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: An Ensemble of Neural Networks for Moist Physics Processes, Its Generalizability and Stable Integration
Abstract With the recent advances in data science, machine learning has been increasingly applied to convection and cloud parameterizations in global climate models (GCMs). This study extends the work of Han et al. (2020,https://doi.org/10.1029/2020MS002076) and uses an ensemble of 32‐layer deep convolutional residual neural networks, referred to as ResCu‐en, to emulate convection and cloud processes simulated by a superparameterized GCM, SPCAM. ResCu‐en predicts GCM grid‐scale temperature and moisture tendencies, and cloud liquid and ice water contents from moist physics processes. The surface rainfall is derived from the column‐integrated moisture tendency. The prediction uncertainty inherent in deep learning algorithms in emulating the moist physics is reduced by ensemble averaging. Results in 1‐year independent offline validation show that ResCu‐en has high prediction accuracy for all output variables, both in the current climate and in a warmer climate with +4K sea surface temperature. The analysis of different neural net configurations shows that the success to generalize in a warmer climate is attributed to convective memory and the 1‐dimensional convolution layers incorporated into ResCu‐en. We further implement a member of ResCu‐en into CAM5 with real world geography and run the neural‐network‐enabled CAM5 (NCAM) for 5 years without encountering any numerical integration instability. The simulation generally captures the global distribution of the mean precipitation, with a better simulation of precipitation intensity and diurnal cycle. However, there are large biases in temperature and moisture in high latitudes. These results highlight the importance of convective memory and demonstrate the potential for machine learning to enhance climate modeling.  more » « less
Award ID(s):
2054697
PAR ID:
10518968
Author(s) / Creator(s):
; ;
Publisher / Repository:
American Geophysical Union
Date Published:
Journal Name:
Journal of Advances in Modeling Earth Systems
Volume:
15
Issue:
10
ISSN:
1942-2466
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, Space Weather)
    Abstract We introduce a new framework called Machine Learning (ML) based Auroral Ionospheric electrodynamics Model (ML‐AIM). ML‐AIM solves a current continuity equation by utilizing the ML model of Field Aligned Currents of Kunduri et al. (2020,https://doi.org/10.1029/2020JA027908), the FAC‐derived auroral conductance model of Robinson et al. (2020,https://doi.org/10.1029/2020JA028008), and the solar irradiance conductance model of Moen and Brekke (1993,https://doi.org/10.1029/92gl02109). The ML‐AIM inputs are 60‐min time histories of solar wind plasma, interplanetary magnetic fields (IMF), and geomagnetic indices, and its outputs are ionospheric electric potential, electric fields, Pedersen/Hall currents, and Joule Heating. We conduct two ML‐AIM simulations for a weak geomagnetic activity interval on 14 May 2013 and a geomagnetic storm on 7–8 September 2017. ML‐AIM produces physically accurate ionospheric potential patterns such as the two‐cell convection pattern and the enhancement of electric potentials during active times. The cross polar cap potentials (ΦPC) from ML‐AIM, the Weimer (2005,https://doi.org/10.1029/2004ja010884) model, and the Super Dual Auroral Radar Network (SuperDARN) data‐assimilated potentials, are compared to the ones from 3204 polar crossings of the Defense Meteorological Satellite Program F17 satellite, showing better performance of ML‐AIM than others. ML‐AIM is unique and innovative because it predicts ionospheric responses to the time‐varying solar wind and geomagnetic conditions, while the other traditional empirical models like Weimer (2005,https://doi.org/10.1029/2004ja010884) designed to provide a quasi‐static ionospheric condition under quasi‐steady solar wind/IMF conditions. Plans are underway to improve ML‐AIM performance by including a fully ML network of models of aurora precipitation and ionospheric conductance, targeting its characterization of geomagnetically active times. 
    more » « less
  2. ; ; ; (, Geophysical Research Letters)
    Abstract A tropical cyclone (TC) can generally be divided into three regions: inner core with vigorous convection, intermediate region with intermittent convection, and far outer region with less convective activity. The different physics in these three regions suggest correspondingly different wind structure models. In this study, we combine the inner‐core wind model from Tao et al. (2023,https://doi.org/10.1029/2023gl104583, T23), the outer wind model from Emanuel (2004,https://texmex.mit.edu/pub/emanuel/PAPERS/Energetics_Structure.pdf, E04), and a transition model of a modified Rankine vortex to create a new fast and analytical model for the complete radial structure of the TC wind field. The T23 model captures inner‐core wind variation with small errors, while the E04 model reproduces the broad outer wind structure at large radii well. The new wind model combines the strengths from both T23 and E04 models without the need for statistical fitting, showing great potential in reproducing the full range of simulated and observed TC winds. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, Journal of Geophysical Research: Atmospheres)
    Abstract We report on the mountain top observation of three terrestrial gamma‐ray flashes (TGFs) that occurred during the summer storm season of 2021. To our knowledge, these are the first TGFs observed in a mountaintop environment and the first published European TGFs observed from the ground. A gamma‐ray sensitive detector was located at the base of the Säntis Tower in Switzerland and observed three unique TGF events with coincident radio sferic data characteristic of TGFs seen from space. We will show an example of a “slow pulse” radio signature (Cummer et al., 2011,https://doi.org/10.1029/2011GL048099; Lu et al., 2011,https://doi.org/10.1029/2010JA016141; Pu et al., 2019,https://doi.org/10.1029/2019GL082743; Pu et al., 2020,https://doi.org/10.1029/2020GL089427), a −EIP (Lyu et al., 2016,https://doi.org/10.1002/2016GL070154; Lyu et al., 2021,https://doi.org/10.1029/2021GL093627; Wada et al., 2020,https://doi.org/10.1029/2019JD031730), and a double peak TGF associated with an extraordinarily powerful and complicated positive‐polarity sferic, where each TGF peak is possibly preceded by a short burst of stepped leader emission. 
    more » « less
  4. ; ; (, Journal of Geophysical Research: Atmospheres)
    x (Ed.)
    Abstract We present modeling results of tube and knot (T&K) dynamics accompanying thermospheric Kelvin Helmholtz Instabilities (KHI) in an event captured by the 2018 Super Soaker campaign (R. L. Mesquita et al., 2020,https://doi.org/10.1029/2020JA027972). Chemical tracers released by a rocketsonde on 26 January 2018 showed coherent KHI in the lower thermosphere that rapidly deteriorated within 45–90 s. Using wind and temperature data from the event, we conducted high resolution direct numerical simulations (DNS) employing both wide and narrow spanwise domains to facilitate (wide domain case) and prohibit (narrow domain case) the axial deformation of KH billows that allows tubes and knots to form. KHI T&K dynamics are shown to produce accelerated instability evolution consistent with the observations, achieving peak dissipation rates nearly two times larger and 1.8 buoyancy periods faster than axially uniform KHI generated by the same initial conditions. Rapidly evolving twist waves are revealed to drive the transition to turbulence; their evolution precludes the formation of secondary convective instabilities and secondary KHI seen to dominate the turbulence evolution in artificially constrained laboratory and simulation environments. T&K dynamics extract more kinetic energy from the background environment and yield greater irreversible energy exchange and entropy production, yet they do so with weaker mixing efficiency due to greater energy dissipation. The results suggest that enhanced mixing from thermospheric KHI T&K events could account for the discrepancy between modeled and observed mixing in the lower thermosphere (Garcia et al., 2014,https://doi.org/10.1002/2013JD021208; Liu, 2021,https://doi.org/10.1029/2020GL091474) and merits further study. 
    more » « less
  5. ; (, Geophysical Research Letters)
    Abstract We show that atmospheric gravity waves can generate plasma ducts and irregularities in the plasmasphere using the coupled SAMI3/WACCM‐X model. We find the equatorial electron density is irregular as a function of longitude which is consistent with CRRES measurements (Clilverd et al., 2007,https://doi.org/10.1029/2007ja012416). We also find that plasma ducts can be generated forL‐shells in the range 1.5–3.0 with lifetimes of ∼ 0.5 hr; this is in line with observations of ducted VLF wave propagation with lifetimes of 0.5–2.0 hr (Clilverd et al., 2008,https://doi.org/10.1029/2007ja012602; Singh et al., 1998,https://doi.org/10.1016/s1364-6826(98)00001-7). 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email