Simulation model of biomass-based cogeneration plant
Missing value especially in environmental study is a common problem including in rainfall modelling. Incomplete data will affect the accuracy and efficiency in any modelling process. In this study, simulation method is used to demonstrate the efficiency of the old normal ratio inverse distance co...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/24176/ http://umpir.ump.edu.my/id/eprint/24176/ http://umpir.ump.edu.my/id/eprint/24176/1/34.%20Simulation%20study%20of%20adjusted%20spatial%20weighting%20method.pdf http://umpir.ump.edu.my/id/eprint/24176/2/34.1%20Simulation%20study%20of%20adjusted%20spatial%20weighting%20method.pdf |
| Summary: | Missing value especially in environmental study is a common problem including in rainfall
modelling. Incomplete data will affect the accuracy and efficiency in any modelling process.
In this study, simulation method is used to demonstrate the efficiency of the old normal ratio
inverse distance correlation weighting method (ONRIDCWM) in solving missing rainfall
data. The simulation study is used to identify the best parameters for correlation power
of p, percentage of missing value and sample size, n of the ONRIDCWM by simulating
for 10,000 times by varying the value of the parameters systematically. The results of the
simulation are compared with other available weighting methods. The estimated complete
rainfall data of the target station are compared and assessed with the observed data from
the neighbouring station using mean, estimated bias (EB) and estimated root mean square
error (ERMSE). The results show that ONRIDCWM is better than the other weighting
methods for the correlation power of p at least four. For illustration of the weighting
method, monthly rainfall data from Pahang has used to demonstrate the efficiency of the
method using three error indices: S-Index, mean absolute error (MAE) and correlation, R. |
|---|