TY - JOUR
T1 - Deriving global parameter estimates for the Noah land surface model using FLUXNET and machine learning
AU - Chaney, Nathaniel W.
AU - Herman, Jonathan D.
AU - Ek, Michael B.
AU - Wood, Eric F.
N1 - Funding Information:
This study was supported by funding from NOAA grant NA11OAR4310175 (Improving land evaporative processes and land-atmosphere interactions in the NCEP Global Forecast System (GFS) and Climate Forecast System (CFS)). We wish to give a special thanks to the FLUXNET community for making the free fair-use subset of the La Thuile database available for this study. The data used in this study are hosted at Princeton University and are available from the authors upon request (nchaney@princeton.edu).
Publisher Copyright:
©2016. American Geophysical Union. All Rights Reserved.
PY - 2016/11/27
Y1 - 2016/11/27
N2 - With their origins in numerical weather prediction and climate modeling, land surface models aim to accurately partition the surface energy balance. An overlooked challenge in these schemes is the role of model parameter uncertainty, particularly at unmonitored sites. This study provides global parameter estimates for the Noah land surface model using 85 eddy covariance sites in the global FLUXNET network. The at-site parameters are first calibrated using a Latin Hypercube-based ensemble of the most sensitive parameters, determined by the Sobol method, to be the minimum stomatal resistance (rs,min), the Zilitinkevich empirical constant (Czil), and the bare soil evaporation exponent (fxexp). Calibration leads to an increase in the mean Kling-Gupta Efficiency performance metric from 0.54 to 0.71. These calibrated parameter sets are then related to local environmental characteristics using the Extra-Trees machine learning algorithm. The fitted Extra-Trees model is used to map the optimal parameter sets over the globe at a 5 km spatial resolution. The leave-one-out cross validation of the mapped parameters using the Noah land surface model suggests that there is the potential to skillfully relate calibrated model parameter sets to local environmental characteristics. The results demonstrate the potential to use FLUXNET to tune the parameterizations of surface fluxes in land surface models and to provide improved parameter estimates over the globe.
AB - With their origins in numerical weather prediction and climate modeling, land surface models aim to accurately partition the surface energy balance. An overlooked challenge in these schemes is the role of model parameter uncertainty, particularly at unmonitored sites. This study provides global parameter estimates for the Noah land surface model using 85 eddy covariance sites in the global FLUXNET network. The at-site parameters are first calibrated using a Latin Hypercube-based ensemble of the most sensitive parameters, determined by the Sobol method, to be the minimum stomatal resistance (rs,min), the Zilitinkevich empirical constant (Czil), and the bare soil evaporation exponent (fxexp). Calibration leads to an increase in the mean Kling-Gupta Efficiency performance metric from 0.54 to 0.71. These calibrated parameter sets are then related to local environmental characteristics using the Extra-Trees machine learning algorithm. The fitted Extra-Trees model is used to map the optimal parameter sets over the globe at a 5 km spatial resolution. The leave-one-out cross validation of the mapped parameters using the Noah land surface model suggests that there is the potential to skillfully relate calibrated model parameter sets to local environmental characteristics. The results demonstrate the potential to use FLUXNET to tune the parameterizations of surface fluxes in land surface models and to provide improved parameter estimates over the globe.
KW - evapotranspiration
KW - land surface model
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85003674368&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85003674368&partnerID=8YFLogxK
U2 - 10.1002/2016JD024821
DO - 10.1002/2016JD024821
M3 - Article
AN - SCOPUS:85003674368
SN - 2169-897X
VL - 121
SP - 218
EP - 235
JO - Journal of Geophysical Research: Atmospheres
JF - Journal of Geophysical Research: Atmospheres
IS - 22
ER -