health monitoring safety indicator which runs estimation and prediction algorithms to estimate remaining useful life predictions at system, subsystem swell as component levels. Given models of the current and future system behavior, a general approach of model-based prognostics is discussed as a solution to the prediction problem and further for decision making. Data driven prognostics approaches have been equally used with good results in the past, where respective approaches have their own challenges to tackle. This limits their applicability to complex real-world domains: (a) high complexity or incompleteness of physics-based models and (b) limited representativeness of the training dataset for data-driven models. With the advent of internet of things for data collection and increased use of ML algorithms, hybrid approaches are the next avenue to reduce the challenges and achieve better results. An hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, we use physics-based performance models to infer unobservable model parameters related to the system's components health solving a calibration problem.

Prognostics↗

NASA NTRSDate not supplied

Retrieve Methane from IR sounder measurements Using Machine Learning-Enhanced Physical Inversion

The sensitivity of IR sounder measurements to atmospheric CH 4 is often limited due to interferences from signals of other trace gases, insufficient thermal contrast, and cloud blockage. In order to resolve the geographical and vertical distribution of atmospheric CH 4 profiles, accurate scene-dependent a priori information is critically needed to support an optimal estimation method-based physical inversion scheme. Following the principles of indexing, representation, and retrieval, a spectral fingerprinting methodology is developed to address the needs for both accuracy and computational efficiency in sounder-based CH 4 retrieval. Within this framework, a clustering method based on machine learning is first employed to stratify and identify the a priori state within the pre-constructed database, using optimized spectral radiances as predictors. The corresponding radiative kernel is then used to establish the physical inversion scheme for finding the solution. High-quality data from CH 4 data assimilation systems like the Carbon-Tracker and the Copernicus Atmosphere Monitoring Service (CAMS) reanalysis, as well as the state-of-art sounder products are used to build the training database, including radiative kernels. We will demonstrate the results retrieved from CrIS observations and the associated validation work.

Wan Wu↗

DOE OSTI2024

Active learning for the design of polycrystalline textures using conditional normalizing flows

Generative modeling has opened new avenues for solving previously intractable materials design problems. However, these new opportunities are accompanied by a drastic increase in the required amount of training data. This is in stark juxtaposition to the high expense and difficulty in curating such large materials datasets. In this work, we propose a novel framework for integrating generative models within an active learning loop. Further, this enables the training of generative models with datasets significantly smaller than what has previously been demonstrated, providing a direct route for their application in data constrained environments. The functionality of this framework is then demonstrated by addressing the challenge of designing polycrystalline textures associated with target anisotropic mechanical properties. The developed protocol exhibited a cost reduction between 14 to 18 times over a randomly sampled experimental design.

36 MATERIALS SCIENCE↗

DOE OSTI2026

A Decomposition-Based Learn-To-Optimize Approach with Feasibility Layer Assistance for Sub-Hourly Unit Commitment

Sub-hourly unit commitment (UC) with 15-min intervals is gaining significant attention as a way to respond rapidly to the fluctuations in electricity supply and demand introduced by renewable resources. However, the increased temporal resolution and complex inter-temporal dependencies pose substantial computational challenges for traditional optimization methods. To this end, this paper explores a decomposition-based learn-to-optimize approach. Building on recent advances in machine learning, our method revisits the long- overlooked Lagrangian relaxation framework, which is a classical decomposition technique that enables tractable subproblem solving. These smaller subproblems are inherently well-suited for machine learning, as their reduced dimensionality and structural regularity allow predictive models to efficiently learn and generalize solution patterns. We thus propose a generic predictive model, which embeds Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure, and integrate a rule-based feasibility layer to capture temporal dependencies, reduce training effort, and improve feasibility w.r.t. unit-level constraints. Our method has been validated on the IEEE 118-bus system, demonstrating promising performance in solving sub-hourly UC problems efficiently and feasibly.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2002

The Design of Collectives of Agents to Control Non-Markovian Systems

The 'Collective Intelligence' (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided 'world' utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional-'team games'. We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that 'learning' is a property only of high-enough dimensional systems.

Lawson, John W.↗

NASA NTRS2004

The Design of Collectives of Agents to Control Non-Markovian Systems

The Collective Intelligence (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided "world" utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional "team games". We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents ability to learn. The implication is that learning is a property only of high-enough dimensional systems.

Lawson, John W.↗

DOE OSTI2025

Python Library for Monte Carlo Simulations with Ab Initio and Machine-Learned Interatomic Potentials

There is a growing need in the simulation community for software that provides a transparent, reproducible, usable, and extensible (TRUE) Monte Carlo (MC) simulation framework employing energies from ab initio methods and machine-learning interatomic potentials (MLIPs). We introduce a Python library (ASE-MC) that adds Monte Carlo functionality to the Atomic Simulation Environment (ASE) package. Now, we can combine the powerful tools used to build systems and perform ab initio and MLIP in ASE with MC simulation algorithms to sample the configurational space with a concise Python script. After presenting the design philosophy, we demonstrate the flexibility of our approach using selected examples. These example simulations include liquid water described with a message-passing MLIP in the canonical and isothermal–isobaric ensembles, sampling the characteristic dihedral angle of biphenyl and comparing an MLIP to first-principles calculations, and a grand canonical Monte Carlo simulation of ammonia adsorption on Pt(111). These examples showcase the main features of the software, which include flexibility in the choice of ab initio or MLIP engine, ab initio or MLIP grand canonical MC with cavity bias insertions and deletions, the ability to add custom MC moves to the move set, and how users can condense complex MC workflows into a single Python script. Finally, this library serves as a framework for reproducible Monte Carlo simulations, facilitating easy reproduction of the work and application to new systems.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2004

Perceptual learning through optimization of attentional weighting: human versus optimal Bayesian learner

Human performance in visual detection, discrimination, identification, and search tasks typically improves with practice. Psychophysical studies suggest that perceptual learning is mediated by an enhancement in the coding of the signal, and physiological studies suggest that it might be related to the plasticity in the weighting or selection of sensory units coding task relevant information (learning through attention optimization). We propose an experimental paradigm (optimal perceptual learning paradigm) to systematically study the dynamics of perceptual learning in humans by allowing comparisons to that of an optimal Bayesian algorithm and a number of suboptimal learning models. We measured improvement in human localization (eight-alternative forced-choice with feedback) performance of a target randomly sampled from four elongated Gaussian targets with different orientations and polarities and kept as a target for a block of four trials. The results suggest that the human perceptual learning can occur within a lapse of four trials (<1 min) but that human learning is slower and incomplete with respect to the optimal algorithm (23.3% reduction in human efficiency from the 1st-to-4th learning trials). The greatest improvement in human performance, occurring from the 1st-to-2nd learning trial, was also present in the optimal observer, and, thus reflects a property inherent to the visual task and not a property particular to the human perceptual learning mechanism. One notable source of human inefficiency is that, unlike the ideal observer, human learning relies more heavily on previous decisions than on the provided feedback, resulting in no human learning on trials following a previous incorrect localization decision. Finally, the proposed theory and paradigm provide a flexible framework for future studies to evaluate the optimality of human learning of other visual cues and/or sensory modalities.

Non-NASA Center↗

NASA NTRSDate not supplied

Knowledge Discovery for Early Failure Assessment of Complex Engineered Systems Using Natural Language Processing

Emerging complex engineered systems may have unexpected safety issues due to novel operational environments, increasing autonomy, human-machine interaction, and other factors. To prevent failures in operation or testing that necessitate costly redesign, it is desirable to predict likely failure modes early in the design process. Information about past engineering failures in natural language format presents one possible solution by enabling the retrieval of information that can inform new designs. However, identifying documents containing usable information and extracting the required information can be prohibitively time-consuming when implemented at scale. In this research, an automated natural language processing (NLP) framework is proposed to discover relevant knowledge from documents containing failure-related design information. The framework is applied to NASA’s Lessons Learned Information System (LLIS),which is publicly available. Documents containing usable information are filtered using two different NLP-based models. Next, from the identified usable documents, a failure taxonomy is extracted using a partitioned hierarchical topic modeling approach. Partitions of the document describe different sections of the failure taxonomy – i.e., failure, cause of failure, and recommendations – as indicated by the structure of the original document. The extracted failure taxonomy can be leveraged in early design failure assessment methods. Moreover, the framework can be used to identify documents containing usable failure-related design information from other databases and extract relevant information from these documents.

Documentation and Information Science↗

NASA NTRSDate not supplied

Knowledge Discovery for Early Failure Assessment of Complex Engineered Systems Using Natural Language Processing

Emerging complex engineered systems may have unexpected safety issues due to novel operational environments, increasing autonomy, human-machine interaction, and other factors. To prevent failures in operation or testing that necessitate costly redesign, it is desirable to predict likely failure modes early in the design process. Information about past engineering failures in natural language format presents one possible solution by enabling the retrieval of information that can inform new designs. However, identifying documents containing usable information and extracting the required information can be prohibitively time-consuming when implemented at scale. In this research, an automated natural language processing (NLP) framework is proposed to discover relevant knowledge from documents containing failure-related design information. The framework is applied to NASA’s Lessons Learned Information System (LLIS),which is publicly available. Documents containing usable information are filtered using two different NLP-based models. Next, from the identified usable documents, a failure taxonomy is extracted using a partitioned hierarchical topic modeling approach. Partitions of the document describe different sections of the failure taxonomy – i.e., failure, cause of failure, and recommendations – as indicated by the structure of the original document. The extracted failure taxonomy can be leveraged in early design failure assessment methods. Moreover, the framework can be used to identify documents containing usable failure-related design information from other databases and extract relevant information from these documents.

Documentation and Information Science↗

DOE OSTI2025

A Fortran–Python interface for integrating machine learning parameterization into earth system models

Abstract. Parameterizations in earth system models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex problems has spawned immense interests in climate science applications. Specifically, ML-based parameterizations have been developed to represent convection, radiation, and microphysics processes in ESMs by learning from observations or high-resolution simulations, which have the potential to improve the accuracies and alleviate the uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to be coupled with the dynamical core of ESMs to investigate the effectiveness and their performance in a coupled system. In this study, we present a novel Fortran–Python interface designed to seamlessly integrate ML parameterizations into ESMs. This interface showcases high versatility by supporting popular ML frameworks like PyTorch, TensorFlow, and scikit-learn. We demonstrate the interface's modularity and reusability through two cases: an ML trigger function for convection parameterization and an ML wildfire model. We conduct a comprehensive evaluation of memory usage and computational overhead resulting from the integration of Python codes into the Fortran ESMs. By leveraging this flexible interface, ML parameterizations can be effectively developed, tested, and integrated into ESMs.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

A Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models

Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex problems has spawned immense interests in climate science applications. Specifically, ML-based parameterizations have been developed to represent convection, radiation and microphysics processes in ESMs by learning from observations or high-resolution simulations, which have the potential to improve the accuracies and alleviate the uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to be coupled with the dynamical core of ESMs to investigate the effectiveness and their performance in a coupled system. In this study, we present a novel Fortran-Python interface designed to seamlessly integrate ML parameterizations into ESMs. This interface showcases high versatility by supporting popular ML frameworks like PyTorch, TensorFlow, and Scikit-learn. We demonstrate the interface's modularity and reusability through two cases: a ML trigger function for convection parameterization and a ML wildfire model. We conduct a comprehensive evaluation of memory usage and computational overhead resulting from the integration of Python codes into the Fortran ESMs. By leveraging this flexible interface, ML parameterizations can be effectively developed, tested, and integrated into ESMs.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2001

Design and Control of Large Collections of Learning Agents

The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.

Agogino, Adrian↗

DOE OSTI2025

Evaluation of Seismic Artificial Intelligence with Uncertainty

Artificial intelligence has transformed the seismic community with deep learning models (DLMs) that are trained to complete specific tasks within workflows. However, there is still a lack of robust evaluation frameworks for evaluating and comparing DLMs. Here, we address this gap by designing an evaluation framework that jointly incorporates two crucial aspects: performance uncertainty and learning efficiency. To target these aspects, we meticulously construct the training, validation, and test splits using a clustering method tailored to seismic data and enact an expansive training design to segregate performance uncertainty arising from stochastic training processes and random data sampling. The framework’s ability to guard against misleading declarations of model superiority is demonstrated through the evaluation of PhaseNet (Zhu and Beroza, 2018), a popular seismic phase picking DLM, under three training approaches. Our framework helps practitioners choose the best model for their problem and set performance expectations by explicitly analyzing model performance with uncertainty at varying budgets of training data.

58 GEOSCIENCES↗

NASA NTRSDate not supplied

Health Monitoring and Prognostics in Li-ion Batteries

Space applications need to overcome a very critical challenge of predicting remaining useful life of its critical systems/subsystems, with batteries being one of them. Batteries, power electronics conditioning system and motors and one of the most critical systems. Similarly in case of electric aircrafts, computing remaining flying time is safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. To tackle and solve the prediction problem, it is essential to have awareness of the current state and health of the system, especially since it is necessary to perform condition-based predictions. To be able to accurately predict the future state of any system, it is required to possess knowledge of its current and future operations. Given models of the current and future system behavior, the general approach of model-based prognostics can be employed as a solution to the prior stated prediction problem. Two approaches are presented with battery prognostics application. The first approach presentation covers a physics based-modeling approach implemented for battery prognostics. Given models of the current and future system behavior, a general approach of model-based prognostics can be employed as a solution to the prediction problem and further for decision making. A second hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems i.e. batteries is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Batteries↗

NASA NTRSDate not supplied

Health Monitoring and Prognostics in Li-ion Batteries

Space applications need to overcome a very critical challenge of predicting remaining useful life of its critical systems/subsystems, with batteries being one of them. Batteries, power electronics conditioning system and motors and one of the most critical systems. Similarly in case of electric aircrafts, computing remaining flying time is safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. To tackle and solve the prediction problem, it is essential to have awareness of the current state and health of the system, especially since it is necessary to perform condition-based predictions. To be able to accurately predict the future state of any system, it is required to possess knowledge of its current and future operations. Given models of the current and future system behavior, the general approach of model-based prognostics can be employed as a solution to the prior stated prediction problem. Two approaches are presented with battery prognostics application. The first approach presentation covers a physics based-modeling approach implemented for battery prognostics. Given models of the current and future system behavior, a general approach of model-based prognostics can be employed as a solution to the prediction problem and further for decision making. A second hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems i.e. batteries is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Battery Prognostics↗

DOE OSTI2025

Chromatin structures from integrated AI and polymer physics model

The physical organization of the genome in three-dimensional space regulates many biological processes, including gene expression and cell differentiation. Three-dimensional characterization of genome structure is critical to understanding these biological processes. Direct experimental measurements of genome structure are challenging; computational models of chromatin structure are therefore necessary. We develop an approach that combines a particle-based chromatin polymer model, molecular simulation, and machine learning to efficiently and accurately estimate chromatin structure fromindirectmeasures of genome structure. More specifically, we introduce a new approach where the interaction parameters of the polymer model are extracted from experimental Hi-C data using a graph neural network (GNN). We train the GNN on simulated data from the underlying polymer model, avoiding the need for large quantities of experimental data. The resulting approach accurately estimates chromatin structures across all chromosomes and across several experimental cell lines despite being trained almost exclusively on simulated data. The proposed approach can be viewed as a general framework for combining physical modeling with machine learning, and it could be extended to integrate additional biological data modalities. Ultimately, we achieve accurate and high-throughput estimations of chromatin structure from Hi-C data, which will be necessary as experimental methodologies, such as single-cell Hi-C, improve.

Biochemistry & Molecular Biology↗

DOE OSTI2024

Temperature-dependent mechanical properties and crystal plasticity parameters for additively manufactured Haynes-214 alloy: Experiments and numerical modeling

Our experimental mechanical testing data demonstrated that the additively manufactured (AM) laser powder bed fusion (L-PBF) Haynes-214 alloy exhibits non-linear mechanical properties as the temperature rises from ambient to 870 °C. Crystal plasticity (CP) simulations provide an effective approach to gaining deeper insights into microstructure-property linkages under thermomechanical loading. This method can reduce the need for costly high-temperature mechanical testing while accounting for the effects of crystallographic texture and grain morphology on the mechanical behavior of AM materials. However, calibrating a CP model is time-consuming because individual simulations are computationally expensive and hundreds (or more) of iterations over parameter sets may be required. To address this issue, we have designed a machine learning-differential evolution (ML-DE) CP framework that can accurately interpolate the tensile properties of AM L-PBF Haynes-214 alloy across a wide temperature range from ambient to 870 °C, with minimal reliance on experimental data. The framework uses electron backscatter diffraction (EBSD) measurements to generate statistically equivalent microstructural volume elements to serve as inputs to the CP modeling framework. Stress–strain curves were generated from 1000 CP simulations, which serve as the training data set for the three ML regression algorithms explored: linear, extra-trees, and multi-layer perceptron. These three regression models were independently evaluated to compare their efficiency and identify the most suitable algorithm for the given problem. Results revealed that the extra-trees ML regressor outperforms the other models in both qualitative and quantitative aspects with an R 2 of 0.98. Subsequently, the differential evolution optimization approach is employed to calibrate the ML-based CP material parameters with experimental results obtained at various temperatures. Finally, temperature-dependent CP material parameters are formulated. The effectiveness and efficiency of the designed framework are validated through comparison with experimental results, demonstrating a high degree of agreement. These calibrated parametric constitutive equations enable further use of the CP model to study the deformation behavior of this alloy under a wide range of thermo-mechanical loading conditions.

36 MATERIALS SCIENCE↗