Search NASA⌕ Search

SEARCH · Search NASA

Results for “sequential training method”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Sequence-Based Anomaly Detection in Critical Infrastructure Networks

United States critical infrastructure faces new cyber threats from adversarial nation-state actors in the form of malware-free attacks. Traditional cybersecurity techniques use rules-based methods to identify indicators of compromise on networks, often missing these sophisticated attacks. Our approach leverages multiple state of the art machine learning models in a pipeline to identify abnormal network events through sequential analysis. We combine both device and packet-level information into individual events to characterize anomalous network actions. The model is trained and tested on real network traffic from the Idaho National Lab High Performance Computing (HPC) with greater than 98% precision. It is capable of flagging malicious tactics used by adversaries in malware-free attacks, severe changes to the network, and abnormal user activity by network devices.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Quantifying neptunium oxidation states in nitric acid through spectroelectrochemistry and chemometrics

Controlled-potential in situ thin-layer spectropotentiometry was leveraged to generate visible/near-infrared (VIS/NIR) absorption spectral data sets for the development of chemometric models to quantify Np(III/IV/V/VI) oxidation states in HNO 3 . This technology would be valuable in laboratory studies and when monitoring process solutions to guide feed adjustments for radiochemical separations—the performance of which depends on oxidation state. This approach successfully isolated and stabilized Np species in pure (~99%) oxidation states without compromising solution optical properties. Multivariate curve resolution–alternating least squares models were evaluated to resolve spectral and component concentrations from a scan that sequentially produced Np(VI), Np(V), Np(IV), and Np(III) spectra with mixtures of two valences at a time. Although it provided a useful approximation, the method was not able to quantitively resolve each component likely because of rotational ambiguity. Additionally, partial least squares regression models were built from artificial and electrochemically generated VIS/NIR spectral training sets to study the effect of interionic interactions on spectral characteristics. Models built with true Bi-chemical mixtures of coexisting Np oxidation states and spectra generated from additive combinations of pure end points had similar prediction performance. This methodology can be used to directly quantify Np concentration and the ratio of Np oxidation states and other actinides in remote settings such as hot cells.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2020

Quantum adiabatic machine learning by zooming into a region of the energy surface

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. Here, we propose QAML-Z, an algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the receiver operating characteristic curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration: Preprint

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions, i.e., the reserve requirement, renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained off-line using historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine and battery. Case studies demonstrated that the proposed method outperforms other operating reserve determination methods.

distribution system↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained offline using a historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery. Case studies demonstrated that the proposed method outperforms other policies with static operating reserves.

distribution system↗
DOE OSTI2021

Gaming the beamlines—employing reinforcement learning to maximize scientific outcomes at large-scale user facilities

Abstract Beamline experiments at central facilities are increasingly demanding of remote, high-throughput, and adaptive operation conditions. To accommodate such needs, new approaches must be developed that enable on-the-fly decision making for data intensive challenges. Reinforcement learning (RL) is a domain of AI that holds the potential to enable autonomous operations in a feedback loop between beamline experiments and trained agents. Here, we outline the advanced data acquisition and control software of the Bluesky suite, and demonstrate its functionality with a canonical RL problem: cartpole. We then extend these methods to efficient use of beamline resources by using RL to develop an optimal measurement strategy for samples with different scattering characteristics. The RL agents converge on the empirically optimal policy when under-constrained with time. When resource limited, the agents outperform a naive or sequential measurement strategy, often by a factor of 100%. We interface these methods directly with the data storage and provenance technologies at the National Synchrotron Light Source II, thus demonstrating the potential for RL to increase the scientific output of beamlines, and layout the framework for how to achieve this impact.

36 MATERIALS SCIENCE↗
DOE OSTI2023

CCSI Toolset 3.19 Release

CCSI Toolset 3.19 Release Highlights A gradient generation tool was developed to support GENN models in FOQUS. Certain machine learning tools train gradient-enhanced neural network (GENN) models which can be more accurate for complex datasets given a priori knowledge of model derivatives. However, the derivatives must be known beforehand and are not often available for process data. This tool automatically predicts the gradients for a training dataset in a form usable by common GENN trainers, such as Surrogate Modeling Toolbox. Support was added for Surrogate Modeling Toolbox GENN models in FOQUS, including updates to the run methods, node properties, test framework, documentation and optional dependencies list. Users can train/save Surrogate Modeling Toolbox gradient-enhanced neural network (GENN) models with custom objects and produce .pkl files compatible with the Machine Learning/Artificial Intelligence Plugin in FOQUS. A simpler implementation of the ordering algorithm in the Sequential Design of Experiments (SDOE) module was included. The SDOE examples documentation was updated. The Optimality-Based Design of Experiments was updated to improve the error handling when the results are None.

AS↗
DOE OSTI2023

Safe Exploration Reinforcement Learning for Load Restoration using Invalid Action Masking

This paper addresses the load restoration problem after a power outage event. Our primary proposed methodology uses a multi-agent reinforcement learning method to make the optimal sequential decisions on picking up critical loads. Typically, a negative reward is provided to discourage the agents from selecting decisions that violate physical constraints during the restoration process. However, the main disadvantage of this approach is its difficulty in applying it to large-scale systems due to the curse of dimensionality. This paper introduces the invalid action masking technique to overcome this limitation. The features of this technique include zero physical constraint violations, reduced training time, and stabilization of the explo- ration process. Simulation results are performed in IEEE 13-node and IEEE 123-node systems showing the better performance of the proposed algorithm in comparison to the conventional approaches both in terms of restored power and learning curve.

reinforcement learning, blackstart, artificial int↗
DOE OSTI2025

Direct nonparametric multimessenger constraints on the equation of state of cold dense nuclear matter

We utilize the now substantial amount of astrophysical observations of neutron stars (NSs), along with perturbative quantum chromodynamics (pQCD) calculations at high density, to directly constrain the NS equation of state (EOS). To this end, we construct nonparametric EOS priors by using Gaussian processes trained on 75 EOSs, which include models with either hadrons, hyperons, or quarks at high densities. We create a prior using the full EOS sample (model agnostic), and one prior for each EOS family to test model discrimination. We introduce a novel inference approach, which allows the simultaneous sampling of intrinsic and extrinsic parameters of binary NS mergers, as well as a nonparametric equation of state. We showcase this method in a Bayesian updating scheme by first performing a complete analysis of the binary NS merger event GW170817 with minimal assumptions, and sequentially adding information from x-ray and radio NS observations, along with pQCD calculations. Besides providing standard constraints, such as the pressure at twice nuclear saturation density 𝑝⁡(2⁢𝜌 sat ) = 4.3$^{+0.6}_{−0.6}$ × 10 34 dyne/cm 2 , at 95% confidence level, for the model agnostic prior, our methodology shows how the choice of EOS families used in conditioning changes the inferred astrophysical properties of the EOS, namely tidal deformability and maximum supported NS mass. We find hyperonic priors predicting higher tidal deformabilities for a 1.4⁢𝑀 ⊙ NS, and hadronic priors being preferred by the considered astrophysical data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Heterogeneous Graph Neural Network for identifying hadronically decayed tau leptons at the High Luminosity LHC

Here, we present a new algorithm that identifies reconstructed jets originating from hadronic decays of tau leptons against those from quarks or gluons. No tau lepton reconstruction algorithm is used. Instead, the algorithm represents jets as heterogeneous graphs with tracks and energy clusters as nodes and trains a Graph Neural Network to identify tau jets from other jets. Different attributed graph representations and different GNN architectures are explored. We propose to use differential track and energy cluster information as node features and a heterogeneous sequentially-biased encoding for the inputs to final graph-level classification.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗
DOE OSTI2021

An adaptive adversarial domain adaptation approach for corn yield prediction

Recently, statistical machine learning and deep learning methods have been widely explored for corn yield prediction. Though successful, machine learning models generated within a specific spatial domain often lose their validity when directly applied to new regions. To address this issue, we designed an unsupervised adaptive domain adversarial neural network (ADANN). Specifically, through domain adversarial training, the ADANN model reduced the impact of domain shift by projecting data from different domains into the same subspace. Also, the ADANN model was designed to be trained in an adaptive way, which guaranteed the model can learn the domain-invariant features and perform accurate yield prediction simultaneously. Informative variables including time-series vegetation indices and sequential weather observations were first collected from multiple data sources and aggregated to the county level. Then, we trained the ADANN model with the extracted features and corresponding reported county-level corn yield from the U.S. Department of Agriculture (USDA). Finally, the trained model was evaluated in four testing years 2016–2019. The U.S. corn belt was used as the study area and counties under study were grouped into two diverse ecological regions. Overall, the experimental results showed that the developed ADANN model had better performance than three other state-of-the-art machine learning models in both local experiments (train and test in the same region) and transfer experiments (train and test in different regions). As the first study using adversarial learning for crop yield prediction, this research demonstrates a novel solution for improving model transferability on crop yield prediction.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A localized ensemble of approximate Gaussian processes for fast sequential emulation

More attention has been given to the computational cost associated with the fitting of an emulator. Substantially less attention is given to the computational cost of using that emulator for prediction. This is primarily because the cost of fitting an emulator is usually far greater than that of obtaining a single prediction, and predictions can often be obtained in parallel. In many settings, especially those requiring Markov Chain Monte Carlo, predictions may arrive sequentially and parallelization is not possible. In this case, using an emulator procedure which can produce accurate predictions efficiently can lead to substantial time savings in practice. In this paper, we propose a global model approximate Gaussian process framework via extension of a popular local approximate Gaussian process (laGP) framework. Our proposed emulator can be viewed as a treed Gaussian process where the leaf nodes are laGP models, and the tree structure is learned greedily as a function of the prediction stream. The suggested method (called leapGP) has interpretable tuning parameters which control the time‐memory trade‐off. One reasonable choice of settings leads to an emulator with a training cost and makes predictions rapidly with an asymptotic amortized cost of .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Band gap predictions of double perovskite oxides using machine learning

Abstract The compositional and structural variety inherent to oxide perovskites spawn wide-ranging applications. In perovskites, the band gap E g , a key material parameter for these applications, can be optimally controlled by varying the composition. Here, we implement a hierarchical screening process in which two cross-validated and predictive machine learning models for band gap classification and regression, trained using exhaustive datasets that span 68 elements of the periodic table, are applied sequentially. The classification model separates wide band gap materials, with E g ≥ 0.5 eV, from materials which have zero or relatively small band gaps, namely E g < 0.5 eV, and the second regression model quantitatively predicts the gap value of the wide band gap compounds. The study down-selects 13,589 cubic oxide perovskite compositions that are predicted to be experimentally formable, thermodynamically stable, and have a wide band gap. Of these, a subset of 310 compounds, which are predicted to be stable and formable with a confidence greater than 90%, are identified for further investigation. Our models are methodically analyzed via performance metrics and inter-dependence of model features to gain physical insight into the band gap prediction problem. Design maps to identify the variation of band gap with substitution of different elements are also presented.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Anderson Acceleration for Distributed Training of Deep Learning Models

Anderson acceleration (AA) is an extrapolation technique that has recently gained interest in the deep learning (DL) community to speed-up the sequential training of DL models. However, when performed at large scale, the DL training is exposed to a higher risk of getting trapped into steep local minima of the training loss function, and standard AA does not provide sufficient acceleration to escape from these steep local minima. This results in poor generalizability and makes AA ineffective. To restore AA’s advantage to speed-up the training of DL models on large scale computing platforms, we combine AA with an adaptive moving average procedure that boosts the training to escape from steep local minima. By monitoring the relative standard deviation between consecutive iterations, we also introduce a criterion to automatically assess whether the moving average is needed. We applied the method to the following DL instantiations for image classification: (i) ResNet50 trained on the open-source CIFAR100 dataset and (ii) ResNet50 trained on the open-source ImageNet1k dataset. Numerical results obtained using up to 1,536 NVIDIA V100 GPUs on the OLCF supercomputer Summit showed the stabilizing effect of the moving average on AA for all the problems above.

Lupo Pasini, Massimiliano↗
DOE OSTI2022

Autodifferentiable Ensemble Kalman Filters

Data assimilation is concerned with sequentially estimating a temporally evolving state. This task, which arises in a wide range of scientific and engineering applications, is particularly challenging when the state is high-dimensional and the state-space dynamics are unknown. This paper introduces a machine learning framework for learning dynamical systems in data assimilation. Here, our auto-differentiable ensemble Kalman filters (AD-EnKFs) blend ensemble Kalman filters for state recovery with machine learning tools for learning the dynamics. In doing so, AD-EnKFs leverage the ability of ensemble Kalman filters to scale to high-dimensional states and the power of automatic differentiation to train high-dimensional surrogate models for the dynamics. Numerical results using the Lorenz-96 model show that AD-EnKFs outperform existing methods that use expectation-maximization or particle filters to merge data assimilation and machine learning. In addition, AD-EnKFs are easy to implement and require minimal tuning.

autodifferentiation↗
DOE OSTI2021

Restoring Critical Loads In Resilient Distribution Systems using A Curriculum Learned Controller

In this paper, we propose a curriculum learned reinforcement learning (RL) controller to facilitate distribution system critical load restoration (CLR), leveraging RL's fast online response and its outstanding optimal sequential control capability. Like many grid control problems, CLR is complicated due to the large control action space and renewable uncertainty in a heavily constrained non-linear environment with strong intertemporal dependency. The nature of the problem oftentimes causes the RL policy to converge to a poor-performing local optimum if learned directly. To overcome this, we design a two-stage curriculum in which the RL agent will learn generation control and load restoration decision under different scenarios progressively. Via curriculum learning, the trained RL controller is expected to achieve a better control performance, with critical loads restored as rapidly and reliably as possible. Using the IEEE 13-bus test system, we illustrate the performance of the RL controller trained by the proposed curriculum-based method.

curriculum learning↗
DOE OSTI2021

Restoring Critical Loads in Resilient Distribution Systems Using a Curriculum Learned Controller: Preprint

In this paper, we propose a curriculum learned reinforcement learning (RL) controller to facilitate distribution system critical load restoration (CLR), leveraging RL's fast online response and its outstanding optimal sequential control capability. Like many grid control problems, CLR is complicated due to the large control action space and renewable uncertainty in a heavily constrained non-linear environment with strong intertemporal dependency. The nature of the problem oftentimes causes the RL policy to converge to a poor-performing local optimum if learned directly. To overcome this, we design a two-stage curriculum in which the RL agent will learn generation control and load restoration decision under different scenarios progressively. Via curriculum learning, the trained RL controller is expected to achieve a better control performance, with critical loads restored as rapidly and reliably as possible. Using the IEEE 13-bus test system, we illustrate the performance of the RL controller trained by the proposed curriculum-based method.

61 RADIATION PROTECTION AND DOSIMETRY↗