Abstract:
The land surface soil moisture is a crucial variable in weather and climate models. This study presents a
land data assimilation system (LDAS) that aims to improve the simulation of the land surface soil moisture
and energy fluxes by merging the microwave remote sensing data and the general circulation model
(GCM) output into a land surface model (LSM). This system was applied over the Tibetan Plateau, using the
National Centers for Environmental Prediction (NCEP) reanalysis data as forcing data and the Advanced
Microwave Scanning Radiometers for EOS (AMSR-E) brightness temperatures as an observation. The performance
of our four data sources, which were NCEP, AMSR-E, LDAS and simulations of Simple Biosphere
Model 2 (SiB2), was assessed against 5 months of in situ measurements that were performed at two stations:
Gaize and Naqu. For the surface soil moisture, the LDAS simulations were superior to both NCEP
and SiB2, and there was more than a one-third reduction in the root mean squared errors (RMSE) for
both of the stations. Compared with the AMSR-E soil moisture retrievals, the LDAS simulations were
comparable at the Gaize station, and they were superior at the Naqu station. For the whole domain intercomparison,
the results showed that the LDAS simulation of the soil moisture field was more realistic
than the NCEP and SiB2 simulations and that the LDAS could estimate land surface states properly even
in the regions where AMSR-E failed to cover and/or during the periods that the satellite did not overpass.
For the surface energy fluxes, the LDAS estimated the latent heat flux with an acceptable accuracy
(RMSE less than 35W/m2), with a one-third reduction in the RMSE from the SiB2. For the 5-month whole
plateau simulation, the LDAS produced a much more reasonable Bowen Ratio than the NCEP, and it also
generated a clear contrast of the land surface status over the plateau, which was wet in the southeast
and dry in the northwest, during the monsoon and post-monsoon seasons. Because the LDAS only uses
globally available data sets, this study reveals the potential of the LDAS to improving the land surface
energy and water flux simulations in ungauged and/or poorly gauged regions.
