137
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 4. The FAO-56 PM ET0 and estimated
ET
0 values of Hanzhong.
The total
ET
0 estimation of every model is
compared in table 7 because of its importance
in irrigation management. The ISO-ELM clearly
performed better than the other models from
the relative error, which was 4.76, 0.23, 0.02 and
0.54%, respectively. In four of the cities, it gave
the closest estimate to the total FAO-56 PM
ET
0
during the validation period.
For Yulin, the ELM and LSSVM had the
same accuracy, which was the second best, and
