 |
| Titel |
Spatial Ensemble Postprocessing of Precipitation Forecasts Using High Resolution Analyses |
| VerfasserIn |
Moritz N. Lang, Irene Schicker, Alexander Kann, Yong Wang |
| Konferenz |
EGU General Assembly 2017
|
| Medientyp |
Artikel
|
| Sprache |
en
|
| Digitales Dokument |
PDF |
| Erschienen |
In: GRA - Volume 19 (2017) |
| Datensatznummer |
250139308
|
| Publikation (Nr.) |
 EGU/EGU2017-2522.pdf |
|
|
|
|
|
| Zusammenfassung |
| Ensemble prediction systems are designed to account for errors or uncertainties in the
initial and boundary conditions, imperfect parameterizations, etc. However, due to
sampling errors and underestimation of the model errors, these ensemble forecasts
tend to be underdispersive, and to lack both reliability and sharpness. To overcome
such limitations, statistical postprocessing methods are commonly applied to these
forecasts.
In this study, a full-distributional spatial post-processing method is applied to short-range
precipitation forecasts over Austria using Standardized Anomaly Model Output Statistics
(SAMOS). Following Stauffer et al. (2016), observation and forecast fields are
transformed into standardized anomalies by subtracting a site-specific climatological
mean and dividing by the climatological standard deviation. Due to the need of
fitting only a single regression model for the whole domain, the SAMOS framework
provides a computationally inexpensive method to create operationally calibrated
probabilistic forecasts for any arbitrary location or for all grid points in the domain
simultaneously.
Taking advantage of the INCA system (Integrated Nowcasting through Comprehensive
Analysis), high resolution analyses are used for the computation of the observed climatology
and for model training. The INCA system operationally combines station measurements and
remote sensing data into real-time objective analysis fields at 1 km-horizontal resolution and
1 h-temporal resolution. The precipitation forecast used in this study is obtained
from a limited area model ensemble prediction system also operated by ZAMG.
The so called ALADIN-LAEF provides, by applying a multi-physics approach, a
17-member forecast at a horizontal resolution of 10.9 km and a temporal resolution of 1
hour.
The performed SAMOS approach statistically combines the in-house developed high
resolution analysis and ensemble prediction system. The station-based validation of 6 hour
precipitation sums shows a mean improvement of more than 40% in CRPS when compared to
bilinearly interpolated uncalibrated ensemble forecasts. The validation on randomly
selected grid points, representing the true height distribution over Austria, still
indicates a mean improvement of 35%. The applied statistical model is currently set up
for 6-hourly and daily accumulation periods, but will be extended to a temporal
resolution of 1-3 hours within a new probabilistic nowcasting system operated by
ZAMG. |
|
|
|
|
|
|