Vol.2, No 3, 2001
pp. 185-191
UDC 626.85 (045)
ESTIMATION OF FAO PENMAN C FACTOR
BY RBF NETWORKS
Slaviša Trajković1,
Branimir Todorović2, Miomir Stanković2
1Faculty of Civil
Engineering and Architecture, University of Niš,
Aleksandra Medvedeva 14, 18000 Niš, Serbia and
Montenegro,
E-mail: slavisa@mail.gaf.ni.ac.yu
2Faculty of Occupational
Safety, University of Niš, Čarnojevića 10a, 18000 Niš
Abstract. An accurate estimation of the c
factor is necessary in order to improve the validity of evapotranspiration
estimation by the FAO (United Nations Food and Agriculture Organization)
Penman method. The calculation of the c factor using the table interpolation
or regression expressions can lead to a considerable error that is directly
transferred to the estimated evapotranspiration. This paper reviews the
application of RBF (Radial Basis Function) networks to estimate the FAO
Penman c factor. The values of the c factors obtained by RBF networks were
compared to the appropriate c values produced using regression expressions.
It was shown that the RBF networks ensure a better agreement with table
c values, thus improving the accuracy of the estimation of reference crop
evapotranspiration. At the end of the paper, an example that demonstrates
the simplicity of the use of RBF networks and the accuracy of the c factor
estimation is presented.
Key words: Evapotranspiration, FAO-24
Penman, Artificial Neural Networks.
ESTIMACIJA FAO-24 PENMAN C FAKTORA
PRIMENOM RBF MREŽA
U ovom radu je prikazana estimacija FAO-24 Penman
c faktora primenom RBF mreža. Vrednosti c faktora dobijene RBF mrežom su
uporedjivane sa odgovarajućim vrednostima iz regresionih jednačina. Pokazano
je da RBF mreža obezbedjuje bolje slaganje sa tabelarnim FAO-24 Penman
c faktorima u poredjenju sa regresionim jednačinama. Na kraju rada je kroz
praktičan primer pokazana sva jednostavnost korišćenja RBF mreže kao i
pouzdanost proračuna FAO-24 c faktora.
Ključne reči: Evapotranspiracija, FAO-24
Penman, Veštačke neuronske mreže.
