SEARCH · Search NASA

Results for “Neural Network Potentials”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Evolution at the Edge: Real-Time Evolution for Neuromorphic Engine Control

Neuromorphic computing systems are attractive for real-time control at the edge because of their low power operation, real-time processing capabilities and their potential ability to do online learning. In this work, we describe an approach for performing real-time evolution of spiking neural networks for neuromorphic systems at the edge called Neuromorphic Optimization using Dynamic Evolutionary Systems or NODES. We apply this approach to real-time combustion engine control and develop an engine-specific hardware platform for NODES called FireBox. We demonstrate how the real-time evolution approach works in simulation and the performance of networks trained in simulation on the physical engine.

Maldonado Puente, Bryan [ORNL] (ORCID:000000033880↗

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↗

NASA NTRS2009

Flight Test Comparison of Different Adaptive Augmentations for Fault Tolerant Control Laws for a Modified F-15 Aircraft

This report describes the improvements and enhancements to a neural network based approach for directly adapting to aerodynamic changes resulting from damage or failures. This research is a follow-on effort to flight tests performed on the NASA F-15 aircraft as part of the Intelligent Flight Control System research effort. Previous flight test results demonstrated the potential for performance improvement under destabilizing damage conditions. Little or no improvement was provided under simulated control surface failures, however, and the adaptive system was prone to pilot-induced oscillations. An improved controller was designed to reduce the occurrence of pilot-induced oscillations and increase robustness to failures in general. This report presents an analysis of the neural networks used in the previous flight test, the improved adaptive controller, and the baseline case with no adaptation. Flight test results demonstrate significant improvement in performance by using the new adaptive controller compared with the previous adaptive system and the baseline system for control surface failures.

Burken, John J.↗

DOE OSTI2025

High‐Resolution National‐Scale Water Modeling Is Enhanced by Multiscale Differentiable Physics‐Informed Machine Learning

Abstract The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high‐resolution (∼37 km 2 ) differentiable models (a type of hybrid model): one with implicit, unit‐hydrograph‐style routing and another with explicit Muskingum‐Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and process‐based equations to provide a structural backbone, which were trained simultaneously (“end‐to‐end”) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily Nash‐Sutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long‐standing modeling challenge. The Muskingum‐Cunge version further improved performance for basins >10,000 km 2 . Overall, our results show how neural‐network‐based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next‐generation NWM. We also provide a CONUS‐scale hydrologic data set for further evaluation and use.

Song, Yalan [Civil and Environmental Engineering T↗

DOE OSTI2025

Machine Learning for Well Log Analysis in Uranium Mining

This project explores the use of Artificial Intelligence (AI) and Machine Learning (ML) techniques to automate well log analysis for uranium mining. Geophysical log data—spontaneous potential, resistivity, and gamma ray—were used to classify lithology, correlate well logs and identify roll front zonation patterns, which are critical for locating uranium ore bodies. Supervised ML algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Random Forest were trained to classify lithology with high accuracy. Gradient Boosting Machines (GBM), XGBoost, Random Forest, and Neural Networks were also used for role front zone identification. Moreover, a Fast Dynamic Time Warping (FastDTW) algorithm was employed for well log correlation. Additionally, sample lag was addressed using dynamic programming. Results demonstrate the potential of AI and ML to streamline well log analysis and enhance uranium exploration workflows.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

NASA NTRS1987

Similarity networks as a knowledge representation for space applications

Similarity networks are a powerful form of knowledge representation that are useful for many artificial intelligence applications. Similarity networks are used in applications ranging from information analysis and case based reasoning to machine learning and linking symbolic to neural processing. Strengths of similarity networks include simple construction, intuitive object storage, and flexible retrieval techniques that facilitate inferencing. Therefore, similarity networks provide great potential for space applications.

Bailey, David↗

DOE OSTI2024

Accelerating Resonance Searches via Signature-Oriented Pre-training

The search for heavy resonances beyond the Standard Model (BSM) is a key objective at the LHC. While the recent use of advanced deep neural networks for boosted-jet tagging significantly enhances the sensitivity of dedicated searches, it is limited to specific final states, leaving vast potential BSM phase space underexplored. We introduce a novel experimental method, Signature-Oriented Pre-training for Heavy-resonance ObservatioN (Sophon), which leverages deep learning to cover an extensive number of boosted final states. Pre-trained on the comprehensive JetClass-II dataset, the Sophon model learns intricate jet signatures, ensuring the optimal constructions of various jet tagging discriminates and enabling high-performance transfer learning capabilities. We show that the method can not only push widespread model-specific searches to their sensitivity frontier, but also greatly improve model-agnostic approaches, accelerating LHC resonance searches in a broad sense.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS1992

Neural networks application to divergence-based passive ranging

The purpose of this report is to summarize the state of knowledge and outline the planned work in divergence-based/neural networks approach to the problem of passive ranging derived from optical flow. Work in this and closely related areas is reviewed in order to provide the necessary background for further developments. New ideas about devising a monocular passive-ranging system are then introduced. It is shown that image-plan divergence is independent of image-plan location with respect to the focus of expansion and of camera maneuvers because it directly measures the object's expansion which, in turn, is related to the time-to-collision. Thus, a divergence-based method has the potential of providing a reliable range complementing other monocular passive-ranging methods which encounter difficulties in image areas close to the focus of expansion. Image-plan divergence can be thought of as some spatial/temporal pattern. A neural network realization was chosen for this task because neural networks have generally performed well in various other pattern recognition applications. The main goal of this work is to teach a neural network to derive the divergence from the imagery.

Barniv, Yair↗

DOE OSTI2025

Graph Neural Networks for Surrogate Modeling of Offshore Floating Platforms

Floating offshore wind turbines (FOWTs) present an significant opportunity to increase renewable energy generation. However, significant challenges remain before FOWTs can be widely commercialized and deployed. In particular, hydrodynamic loading on the platforms can stress the overall structure, damage the mooring systems, and impact power generation. Studying these loads is difficult and often relies on computationally expensive models or experiments. In this work, we explore the use of graph neural networks (GNNs) to construct flexible, data-driven surrogates for hydrodynamic loads on platforms. We leverage the natural graph-like structure of offshore wind platform designs to enable the GNN model to learn to approximate the loads for different wave conditions and structural designs. We demonstrate potential uses for the surrogate by performing parameter sweeps and ridge analysis on the trained model to identify the impacts of different wave and structural features on the loads.

floating offshore wind turbines↗

NASA NTRSDate not supplied

Lunar Gateway Charging and Effects on Low-Energy Electron Measurements

The Electron Electrostatic Analyzer (EEA) is part of the HERMES instrument suite on Lunar Gateway and is designed to measure electrons in the energy range from 1 eV to 18 keV. Electrons in this range can be deflected or blocked from entering a detector by electric fields from a charged spacecraft platform, so many heliophysics missions (MMS, Cluster, etc.) use active potential control to minimize stray electric fields which would corrupt low-energy plasma measurements. Gateway, however, does not have such capabilities so the surface charging effects will influence the electron data. Further, some elements of Gateway partially block the instrument’s field of view to space. The effects of the Gateway platform on the low-energy electron population must be understood to maximize the accuracy of the EEA data. To investigate the electrostatic environment near Gateway and its effects on the EEA measurements, we use Nascap-2K to model the expected charging of Gateway under representative solar wind, magnetosheathic, and magnetospheric conditions. Next, we use the potential and electric field outputs from Nascap-2K along with in-house particle tracing codes to investigate how low-energy electrons are perturbed, blocked, or deflected by the spacecraft. We discuss how these perturbations impact the plasma moments computed from the EEA data and possible approaches for correcting the charging effects including application of advanced methods such as neural networks. In addition to electrons from the space environment being influenced by the electrostatic environment around Gateway, photoelectrons generated on Gateway surfaces will also be measured by EEA. We are investigating how knowledge of the potentials of various Gateway surfaces can be extracted from these measured photoelectrons using advanced numerical modeling and analysis. Such information would be valuable for validating charging models and planning mission operations around the platform. Finally, we discuss how the specific workflow developed for Gateway can be extended to a generalized process that is applicable to other future missions. As the space industry prepares for human exploration beyond low-Earth orbit, the need to obtain accurate space weather data from rideshare science payloads is critical. Our process for removing platform effects from the science data serves as a pathfinder for leveraging advanced simulations to maximize science returns and ensure the safety and success of future crewed missions.

Miles Bengtson↗

NASA NTRS2005

Artificial Neural Network Test Support Development for the Space Shuttle PRCS Thrusters

A significant anomaly, Fuel Valve Pilot Seal Extrusion, is affecting the Shuttle Primary Reaction Control System (PRCS) Thrusters, and has caused 79 to fail. To help address this problem, a Shuttle PRCS Thruster Process Evaluation Team (TPET) was formed. The White Sands Test Facility (WSTF) and Boeing members of the TPET have identified many discrete valve current trace characteristics that are predictive of the problem. However, these are difficult and time consuming to identify and trend by manual analysis. Based on this exhaustive analysis over months, 22 thrusters previously delivered by the Depot were identified as high risk for flight failures. Although these had only recently been installed, they had to be removed from Shuttles OV103 and OV104 for reprocessing, by directive of the Shuttle Project Office. The resulting impact of the thruster removal, replacement, and valve replacement was significant (months of work and hundreds of thousands of dollars). Much of this could have been saved had the proposed Neural Network (NN) tool described in this paper been in place. In addition to the significant benefits to the Shuttle indicated above, the development and implementation of this type of testing will be the genesis for potential Quality improvements across many areas of WSTF test data analysis and will be shared with other NASA centers. Future tests can be designed to incorporate engineering experience via Artificial Neural Nets (ANN) into depot level acceptance of hardware. Additionally, results were shared with a NASA Engineering and Safety Center (NESC) Super Problem Response Team (SPRT). There was extensive interest voiced among many different personnel from several centers. There are potential spin-offs of this effort that can be directly applied to other data acquisition systems as well as vehicle health management for current and future flight vehicles.

Lehr, Mark E.↗

DOE OSTI2025

Neuronal Plasma Membranes as Supramolecular Assemblies for Biological Memory

Biological memory is the ability to develop, retain, and retrieve information over time. Currently, it is widely accepted that memories are stored in synapses (i.e., connections between brain cells throughout the brain) through a process known as synaptic plasticity, which leads to either long-term potentiation (LTP) or long-term depression (LTD). However, the strengthening (LTP) and weakening (LTD) of synapses involve post-translational modifications to neural networks requiring de novo gene expression, a lengthy and energetically expensive process. Recently, we observed that lipid bilayers in the absence of peptides/proteins are capable of LTP, not unlike what has been observed in mammals and birds. As such, this finding has prompted us to postulate that the lipid bilayer provides a good model for understanding the molecular basis of biological memory. Here, in this article, we discuss the status, challenges, and opportunities of neuronal plasma membranes as structures for biological memory and learning, therapeutic targets for various brain disorders, and platforms for neural network developments.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Status of the Muon Neutrino Charged-Current Mesonless Cross Section Measurement in the NOvA Near Detector

NOvA is a long-baseline accelerator neutrino experiment at Fermilab whose physics goals include precision neutrino oscillation as well as cross-section measurements. We present the status of the measurement of a muon neutrino charged-current cross section with zero mesons in the final state at the NOvA near detector. This measurement is being made with respect to the kinematics of the final state muon. The chosen interaction channel is especially sensitive to quasielastic and meson exchange current interactions and aims to provide experimental constraints for the development of models of neutrino interactions. It will also provide a handle for constraining cross section systematic uncertainties in oscillation analyses in current and future experiments. For particle identification, we use a convolutional neural network (CNN) trained on individual particles simulated in the NOvA near detector that allows us to select the desired signal while reducing the potential bias from neutrino interaction modeling. Charged pion background constraining is further improved via Michel electron tagging.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Status of the Muon Neutrino Charged-Current Zero Mesons Cross Section at the NOvA Near Detector

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

Web-Based Tools for Data-Informed Remedy Optimization: Software Theory and User Guide

This report documents the development and application of two web-based decision-support tools for pump-and-treat (P&T) groundwater remediation systems: PTOLEMY (Pump-and-Treat Optimized Location Evaluation to Maximize Yields) and OPTIMA (Optimization for Pump-and-Treat Implementation, Management, & Assessment). These tools enhance remedy design and management by leveraging advanced computational methods – specifically deep learning and multi-objective optimization – within a user-friendly platform. By integrating data-driven models with established hydrogeological knowledge, PTOLEMY and OPTIMA enable more efficient evaluation of well placement and operational strategies, helping site managers balance multiple remediation objectives under complex conditions. Both tools are implemented as modules within the SOCRATES (Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites) web platform, which provides data access, visualization, and analytics to support remedy optimization across sites in the U.S. Department of Energy Office of Environmental Management complex. PTOLEMY is a rapid screening module designed to identify promising locations for new extraction wells. It employs a multi-channel three-dimensional convolutional neural network (MC3D-CNN) trained on high-fidelity simulation data to predict the relative performance (in terms of contaminant mass recovery) of potential well sites. Through an interactive web interface, PTOLEMY visualizes the probability of high performance across a site, highlighting areas where an extraction well is likely to yield above-threshold contaminant removal over a multi-year period. PTOLEMY’s map-based displays and exportable results support transparent communication of screening analyses. By focusing attention on the most favorable candidate locations, the tool augments traditional engineering judgment and physics-based modeling, providing a data informed basis for subsequent detailed evaluations. OPTIMA is a multi objective optimization module designed to find wellfield layouts and operating schedules that meet various cleanup goals. It quickly evaluates thousands of candidate setups – combinations of well locations, timing, and rates – and returns a small set of best trade-off options for comparison. At its core, OPTIMA uses a U-Net-based surrogate model – a deep-learning emulator of a groundwater flow and transport simulator – to dramatically accelerate scenario evaluations. Coupling this fast surrogate with the NSGA-II (Non-dominated Sorting Genetic Algorithm II) evolutionary algorithm, OPTIMA explores a wide decision space of well locations and schedules to identify Pareto-optimal solutions that trade off key objectives (e.g., minimizing cleanup time, maximizing contaminant mass removal, and minimizing plume extent). The tool outputs a family of optimal configurations and visualizes their trade-offs (Pareto frontiers of cleanup metrics and maps of optimized well placements). Site managers can use these results to understand the range of viable strategies and to select candidate designs for more detailed verification. OPTIMA is currently under active development and not yet fully released; this guide provides early documentation to support planning and gather user feedback.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1996

Hybrid Architectures and Their Impact on Intelligent Design

In this presentation we investigate a novel framework for the design of autonomous fuzzy intelligent systems. The system integrates the following modules into a single autonomous entity: (1) a fuzzy expert system; (2) artificial neural network; (3) genetic algorithm; and (4) case-base reasoning. We describe the integration of these units into one intelligent structure and discuss potential applications.

Kandel, Abe↗

DOE OSTI2026

Measurement of the muon neutrino charged-current mesonless cross section in the NOvA near detector

NOvA is a long-baseline accelerator neutrino experiment at Fermilab. Its physics goals include precision neutrino oscillation measurements, neutrino interaction cross-section measurements and beyond Standard Model explorations. We present a measurement of muon neutrino charged-current cross section with zero mesons in the final state at the NOvA near detector. This measurement is performed as a function of the kinematics of the final state muon. Our chosen interaction channel is especially sensitive to quasielastic and meson exchange current interactions and it provides handles for constraining the cross section systematic uncertainties in oscillation analyses in present and future experiments. For particle identification, we use a convolutional neural network (CNN) trained on individual particles simulated in the NOvA Near detector. This allows us to select the desired signal while reducing the potential bias from neutrino interaction modeling. We study strategies for constraining the remaining charged-pion background via Michel electron information in a template fitting approach. The main experimental result is a two-dimensional differential cross section as a function of final-state muon kinetic energy and polar angle. The parameters of this measurement, including binning and unfolding, were optimized to reduce the expected systematic uncertainty in the total cross section. The final result shows good agreement with the main GENIE-based simulation framework that was independently fine-tuned in NOvA. We finally propose improvements and subsequent steps that build on this analysis and further dissect the final states of neutrino interactions. This work has been supported by US DOE grant DE-SC0015684.

Sánchez Falero, Sebastián Jesús [Iowa State U.]↗

NASA NTRS2010

Multi-Stage System for Automatic Target Recognition

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feedforward back-propagation neural network (NN) is then trained to classify each feature vector and to remove false positives. The system parameter optimizations process has been developed to adapt to various targets and datasets. The objective was to design an efficient computer vision system that can learn to detect multiple targets in large images with unknown backgrounds. Because the target size is small relative to the image size in this problem, there are many regions of the image that could potentially contain the target. A cursory analysis of every region can be computationally efficient, but may yield too many false positives. On the other hand, a detailed analysis of every region can yield better results, but may be computationally inefficient. The multi-stage ATR system was designed to achieve an optimal balance between accuracy and computational efficiency by incorporating both models. The detection stage first identifies potential ROIs where the target may be present by performing a fast Fourier domain OT-MACH filter-based correlation. Because threshold for this stage is chosen with the goal of detecting all true positives, a number of false positives are also detected as ROIs. The verification stage then transforms the regions of interest into feature space, and eliminates false positives using an artificial neural network classifier. The multi-stage system allows tuning the detection sensitivity and the identification specificity individually in each stage. It is easier to achieve optimized ATR operation based on its specific goal. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar and video image datasets.

Chao, Tien-Hsin↗