skip to main content

DOE PAGESDOE PAGES

Title: Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence

A new global estimate of surface turbulent fluxes, latent heat flux (LE) and sensible heat flux ( H), and gross primary production (GPP) is developed using a machine learning approach informed by novel remotely sensed solar-induced fluorescence (SIF) and other radiative and meteorological variables. This is the first study to jointly retrieve LE, H, and GPP using SIF observations. The approach uses an artificial neural network (ANN) with a target dataset generated from three independent data sources, weighted based on a triple collocation (TC) algorithm. The new retrieval, named Water, Energy, and Carbon with Artificial Neural Networks (WECANN), provides estimates of LE, H, and GPP from 2007 to 2015 at 1° × 1° spatial resolution and at monthly time resolution. The quality of ANN training is assessed using the target data, and the WECANN retrievals are evaluated using eddy covariance tower estimates from the FLUXNET network across various climates and conditions. When compared to eddy covariance estimates, WECANN typically outperforms other products, particularly for sensible and latent heat fluxes. Analyzing WECANN retrievals across three extreme drought and heat wave events demonstrates the capability of the retrievals to capture the extent of these events. Uncertainty estimates of the retrievals are analyzedmore » and the interannual variability in average global and regional fluxes shows the impact of distinct climatic events – such as the 2015 El Niño – on surface turbulent fluxes and GPP.« less
Authors:
ORCiD logo [1] ;  [1] ; ORCiD logo [2] ;  [3] ;  [1] ;  [4] ; ORCiD logo [5] ;  [6] ;  [7]
  1. Columbia Univ., New York, NY (United States). Department of Earth and Environmental Engineering and Columbia Water Center
  2. Stanford Univ., CA (United States). Department of Earth System Science
  3. Columbia Univ., New York, NY (United States). Department of Earth and Environmental Engineering ; Observatoire de Paris (France)
  4. Universities Space Research Association/NPP, Columbia, MD (United States); NASA Goddard Space Flight Center (GSFC), Greenbelt, MD (United States). Global Modeling and Assimilation Office
  5. Ghent University (Belgium). Laboratory of Hydrology and Water Management
  6. Columbia Univ., New York, NY (United States). Department of Earth and Environmental Engineering; NASA Goddard Space Flight Center (GSFC), Greenbelt, MD (United States). Global Modeling and Assimilation Office
  7. Columbia Univ., New York, NY (United States). Department of Earth and Environmental Engineering, Columbia Water Center and Earth Institute
Publication Date:
Grant/Contract Number:
FG02-04ER63917; FG02-04ER63911
Type:
Accepted Manuscript
Journal Name:
Biogeosciences (Online)
Additional Journal Information:
Journal Name: Biogeosciences (Online); Journal Volume: 14; Journal Issue: 18; Journal ID: ISSN 1726-4189
Publisher:
European Geosciences Union
Research Org:
Oregon State Univ., Corvallis, OR (United States)
Sponsoring Org:
USDOE Office of Science (SC), Biological and Environmental Research (BER) (SC-23)
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES
OSTI Identifier:
1429885

Alemohammad, Seyed Hamed, Fang, Bin, Konings, Alexandra G., Aires, Filipe, Green, Julia K., Kolassa, Jana, Miralles, Diego, Prigent, Catherine, and Gentine, Pierre. Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence. United States: N. p., Web. doi:10.5194/bg-14-4101-2017.
Alemohammad, Seyed Hamed, Fang, Bin, Konings, Alexandra G., Aires, Filipe, Green, Julia K., Kolassa, Jana, Miralles, Diego, Prigent, Catherine, & Gentine, Pierre. Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence. United States. doi:10.5194/bg-14-4101-2017.
Alemohammad, Seyed Hamed, Fang, Bin, Konings, Alexandra G., Aires, Filipe, Green, Julia K., Kolassa, Jana, Miralles, Diego, Prigent, Catherine, and Gentine, Pierre. 2017. "Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence". United States. doi:10.5194/bg-14-4101-2017. https://www.osti.gov/servlets/purl/1429885.
@article{osti_1429885,
title = {Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence},
author = {Alemohammad, Seyed Hamed and Fang, Bin and Konings, Alexandra G. and Aires, Filipe and Green, Julia K. and Kolassa, Jana and Miralles, Diego and Prigent, Catherine and Gentine, Pierre},
abstractNote = {A new global estimate of surface turbulent fluxes, latent heat flux (LE) and sensible heat flux (H), and gross primary production (GPP) is developed using a machine learning approach informed by novel remotely sensed solar-induced fluorescence (SIF) and other radiative and meteorological variables. This is the first study to jointly retrieve LE, H, and GPP using SIF observations. The approach uses an artificial neural network (ANN) with a target dataset generated from three independent data sources, weighted based on a triple collocation (TC) algorithm. The new retrieval, named Water, Energy, and Carbon with Artificial Neural Networks (WECANN), provides estimates of LE, H, and GPP from 2007 to 2015 at 1° × 1° spatial resolution and at monthly time resolution. The quality of ANN training is assessed using the target data, and the WECANN retrievals are evaluated using eddy covariance tower estimates from the FLUXNET network across various climates and conditions. When compared to eddy covariance estimates, WECANN typically outperforms other products, particularly for sensible and latent heat fluxes. Analyzing WECANN retrievals across three extreme drought and heat wave events demonstrates the capability of the retrievals to capture the extent of these events. Uncertainty estimates of the retrievals are analyzed and the interannual variability in average global and regional fluxes shows the impact of distinct climatic events – such as the 2015 El Niño – on surface turbulent fluxes and GPP.},
doi = {10.5194/bg-14-4101-2017},
journal = {Biogeosciences (Online)},
number = 18,
volume = 14,
place = {United States},
year = {2017},
month = {9}
}