Determination of land surface temperature using precipitable water based Split-Window and Artificial Neural Network in Turkey

摘要: Abstract Land surface temperature (LST) calculation utilizing satellite thermal images is very difficult due to the great temporal variance of atmospheric water vapor in atmosphere which strongly affects radiance incoming sensors. In this study, Split-Window (SW) and Radial Basis Function (RBF) methods were utilized for prediction LST using precipitable Turkey. Coll 94 algorithm was modified regional values estimated from upper-air Radiosond observations years 1990–2007 Local (LSW) algorithms generated study area. Using local Advanced Very High Resolution Radiometer (AVHRR) data, monthly mean daily sum calculated. RBF method latitude, longitude, altitude, emissivity, sun shine duration used as input variables structure. Correlation coefficients between measured obtained 99.23% (for RBF) 94.48% LSW) at 00:00 UTC 92.77% 89.98% 12:00 UTC. These meaningful statistical results suggest that LSW could be calculation.