138
Zhang
et al
.,
Improved online sequential extreme learning machine for simulation of daily reference evapotranspiration
Tecnología y Ciencias del Agua
, vol. VIII, núm. 2, marzo-abril de 2017, pp. 127-140
•
ISSN 2007-2422
Figure 5. The FAO-56 PM ET0 and estimated
ET
0 values of Xi’an.
had 5274 and 5488 estimates lower than the
10% error, respectively. They were followed
by Hargreaves, Priestley-Taylor and, lastly,
McCloud (1955), which had the highest error
at 64.60%. For Ankang, the LSSVM was ranked
as the second best, followed by the ELM, Mc
Cloud, Hargreaves and, finally, Priestley-Taylor.
For Hangzhong, the LSSVM was ranked as the
second best, followed by ELM, Hargreaves, Mc
Cloud, and Priestley-Taylor, which had 28.49,
