skip to main content

Explore Research Products in the NSF-PAR

Title: A Hybrid Approach to Atmospheric Modeling That Combines Machine Learning With a Physics‐Based Numerical Model
Abstract

This paper describes an implementation of the combined hybrid‐parallel prediction (CHyPP) approach of Wikner et al. (2020),https://doi.org/10.1063/5.0005541on a low‐resolution atmospheric global circulation model (AGCM). The CHyPP approach combines a physics‐based numerical model of a dynamical system (e.g., the atmosphere) with a computationally efficient type of machine learning (ML) called reservoir computing to construct a hybrid model. This hybrid atmospheric model produces more accurate forecasts of most atmospheric state variables than the host AGCM for the first 7–8 forecast days, and for even longer times for the temperature and humidity near the earth's surface. It also produces more accurate forecasts than a model based only on ML, or a model that combines linear regression, rather than ML, with the AGCM. The potential of the CHyPP approach for climate research is demonstrated by a 10‐year long hybrid model simulation of the atmospheric general circulation, which shows that the hybrid model can simulate the general circulation with substantially smaller systematic errors and more realistic variability than the host AGCM.

  more » « less
NSF-PAR ID:
10366873
Author(s) / Creator(s):
 ;  ;  ;  ;  ;  
Publisher / Repository:
DOI PREFIX: 10.1029
Date Published:
Journal Name:
Journal of Advances in Modeling Earth Systems
Volume:
14
Issue:
3
ISSN:
1942-2466
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ( , James)
    null (Ed.)
    This paper describes an implementation of the Combined Hybrid-Parallel Prediction (CHyPP) approach of Wikner et al. (2020) on a low-resolution atmospheric global circulation model (AGCM). This approach combines a physics-based numerical model of a dynamical system (e.g., the atmosphere) with a computationally efficient type of machine learning (ML) called reservoir computing (RC) to construct a hybrid model. This hybrid atmospheric model produces more accurate forecasts of most atmospheric state variables than the host AGCM for the first 7-8 forecast days, and for even longer times for the temperature and humidity near the earth's surface. It also produces more accurate forecasts than a purely ML-based model, or a model that combines linear regression, rather than ML, with the AGCM. The potential of the approach for climate research is demonstrated by a 10-year long hybrid model simulation of the atmospheric general circulation, which shows that the hybrid model can simulate the general circulation with substantially smaller systematic errors and more realistic variability than the host AGCM. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; 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
  3. ; ; ; ; ; ; ; ; ; ( , Journal of Geophysical Research: Space Physics)
    Abstract

    A dramatic thermospheric temperature enhancement and inversion layer (TTEIL) was observed by the Fe Boltzmann lidar at McMurdo, Antarctica during a geomagnetic storm (Chu et al. 2011,https://doi.org/10.1029/2011GL050016). The Thermosphere‐Ionosphere‐Electrodynamics General Circulation Model (TIEGCM) driven by empirical auroral precipitation and background electric fields cannot adequately reproduce the TTEIL. We incorporate the Defense Meteorological Satellite Program (DMSP)/Special Sensor Ultraviolet Spectrographic Imager (SSUSI) auroral precipitation maps, which capture the regional‐scale features into TIEGCM and add subgrid electric field variability in the regions with strong auroral activity. These modifications enable the simulation of neutral temperatures closer to lidar observations and neutral densities closer to GRACE satellite observations (~475 km). The regional scale auroral precipitation and electric field variabilities are both needed to generate strong Joule heating that peaks around 120 km. The resulting temperature increase leads to the change of pressure gradients, thus inducing a horizontal divergence of air flow and large upward winds that increase with altitude. Associated with the upwelling wind is the adiabatic cooling gradually increasing with altitude and peaking at ~200 km. The intense Joule heating around 120 km and strong cooling above result in differential heating that produces a sharp TTEIL. However, vertical heat advection broadens the TTEIL and raises the temperature peak from ~120 to ~150 km, causing simulations deviating from observations. Strong local Joule heating also excites traveling atmospheric disturbances that carry the TTEIL signatures to other regions. Our study suggests the importance of including fine‐structure auroral precipitation and subgrid electric field variability in the modeling of storm‐time ionosphere‐thermosphere responses.

     
    more » « less
  4. ; ; ( , Radio Science)
    Abstract

    Ionospheric modification experiments have been performed at the High‐Frequency Active Auroral Research Program (HAARP) facility in Gakona, Alaska, using a Very High Frequency (VHF) coherent scatter radar in Homer, Alaska, for experimental diagnostics. The experiments were intended to determine the threshold pump electric field required to initiate thermal parametric instability in theEregion. The pump power level was ramped systematically to determine the threshold, and the experiment was repeated at four closely spaced pump frequencies. This provided threshold estimates at fourEregion altitudes. The theory for thermal parametric instability based on the work of Dysthe et al. (1983,https://doi.org/10.1063/1.863993) has been modified for application in theEregion. The theory considers magneto‐ionic effects on the pump mode, linear mode conversion theory for upper hybrid wave generation, wave heating, and the effects of transport and dissipation based on fluid theory. The theory amounts to an eigenvalue problem where the eigenvalue is the threshold pump electric field for instability. The theory shows how the threshold depends on ionospheric transport coefficients and on the fractional cooling rate for inelastic electron‐neutral collisions. The theoretical predictions for threshold are roughly consistent with experimental values although the latter are probably affected by excess ionospheric absorption.

     
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al ( , Journal of Advances in Modeling Earth Systems)
    Abstract

    Dynamical cores used to study the circulation of the atmosphere employ various numerical methods ranging from finite‐volume, spectral element, global spectral, and hybrid methods. In this work, we explore the use of Flux‐Differencing Discontinuous Galerkin (FDDG) methods to simulate a fully compressible dry atmosphere at various resolutions. We show that the method offers a judicious compromise between high‐order accuracy and stability for large‐eddy simulations and simulations of the atmospheric general circulation. In particular, filters, divergence damping, diffusion, hyperdiffusion, or sponge‐layers are not required to ensure stability; only the numerical dissipation naturally afforded by FDDG is necessary. We apply the method to the simulation of dry convection in an atmospheric boundary layer and in a global atmospheric dynamical core in the standard benchmark of Held and Suarez (1994,https://doi.org/10.1175/1520-0477(1994)075〈1825:apftio〉2.0.co;2).

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email