SEARCH · Search NASA

Results for “Adaptive convolution.”

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.

113 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Mitigating Catastrophic Forgetting in Deep Learning in a Streaming Setting Using Historical Summary

Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.

Dash, Sajal↗

DOE OSTI2022

Towards a neutron multiplicity measurement with the Accelerator Neutrino Neutron Interaction Experiment

The Accelerator Neutrino Neutron Interaction Experiment (ANNIE) is a 26 ton Gadolinium (Gd)-loaded water Cherenkov detector located on the Booster Neutrino Beam line at Fermilab. Its main goals are the measurement of the neutron multiplicity in neutrino-nucleus interactions as well as the cross-section of Charged Current Quasi-Elastic (CCQE) neutrino interactions on water. Besides the physics goals, the experiment also aims to be a testbed for new technologies such as Large Area Picosecond Photodetectors (LAPPDs) and Water-based Liquid Scintillators (WbLS). This thesis presents a preliminary measurement of the neutron multiplicity with {ANNIE}, using an analysis conducted on a fraction of the 2021 beam year. As preparatory measures, the efficiency of ANNIE's Front Muon Veto (FMV) was determined to be {$\bar{\varepsilon}_{\mathrm{FMV}} = (95.6 \pm 1.6)\%$} while the average efficiency for active scintillator paddles in the Muon Range Detector (MRD) was found to be {$\bar{\varepsilon}_ {\mathrm{MRD}} = (92.1 \pm 7.9)\%$}. Furthermore, the simulation framework used for ANNIE was validated and adapted to reproduce the experimental data by comparing the detector response for samples of Michel electrons, Americium Beryllium neutrons, and through-going muons. The analysis finds average neutron yields of {$\bar{n}_{\mathrm{data}} (\mathrm{beam}) = (0.272 \pm 0.010_{\mathrm{stat}})$} for an inclusive set of all identified muon neutrino candidates and {$\bar{n}_{\mathrm{data}} (\mathrm{beam,FV}) = (0.287 \pm 0.044_{\mathrm{stat}})$ for interactions which happened inside of the Fiducial Volume of ANNIE, which was optimized to increase the neutron detection acceptance. The presented neutron multiplicity values represent the number of detected neutrons after all event selection cuts and are not yet corrected for the neutron detection efficiency. An equivalent analysis on a simulated beam sample predicts neutron yields of $\bar{n}_{\mathrm{MC}}(\mathrm{beam}) = (0.515 \pm 0.0 07_{\mathrm{stat}})$ and $\bar{n}_{\mathrm{MC}}(\mathrm{beam,FV}) = (0.627 \pm 0.031_{\mathrm{stat}})$, indicating that the models tend to overpredict the number of neutrons produced in such interactions. Systematic errors have been briefly considered to contribute {$\sigma_{\mathrm{sys,FMV}} \sim 0.01\,$neutrons/$\nu$-interaction} due to the slight FMV inefficiency and {$\sigma_{\mathrm{sys,n}} \sim 0.05\,$neutrons/$\nu$-interaction} due to the neutron detection efficiency. Simulation studies further highlighted the importance of neutron detection in Diffuse Supernova Background (DSNB) searches. A combination of neutron tagging and Convolutional Neural Networks was found to reduce the most relevant Neutral Current Quasi-Elastic (NCQE) interaction background below the signal level, achieving a Signal-to-Background ratio of 4:1. In a further study, we investigated the positive impact of a deployment of a WbLS target on the energy reconstruction in ANNIE. WbLS provides a scintillation signal from hadronic recoils in addition to the charged lepton that can be included in neutrino energy reconstruction. It was found that a deployed WbLS volume in ANNIE improves the neutrino energy reconstruction from 14\% to 12\%, with the potential of going beyond this if more sophisticated reconstruction algorithms are developed in the future.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

Integrating static PRA information with risk informed safety margin characterization (RISMC) simulation methods

The overall objective of the project was to develop a computationally feasible and user-friendly mechanized process to integrate traditional probabilistic risk assessment (PRA) and dynamic PRA (DPRA) results. Starting with the systematic identification of items in an existing PRA that need dynamic augmentation, the project used a generic 4-loop pressurized reactor (PWR) and 3-loop PWR as example plants. Station blackout (SBO) and large break loss of coolant accident SBLOCA) were selected as the example initiating events. Using the traditional event-tree (ET)/fault-tree (FT) methodology augmented by dynamic evet tree approach, the potential consequences of the initiating events were simulated with RELAP-3D and MELCOR/RASCAL codes to cover Level 1 through Level 3 of PRA. RAVEN and ADAPT software were used to generate Level 1 simulations with RELAP-3D and Level 2/3 simulations with MELCOR (Level 2)/RASCAL (Level 3), respectively. Example branching conditions (BCs) for SBO included AC power recovery time, valve repair failure time, reactor coolant pump leak time/break size and emergency power supply duration to a total of 9. Example BCs for LOCA included off-site power recovery time, diesel generator power recovery time, auxiliary feed water system operation time, safety relief valve failure to open upon demand, reactor coolant pump seal break time and size to a total of 21. Each RELAP-3D simulation (9,587 scenarios) was labelled OK or Core Damage based on the maximum allowed peak clad temperature (2,100oF). Each MELCOR simulation (4610 scenarios) was labeled as Bin over 10rem or Bin 0-10rem based on the dose at the site boundary. The scenarios were clustered based on the criteria above using the mean shift methodology. Classical PRA (CPRA) and DPRA results were compared to identify the ET sequences that need DPRA augmentation. Several approaches were proposed for the incorporation of these sequences into CPRA using clustering with the mean shift methodology, restructuring the CPRA ETs by adding new BCs/sequences, and using the concept of a limit surface. Procedures for decision making regarding the possible consequences of an initiating event (e.g. core damage or not, site evacuation or not) were developed using a convolutional neural network (CNN), a recurrent neural network (RNN) and a transformer neural network (TNN). The project has led to two PhD degrees, three archival journal papers and five refereed conference proceedings.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗

DOE OSTI2026

Transfer learning for analysis of collective and non-collective Thomson scattering spectra

Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density (⁠n e ) and electron temperature (⁠T e ⁠). Deep neural networks can provide accurate estimates of ⁠n e and T e when conventional fitting algorithms may fail, such as when TS spectra are dominated by noise, or when fast analysis is required for real-time operation. Although deep neural networks typically require large training sets, transfer learning can improve model performance on a target task with limited data by leveraging pre-trained models from related source tasks, where select hidden layers are further trained using target data. We present five architecturally diverse deep neural networks, pre-trained on synthetic TS data and adapted for experimentally measured TS data, to evaluate the efficacy of transfer learning in estimating n e and T e in both the collective and non-collective scattering regimes. We evaluate errors in n e and T e estimates as a function of training set size for models trained with and without transfer learning, and we observe decreases in model error from transfer learning when the training set contains ≲ 200 experimentally measured spectra.

Artificial neural networks↗