Browsing by Author "Sales, Ali Kozekalani"

Now showing 1 - 3 of 3

Citation - WoS: 15
Citation - Scopus: 16
Estimating the short-term and long-term wind speeds: implementing hybrid models through coupling machine learning and linear time series models
(SPRINGER INT PUBL AG, 2020) Saeid Mehdizadeh; Ali Kozekalani Sales; Mir Jafar Sadegh Safari; Sales, Ali Kozekalani; Safari, Mir Jafar Sadegh; Kozekalani Sales, Ali; Mehdizadeh, Saeid
Wind speed data are of particular importance in the design and management of wind power projects. In the current study three types of linear time series models including autoregressive (AR) moving average (MA) and autoregressive moving average (ARMA) were employed to estimate short-term (i.e. daily) and long-term (i.e. monthly) wind speeds. The required data were gathered respectively from the Tabriz and Zahedan stations in the northwest and southeast of Iran. The MA models outperformed the AR and ARMA on the both daily and monthly scales. Daily and monthly wind speed values as a function of lagged wind speed data were then estimated using two machine learning models of random forests (RF) and multivariate adaptive regression splines (MARS). It was found that the RF and MARS provided similar results, however RF performed slightly better than the MARS. Finally the stand-alone time series and machine learning models were coupled to improve the accuracy of the wind speed estimation. Accordingly the hybrid RF-AR RF-MA RF-ARMA MARS-AR MARS-MA and MARS-ARMA models were implemented. It was concluded that the hybrid models outperformed the stand-alone RF and MARS for both short- and long-term wind speed estimations where the RF-AR and MARS-AR hybrid models provided the best performances. The hybrid models tested in the present study could be effective alternatives to the stand-alone machine learning-based RF and MARS models for the estimation of wind speed time series.
Citation - WoS: 104
Citation - Scopus: 119
Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models
(Elsevier B.V., 2019) Farshad Fathian; Saeid Mehdizadeh; Ali Kozekalani Sales; Mir Jafar Sadegh Safari; Sales, Ali Kozekalani; Fathian, Farshad; Safari, Mir Jafar Sadegh; Kozekalani Sales, Ali; Mehdizadeh, Saeid
Prediction of river flow as a fundamental source of hydrological information plays a crucial role in various fields of water projects. In this study at first the capabilities of two time series analysis approaches namely self-exciting threshold autoregressive (SETAR) and generalized autoregressive conditional heteroscedasticity (GARCH) models then three artificial intelligence approaches including artificial neural networks (ANN) multivariate adaptive regression splines (MARS) and random forests (RF) models were investigated to predict monthly river flow. For this purpose monthly river flow data of Brantford and Galt stations on Grand River Canada for the period from October 1948 to September 2017 were used and their performances were evaluated based on various evaluation criteria. The SETAR model showed better performance than the GARCH one in prediction of river flows at the stations of study. Additionally the stand-alone MARS and RF models performed slightly better than the ANN. Next hybrid models were developed by coupling the used ANN MARS and RF models with SETAR and GARCH models as the non-linear time series models. The performance of various models presented in this study indicated that the new hybrid models demonstrated a much better performance compared with the stand-alone ones at both stations. Among the developed hybrid models the RF-SETAR models generally had the best accuracy to improve the river flows modeling. As a result it can be concluded that the presented methodology can be used to predict hydrological time series such as river flow with a high level of accuracy. © 2019 Elsevier B.V. All rights reserved.
Citation - WoS: 18
Citation - Scopus: 22
Urmia lake water depth modeling using extreme learning machine-improved grey wolf optimizer hybrid algorithm
(SPRINGER WIEN, 2021) Ali Kozekalani Sales; Enes Gul; Mir Jafar Sadegh Safari; Hadi Ghodrat Gharehbagh; Babak Vaheddoost; Sales, Ali Kozekalani; Ghodrat Gharehbagh, Hadi; Vaheddoost, Babak; Safari, Mir Jafar Sadegh; Gul, Enes
Lake water level changes are relatively sensitive to the climate-born events that rely on numerous phenomena e.g. surface soil type adjacent groundwater discharge and hydrogeological situations. By incorporating the streamflow groundwater evaporation and precipitation parameters into the models Urmia lake water depth is simulated in the current study. For this 40 years of streamflow and groundwater recorded data respectively collected from 18 and 9 stations are utilized together with evaporation and precipitation data from 7 meteorological stations. Extreme learning machine (ELM) is hybridized with four different optimizers namely artificial bee colony (ABC) ant colony optimization for continuous domains (ACOR) whale optimization algorithm (WOA) and improved grey wolf optimizer (IGWO). In the analysis 13 various scenarios with multiple input combinations are used to train and test the employed models. The best scenarios are then opted based on the performance metrics which are applied to assess the accuracy of the methods. According to the results the hybrid ELM-IGWO shows better performance compared to the ELM-ABC ELM-ACOR and ELM-WOA approaches. Results indicate that the groundwater and persistence of the lake water depth have effective roles in models while incorporating higher number of variables can lower the performance of the models. Statistical analysis showed a 62% improvement in the performance of ELM-IGWO in comparison to the ELM-WOA with regard to the root mean square error. The promising outcomes obtained in this study may encourage the application of the utilized algorithms for modeling alternative hydrological problems.