Evaluation of WRF and artificial intelligence models in short-term rainfall, temperature and flood forecast (case study)
- PDF / 1,621,965 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 128 Views
Ó Indian Academy of Sciences (0123456789().,-volV)(0123456789( ).,-volV)
Evaluation of WRF and artiBcial intelligence models in short-term rainfall, temperature and Cood forecast (case study) EMADEDDIN SHIRALI1, ALIREZA NIKBAKHT SHAHBAZI1,* , HOSSEIN FATHIAN1, NARGES ZOHRABI1 and ELHAM MOBARAK HASSAN2 1
Department of Water Resources Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran. Department of Environment, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran. *Corresponding author. e-mail: [email protected] [email protected] 2
MS received 16 July 2019; revised 25 May 2020; accepted 26 May 2020
Flood prediction is very critical for eDcient use of Cood control reservoirs, and earthen and concrete levees systems. As a result, Cood prediction has a great importance in catchment areas. In this study, rainfall and air temperature were predicted in Karun-4 basin in southwest of Iran by using three different models including WRF numerical model, ANN, and SVM model in order to evaluate accuracy in Cood forecasting. The rainfall and air temperature prediction and Cood forecasting results using different schemas of WRF model indicated that MYJLG schema has more accuracy than other schemas. Partial mutual information (PMI) algorithm was used in order to determine the eAective input variables in ANN and SVM models. The results of using PMI algorithm showed that rainfall at rain gauge stations in the next 6 hrs indicated that the eAective variables included relative humidity, current rain status (present rainfall), rainfall in 6 hrs ago, and rainfall and temperature of 12 hrs ago. Also, the PMI algorithm results for predicting air temperature in the next 6 hrs showed that the eAective input variables including the temperature of 18 hrs ago, current temperature, temperature of 12 hrs ago, and temperature of 6 hrs ago. The comparison between the peak discharge and runoA height values of the predicted Cood hydrograph in different models showed that SVM model had more eDciency and accuracy than the other two models in predicting rainfall, air temperature, and Cood hydrograph. Keywords. Rainfall prediction; WRF model; support vector machine; Cood events.
1. Introduction An accurate Cood forecasting with long lead time could have a great value for Cood prevention and utilization. The rainfall short-term prediction is very important for watershed hydrologic forecasting with a short response time, especially, under the global warming and extreme weather condition. Warning of extreme atmospheric phenomena like heavy rainfall caused by storms, is one of
the reasons for developing the very short-term prediction systems along with the radar data use, in which lots of studies have been accomplished for that Beld. Accurate Cood forecasting depends on accurate precipitation and temperature estimation. Extremely heavy rainfall at shorter time scales is particularly difBcult to predict in mountainous terrains, and continue to be a challenge to operational and research community (Das et al. 2008; Li et al. 2017). R
Data Loading...
