skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Detection and Classification of Sporadic E Using Convolutional Neural Networks
Abstract In this work, convolutional neural networks (CNN) are developed to detect and characterize sporadic E (Es), demonstrating an improvement over current methods. This includes a binary classification model to determine ifEsis present, followed by a regression model to estimate theEsordinary mode critical frequency (foEs), a proxy for the intensity, along with the height at which theEslayer occurs (hEs). Signal‐to‐noise ratio (SNR) and excess phase profiles from six Global Navigation Satellite System (GNSS) radio occultation (RO) missions during the years 2008–2022 are used as the inputs of the model. Intensity (foEs) and the height (hEs) values are obtained from the global network of ground‐based Digisonde ionosondes and are used as the “ground truth,” or target variables, during training. After corresponding the two data sets, a total of 36,521 samples are available for training and testing the models. The foEs CNN binary classification model achieved an accuracy of 74% and F1‐score of 0.70. Mean absolute errors (MAE) of 0.63 MHz and 5.81 km along with root‐mean squared errors (RMSE) of 0.95 MHz and 7.89 km were attained for estimating foEs and hEs, respectively, when it was known thatEswas present. When combining the classification and regression models together for use in practical applications where it is unknown ifEsis present, an foEs MAE and RMSE of 0.97 and 1.65 MHz, respectively, were realized. We implemented three other techniques for sporadic E characterization, and found that the CNN model appears to perform better.  more » « less
Award ID(s):
2139916 2221765
PAR ID:
10488841
Author(s) / Creator(s):
; ;
Publisher / Repository:
Wiley
Date Published:
Journal Name:
Space Weather
Volume:
22
Issue:
1
ISSN:
1542-7390
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, PLOS ONE)
    Le, Khanh N.Q. (Ed.)
    In current clinical settings, typically pain is measured by a patient’s self-reported information. This subjective pain assessment results in suboptimal treatment plans, over-prescription of opioids, and drug-seeking behavior among patients. In the present study, we explored automatic objective pain intensity estimation machine learning models using inputs from physiological sensors. This study uses BioVid Heat Pain Dataset. We extracted features from Electrodermal Activity (EDA), Electrocardiogram (ECG), Electromyogram (EMG) signals collected from study participants subjected to heat pain. We built different machine learning models, including Linear Regression, Support Vector Regression (SVR), Neural Networks and Extreme Gradient Boosting for continuous value pain intensity estimation. Then we identified the physiological sensor, feature set and machine learning model that give the best predictive performance. We found that EDA is the most information-rich sensor for continuous pain intensity prediction. A set of only 3 features from EDA signals using SVR model gave an average performance of 0.93 mean absolute error (MAE) and 1.16 root means square error (RMSE) for the subject-independent model and of 0.92 MAE and 1.13 RMSE for subject-dependent. The MAE achieved with signal-feature-model combination is less than 1 unit on 0 to 4 continues pain scale, which is smaller than the MAE achieved by the methods reported in the literature. These results demonstrate that it is possible to estimate pain intensity of a patient using a computationally inexpensive machine learning model with 3 statistical features from EDA signal which can be collected from a wrist biosensor. This method paves a way to developing a wearable pain measurement device. 
    more » « less
  2. ; (, Journal of Geophysical Research: Space Physics)
    Abstract Observations of backscatter from field‐aligned plasma density irregularities in sporadicE(Es) layers made with a 30‐MHz coherent scatter radar imager in Ithaca, New York are presented and analyzed. The volume probed by the radar lies at approximately 54° geomagnetic latitude, under the midlatitude trough and at the extreme northern edge of the zone whereEslayers are prevalent. Nonetheless, the irregularities exhibit many of the characteristics of quasiperiodic echoes observed commonly at lower middle latitudes. These include a tendency to occur in elongated bands stretching from the northwest to southeast in the Northern hemisphere separated by tens of kilometers and propagating to the southwest. In addition, the irregularities were found to exhibit finer‐scale structures with secondary bands oriented nearly normally to the primary bands. We investigate the proposition that the primary bands are telltale ofEs‐layer structuring caused by neutral Kelvin Helmholtz (KH) instability in the lower thermosphere and that the secondary bands signify secondary KH instability. Results from a 3D numerical simulation of KH support this proposition. 
    more » « less
  3. ; ; ; ; ; ; (, GeoHealth)
    Abstract The paucity of fine particulate matter (PM2.5) measurements limits estimates of air pollution mortality in Sub‐Saharan Africa. Well calibrated low‐cost sensors can provide reliable data especially where reference monitors are unavailable. We evaluate the performance of Clarity Node‐S PM monitors against a Tapered element oscillating microbalance (TEOM) 1400a and develop a calibration model in Mombasa, Kenya's second largest city. As‐reported Clarity Node‐S data from January 2023 through April 2023 was moderately correlated with the TEOM‐1400a measurements (R2 = 0.61) and exhibited a mean absolute error (MAE) of 7.03 μg m−3. Employing three calibration models, namely, multiple linear regression (MLR), Gaussian mixture regression and random forest (RF) decreased the MAE to 4.28, 3.93, and 4.40 μg m−3respectively. TheR2value improved to 0.63 for the MLR model but all other models registered a decrease (R2 = 0.44 and 0.60 respectively). Applying the correction factor to a five‐sensor network in Mombasa that was operated between July 2021 and July 2022 gave insights to the air quality in the city. The average daily concentrations of PM2.5within the city ranged from 12 to 18 μg m−3. The concentrations exceeded the WHO daily PM2.5limits more than 50% of the time, in particular at the sites nearby frequent industrial activity. Higher averages were observed during the dry and cold seasons and during early morning and evening periods of high activity. These results represent some of the first air quality monitoring measurements in Mombasa and highlight the need for more study. 
    more » « less
  4. ; ; (, Journal of Geophysical Research: Space Physics)
    Abstract Observations of coherent scatter from patchy sporadicElayers in the subauroral zone made with a 30‐MHz coherent scatter radar imager are presented. The quasiperiodic (QP) echoes are similar to what has been observed at middle latitudes but with some differences. The echoes arise from bands of scatterers aligned mainly northwest to southeast and propagating to the southwest. A notable difference from observations at middle latitudes is the appearance of secondary irregularities or braids oriented obliquely to the primary bands and propagating mainly northward along them. We present a spectral simulation of the patchy layers that describes neutral atmospheric dynamics with the incompressible Navier Stokes equations and plasma dynamics with an extended MHD model. The simulation is initialized with turning shears in the form of an Ekman spiral. Ekman‐type instability deforms the sporadicElayer through compressible and incompressible motion. The layer ultimately exhibits both the QP bands and the braids, consequences mainly of primary and secondary neutral dynamic instability. Vorticity due to dynamic instability is an important source of structuring in the sporadicElayer. 
    more » « less
  5. ; (, Journal of Geophysical Research: Space Physics)
    Abstract We present a new version of the high‐resolution Kühlungsborn Mechanistic general Circulation Model (KMCM) extended toz ∼ 450 km. This model is called HIAMCM (HI Altitude Mechanistic general Circulation Model) and explicitly simulates gravity waves (GWs) down to horizontal wavelengths ofλh ∼ 165 km. We find predominant tertiary GWs in the winter thermosphere at middle/high latitudes. These GWs typically have horizontal wavelengthsλh ∼ 300–1,100 km, ground‐based periods∼25–90 min, and intrinsic horizontal phase speedscIh ∼ 250–350 m s−1. Abovez∼ 200 km, the predominant GW horizontal propagation directions are roughly against the background winds from the diurnal tide; the GWs propagate mainly poleward at midnight, eastward at 6 local time (LT), equatorward at noon, and westward at 18 LT. Wintertime GWs atz∼ 300 km having 165 km ≤λh≤ 330 km create a large hot spot over the Southern Andes/Antarctic Peninsula that agrees well with quiet time satellite measurements. Due to cancelation effects, the time‐averaged zonal mean Eliassen‐Palm flux divergence from the resolved GWs in the thermosphere is negligible compared to that of the tides and compared to the zonal component of the time‐averaged zonal mean ion drag. We also find that the thermospheric GWs dissipate mainly from macroturbulent diffusion and, abovez∼ 200 km, from molecular diffusion, whereas the tides dissipate mainly from ion drag. The averaged dissipative heating in the thermosphere due to tides is much stronger than that due to GWs. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email