Deriving global parameter estimates for the Noah land surface model using FLUXNET and machine learning

Nathaniel W. Chaney, Jonathan D. Herman, Michael B. Ek, Eric F. Wood

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)218-235
Number of pages18
JournalJournal of Geophysical Research: Atmospheres
Issue number22
StatePublished - Nov 27 2016

All Science Journal Classification (ASJC) codes

  • Geophysics
  • Forestry
  • Oceanography
  • Aquatic Science
  • Ecology
  • Water Science and Technology
  • Soil Science
  • Geochemistry and Petrology
  • Earth-Surface Processes
  • Atmospheric Science
  • Earth and Planetary Sciences (miscellaneous)
  • Space and Planetary Science
  • Palaeontology


  • evapotranspiration
  • land surface model
  • machine learning

Fingerprint Dive into the research topics of 'Deriving global parameter estimates for the Noah land surface model using FLUXNET and machine learning'. Together they form a unique fingerprint.

Cite this