Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
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 NTRSDate not supplied

A Preliminary Development of The Intelligent Change Detection System (ICDS): Using Machine Learning to Combat Change Blindness in Remote Operation Environments

The emergence of Advance Air Mobility (AAM) will increase the number and types of aerial vehicles operating in shared airspaces, which will subsequently affect the amount of actionable data that ground control station operators (GCSOs) will be expected to manage. In this environment, GCSOs are particularly susceptible to the visual perceptual phenomenon known as change blindness, in which a stimulus undergoes a change without the change being noticed by its observer. A machine agent designed to detect change blindness and mitigate the effects could improve human agent performance in a data-saturated remote operations environment. The objective of this paper is to describe a proof-of-concept system architecture that integrates real-time eye tracking and vehicle telemetry data to prevent human-agent errors resulting from change blindness while operating aircraft from a remote ground control station (GCS).

Real-Time Streaming Data Architecture↗
NASA NTRSDate not supplied

A Preliminary Development of The Intelligent Change Detection System (ICDS): Using Machine Learning to Combat Change Blindness in Remote Operation Environments

The emergence of Advance Air Mobility (AAM) will increase the number and types of aerial vehicles operating in shared airspaces, which will subsequently affect the amount of actionable data that ground control station operators (GCSOs) will be expected to manage. In this environment, GCSOs are particularly susceptible to the visual perceptual phenomenon known as change blindness, in which a stimulus undergoes a change without the change being noticed by its observer. A machine agent designed to detect change blindness and mitigate the effects could improve human agent performance in a data-saturated remote operations environment. The objective of this paper is to describe a proof-of-concept system architecture that integrates real-time eye tracking and vehicle telemetry data to prevent human-agent errors resulting from change blindness while operating aircraft from a remote ground control station (GCS).

Real-Time Streaming Data Architecture↗
NASA NTRSDate not supplied

Combining Earth System Modeling and Machine Learning to Investigate Volcanic Sulfate Deposition in Polar Ice Cores

Volcanic eruptions emit large amounts of sulfur dioxide (SO2), water, and other chemicals into the atmosphere, both in the troposphere and the stratosphere. Most of the SO2 is converted to sulfate aerosol, which is eventually deposited following long-range transport. The deposits from large eruptions are potentially detectable in ice cores, but there are many cases in which sulfate layers have not been linked to their source volcanoes. As volcanoes can act as significant shocks to the global climate system, we are interested in locating these eruptions in order to increase understanding of the volcanic record. To narrow down the search, we performed 140 simulations of volcanic eruptions using the GISS ModelE Earth system model. We varied the latitude, longitude, Julian day, plume top, plume bottom, and injected SO2 and H2O amounts using a Latin hypercube sampling approach, and analyzed correlations between these parameters and sulfate depositions at ice core sites in Antarctica and Greenland. Using machine learning and parameter estimation, we generated probability distributions and maximum likelihood estimates for the parameters given sulfate deposition data, which can predict latitude with some skill. We find that the volcano latitude and SO2 content are best correlated with sulfate depositions at each pole, while longitude, Julian day, and H2O have small or insignificant effects. Plume altitude and thickness are important because they determine how much of the SO2 is injected into the stratosphere, which has implications for sulfur transport and lifetimes.

Earth system models↗
DOE OSTI2019

Alliance Project: Secure Control Systems for the Energy Sector

The Alliance Project addresses Area of Interest 4: Secure Remote Access for the Energy Sector, by combining physical and cyber access under one cybersecurity access system. The Alliance Project built on the successful completion of the Lemnos and Padlock Project (DOE-Funded Project started in 2007 and 2010) and researched and developed a solution for an Ethernet Security Gateway with the functionality required to integrate the physical access control cyber system and interface with legacy and new proximity card readers used for physical access requests. This project focused on securing and enhancing the cyber system the physical access control system operates on. The team tested and demonstrated the system solution on the SEL campus. Currently the physical access cyber system is completely separate from the cyber access control cyber system. With a single system industry benefits include: (1) Single system to learn and teach employees; (2) Single system that collects and alerts on logs and events simplifying incident response plans and NERC CIP compliance; (3) Unifies trust management to a single system reducing the potential errors in privilege escalation or revocation; (4) Provides a stronger cybersecurity platform the physical access control system operates on. Today they are mostly plain text protocols and little cyber awareness; (5) Integration of physical access awareness allows the cyber system to react and adjust. In some cases, the cyber access can be enhanced with authorized physical access and other cases the cyber access can be more restricted with unauthorized physical access; and (6) Enables the utility to establish as large or as small a physical access control system as they require. One example would be when a utility shares a substation with a neighbor utility and can’t rely on the substation door for the physical access control. The Alliance technology enables them to lock equipment racks simply with no scalability issues because it stands on the cyber security infrastructure which is already highly scalable.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1988

Blindness in designing intelligent systems

New investigations of the foundations of artificial intelligence are challenging the hypothesis that problem solving is the cornerstone of intelligence. New distinctions among three domains of concern for humans--description, action, and commitment--have revealed that the design process for programmable machines, such as expert systems, is based on descriptions of actions and induces blindness to nonanalytic action and commitment. Design processes focusing in the domain of description are likely to yield programs like burearcracies: rigid, obtuse, impersonal, and unable to adapt to changing circumstances. Systems that learn from their past actions, and systems that organize information for interpretation by human experts, are more likely to be successful in areas where expert systems have failed.

Denning, Peter J.↗
NASA NTRS2003

NASA Technical Standards Program

The NASA Technical Standards Program was officially established in 1997 as result of a directive issued by the Administrator. It is responsible for Agency wide technical standards development, adoption (endorsement), and conversion of Center-unique standards for Agency wide use. One major element of the Program is the review of NSA technical standards products and replacement with non-Government Voluntary Consensus Standards in accordance with directions issued by the Office of Management and Budget. As part of the Program s function, it developed a NASA Integrated Technical Standards Initiative that consists of and Agency wide full-text system, standards update notification system, and lessons learned - standards integration system. The Program maintains a "one stop-shop" Website for technical standards ad related information on aerospace materials, etc. This paper provides information on the development, current status, and plans for the NAS Technical Standards Program along with metrics on the utility of the products provided to both users within the nasa.gov Domain and the Public Domain.

Gill, Paul S.↗
DOE OSTI2020

Phase behavior of continuous-space systems: A supervised machine learning approach

The phase behavior of complex fluids is a challenging problem for molecular simulations. Supervised machine learning (ML) methods have shown potential for identifying the phase boundaries of lattice models. In this work, we extend these ML methods to continuous-space systems. We propose a convolutional neural network model that utilizes grid-interpolated coordinates of molecules as input data of ML and optimizes the search for phase transitions with different filter sizes. We test the method for the phase diagram of two off-lattice models, namely, the Widom–Rowlinson model and a symmetric freely jointed polymer blend, for which results are available from standard molecular simulations techniques. The ML results show good agreement with results of previous simulation studies with the added advantage that there is no critical slowing down. We find that understanding intermediate structures near a phase transition and including them in the training set is important to obtain the phase boundary near the critical point. The method is quite general and easy to implement and could find wide application to study the phase behavior of complex fluids.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Restoring Distribution System Under Renewable Uncertainty Using Reinforcement Learning

Distributed energy resources (DERs) in distribution systems, including renewable generation, micro-turbine, and energy storage, can be used to restore critical loads following extreme events to increase grid resiliency. However, properly coordinating multiple DERs in the system for multi-step restoration process under renewable uncertainty and fuel availability is a complicated sequential optimal control problem. Due to its capability to handle system non-linearity and uncertainty, reinforcement learning (RL) stands out as a potentially powerful candidate in solving complex sequential control problems. Moreover, the offline training of RL provides excellent action readiness during online operation, making it suitable to problems such as load restoration, where in-time, correct and coordinated actions are needed. In this study, a distribution system prioritized load restoration based on a simplified single-bus system is studied: with imperfect renewable generation forecast, the performance of an RL controller is compared with that of a deterministic model predictive control (MPC). Our experiment results show that the RL controller is able to learn from experience, adapt to the imperfect forecast information and provide a more reliable restoration process when compared with the baseline controller.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2021

Restoring Distribution System Under Renewable Uncertainty Using Reinforcement Learning

Distributed energy resources (DER) in distribution systems, including renewable generation, micro-turbine, and energy storage, can be used to restore critical loads following extreme events to increase grid resiliency. However, properly coordinating multiple DERs in the system for multi-step restoration process under renewable uncertainty and fuel availability is a complicated sequential optimal control problem. Due to its capability to handle system non-linearity and uncertainty, reinforcement learning (RL) stands out as a potentially powerful candidate in solving complex sequential control problems. Moreover, the offline training of RL provides excellent action readiness during online operation, making it suitable to problems such as load restoration, where in-time, correct and coordinated actions are needed. In this study, a distribution system prioritized load restoration based on a simplified single-bus system is studied: with imperfect renewable generation forecast, the performance of an RL controller is compared with that of a deterministic model predictive control (MPC). Our experiment results show that the RL controller is able to learn from experience, adapt to the imperfect forecast information and provide a more reliable restoration process when compared with the baseline MPC controller.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2018

Machine learning based energy management system for grid disaster mitigation

The recent increase in infiltration of distributed resources has challenged the traditional operation of power systems. Simultaneously, devastating effects of recent natural disasters have questioned the resilience of power infrastructure for an electricity dependent community. In this study, a solution has been presented in the form of a resilient smart grid network which utilizes Distributed Energy Resources (DERs) and Machine Learning (ML) algorithms to improve the power availability during disastrous events. In addition to power electronics with load categorization features, the presented system utilizes ML tools to use the information from neighbouring units and external sources to make complicated logical decisions directed towards provide power to critical loads at all times. Furthermore, provided model encourages consideration of ML tools as a part of smart grid design process together with power electronics and controls, not as an additional feature.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2015

Resurrected DSCOVR Propulsion System - Challenges and Lessons Learned

The Deep Space Climate Observatory (DSCOVR), formerly known as Triana, is a unique mission, not because of its objectives but because of how long it was in storage before launch. The Triana spacecraft was built in the late 90s and later renamed as DSCOVR, but the project was canceled before the spacecraft was launched. The nearly-complete spacecraft was put in controlled storage for 10 years, until the National Oceanic and Atmospheric Administration (NOAA) provided funding for the National Aeronautics and Space Administration (NASA) to refurbish the spacecraft. On February 11, 2015, DSCOVR was launched on a Falcon 9 v1.1 from launch complex 40 at Cape Canaveral Air Force Station. This paper describes the DSCOVR propulsion system, which utilizes ten 4.5 N thrusters in blowdown mode to perform Midcourse Correction (MCC) maneuvers, Lissajous Orbit Insertion (LOI) at Lagrangian point L1, momentum unloading maneuvers, and station keeping delta-v maneuvers at L1. This paper also describes the testing that was performed, including susbsystem-level and spacecraft-level tests, to verify the propulsion system's integrity for flight. Finally, this paper concludes with a discussion of the challenges and lessons learned during this unique mission, including replacement of a bent thruster and installation of an auxiliary heater over existing propellant line heaters.

System↗
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 OSTI2021

MULTICOM2 open-source protein structure prediction system powered by deep learning and distance prediction

Protein structure prediction is an important problem in bioinformatics and has been studied for decades. However, there are still few open-source comprehensive protein structure prediction packages publicly available in the field. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. The template-based modeling uses sequence alignment tools with deep multiple sequence alignments to search for structural templates, which are much faster and more accurate than MULTICOM1. The template-free (ab initio or de novo) modeling uses the inter-residue distances predicted by DeepDist to reconstruct tertiary structure models without using any known structure as template. In the blind CASP14 experiment, the average TM-score of the models predicted by our server predictor based on the MULTICOM2 system is 0.720 for 58 TBM (regular) domains and 0.514 for 38 FM and FM/TBM (hard) domains, indicating that MULTICOM2 is capable of predicting good tertiary structures across the board. It can predict the correct fold for 76 CASP14 domains (95% regular domains and 55% hard domains) if only one prediction is made for a domain. The success rate is increased to 3% for both regular and hard domains if five predictions are made per domain. Moreover, the prediction accuracy of the pure template-free structure modeling method on both TBM and FM targets is very close to the combination of template-based and template-free modeling methods. This demonstrates that the distance-based template-free modeling method powered by deep learning can largely replace the traditional template-based modeling method even on TBM targets that TBM methods used to dominate and therefore provides a uniform structure modeling approach to any protein. Finally, on the 38 CASP14 FM and FM/TBM hard domains, MULTICOM2 server predictors (MULTICOM-HYBRID, MULTICOM-DEEP, MULTICOM-DIST) were ranked among the top 20 automated server predictors in the CASP14 experiment. After combining multiple predictors from the same research group as one entry, MULTICOM-HYBRID was ranked no. 5. The source code of MULTICOM2 is freely available at https://github.com/multicom-toolbox/multicom/tree/multicom_v2.0 .

97 MATHEMATICS AND COMPUTING↗
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↗