An official website of the United States government
ABSTRACT In this paper, we introduce a novel data augmentation methodology based on Conditional Progressive Generative Adversarial Networks (CPGAN) to generate diverse black hole (BH) images, accounting for variations in spin and electron temperature prescriptions. These generated images are valuable resources for training deep learning algorithms to accurately estimate black hole parameters from observational data. Our model can generate BH images for any spin value within the range of [−1, 1], given an electron temperature distribution. To validate the effectiveness of our approach, we employ a convolutional neural network to predict the BH spin using both the GRMHD images and the images generated by our proposed model. Our results demonstrate a significant performance improvement when training is conducted with the augmented data set while testing is performed using GRMHD simulated data, as indicated by the high R2 score. Consequently, we propose that GANs can be employed as cost-effective models for black hole image generation and reliably augment training data sets for other parametrization algorithms.
more »
« less
Electron Density Specification in the Inner Magnetosphere From the Narrow Band Receiver Onboard DSX
Abstract Electron density plays an important role in the study of wave propagation and is known to be associated with the index of refraction and radiation belt diffusion coefficients. The primary objective of our investigation is to explore the possibility of implementing an onboard signal processing algorithm to automatically obtain electron densities from the upper hybrid resonance traces of wave spectrograms for future missions. U‐Net, developed for biomedical image segmentation, has been adapted as our deep learning architecture with results being compared with those extracted from a more traditional semi‐automated method. As a product, electron densities and cyclotron frequencies for the entire DSX mission between 2019 and 2021 are acquired for further analysis and applications. Due to limited space measurements, a synthetic image generator based on data statistics and randomization is proposed as an initial step toward the development of a generative adversarial network in hopes of providing unlimited realistic data sources for advanced machine learning.
more »
« less
- Award ID(s):
- 2247256
- PAR ID:
- 10508762
- Publisher / Repository:
- Radio Science
- Date Published:
- Journal Name:
- Radio Science
- Volume:
- 59
- Issue:
- 2
- ISSN:
- 0048-6604
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract The active-particle number density is a key parameter for plasma material processing, space propulsion, and plasma-assisted combustion. The traditional actinometry method focuses on measuring the density of the atoms in the ground state, but there is a lack of an effective optical emission spectroscopy method to measure intra-shell excited-state densities. The latter atoms have chemical selectivity and higher energy, and they can easily change the material morphology as well as the ionization and combustion paths. In this work, we present a novel state-resolved actinometry (SRA) method, supported by a krypton line-ratio method for the electron temperature and density, to measure the number densities of nitrogen atoms in the ground and intra-shell excited states. The SRA method is based on a collisional-radiative model, considering the kinetics of atomic nitrogen and krypton including their excited states. The densities measured by our method are compared with those obtained from a dissociative model in a miniature electron cyclotron resonance (ECR) plasma source. Furthermore, the saturation effect, in which the electron density remains constant due to the microwave propagation in an ECR plasma once the power reaches a certain value, is used to verify the electron density measured by the line-ratio method. An ionization balance model is also presented to examine the measured electron temperature. All the values obtained with the different methods are in good agreement with each other, and hence a set of verified rate coefficient data used in our method can be provided. A novel concept, the ‘excited-state system’, is presented to quickly build an optical diagnostic method based on the analysis of quantum number propensity and selection rules.more » « less
-
Abstract The nature and radial evolution of solar wind electrons in the suprathermal energy range are studied. A wave–particle interaction tensor and a Fokker–Planck Coulomb collision operator are introduced into the kinetic transport equation describing electron collisions and resonant interactions with whistler waves. The diffusion tensor includes diagonal and off-diagonal terms, and the Coulomb collision operator applies to arbitrary electron velocities describing collisions with both background protons and electrons. The background proton and electron densities and temperatures are based on previous turbulence models that mediate the supersonic solar wind. The electron velocity distribution functions and electron heat flux are calculated. Comparison and analysis of the numerical results with analytical solutions and observations in the near-Sun region are made. The numerical results reproduce well the creation of the sunward electron deficit observed in the near-Sun region. The deficit of the electron velocity distribution function below the core Maxwellian fit at low velocities results from Coulomb collisions, and the excess part above the core Maxwellian fit at high velocities is determined by strong wave–particle interactions.more » « less
-
Context.High-precision pulsar timing is highly dependent on the precise and accurate modelling of any effects that can potentially impact the data. In particular, effects that contain stochastic elements contribute to some level of corruption and complexity in the analysis of pulsar-timing data. It has been shown that commonly used solar wind models do not accurately account for variability in the amplitude of the solar wind on both short and long timescales. Aims.In this study, we test and validate a new, cutting-edge solar wind modelling method included in theenterprisesoftware suite (widely used for pulsar noise analysis) through extended simulations. We use it to investigate temporal variability in LOFAR data. Our model testing scheme in itself provides an invaluable asset for pulsar timing array (PTA) experiments. Since, improperly accounting for the solar wind signature in pulsar data can induce false-positive signals, it is of fundamental importance to include in any such investigations. Methods.We employed a Bayesian approach utilising a continuously varying Gaussian process to model the solar wind. It uses a spherical approximation that modulates the electron density. This method, which we refer to as a solar wind Gaussian process (SWGP), has been integrated into existing noise analysis software, specificallyenterprise. Our Validation of this model was performed through simulations. We then conduct noise analysis on eight pulsars from the LOFAR dataset, with most pulsars having a time span of ∼11 years encompassing one full solar activity cycle. Furthermore, we derived the electron densities from the dispersion measure values obtained by the SWGP model. Results.Our analysis reveals a strong correlation between the electron density at 1 AU and the ecliptic latitude (ELAT) of the pulsar. Pulsars with |ELAT|< 3° exhibit significantly higher average electron densities. Furthermore, we observed distinct temporal patterns in the electron densities in different pulsars. In particular, pulsars within |ELAT|< 3° exhibit similar temporal variations, while the electron densities of those outside this range correlate with the solar activity cycle. Notably, some pulsars exhibit sensitivity to the solar wind up to 45° away from the Sun in LOFAR data. Conclusions.The continuous variability in electron density offered in this model represents a substantial improvement over previous models, that assume a single value for piece-wise bins of time. This advancement holds promise for solar wind modelling in future International Pulsar Timing Array (IPTA) data combinations.more » « less
-
Abstract Sinkholes are the most abundant surface features in karst areas worldwide. Understanding sinkhole occurrences and characteristics is critical for studying karst aquifers and mitigating sinkhole‐related hazards. Most sinkholes appear on the land surface as depressions or cover collapses and are commonly mapped from elevation data, such as digital elevation models (DEMs). Existing methods for identifying sinkholes from DEMs often require two steps: locating surface depressions and separating sinkholes from non‐sinkhole depressions. In this study, we explored deep learning to directly identify sinkholes from DEM data and aerial imagery. A key contribution of our study is an evaluation of various ways of integrating these two types of raster data. We used an image segmentation model, U‐Net, to locate sinkholes. We trained separate U‐Net models based on four input images of elevation data: a DEM image, a slope image, a DEM gradient image, and a DEM‐shaded relief image. Three normalization techniques (Global, Gaussian, and Instance) were applied to improve the model performance. Model results suggest that deep learning is a viable method to identify sinkholes directly from the images of elevation data. In particular, DEM gradient data provided the best input for U‐net image segmentation models to locate sinkholes. The model using the DEM gradient image with Gaussian normalization achieved the best performance with a sinkhole intersection‐over‐union (IoU) of 45.38% on the unseen test set. Aerial images, however, were not useful in training deep learning models for sinkholes as the models using an aerial image as input achieved sinkhole IoUs below 3%.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1029/2023RS007907
