Search NASA⌕ Search

SEARCH · Search NASA

Results for “supervised learning”

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 883 records · Page 49

Scalable 3D reconstruction for X-ray single particle imaging with online machine learning

X-ray free-electron lasers offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate free-electron lasers enable single particle imaging, where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray single particle reconstruction algorithms, which estimate the particle orientation for each image independently, are slow and memory-intensive when handling the massive datasets generated by emerging free-electron lasers. Here, we introduce X-RAI (X-Ray single particle imaging with Amortized Inference), an online reconstruction framework that estimates the structure of 3D macromolecules from large X-ray single particle datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray single particle imaging towards real-time reconstruction.

Computer science↗

Polymers in Deep Eutectic Solvents

The project investigated the behavior of polymers in ionic liquids such as deep eutectic solvents using an array of techniques. These included the development of atomistic force fields, coarse graining these force fields to the united atom level, large scale molecular dynamics (MD) simulations using new thermostat algorithms, and machine learning (ML) methods for the phase behavior. The project demonstrated the feasibility and accuracy of first principles force fields for ionic liquids, deep-eutectic solvents, and urea-water mixtures. A novel hierarchical coarse graining method was then used to develop accurate and efficient united-atom models, using which microsecond simulations were performed for polymers in ionic liquids. These simulations were in quantitative agreement with experiment, thus resolving previous controversies. Methods were also developed to obtain the potential of mean force between complex ions in solution. Finally, supervised ML methods were developed for the phase behavior of polymers in ionic liquids.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images

Recent decade has witnessed major changes on the Earth, for example, deforestation, varying cropping and human settlement patterns, and crippling damages due to disasters. Accurate damage assessment caused by major natural and anthropogenic disasters is becoming critical due to increases in human and economic loss. This increase in loss of life and severe damages can be attributed to the growing population, as well as human migration to the disaster prone regions of the world. Rapid assessment of these changes and dissemination of accurate information is critical for creating an effective emergency response. Change detection using high-resolution satellite images is a primary tool in assessing damages, monitoring biomass and critical infrastructures, and identifying new settlements. In this demo, we present a novel supervised probabilistic framework for identifying changes using very high-resolution multispectral, and bitemporal remote sensing images. Our demo shows that the rapid damage explorer (RDX) system is resilient to registration errors and differing sensor characteristics.

Change detection↗

LDRD 22A1059-068FP Tailoring the Properties of Multi-Phase Materials Through the Use of Correlative Microscopy and Machine Learning - Poster

High strength alloys with good ductility, hardness, and toughness are needed to meet stringent design requirements for extreme environments. One complication in this pursuit is the evidence that metals rarely exhibit both high strength and good fracture toughness as the underlying mechanisms work in opposition. An exception to this behavior is found in multiphase alloys that form complex microstructures of mixed phases with variable grain sizes and shapes that provide increased fracture toughness by the arrangement of their constituent elements. We propose to explore this phenomenon using state-of-the-art machine learning (ML) techniques in a new and novel manner to identify and correlate the critical microstructural features in a Titanium-10Vanadium-2Iron-3Aluminum (Ti-10V-2Fe-3Al) alloy that is reported to exhibit high strength and fracture toughness. Additionally, we will employ multiple, complementary characterization techniques such as optical microscopy, electron backscatter diffraction (EBSD), energy dispersive spectroscopy (EDS) and scanning electron microscopy to provide multi-layer, quantitative ground truth measures of the microstructures. This data will be used to train a Convolutional Neural Network (CNN) in a semi-supervised environment to identify key microstructural features such as ? platelet dimensions and locations and ?/? phase boundaries and correlate those features with the strength and toughness. Here the ? and ? nomenclature refers to hexagonal close pack (hcp) and body center cubic (bcc) crystal structures, respectively. Previous work has focused on popular alloys and typically used one characterization technique. This research is focused on a promising titanium alloy, uses multiple complimentary characterization tools to provide precise microstructural information and correlates to improved fracture toughness. The resulting ML tool can be trained for additional microstructural features, different alloy(s), and or target mechanical properties.

36 MATERIALS SCIENCE↗

Enhancing Qubit Readout with Autoencoders

In addition to the need for stable and precisely controllable qubits, quantum computers take advantage of good readout schemes. Superconducting qubit states can be inferred from the readout signal transmitted through a dispersively coupled resonator. Here, this work proposes a readout classification method for superconducting qubits based on a neural network pretrained with an autoencoder approach. A neural network is pretrained with qubit readout signals as autoencoders in order to extract relevant features from the data set. Afterward, the pretrained-network inner-layer values are used to perform a classification of the inputs in a supervised manner. We demonstrate that this method can enhance classification performance, particularly for short- and long-time measurements where more traditional methods present inferior performance.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

TU-A-18C-01: ACR Accreditation Updates in CT, Ultrasound, Mammography and MRI

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, the ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, mammography, ultrasound, and computed tomography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program. To understand the new requirements of the ACR ultrasound accreditation program, and roles the physicist can play in annual equipment surveys and setting up and supervising the routine QC program. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process.

60 APPLIED LIFE SCIENCES↗

MO-AB-207-00: ACR Update in MR, CT, Nuclear Medicine, and Mammography

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, computed tomography, nuclear medicine, and mammography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR Accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process. To understand the requirements of the ACR nuclear medicine accreditation program, and the role of the physicist in annual equipment surveys and the set up and supervision of the routine QC program. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program.

60 APPLIED LIFE SCIENCES↗

MO-AB-207-01: ACR Update in CT

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, computed tomography, nuclear medicine, and mammography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR Accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process. To understand the requirements of the ACR nuclear medicine accreditation program, and the role of the physicist in annual equipment surveys and the set up and supervision of the routine QC program. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program.

60 APPLIED LIFE SCIENCES↗

MO-AB-207-02: ACR Update in MR

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, computed tomography, nuclear medicine, and mammography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR Accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process. To understand the requirements of the ACR nuclear medicine accreditation program, and the role of the physicist in annual equipment surveys and the set up and supervision of the routine QC program. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program.

60 APPLIED LIFE SCIENCES↗

MO-AB-207-03: ACR Update in Nuclear Medicine

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, computed tomography, nuclear medicine, and mammography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR Accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process. To understand the requirements of the ACR nuclear medicine accreditation program, and the role of the physicist in annual equipment surveys and the set up and supervision of the routine QC program. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program.

60 APPLIED LIFE SCIENCES↗

MO-AB-207-04: ACR Update in Mammography

A goal of an imaging accreditation program is to ensure adequate image quality, verify appropriate staff qualifications, and to assure patient and personnel safety. Currently, more than 35,000 facilities in 10 modalities have been accredited by the American College of Radiology (ACR), making the ACR program one of the most prolific accreditation options in the U.S. In addition, ACR is one of the accepted accreditations required by some state laws, CMS/MIPPA insurance and others. Familiarity with the ACR accreditation process is therefore essential to clinical diagnostic medical physicists. Maintaining sufficient knowledge of the ACR program must include keeping up-to-date as the various modality requirements are refined to better serve the goals of the program and to accommodate newer technologies and practices. This session consists of presentations from authorities in four ACR accreditation modality programs, including magnetic resonance imaging, computed tomography, nuclear medicine, and mammography. Each speaker will discuss the general components of the modality program and address any recent changes to the requirements. Learning Objectives: To understand the requirements of the ACR MR Accreditation program. The discussion will include accreditation of whole-body general purpose magnets, dedicated extremity systems well as breast MRI accreditation. Anticipated updates to the ACR MRI Quality Control Manual will also be reviewed. To understand the requirements of the ACR CT accreditation program, including updates to the QC manual as well as updates through the FAQ process. To understand the requirements of the ACR nuclear medicine accreditation program, and the role of the physicist in annual equipment surveys and the set up and supervision of the routine QC program. To understand the current ACR MAP Accreditation requirement and present the concepts and structure of the forthcoming ACR Digital Mammography QC Manual and Program.

60 APPLIED LIFE SCIENCES↗

Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram

X-ray phase contrast imaging significantly improves the visualization of structures with weak or uniform absorption, broadening its applications across a wide range of scientific disciplines. Propagation-based phase contrast is particularly suitable for time- or dose-critical in vivo/in situ/operando (tomography) experiments because it requires only a single intensity measurement. However, the phase information of the wave field is lost during the measurement and must be recovered. Conventional algebraic and iterative methods often rely on specific approximations or boundary conditions that may not be met by many samples or experimental setups. In addition, they require manual tuning of reconstruction parameters by experts, making them less adaptable for complex or variable conditions. Here we present a self-learning approach for solving the inverse problem of phase retrieval in the near-field regime of Fresnel theory using a single intensity measurement (hologram). A physics-informed generative adversarial network is employed to reconstruct both the phase and absorbance of the unpropagated wave field in the sample plane from a single hologram. Unlike most state-of-the-art deep learning approaches for phase retrieval, our approach does not require paired, unpaired, or simulated training data. This significantly broadens the applicability of our approach, as acquiring or generating suitable training data remains a major challenge due to the wide variability in sample types and experimental configurations. The algorithm demonstrates robust and consistent performance across diverse imaging conditions and sample types, delivering quantitative, high-quality reconstructions for both simulated data and experimental datasets acquired at beamline P05 at PETRA III (DESY, Hamburg), operated by Helmholtz-Zentrum Hereon. Furthermore, it enables the simultaneous retrieval of both phase and absorption information.

36 MATERIALS SCIENCE↗

Physics-driven learning of Wasserstein GAN for density reconstruction in dynamic tomography

Object density reconstruction from projections containing scattered radiation and noise is of critical importance in many applications. Existing scatter correction and density reconstruction methods may not provide the high accuracy needed in many applications and can break down in the presence of unmodeled or anomalous scatter and other experimental artifacts. Incorporating machine-learning models could prove beneficial for accurate density reconstruction, particularly in dynamic imaging, where the time evolution of the density fields could be captured by partial differential equations or by learning from hydrodynamics simulations. In this work, we demonstrate the ability of learned deep neural networks to perform artifact removal in noisy density reconstructions, where the noise is imperfectly characterized. Here, we use a Wasserstein generative adversarial network (WGAN), where the generator serves as a denoiser that removes artifacts in densities obtained from traditional reconstruction algorithms. We train the networks from large density time-series datasets, with noise simulated according to parametric random distributions that may mimic noise in experiments. The WGAN is trained with noisy density frames as generator inputs, to match the generator outputs to the distribution of clean densities (time series) from simulations. A supervised loss is also included in the training, which leads to an improved density restoration performance. In addition, we employ physics-based constraints such as mass conservation during the network training and application to further enable highly accurate density reconstructions. Our preliminary numerical results show that the models trained in our frameworks can remove significant portions of unknown noise in density time-series data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Supervised classification of electric power transmission line nominal voltage from high-resolution aerial imagery

For many researchers, government agencies, and emergency responders, access to the geospatial data of US electric power infrastructure is invaluable for analysis, planning, and disaster recovery. Historically, however, access to high quality geospatial energy data has been limited to few agencies because of commercial licenses restrictions, and those resources which are widely accessible have been of poor quality, particularly with respect to reliability. Recent efforts to develop a highly reliable and publicly accessible alternative to the existing datasets were met with numerous challenges – not the least of which was filling the gaps in power transmission line voltage ratings. To address the line voltage rating problem, we developed and tested a basic methodology that fuses knowledge and techniques from power systems, geography, and machine learning domains. Specifically, we identified predictors of nominal voltage that could be extracted from aerial imagery and developed a tree-based classifier to classify nominal line voltage ratings. Overall, we found that line support height, support span, and conductor spacing are the best predictors of voltage ratings, and that the classifier built with these predictors had a reliable predictive accuracy (that is, within one voltage class for four out of the five classes sampled). In conclusion, we applied our approach to a study area in Minnesota.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Anomaly detection with flow-based fast calorimeter simulators

Recently, several normalizing flow-based deep generative models have been proposed to accelerate the simulation of calorimeter showers. Using caloflow as an example, we show that these models can simultaneously perform unsupervised anomaly detection with no additional training cost. As a demonstration, we consider electromagnetic showers initiated by one (background) or multiple (signal) photons. The caloflow model is designed to generate single-photon showers, but it also provides access to the shower likelihood. We use this likelihood as an anomaly score and study the showers tagged as being unlikely. As expected, the tagger struggles when the signal photons are nearly collinear but is otherwise effective. This approach is complementary to a supervised classifier trained on only specific signal models using the same low-level calorimeter inputs. While the supervised classifier is also highly effective at unseen signal models, the unsupervised method is more sensitive in certain regions, and, thus, we expect that the ultimate performance will require a combination of these approaches.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Discrimination Analysis of Earthquakes and Man-Made Events Using ARMA Coefficients Determination by Artificial Neural Networks

A Quadratic Neural Networks (QNNs) model has been developed for identifying seismic source classification problem at regional distances using ARMA coefficients determination by Artificial Neural Networks (ANNs). We have devised a supervised neural system to discriminate between earthquakes and chemical explosions with filter coefficients obtained by windowed P-wave phase spectra (15 s). First, we preprocess the recording's signals to cancel out instrumental and attenuation site effects and obtain a compact representation of seismic records. Second, we use a QNNs system to obtain ARMA coefficients for feature extraction in the discrimination problem. The derived coefficients are then applied to the neural system to train and classification. In this study, we explore the possibility of using single station three-component (3C) covariance matrix traces from a priori-known explosion sites (learning) for automatically recognizing subsequent explosions from the same site. The results have shown that this feature extraction gives the best classifier for seismic signals and performs significantly better than other classification methods. The events have been tested, which include 36 chemical explosions at the Semipalatinsk test site in Kazakhstan and 61 earthquakes (mb = 5.0-6.5) recorded by the Iranian National Seismic Network (INSN). The 100% correct decisions were obtained between site explosions and some of non-site events. The above approach to event discrimination is very flexible as we can combine several 3C stations.

58 GEOSCIENCES↗

femto-PIXAR: a self-supervised neural network method for reconstructing femtosecond X-ray free electron laser pulses

X-ray Free Electron Lasers (X-FELs) operate in a wide range of lasing configurations for a broad variety of scientific applications at ultrafast time-scales such as structural biology, materials science, and atomic and molecular physics. Shot-by-shot characterization of the X-FEL pulses is crucial for analysis of many experiments as well as tuning the X-FEL performance. However, for the weak pulses found in advanced configurations, e.g. those needed for coherent, two-pulse studies of quantum materials, there is no current method for reliably resolving pulse profiles. Here we show that a physics-based U-net model can reconstruct the individual pulse power profiles for sub-picosecond pulse separation without the need for simulations. Using experimental data from weak X-FEL pulse pairs, we demonstrate we can learn the pulse characteristics on a shot-by-shot basis when conventional methods fail.

43 PARTICLE ACCELERATORS↗