ZTF_image_classification
This repo demonstrates how to use the LLNL developed Gaussian process hyperparameter estimation method, MuyGPS, for image classification using Zwicky Transient Facility (ZTF) data.
Pruett, Kerianne↗
SEARCH · Engineering Papers
Results for “classification”
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.
Classification of Semiconductors Using Photoluminescence Spectroscopy and Machine Learning
Photoluminescence spectroscopy is a nondestructive optical method that is widely used to characterize semiconductors. In the photoluminescence process, a substance absorbs photons and emits light with longer wavelengths via electronic transitions. This paper discusses a method for identifying substances from their photoluminescence spectra using machine learning, a technique that is efficient in making classifications. Neural networks were constructed by taking simulated photoluminescence spectra as the input and the identity of the substance as the output. Here, six different semiconductors were chosen as categories: gallium oxide (Ga 2 O 3 ), zinc oxide (ZnO), gallium nitride (GaN), cadmium sulfide (CdS), tungsten disulfide (WS 2 ), and cesium lead bromide (CsPbBr 3 ). The developed algorithm has a high accuracy (>90%) for assigning a substance to one of these six categories from its photoluminescence spectrum and correctly identified a mixed Ga 2 O 3 /ZnO sample.
47 OTHER INSTRUMENTATION↗
A robust approach to 3D neuron shape representation for quantification and classification
We consider the problem of finding an accurate representation of neuron shapes, extracting sub-cellular features, and classifying neurons based on neuron shapes. In neuroscience research, the skeleton representation is often used as a compact and abstract representation of neuron shapes. However, existing methods are limited to getting and analyzing “curve” skeletons which can only be applied for tubular shapes. This paper presents a 3D neuron morphology analysis method for more general and complex neuron shapes. First, we introduce the concept of skeleton mesh to represent general neuron shapes and propose a novel method for computing mesh representations from 3D surface point clouds. A skeleton graph is then obtained from skeleton mesh and is used to extract sub-cellular features. Finally, an unsupervised learning method is used to embed the skeleton graph for neuron classification. Extensive experiment results are provided and demonstrate the robustness of our method to analyze neuron morphology.
3D neuron morphology↗
Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports
PURPOSE Surgical pathology reports are critical for cancer diagnosis and management. To accurately extract information about tumor characteristics from pathology reports in near real time, we explore the impact of using domain-specific transformer models that understand cancer pathology reports. METHODS We built a pathology transformer model, Path-BigBird, by using 2.7 million pathology reports from six SEER cancer registries. We then compare different variations of Path-BigBird with two less computationally intensive methods: Hierarchical Self-Attention Network (HiSAN) classification model and an offthe-shelf clinical transformer model (Clinical BigBird). We use five pathology information extraction tasks for evaluation: site, subsite, laterality, histology, and behavior. Model performance is evaluated by using macro and micro F 1 scores. RESULTS We found that Path-BigBird and Clinical BigBird outperformed the HiSAN in all tasks. Clinical BigBird performed better on the site and laterality tasks. Versions of the Path-BigBird model performed best on the two most difficult tasks: subsite (micro F 1 score of 72.53, macro F 1 score of 35.76) and histology (micro F 1 score of 80.96, macro F 1 score of 37.94). The largest performance gains over the HiSAN model were for histology, for which a Path-BigBird model increased the micro F 1 score by 1.44 points and the macro F 1 score by 3.55 points. Overall, the results suggest that a Path-BigBird model with a vocabulary derived from wellcurated and deidentified data is the best-performing model. CONCLUSION The Path-BigBird pathology transformer model improves automated information extraction from pathology reports. Although Path-BigBird outperforms Clinical BigBird and HiSAN, these less computationally expensive models still have utility when resources are constrained.
60 APPLIED LIFE SCIENCES↗
Classification methodology for tritiated waste requiring interim storage
Fusion machines like the ITER experimental research facility will use tritium as fuel. Therefore, most of the solid radioactive waste will result not only from activation by 14 MeV neutrons, but also from contamination by tritium. As a consequence, optimizing the treatment process for waste containing tritium (tritiated waste) is a major challenge. This paper summarizes the studies conducted in France within the framework of the French national plan for the management of radioactive materials and waste. The paper recommends a reference program for managing this waste based on its sorting, treatment and packaging by the producer. It also recommends setting up a 50-year temporary storage facility to allow for tritium decay and designing future disposal facilities using tritiated radwaste characteristics as input data. This paper first describes this waste program and then details an optimized classification methodology which takes into account tritium decay over a 50-year storage period. The paper also describes a specific application for purely tritiated waste and discusses the set-up expected to be implemented for ITER decommissioning waste (current assumption). Comparison between this optimized approach and other viable detritiation techniques will be drawn. (authors)
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Unsupervised classification of single-particle X-ray diffraction snapshots by spectral clustering
Single-particle experiments using X-ray Free Electron Lasers produce more than 105 snapshots per hour, consisting of an admixture of blank shots (no particle intercepted), and exposures of one or more particles. Experimental data sets also often contain unintentional contamination with different species. We present an unsupervised method able to sort experimental snapshots without recourse to templates, specific noise models, or user-directed learning. The results show 90% agreement with manual classification.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Effectiveness of Deep Learning Trained on SynthCity Data for Urban Point-Cloud Classification
3D object recognition is one of the most popular areas of study in computer vision. Many of the more recent algorithms focus on indoor point clouds, classifying 3D geometric objects, and segmenting outdoor 3D scenes. One of the challenges of the classification pipeline is finding adequate and accurate training data. Hence, this article seeks to evaluate the accuracy of a synthetically generated data set called SynthCity, tested on two mobile laser-scan data sets. Varying levels of noise were applied to the training data to reflect varying levels of noise in different scanners. The chosen deep-learning algorithm was Kernel Point Convolution, a convolutional neural network that uses kernel points in Euclidean space for convolution weights.
Geology↗
Classification of River Catchments in the Contiguous United States: Code, Dataset, Similarity Patterns, and Resulting Classes
This dataset serves as supplementary information for the paper by Ciulla F. and Varadharajan C. A Network Approach for Multiscale Catchment Classification using Traits (see reference 1). It contains environmental and physical catchment traits, such as temperatures, precipitation, land use and human interference, from 9067 sites across the contiguous United States (CONUS). The purpose of this dataset is to provide information for a better trait-based categorization of river catchments in the CONUS using networks as an analytical tool. The traits variables match the ones present in the GAGES-II dataset and the preprocessing steps are described in the Methods section (processed_dataset.csv). Additionally we include the topologies (nodes, edges and clusters, also referred as classes) of the catchment network and traits network generated by said dataset (csv and json files). A series of tables support the information carried by the network providing more detailed descriptions of cluster components (SI1.pdf). A summary of all the plots of clusters of catchments with at least 50 nodes is provided (SI2.pdf). The characteristic traits for each cluster of catchments is presented as z-score (traits_categories_zscores_per_catchment_class.csv). The link to the hydrological behavior of clusters of catchments is displayed by boxplots, each describing a particular river discharge index (SI3.pdf). Both csv and json files can be read by common text editors but the data contained into them can be better handled using programming languages like python and database oriented libraries like pandas. Pdf files can be read by any pdf reader software.[02-23-2024] Update: The code and datasets necessary to reproduce the results of the study are available as a zipped repository (code_datasets_catchments_similarity.zip).
54 ENVIRONMENTAL SCIENCES↗
Classification of Local Seismic Events in the Utah Region: A Comparison of Amplitude Ratio Methods with a Spectrogram-Based Machine Learning Approach
Abstract The capability to discriminate low-magnitude earthquakes from low-yield anthropogenic sources, both detectable only at local distances, is of increasing interest to the event monitoring community. Here, we used a dataset of seismic events in Utah recorded during a 14-day period (1–14 January 2011) by the University of Utah Seismic Stations network to perform a comparative study of event classification at local scale using amplitude ratio (AR) methods and a machine learning (ML) approach. The event catalog consists of 7377 events with magnitudes M C ranging from –2 and lower up to 5.8. Events were subdivided into six populations based on location and source type: tectonic earthquakes (TEs), mining-induced events (MIEs), and mining blasts from four known mines (WMB, SMB, LMB, and CQB). The AR approach jointly exploits Pg-to-Sg phase ARs and Rg-to-Sg spectral ARs in multivariate quadratic discriminant functions and was able to classify 370 events with high signal quality from the three groups with sufficient size (TE, MIE, and SMB). For that subset of the events, the method achieved success rates between about 80% and 90%. The ML technique used trained convolutional neural network (CNN) models to classify the populations. The CNN approach was able to classify the subset of events with accuracies between about 91% and 98%. Because the neural network approach does not have a minimum signal quality requirement, we applied it to the entire event catalog, including the abundant extremely low-magnitude events, and achieved accuracies of about 94%–100%. Furthermore, we compare the AR and ML methodologies using a broad set of criteria and conclude that a major advantage to ML methods is their robustness to low signal-to-noise ratio data, allowing them to classify significantly smaller events.
58 GEOSCIENCES↗
SRF Cavity Fault Classification Using Machine Learning At CEBAF
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab is the first large high power CW recirculating electron accelerator to make use of SRF accelerating structures. The structures are configured in two anti-parallel linacs connected by arcs. Each linac consists of twenty C20/C50 cryomodules each containing eight 5-cell cavities and five C100 upgrade cryomodules each containing eight 7-cell cavities. Accurately classifying the source of cavity faults is critical for improving accelerator performance. A cavity fault triggers a waveform acquisition process where 17 waveform records sampled at 5 kHz are recorded for each of the 8 cavities in the affected cryomodule. The waveform record length is sufficiently long for transient microphonic effects to be observable. This data combined with archived signals sampled at 10 Hz are used to classify faults. Significant time is required for a subject matter expert to analyze and identify the intra-cavity signatures of imminent faults. This paper describes a path forward that utilizes machine learning for automatic fault classification. Post-training identification of the physical origins of faults are discussed, as are potential machine-trained model-free implementations of trip avoidance procedures. These methods should provide new insights into cavity fault mechanisms and facilitate intelligent optimization of cryomodule performance
Solopova, A.↗
Superconducting Radio-frequency Cavity Fault Classification Using Machine Learning at Jefferson Laboratory
We report on the development of machine learning models for classifying C100 superconducting radiofrequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. Of the 418 SRF cavities in CEBAF, 96 are designed with a digital low-level RF system configured such that a cavity fault triggers recordings of RF signals for each of eight cavities in the cryomodule. Subject matter experts analyze the collected time-series data and identify which of the eight cavities faulted first and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time - rather than postmortem - identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the machine learning models during a recent physics run. We also discuss efforts for further insights into fault types through unsupervised learning techniques and present preliminary work on cavity and fault prediction using data collected prior to a failure event.
Tennant, C. D.↗
Classification and Localization of Fracture-Hit Events in Low-Frequency Distributed Acoustic Sensing Strain Rate with Convolutional Neural Networks
Summary Distributed acoustic sensing (DAS) has been used in the oil and gas industry as an advanced technology for surveillance and diagnostics. Operators use DAS to monitor hydraulic fracturing activities, examine well stimulation efficacy, and estimate complex fracture system geometries. Particularly, low-frequency DAS can detect geomechanical events such as fracture hits because hydraulic fractures propagate and create strain rate variations in the rock. Analysis of DAS data today is mostly done post-job and subject to interpretation methods. However, the continuous and dense data stream generated live by DAS poses the opportunity for more efficient and accurate real-time data-driven analysis. The objective of this study is to develop a machine learning-based workflow that can identify and locate fracture-hit events in simulated strain rate responses correlated with low-frequency DAS data. In this paper, “fracture hit” refers to a hydraulic fracture originating from a stimulated well intersecting an offset well. We start with building a single fracture propagation model to produce strain rate patterns observed at a hypothetical monitoring well. This model is used to generate two sets of strain rate responses with one set containing fracture-hit events. The labeled synthetic data are then used to train a custom convolutional neural network (CNN) model for identifying the presence of fracture-hit events. The same model is trained again for locating the event with the output layer of the model replaced with linear units. We achieved near-perfect predictions for both event classification and localization. These promising results prove the feasibility of using CNN for real-time event detection from fiber-optic sensing data. Additionally, we use edge detection techniques to recognize fracture-hit event patterns in strain rate images. The fracture-hit location can be identified using recognized pixels in the image. The accuracy of edge detection-based location identification is also plausible, but edge detection is dependent on the assumption of pattern shape and image quality, hence it is less robust compared to CNN models. This comparison further supports the need for CNN applications in image-based real-time fiber-optic sensing event detection.
Engineering↗
Scaling laws in jet classification
We demonstrate the emergence of scaling laws in the benchmark top versus QCD jet classification problem in collider physics. Six distinct physically-motivated classifiers exhibit power-law scaling of the binary cross-entropy test loss as a function of training set size, with distinct power law indices. This result highlights the importance of comparing classifiers as a function of dataset size rather than for a fixed training set, as the optimal classifier may change considerably as the dataset is scaled up. We speculate on the interpretation of our results in terms of previous models of scaling laws observed in natural language and image datasets.
Batson, Joshua↗
Robustness of RISMC Insights under Alternative Aleatory/Epistemic Uncertainty Classifications: Draft Report under the Risk-Informed Safety Margin Characterization (RISMC) Pathway of the DOE Light Water Reactor Sustainability Program
The Risk-Informed Safety Margin Characterization (RISMC) pathway is a set of activities defined under the U.S. Department of Energy (DOE) Light Water Reactor Sustainability Program. The overarching objective of RISMC is to support plant life-extension decision-making by providing a state-of-knowledge characterization of safety margins in key systems, structures, and components (SSCs). A technical challenge at the core of this effort is to establish the conceptual and technical feasibility of analyzing safety margin in a risk-informed way, which, unlike conventionally defined deterministic margin analysis, would be founded on probabilistic characterizations of uncertainty in SSC performance. In the context of probabilistic risk assessment (PRA) technology, there has arisen a general consensus about the distinctive roles of two types of uncertainty: aleatory and epistemic, where the former represents irreducible, random variability inherent in a system, whereas the latter represents a state of knowledge uncertainty on the part of the analyst about the system which is, in principle, reducible through further research. While there is often some ambiguity about how any one contributing uncertainty in an analysis should be classified, there has nevertheless emerged a broad consensus on the meanings of these uncertainty types in the PRA setting. However, while RISMC methodology shares some features with conventional PRA, it will nevertheless be a distinctive methodology set. Therefore, the paradigms for classification of uncertainty in the PRA setting may not fully port to the RISMC environment. Yet the notion of risk-informed margin is based on the characterization of uncertainty, and it is therefore critical to establish a common understanding of uncertainty in the RISMC setting.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Modernization of Technical Requirements for Licensing of Advanced Non-Light Water Reactors: Safety Classification and Performance Criteria for Structures, Systems, and Components
This report, “Modernization of Technical Requirements for Licensing of Advanced Non-Light Water Reactors: Safety Classification and Performance Criteria for Structures, Systems and Components,” represents a key element in the development of a framework for the efficient licensing of advanced non-Light Water Reactors (non-LWRs).
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
Modernization of Technical Requirements for Licensing of Advanced Non-Light Water Reactors: Safety Classification and Performance Criteria for Structures, Systems, and Components
This report, “Modernization of Technical Requirements for Licensing of Advanced Non-Light Water Reactors: Safety Classification and Performance Criteria for Structures, Systems and Components,” represents a key element in the development of a framework for the efficient licensing of advanced non-Light Water Reactors (non-LWRs). It is the result of a Licensing Modernization Project (LMP) led by Southern Company and cost-shared by the United States Department of Energy (DOE).
42 ENGINEERING↗
Machine Learning Based Cavity Fault Classification and Prediction
We report on the development of machine learning models for classifying C100 superconducting radio frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a continuous-wave recirculating linac utilizing 418 SRF cavities to accelerate electrons up to 12 GeV through 5-passes. Of these, 96 cavities (12 cryomodules) are designed with a digital low-level RF system configured such that a cavity fault triggers waveform recordings of 17 RF signals for each of the eight cavities in the cryomodule. Subject matter experts (SME) can analyze the collected time-series data, identify which of the eight cavities faulted first, and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time – rather than post-mortem – identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the ML models during a recent physics run.
43 PARTICLE ACCELERATORS↗
New Understanding of Cloud Processes via Unsupervised Cloud Classification in Satellite Images
This white paper addresses DOE AI4ESP focus areas #1 and #3. We propose to leverage advances in machine learning and artificial intelligence to create a new unsupervised cloud classification framework that will produce new datasets and cloud process understanding to reduce biases in Earth system models.
58 GEOSCIENCES↗