SEARCH · Search NASA

Results for “neural resources”

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 181 records · Page 10

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Prong Segmentation using Point Set Transformers in Multiple View Neutrino Detectors

NOvA is a long-baseline neutrino experiment studying neutrino oscillations by detecting neutrinos from the NuMI beam at Fermilab. Its physics analysis relies on accurate prong segmentation, which involves matching each hit to its source particle and identifying the particle type. This task has commonly been addressed using a combination of traditional clustering algorithms and convolutional neural networks (CNNs). However, NOvA’s detector design presents data as two sparse and decoupled 2D images (XZ and YZ views) rather than a native 3D representation, posing a significant challenge for traditional CNN-based models. In this talk, we propose a novel neural network based on the Point Set Transformer. By treating detector hits as sparse point clouds and implementing a cross-view attention mechanism, our model enables efficient information mixing between both views. Evaluated on NOvA simulated data, our model achieves superior accuracy while requiring significantly fewer computational resources compared to other models. Furthermore, the model demonstrates great performance when applied to Liquid Argon Time Projection Chamber (LArTPC) data, which shows its potential as a universal prong segmentation algorithm for multiple view neutrino detectors.

Liu, Jiaxi [UC, Irvine]↗

DOE OSTI2026

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture Codesign Package (SNAC-Pack), an open-source AutoML framework for hardware-aware neural architecture codesign and end-to-end FPGA deployment. SNAC-Pack runs a multi-objective global search with Optuna and NSGA-II, loading trials to a shared SQLite store that enables parallel workers across compute nodes. A hardware surrogate model outputs per-trial resource and latency estimates, avoiding the synthesis cost that would otherwise dominate the search loop. A local search stage then applies quantization-aware training (QAT) together with iterative magnitude pruning in a combined compression loop, after which the final model is synthesized to FPGA firmware via the hls4ml Python library. A YAML configuration and an optional agentic frontend let users run the pipeline on new datasets without modifying the framework. We demonstrate SNAC-Pack on jet classification at the Large Hadron Collider and superconducting qubit readout, discovering compact architectures that match or exceed strong baselines on the task metric while reducing FPGA resource utilization and, in the qubit readout case, reducing the design space exploration process from months of manual fine-tuning to hours of automated search.

Weitz, Jason [UC, San Diego]↗

DOE OSTI2022

Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images

Solar forecasting is shifting to the probabilistic paradigm due to the inherent uncertainty within the solar resource. Input uncertainty quantification is one of the widely used and best-performing ways to model solar uncertainty. However, compared to other sources of inputs, such as numerical weather prediction models, pure sky image-based probabilistic solar forecasting lags behind. In this research, an occlusion-perturbed convolutional neural network, named the PSolarNet, is developed. The PSolarNet provides very short-term deterministic forecasts, forecast scenarios, and probabilistic forecasts of the global horizontal irradiance from sky image sequences. Case studies based on 6 years of open-source data show that the developed PSolarNet is able to generate accurate 10-minute ahead deterministic forecasts with a 5.62% normalized root mean square error, realistic and diverse forecast scenarios with a 0.966 average correlation with the actual time series, and reliable and sharp probabilistic forecasts with a 2.77% normalized continuous ranked probability score.

Bayesian model averaging↗

DOE OSTI2022

Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images: Preprint

Bayesian model averaging↗

DOE OSTI2025

Denoising Autoencoder for Reconstructing Sensor Observation Data and Predicting Evapotranspiration: Noisy and Missing Values Repair and Uncertainty Quantification

Abstract Machine learning (ML) methods applied in scientific research often deal with interrelated features in high‐dimensional data. Reducing data noise and redundancy is needed to increase prediction accuracy and efficiency especially when dealing with data from field sensors. We explored an unsupervised learning method, the denoising autoencoder (DAE), to extract the underlying data structure from noisy raw data in the context of predicting hydrologic quantities from multiple field sensors. These sensors have intrinsic instrumental noise and occasional malfunctions that cause missing values. Our DAE neural network reconstructed meteorological sensor data containing noise and missing values to predict evapotranspiration in a mountainous watershed. The DAE reconstructed the sensor variables with a mean coefficient of determination value of 0.77 across 15 dimensions representing individual sensors. It reduced variance and bias uncertainties compared to a classical autoencoder model. The reconstruction quality varied across dimensions depending on their cross‐correlation and alignment with the underlying data structure. Uncertainties arising from the model structure were overall higher than those resulting from data corruption. We attached the DAE structure to a downstream ET‐prediction neural network in three formats and achieved reasonably accurate ET predictions . The use of the DAE notably reduced variance uncertainty in ET prediction. However, excessive variance reduction may be accompanied by an increase in bias due to the intrinsic bias‐variance tradeoff. Our method of evaluating and reducing uncertainties in aggregated data from different sources can be used to improve predictive models, process understanding, and uncertainty quantification for better water resource management. Plain Language Summary We present a machine learning method, namely the denoising autoencoder, which reduces the effects of data noise and missing values typically present in scientific data sets collected through sensor measurements. This method selects the most relevant information from noisy raw data collected by the instruments and fills in missing values. To demonstrate the effectiveness of our method, we applied it to predict evapotranspiration, a hydrologic variable that represents the water moved from the land surface to the atmosphere through a combination of evaporation and plant water use (transpiration). We also used a random sampling technique (the Monte Carlo method) to compare the uncertainty in the predictions when using the raw and noisy data versus the reconstructed data. The denoising process produced more accurate predictions of evapotranspiration with less uncertainty. Improved predictions of evapotranspiration can lead to a better understanding and accounting of water budgets. This ML approach is broadly suitable for a wide variety of applications that involve noisy sensor data with missing values. Key Points We used a denoising autoencoder (DAE) neural network to reduce noise in meteorological and soil sensor observations by on average We used Monte Carlo sampling to estimate the bias and variance of all model outputs, including uncertainty sources from data and the model We attached the DAE component to a downstream neural network to predict ET with the variance reduced by , compared to that without the DAE

denoising autoencoder↗

DOE OSTI2025

Fully‐Printed Ion Sensor Arrays for Measuring Agricultural Nitrogen and Potassium Concentrations Using Nernstian and AI Models

Abstract The chemical composition of growing media is a key factor for plant growth, impacting agricultural yield and sustainability. However, there is a lack of affordable chemical sensors for ubiquitous nutrient ion monitoring in agricultural applications. This work investigates using fully printed ion‐sensor arrays to measure the concentrations of nitrate, ammonium, and potassium in mixed‐electrolyte media. Ion sensor arrays composed of nitrate, ammonium, and potassium ion‐selective electrodes and a printed silver‐silver chloride (Ag/AgCl) reference electrode are fabricated and characterized in aqueous solutions in a range of concentrations that encompass what is typical for agricultural growing media (0.01 m m –1 m ). The sensors are also tested in mixed‐electrolyte solutions of NaNO 3 , NH 4 Cl, and KCl of varying concentrations, and the recorded potentials are input into Nernstian and artificial neural network models to compare the prediction accuracy of the models against ground truth. The artificial neural network models demonstrated higher accuracy over the Nernstian model, and the model using only ion‐sensor inputs is 7.5% more accurate than the Nernstian model under the same conditions. By enabling more precise and efficient fertilizer application, these sensor arrays coupled to computational models can help increase crop yields, optimize resource use, and reduce environmental impact.

Goodrich, Payton [University of California Berkele↗

DOE OSTI2024

Optimal Management of Grid-Interactive Efficient Buildings via Safe Reinforcement Learning

Reinforcement learning (RL)-based methods have achieved significant success in managing grid-interactive efficient buildings (GEBs). However, RL does not carry intrinsic guarantees of constraint satisfaction, which may lead to severe safety consequences. Besides, in GEB control applications, most existing safe RL approaches rely only on the regularisation parameters in neural networks or penalty of rewards, which often encounter challenges with parameter tuning and lead to catastrophic constraint violations. To provide enforced safety guarantees in controlling GEBs, this paper designs a physics-inspired safe RL method whose decision-making is enhanced through safe interaction with the environment. Different energy resources in GEBs are optimally managed to minimize energy costs and maximize customer comfort. The proposed approach can achieve strict constraint guarantees based on prior knowledge of a set of developed hard steady-state rules. Simulations on the optimal management of GEBs, including heating, ventilation, and air conditioning (HVAC), solar photovoltaics, and energy storage systems, demonstrate the effectiveness of the proposed approach.

Huo, Xiang↗

DOE OSTI2022

A Comparison of Machine Learning Methods for Frequency Nadir Estimation in Power Systems

An increasing penetration level of inverter-based renewable energy resources changes the inertia of power systems, posing challenges for maintaining the desired system frequency stability. An accurate frequency nadir estimation is crucial for power system operators to prepare preventive actions against large frequency excursions. In this paper, five machine learning methods - linear regression, gradient boosting, support vector regression, an artificial neural network, and XGBoost - are applied to two different datasets, i.e., 1) the unit generation dataset and 2) the system total inertia and headroom dataset, for the prediction of the frequency nadir. The training and testing datasets are generated through extensive generation scheduling simulations using Multi-timescale Integrated Dynamic and Scheduling (MI-DAS) toolbox on the Western Electricity Coordinating Council 240-bus system with high renewable penetration levels. Numerical results show that all five machine learning methods perform well in predicting the nadir frequency of the system. Among them, the gradient boosting and the XGBoost are clear winners yielding the best prediction accuracy in terms of four evaluation metrics.

data driven↗

DOE OSTI2025

Huge ensembles – Part 2: Properties of a huge ensemble of hindcasts generated with spherical Fourier neural operators

Abstract. In Part 1, we created an ensemble based on spherical Fourier neural operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires orders-of-magnitude fewer computational resources. Here in Part 2, we generate a huge ensemble (HENS), with 7424 members initialized each day of summer 2023. We enumerate the technical requirements for running huge ensembles at this scale. HENS precisely samples the tails of the forecast distribution and presents a detailed sampling of internal variability. HENS has two primary applications: (1) as a large dataset with which to study the statistics and drivers of extreme weather and (2) as a weather forecasting system. For extreme climate statistics, HENS samples events 4σ away from the ensemble mean. At each grid cell, HENS increases the skill of the most accurate ensemble member and enhances coverage of possible future trajectories. As a weather forecasting model, HENS issues extreme weather forecasts with better uncertainty quantification. It also reduces the probability of outlier events, in which the verification value lies outside the ensemble forecast distribution.

Mahesh, Ankur↗

DOE OSTI2022

A Comparison of Machine Learning Methods for Frequency Nadir Estimation in Power Systems: Preprint

An increasing penetration level of inverter-based renewable energy resources changes the inertia of power systems, posing challenges for maintaining the desired system frequency stability. An accurate frequency nadir estimation is crucial for power system operators to prepare preventive actions against large frequency excursions. In this paper, five machine learning methods - linear regression, gradient boosting, support vector regression, an artificial neural network, and XGBoost - are applied to two different sets of preprocess data for the prediction of the frequency nadir in the Western Electricity Coordinating Council 240-bus system with high renewable penetration levels. The training and testing data sets are collected by extensive generation scheduling simulations on the Multi-timescale Integrated Dynamic and Scheduling (MIDAS) toolbox. Numerical results show that all five machine learning methods can achieve high performance accuracy for power system nadir frequency estimation. Among them, the gradient boosting and the XGBoost are clear winners by providing the best prediction accuracy.

data driven↗

DOE OSTI2023

Enhancing Nanoparticle Detection in Interferometric Scattering (iSCAT) Microscopy Using a Mask R-CNN

Interferometric scattering microscopy (iSCAT) is a label-free optical microscopy technique that enables imaging of individual nano-objects such as nanoparticles, viruses, and proteins. Essential to this technique is the suppression of background scattering and identification of signals from nano-objects. In the presence of substrates with high roughness, scattering heterogeneities in the background, when coupled with tiny stage movements, cause features in the background to be manifested in background-suppressed iSCAT images. Traditional computer vision algorithms detect these background features as particles, limiting the accuracy of object detection in iSCAT experiments. Here, in this paper, we present a pathway to improve particle detection in such situations using supervised machine learning via a mask region-based convolutional neural network (mask R-CNN). Using a model iSCAT experiment of 19.2 nm gold nanoparticles adsorbing to a rough layer-by-layer polyelectrolyte film, we develop a method to generate labeled datasets using experimental background images and simulated particle signals and train the mask R-CNN using limited computational resources via transfer learning. We then compare the performance of the mask R-CNN trained with and without inclusion of experimental backgrounds in the dataset against that of a traditional computer vision object detection algorithm, Haar-like feature detection, by analyzing data from the model experiment. Results demonstrate that including representative backgrounds in training datasets improved the mask R-CNN in differentiating between background and particle signals and elevated performance by markedly reducing false positives. The methodology for creating a labeled dataset with representative experimental backgrounds and simulated signals facilitates the application of machine learning in iSCAT experiments with strong background scattering and thus provides a useful workflow for future researchers to improve their image processing capabilities.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Developing machine-learning potentials to study properties of the tritium formation and diffusivity in pure and defective Zircaloy-4 getters

Objective of this work was to study the formation of Sn impurity and hydride phases in Zr and study their impacts on the diffusion kinetics of 3 H by using DFT based ML approach. By implementing deep neural potential (DNP) technique, we developed potential for Zr-H and Sn impurity systems and validated the DNP by using DFT results. We found that by implementing machine learning approach, it is possible to achieve accuracy comparable to DFT level for the more realistic models by using less computational time and resources.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Fast convolutional neural networks on FPGAs with hls4ml

We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on field-programmable gate arrays (FPGAs). By extending the hls4ml library, we demonstrate an inference latency of 5 µs using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Numbers Dataset, we demonstrate various methods for model compression in order to fit the computational constraints of a typical FPGA device used in trigger and data acquisition systems of particle detectors. In particular, we discuss pruning and quantization-aware training, and demonstrate how resource utilization can be significantly reduced with little to no loss in model accuracy. We show that the FPGA critical resource consumption can be reduced by 97% with zero loss in model accuracy, and by 99% when tolerating a 6% accuracy degradation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

Machine learned features from density of states for accurate adsorption energy prediction

Materials databases generated by high-throughput computational screening, typically using density functional theory (DFT), have become valuable resources for discovering new heterogeneous catalysts, though the computational cost associated with generating them presents a crucial roadblock. Hence there is a significant demand for developing descriptors or features, in lieu of DFT, to accurately predict catalytic properties, such as adsorption energies. Here, we demonstrate an approach to predict energies using a convolutional neural network-based machine learning model to automatically obtain key features from the electronic density of states (DOS). The model, DOSnet, is evaluated for a diverse set of adsorbates and surfaces, yielding a mean absolute error on the order of 0.1 eV. In addition, DOSnet can provide physically meaningful predictions and insights by predicting responses to external perturbations to the electronic structure without additional DFT calculations, paving the way for the accelerated discovery of materials and catalysts by exploration of the electronic space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Prediction of organic homolytic bond dissociation enthalpies at near chemical accuracy with sub-second computational cost

Bond dissociation enthalpies (BDEs) of organic molecules play a fundamental role in determining chemical reactivity and selectivity. However, BDE computations at sufficiently high levels of quantum mechanical theory require substantial computing resources. In this paper, we develop a machine learning model capable of accurately predicting BDEs for organic molecules in a fraction of a second. We perform automated density functional theory (DFT) calculations at the M06-2X/def2-TZVP level of theory for 42,577 small organic molecules, resulting in 290,664 BDEs. A graph neural network trained on a subset of these results achieves a mean absolute error of 0.58 kcal mol-1 (vs DFT) for BDEs of unseen molecules. We further demonstrate the model on two applications: first, we rapidly and accurately predict major sites of hydrogen abstraction in the metabolism of drug-like molecules, and second, we determine the dominant molecular fragmentation pathways during soot formation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Emerging Trends and Technologies Used for the Identification, Detection, and Characterisation of Plant-Parasitic Nematode Infestation in Crops

Accurate identification and estimation of the population densities of microscopic, soil-dwelling plant-parasitic nematodes (PPNs) are essential, as PPNs cause significant economic losses in agricultural production systems worldwide. This study presents a comprehensive review of emerging techniques used for the identification of PPNs, including morphological identification, molecular diagnostics such as polymerase chain reaction (PCR), high-throughput sequencing, meta barcoding, remote sensing, hyperspectral analysis, and image processing. Classical morphological methods require a microscope and nematode taxonomist to identify species, which is laborious and time-consuming. Alternatively, quantitative polymerase chain reaction (qPCR) has emerged as a reliable and efficient approach for PPN identification and quantification; however, the cost associated with the reagents, instrumentation, and careful optimisation of reaction conditions can be prohibitive. High-throughput sequencing and meta-barcoding are used to study the biodiversity of all tropical groups of nematodes, not just PPNs, and are useful for describing changes in soil ecology. Convolutional neural network (CNN) methods are necessary to automate the detection and counting of PPNs from microscopic images, including complex cases like tangled nematodes. Remote sensing and hyperspectral methods offer non-invasive approaches to estimate nematode infestations and facilitate early diagnosis of plant stress caused by nematodes and rapid management of PPNs. This review provides a valuable resource for researchers, practitioners, and policymakers involved in nematology and plant protection. It highlights the importance of fast, efficient, and robust identification protocols and decision-support tools in mitigating the impact of PPNs on global agriculture and food security.

Plant Sciences↗

DOE OSTI2024

A framework to enhance disaster debris estimation with AI and aerial photogrammetry

This study addresses the critical need to enhance disaster preparedness and response, focusing on hurricane impact assessment and debris estimation. Accurate assessments in this context are critical for post-event search-and-rescue (SAR) operations and resource distribution. Recent computing advancements are revealing the potential of unmanned aerial vehicles (UAVs) and artificial intelligence (AI) technologies in collecting data and assisting with post-hurricane reconnaissance. However, the use of AI and UAV photogrammetry for accurate disaster impact analysis remains underexplored. To this end, this study proposes a damage and debris analysis framework harnessing reality capture through aerial imagery and photogrammetry. Within this framework, a region-based neural network is leveraged to detect debris locations in aerial imagery with favorable performance. In a testbed within the Beaumont-Port Arthur region, in Southeast Texas, this study performs 3D reality captures of the built environment. Since the accuracy of the 3D reality capture is of importance in research areas associated with time-sensitive disaster response, we further investigate the optimal 2D aerial imagery overlap ratio required to generate a sufficiently accurate 3D model for disaster impact analysis and debris volume estimation. Results indicate that, in the case of aerial imagery for infrastructure systems, a minimum of 60 % overlap is recommended for damage assessment and debris analysis. In contrast, for flat green areas, a minimum of 50 % overlap is adequate. Overall, for disaster response applications, our study reveals that an overlap ratio between 60 % and 70 % is optimal for achieving a balance between time efficiency and data quality in aerial data collection. Furthermore, these quantitative recommendations are crucial for enabling efficient disaster response efforts. Additionally, our study outcomes will improve disaster impact analysis and facilitating timely and effective response strategies.

Artificial intelligence↗