Share Email Print
cover

Proceedings Paper

Increasing spatial resolution of CHIRPS rainfall datasets for Cyprus with artificial neural networks
Author(s): Filippos Tymvios; Silas Michaelides; Adrianos Retalis; Dimitrios Katsanos; Jos Lelieveld
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The use of high resolution rainfall datasets is an alternative way of studying climatological regions where conventional rain measurements are sparse or not available. Starting in 1981 to near-present, the CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data) dataset incorporates a 5km×5km resolution satellite imagery with in-situ station data to create gridded rainfall time series for trend analysis, severe events and seasonal drought monitoring. The aim of this work is to further increase the resolution of the rainfall dataset for Cyprus to 1km×1km, by correlating the CHIRPS dataset with elevation information, the NDVI index (Normalized Difference Vegetation Index) from satellite images at 1km×1km and precipitation measurements from the official raingauge network of the Cyprus’ Department of Meteorology, utilizing Artificial Neural Networks. The Artificial Neural Networks’ architecture that was implemented is the Multi-Layer Perceptron (MLP) trained with the back propagation method, which is widely used in environmental studies. Seven different network architectures were tested, all with two hidden layers. The number of neurons ranged from 3 to10 in the first hidden layer and from 5 to 25 in the second hidden layer. The dataset was separated into a randomly selected training set, a validation set and a testing set; the latter is independently used for the final assessment of the models’ performance. Using the Artificial Neural Network approach, a new map of the spatial analysis of rainfall is constructed which exhibits a considerable increase in its spatial resolution. A statistical assessment of the new spatial analysis was made using the rainfall ground measurements from the raingauge network. The assessment indicates that the methodology is promising for several applications.

Paper Details

Date Published: 12 August 2016
PDF: 8 pages
Proc. SPIE 9688, Fourth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2016), 96880G (12 August 2016); doi: 10.1117/12.2242820
Show Author Affiliations
Filippos Tymvios, The Cyprus Institute (Cyprus)
Silas Michaelides, The Cyprus Institute (Cyprus)
Cyprus Univ. of Technology (Cyprus)
Adrianos Retalis, National Observatory of Athens (Greece)
Dimitrios Katsanos, National Observatory of Athens (Greece)
Jos Lelieveld, The Cyprus Institute (Cyprus)
Max Planck Institute for Chemistry (Germany)


Published in SPIE Proceedings Vol. 9688:
Fourth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2016)
Kyriacos Themistocleous; Diofantos G. Hadjimitsis; Silas Michaelides; Giorgos Papadavid, Editor(s)

© SPIE. Terms of Use
Back to Top