Hourly gridded air temperatures of South Africa derived from MSG SEVIRI

被引:15
作者
Meyer, Hanna [1 ]
Schmidt, Johannes [2 ]
Detsch, Florian [2 ]
Nauss, Thomas [2 ]
机构
[1] Westfalische Wilhelms Univ Munster, Inst Geoinformat, Heisenbergstr 2, D-48149 Munster, Germany
[2] Philipps Univ Marburg, Fac Geog, Deutschhausstr 10, D-35037 Marburg, Germany
关键词
Air temperature; Climate; Machine leaming; Meteosat; Random Forest; South Africa; SURFACE TEMPERATURE; INTERPOLATION;
D O I
10.1016/j.jag.2019.02.006
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Monitoring of climate variables such as air temperature is gaining increasing importance under climate change. This study aimed at developing an hourly gridded 3.5 x 3.5 km air temperature (T-air) data set for entire South Africa. In a Random Forest approach, MSG SEVIRI data from 2010 to 2014 were used and related to T-air measured by 78 weather stations. An external validation on new climate stations and years that were not used for model training indicated the ability of the model to predict T-air with a RMSE of 2.61 degrees C and a R-2 of 0.89. The resulting model can be applied to the entire MSG SEVIRI time series since 2004. It hence allows for spatiotemporal pattern analysis as well as for the detection of trends which is relevant in the context of climate change.
引用
收藏
页码:261 / 267
页数:7
相关论文
共 48 条
[1]   Characteristics of the Meteosat second generation (MSG) radiometer/imager: SEVIRI [J].
Aminou, DMA ;
Jacquet, B ;
Pasternak, F .
SENSORS, SYSTEMS, AND NEXT-GENERATION SATELLITES, 1997, 3221 :19-31
[2]  
[Anonymous], 2008, HOLE FILLED SRTM GLO
[3]   Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro, Tanzania [J].
Appelhans, Tim ;
Mwangomo, Ephraim ;
Hardy, Douglas R. ;
Hemp, Andreas ;
Nauss, Thomas .
SPATIAL STATISTICS, 2015, 14 :91-113
[4]   Estimating air surface temperature in Portugal using MODIS LST data [J].
Benali, A. ;
Carvalho, A. C. ;
Nunes, J. P. ;
Carvalhais, N. ;
Santos, A. .
REMOTE SENSING OF ENVIRONMENT, 2012, 124 :108-121
[5]   The MSG-SEVIRI-based cloud property data record CLAAS-2 [J].
Benas, Nikos ;
Finkensieper, Stephan ;
Stengel, Martin ;
van Zadelhoff, Gerd-Jan ;
Hanschmann, Timo ;
Hollmann, Rainer ;
Meirink, Jan Fokke .
EARTH SYSTEM SCIENCE DATA, 2017, 9 (02) :415-434
[6]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[7]  
Didan K, 2015, MOD13Q1 MODIS TERRA, DOI [10.5067/MODIS/MOD13A3.006, DOI 10.5067/MODIS/MOD13Q1.006, 10.5067/MODIS/MOD13Q1.006]
[8]  
Didan K., 2015, MOD13C1: MODIS/Terra Vegetation Indices 16-Day L3 Global 0.05 Deg CMG V006
[9]   Evaluation of gridding procedures for air temperature over Southern Africa [J].
Eiselt, Kai-Uwe ;
Kaspar, Frank ;
Moelg, Thomas ;
Kraehenmann, Stefan ;
Posada, Rafael ;
Riede, Jens O. .
ADVANCES IN SCIENCE AND RESEARCH, 2017, 14 :163-173
[10]   Do they? How do they? WHY do they differ? On finding reasons for differing performances of species distribution models [J].
Elith, Jane ;
Graham, Catherine H. .
ECOGRAPHY, 2009, 32 (01) :66-77