135
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 2. The FAO-56 PM
ET
0 and estimated ET0 values of Yulin.
For Ankang, ISO-ELM and Hargreaves were
closer to the FAO-56 PM
ET
0 values, a slight
difference exists between LSSVM, and ELM was
better than the Mc Cloud model. In this city, the
Mc Cloud estimate was also the least accurate
(
R
2
= 0.6141). This leads to the conclusion that in
this city, the ISO-ELM and empirical Hargreaves
models were the best.
