scholarly journals A machine learning-guided adaptive algorithm to reduce the computational cost of atmospheric chemistry in Earth System models: application to GEOS-Chem versions 12.0.0 and 12.9.1

2021 ◽  
Author(s):  
Lu Shen ◽  
Daniel J. Jacob ◽  
Mauricio Santillana ◽  
Kelvin Bates ◽  
Jiawei Zhuang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atmospheric Chemistry ◽  
Computational Cost ◽  
Coupled System ◽  
Atmospheric Composition ◽  
Earth System ◽  
Major Barrier ◽  
System Models ◽  
Computational Bottleneck ◽  
Earth System Models

Abstract. Atmospheric composition plays a crucial role in determining the evolution of the atmosphere, but the high computational cost has been the major barrier to include atmospheric chemistry into Earth system models. Here we present an adaptive and efficient algorithm that can remove this barrier. Our approach is inspired by unsupervised machine learning clustering techniques and traditional asymptotic analysis ideas. We first partition species into 13 blocks, using a novel machine learning approach that analyzes the species network structures and their production and loss rates. Building on these blocks, we pre-select 20 submechanisms, as defined by unique assemblages of the species blocks, and then pick locally on the fly which submechanism to use based on local chemical conditions. In each submechanism, we isolate slow species and unimportant reactions from the coupled system. Application to a global 3-D model shows that we can cut the computational costs of the chemical integration by 50 % with accuracy losses smaller than 1 % that do not propagate in time. Tests show that this algorithm is highly chemically coherent making it easily portable to new models without compromising its performance. Our algorithm will significantly ease the computational bottleneck and will facilitate the development of next generation of earth system models.

scholarly journals Physically regularized machine learning emulators of aerosol activation

2021 ◽  
Vol 14 (5) ◽  
pp. 3067-3077
Author(s):  
Sam J. Silva ◽  
Po-Lun Ma ◽  
Joseph C. Hardin ◽  
Daniel Rothenberg
Keyword(s):  
Machine Learning ◽  
Model Development ◽  
Computational Cost ◽  
Earth System ◽  
Cloud Droplets ◽  
Physical Constraints ◽  
System Models ◽  
Machine Learning Model ◽  
Aerosol Activation ◽  
Earth System Models

Abstract. The activation of aerosol into cloud droplets is an important step in the formation of clouds and strongly influences the radiative budget of the Earth. Explicitly simulating aerosol activation in Earth system models is challenging due to the computational complexity required to resolve the necessary chemical and physical processes and their interactions. As such, various parameterizations have been developed to approximate these details at reduced computational cost and accuracy. Here, we explore how machine learning emulators can be used to bridge this gap in computational cost and parameterization accuracy. We evaluate a set of emulators of a detailed cloud parcel model using physically regularized machine learning regression techniques. We find that the emulators can reproduce the parcel model at higher accuracy than many existing parameterizations. Furthermore, physical regularization tends to improve emulator accuracy, most significantly when emulating very low activation fractions. This work demonstrates the value of physical constraints in machine learning model development and enables the implementation of improved hybrid physical and machine learning models of aerosol activation into next-generation Earth system models.

scholarly journals Physically Regularized Machine Learning Emulators of Aerosol Activation

2020 ◽  
Author(s):  
Sam J. Silva ◽  
Po-Lun Ma ◽  
Joseph C. Hardin ◽  
Daniel Rothenberg
Keyword(s):  
Machine Learning ◽  
Model Development ◽  
Computational Cost ◽  
Earth System ◽  
Cloud Droplets ◽  
Physical Constraints ◽  
System Models ◽  
Machine Learning Model ◽  
Aerosol Activation ◽  
Earth System Models

Abstract. The activation of aerosol into cloud droplets is an important step in the formation of clouds, and strongly influences the radiative budget of the Earth. Explicitly simulating aerosol activation in Earth system models is challenging due to the computational complexity required to resolve the necessary chemical and physical processes and their interactions. As such, various parameterizations have been developed to approximate these details at reduced computational cost and accuracy. Here, we explore how machine learning emulators can be used to bridge this gap in computational cost and parameterization accuracy. We evaluate a set of emulators of a detailed cloud parcel model using physically regularized machine learning regression techniques. We find that the emulators can reproduce the parcel model at higher accuracy than many existing parameterizations. Furthermore, physical regularization tends to improve emulator accuracy, most significantly when emulating very low activation fractions. This work demonstrates the value of physical constraints in machine learning model development and enables the implementation of improved hybrid physical-machine learning models of aerosol activation into next generation Earth system models.

A stationary tropospheric sulphur cycle for Earth system models of intermediate complexit

2021 ◽  
Author(s):  
Alexey V. Eliseev ◽  
Rustam D. Gizatullin ◽  
Alexandr V. Timazhev
Keyword(s):  
Atmospheric Chemistry ◽  
Sulphur Dioxide ◽  
Wet Deposition ◽  
Earth System ◽  
Sulphur Compounds ◽  
Coupled Models ◽  
System Models ◽  
Sulphur Cycle ◽  
Intercomparison Project ◽  
Earth System Models

<p>A stationary, computationally efficient  scheme, ChAP-1.0 (Chemistry and Aerosol Processes, version 1.0) for the sulphur cycle in the troposphereis developed. This scheme is envisaged to be implemented into Earth system models of intermediate complexity (EMICs). The scheme accounts for sulphur dioxide emissions into the atmosphere, its deposition to the surface, oxidation to sulphates, and dry and wet deposition of sulphates on the surface.<br>The calculations with the scheme were performed with the anthropogenic emissions of sulphur compounds into the atmosphere for 1850-2000 according to the CMIP5 (Coupled Models Intercomparison Project, phase 5) 'historical' protocol, with the ERA-Interim meteorology, and assuming that natural sources of sulphur into the atmosphere remain unchanged during this period. The model reasonably reproduces characteristics of the tropospheric sulphur cycle known from observations and other simulations (e.g., in the Atmospheric Chemistry and Climate Model Intercomparison Project phase II (ACCMIP) simulations, Copernicus Atmosphere Monitoring Service (CAMS) reanalysis, and the Meteorological Synthesizing Centre–West of the European Monitoring and Evaluation Programme (EMEP MSC-W) data). In particular, in 1980's and 1990's, , when the global anthropogenic emission of sulphur, global atmospheric burdens of SO<sub>2</sub> and SO<sub>4</sub> account, correspondingly, 0.2 TgS and 0.4 TgS. In our scheme, about half of the emitted sulphur dioxide is deposited to the surface and the rest in oxidised into sulphates. The latter mostly removed from the atmosphere by wet deposition. The lifetime of the SO<sub>2</sub> and SO<sub>4</sub> in the atmosphere is, respectively, 1.0±0.1 days and 4.1±0.3 days.<br>Despite its simplicity, our scheme may be successfully used to simulate sulphur/sulphates pollution in the atmosphere at coarse spatial and time scales and an impact of this pollution to direct radiative effect of sulphates on climate, their respective indirect (cloud- and precipitation-related) effects, as well as an impact of sulphur compounds on the terrestrial carbon cycle.</p>

scholarly journals A map of global peatland distribution created using machine learning for use in terrestrial ecosystem and earth system models

2017 ◽  
Author(s):  
Yuanqiao Wu ◽  
Ed Chan ◽  
Joe R. Melton ◽  
Diana L. Verseghy
Keyword(s):  
Machine Learning ◽  
Statistical Model ◽  
Machine Learning Method ◽  
Learning Method ◽  
Earth System ◽  
Geophysical Field ◽  
Fractional Coverage ◽  
System Models ◽  
Earth System Models ◽  
Global Carbon

Abstract. Peatlands store large amounts of soil carbon and constitute an important component of the global carbon cycle. Accurate information on the global extent and distribution of peatlands is presently lacking but it important for earth system models (ESMs) to be able to simulate the effects of climate change on the global carbon balance. The most comprehensive peatland map produced to date is a qualitative presence/absence product. Here, we present a spatially continuous global map of peatland fractional coverage using the extremely randomized tree machine learning method suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model include spatially distributed climate data, soil data and topographical slopes. Available maps of peatland fractional coverage for Canada and West Siberia were used along with a proxy for non-peatland areas to train and test the statistical model. Regions where the peatland fraction is expected to be zero were estimated from a map of topsoil organic carbon content below a threshold value of 13 kg/m2. The modelled coverage of peatlands yields a root mean square error of 4 % and a coefficient of determination of 0.91 for the 10,978 tested 0.5 degree grid cells. We then generated a complete global peatland fractional coverage map. In comparison with earlier qualitative estimates, our global modelled peatland map is able to reproduce peatland distributions in places remote from the training areas and capture peatland hot spots in both boreal and tropical regions, as well as in the southern hemisphere. Additionally we demonstrate that our machine-learning method has greater skill than solely setting peatland areas based on histosols from a soil database.

scholarly journals Development of a grid-independent GEOS-Chem chemical transport model (v9-02) as an atmospheric chemistry module for Earth system models

2015 ◽  
Vol 8 (3) ◽  
pp. 595-602 ◽  
Author(s):  
M. S. Long ◽  
R. Yantosca ◽  
J. E. Nielsen ◽  
C. A. Keller ◽  
A. da Silva ◽  
...  
Keyword(s):  
Atmospheric Chemistry ◽  
Transport Model ◽  
Chemical Transport ◽  
Earth System ◽  
Chemical Transport Model ◽  
Modeling Framework ◽  
System Models ◽  
Chemistry Research ◽  
Earth System Models ◽  
Chemistry Module

Abstract. The GEOS-Chem global chemical transport model (CTM), used by a large atmospheric chemistry research community, has been re-engineered to also serve as an atmospheric chemistry module for Earth system models (ESMs). This was done using an Earth System Modeling Framework (ESMF) interface that operates independently of the GEOS-Chem scientific code, permitting the exact same GEOS-Chem code to be used as an ESM module or as a stand-alone CTM. In this manner, the continual stream of updates contributed by the CTM user community is automatically passed on to the ESM module, which remains state of science and referenced to the latest version of the standard GEOS-Chem CTM. A major step in this re-engineering was to make GEOS-Chem grid independent, i.e., capable of using any geophysical grid specified at run time. GEOS-Chem data sockets were also created for communication between modules and with external ESM code. The grid-independent, ESMF-compatible GEOS-Chem is now the standard version of the GEOS-Chem CTM. It has been implemented as an atmospheric chemistry module into the NASA GEOS-5 ESM. The coupled GEOS-5–GEOS-Chem system was tested for scalability and performance with a tropospheric oxidant-aerosol simulation (120 coupled species, 66 transported tracers) using 48–240 cores and message-passing interface (MPI) distributed-memory parallelization. Numerical experiments demonstrate that the GEOS-Chem chemistry module scales efficiently for the number of cores tested, with no degradation as the number of cores increases. Although inclusion of atmospheric chemistry in ESMs is computationally expensive, the excellent scalability of the chemistry module means that the relative cost goes down with increasing number of cores in a massively parallel environment.

scholarly journals Ideas and Perspectives: Climate-Relevant Marine Biologically-Driven Mechanisms in Earth System Models

2016 ◽  
Author(s):  
Inga Hense ◽  
Irene Stemmler ◽  
Sebastian Sonntag
Keyword(s):  
Mechanical Properties ◽  
Functional Groups ◽  
Atmospheric Composition ◽  
Marine Biota ◽  
Earth System ◽  
System Models ◽  
System Components ◽  
Optical And Mechanical Properties ◽  
Earth System Models

Abstract. Marine biota drives a number of climate-relevant mechanisms not all of which are included in current Earth system models (ESMs). We identify three classes of mechanisms and distinguish (1) those related to matter cycling via "biogeochemical pumps", (2) those affecting the atmospheric composition via the "biological gas and particle shuttles" and (3) those changing the thermal, optical and mechanical properties of the ocean via the "biogeophysical mechanisms". We argue that to adequately resolve these mechanisms, ESMs need to account for five functional groups, including bulk phyto- and zooplankton, calcifiers as well as coastal gas and surface mat producers. Thereby links to other Earth system components are ensured and a larger number of relevant feedbacks are enabled to take place.

scholarly journals Development of a grid-independent GEOS-chem chemical transport model as an atmospheric chemistry module for Earth System Models

2014 ◽  
Vol 7 (6) ◽  
pp. 7505-7524 ◽  
Author(s):  
M. S. Long ◽  
R. Yantosca ◽  
J. E. Nielsen ◽  
C. A. Keller ◽  
A. da Silva ◽  
...  
Keyword(s):  
Atmospheric Chemistry ◽  
Transport Model ◽  
Chemical Transport ◽  
System Modelling ◽  
Earth System ◽  
Chemical Transport Model ◽  
System Models ◽  
Chemistry Research ◽  
Earth System Models ◽  
Chemistry Module

Abstract. The GEOS-Chem global chemical transport model (CTM), used by a large atmospheric chemistry research community, has been re-engineered to also serve as an atmospheric chemistry module for Earth System Models (ESMs). This was done using an Earth System Modelling Framework (ESMF) interface that operates independently of the GEOS-Chem scientific code, permitting the exact same GEOS-Chem code to be used as an ESM module or as a stand-alone CTM. In this manner, the continual stream of updates contributed by the CTM user community is automatically passed on to the ESM module, which remains state-of-science and referenced to the latest version of the standard GEOS-Chem CTM. A major step in this re-engineering was to make GEOS-Chem grid-independent, i.e., capable of using any geophysical grid specified at run time. GEOS-Chem data "sockets" were also created for communication between modules and with external ESM code via the ESMF. The grid-independent, ESMF-compatible GEOS-Chem is now the standard version of the GEOS-Chem CTM. It has been implemented as an atmospheric chemistry module into the NASA GEOS-5 ESM. The coupled GEOS-5/GEOS-Chem system was tested for scalability and performance with a tropospheric oxidant-aerosol simulation (120 coupled species, 66 transported tracers) using 48–240 cores and MPI parallelization. Numerical experiments demonstrate that the GEOS-Chem chemistry module scales efficiently for the number of processors tested. Although inclusion of atmospheric chemistry in ESMs is computationally expensive, the excellent scalability of the chemistry module means that the relative cost goes down with increasing number of MPI processes.

Future fires in the Coupled Model Intercomparison Project (CMIP) phase 6

2020 ◽  
Author(s):  
Gitta Lasslop ◽  
Stijn Hantson ◽  
Victor Brovkin ◽  
Fang Li ◽  
David Lawrence ◽  
...  
Keyword(s):  
Land Use ◽  
Fire Regime ◽  
Coupled Model ◽  
Fire Regimes ◽  
Atmospheric Composition ◽  
Cloud Formation ◽  
Burned Area ◽  
Earth System ◽  
System Models ◽  
Earth System Models

<p>Fires are an important component in Earth system models (ESMs), they impact vegetation carbon storage, vegetation distribution, atmospheric composition and cloud formation. The representation of fires in ESMs contributing to CMIP phase 5 was still very simplified. Several Earth system models updated their representation of fires in the meantime. Using the latest simulations of CMIP6 we investigate how fire regimes change in the future for different scenarios and how land use, climate and atmospheric CO<sub>2</sub> concentration contribute to the fire regimes changes. We quantify changes in fire danger, burned area and carbon emissions on an annual and seasonal basis. Factorial model simulations allow to quantify the influence of land use, climate and atmospheric CO<sub>2</sub> on fire regimes.</p><p>We complement the information on fire regime change supplied by ESMs that include a fire module with a statistical modelling approach for burned area. This will use information from simulated changes in climate, vegetation and socioeconomic changes (population density and land use) provided for a set of different future scenarios. This allows the integration of information provided by global satellite products on burned area with the process-based simulations of climate and vegetation changes and information from socioeconomic scenarios.</p><p> </p>

Sign in / Sign up

Export Citation Format

Share Document