Integrative stochastic model standardization with genetic algorithm for rainfall pattern forecasting in tropical and semi-arid environments |
| |
| Authors: | Sinan Q Salih Ahmad Sharafati Isa Ebtehaj Hadi Sanikhani Ridwan Siddique Ravinesh C Deo |
| |
| Institution: | 1. Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam;2. Faculty of Civil Engineering, Duy Tan University, Da Nang 550000, Vietnam;3. Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran https://orcid.org/0000-0003-0448-2871;4. Department of Civil Engineering, Razi University, Kermanshah, Iran;5. Environmental Research Center, Razi University, Kermanshah, Iran;6. University of Kurdistan, Agriculture Faculty, Water Engineering Department, Sanandaj, Iran;7. Research Center for Water Sciences and Engineering, University of Kurdistan, Iran;8. Northeast Climate Science Center, University of Massachusetts, Amherst, USA;9. School of Agricultural Computational and Environmental Sciences, Centre of Applied Climate Sciences, Institute of Life Science and the Environment, University of Southern Queensland, Springfield, Australia |
| |
| Abstract: | ABSTRACTClimate patterns, including rainfall prediction, is one of the most complex problems for hydrologist. It is inherited by its natural and stochastic phenomena. In this study, a new approach for rainfall time series forecasting is introduced based on the integration of three stochastic modelling methods, including the seasonal differencing, seasonal standardization and spectral analysis, associated with the genetic algorithm (GA). This approach is specially tailored to eradicate the periodic pattern effects notable on the rainfall time series stationarity behaviour. Two different climates are selected to evaluate the proposed methodology, in tropical and semi-arid regions (Malaysia and Iraq). The results show that the predictive model registered an acceptable result for the forecasting of rainfall for both the investigated regions. The attained determination coefficient (R2) for the investigated stations was approx. 0.91, 0.90 and 0.089 for Mosul, Baghdad and Basrah (Iraq), and 0.80, 0.87 and 0.94 for Selangor, Negeri Sembilan and Johor (Malaysia). |
| |
| Keywords: | genetic algorithm stationarization stochastic model periodic term rainfall forecasting |
|
|
![ORCID Icon]({"type":"image","src":"/templates/jsp/images/orcid.png"} "ORCID Icon")
https://orcid.org/0000-0003-0448-2871;4. Department of Civil Engineering, Razi University, Kermanshah, Iran;5. Environmental Research Center, Razi University, Kermanshah, Iran;6. University of Kurdistan, Agriculture Faculty, Water Engineering Department, Sanandaj, Iran;7. Research Center for Water Sciences and Engineering, University of Kurdistan, Iran;8. Northeast Climate Science Center, University of Massachusetts, Amherst, USA;9. School of Agricultural Computational and Environmental Sciences, Centre of Applied Climate Sciences, Institute of Life Science and the Environment, University of Southern Queensland, Springfield, Australia