Please use this identifier to cite or link to this item:
|Title:||Downscaling CHIRPS precipitation data: an artificial neural network modelling approach||Authors:||Retalis, Adrianos
Tymvios, Filippos S.
Katsanos, Dimitrios K.
|Keywords:||Climate models;Deep neural networks;Gages;Geostationary satellites;Neural networks;Precipitation (meteorology);Rain gages;Satellite imagery||Category:||Civil Engineering||Field:||Engineering and Technology||Issue Date:||3-Jul-2017||Publisher:||Taylor and Francis Ltd.||Source:||International Journal of Remote Sensing, 2017, Volume 38, Issue 13, Pages 3943-3959||metadata.dc.doi:||http:/dx.doi.org/10.1080/01431161.2017.1312031||Abstract:||The Climate Hazards Group Infrared Precipitation with Station data (CHIRPS) is a high-resolution climatic database of precipitation embracing monthly precipitation climatology, quasi-global geostationary thermal infrared satellite observations from the Tropical Rainfall Measuring Mission (TRMM) 3B42 product, atmospheric model rainfall fields from National Oceanic and Atmospheric Administration–Climate Forecast System (NOAA CFS), and precipitation observations from various sources. The key difference with all other existing precipitation databases is the high-resolution of the available data, since the inherent 0.05° resolution is a rather unique threshold. Monthly data for the period from January 1999 to December 2012 were processed in the present research. The main aim of this article is to propose a novel downscaling method in order to attain high resolution (1 km × 1 km) precipitation datasets, by correlating the CHIRPS dataset with altitude information and the normalized difference vegetation index from satellite images at 1 km × 1 km, utilizing artificial neural network models. The final result was validated with precipitation measurements from the rain gauge network of the Cyprus Department of Meteorology.||URI:||http://ktisis.cut.ac.cy/handle/10488/10093||ISSN:||01431161||Rights:||© 2017 Informa UK Limited, trading as Taylor & Francis Group||Type:||Article|
|Appears in Collections:||Άρθρα/Articles|
Show full item record
checked on Feb 24, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.