Arşiv logosu
  • Türkçe
  • English
  • Giriş
    Yeni kullanıcı mısınız? Kayıt için tıklayın. Şifrenizi mi unuttunuz?
Arşiv logosu
  • Koleksiyonlar
  • Sistem İçeriği
  • Analiz
  • Talep/Soru
  • Türkçe
  • English
  • Giriş
    Yeni kullanıcı mısınız? Kayıt için tıklayın. Şifrenizi mi unuttunuz?
  1. Ana Sayfa
  2. Yazara Göre Listele

Yazar "Akturk, Gaye" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
  • [ X ]
    Öğe
    Drought index time series forecasting via three-in-one machine learning concept for the Euphrates basin
    (Springer Heidelberg, 2024) Latifoglu, Levent; Bayram, Savas; Akturk, Gaye; Citakoglu, Hatice
    Droughts are among the most hazardous and costly natural disasters and are hard to quantify and characterize. Accurate drought forecasting reduces droughts' devastating economic effects on ecosystems and people. Eastern Anatolia is the largest and coldest geographical region of T & uuml;rkiye. Previous studies lack drought forecasting in the Eastern Anatolia (Upper Mesopotamia) Region, where agriculture is limited due to being under snow most of the year. This study focuses on the Euphrates basin, specifically the Tercan and the Tunceli meteorological stations of the Karasu River sub-basin, a vital Eastern Anatolia Region water resource. In this context, time series of 1-, 3-, 6-, 9-, and 12-month Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) values were created. The Tuned Q-factor Wavelet Transform (TQWT) method and Univariate Feature Ranking Using F-Tests (FSRFtest) were used for pre-processing and feature selection. Several models were created, such as stand-alone, hybrid, and tribrid. Machine Learning (ML) methods such as Artificial Neural Networks (ANN), Gaussian Process Regression (GPR), and Support Vector Machine (SVM) were conducted for the time series analyses. The GPR approach was concluded to perform better than the ANN and SVM at the Tercan station. In other words, GPR performs better in 80% of cases than SVM and ANN models. At the Tunceli station for the SPI output, SVM, which had a superior performance in 60% of the cases, demonstrated a performance comparable to GPR. At the same time, ANN once again exhibited an inferior performance. Similarly, for the SPEI output at the Tunceli station, no clear superiority was observed between the GPR and ANN methods. Because both methods were successful in 40% of cases. This study contributes by introducing a third concept to the stand-alone and hybrid model comparison of drought forecasting, adding tribrid models. It has been detected that the Hybrid and Tribrid ML methods lead to a 91% and 64% decrease relative root mean square error percentage compared stand-alone ML methods for SPEI and SPI in two stations. While the hybrid model at Tercan station was more successful in 80% of the cases, the hybrid model at Tercan station was more successful in 90% of the cases. While hybrid models were observed to be superior, tribrid models not only demonstrated performance close to the hybrid models but also provided advantages such as reducing computational load and shortening calculation time.
  • [ X ]
    Öğe
    Effects of Climate Change on Streamflow in the Ayazma River Basin in the Marmara Region of Turkey
    (Mdpi, 2023) Seddiqe, Khaja Haroon; Sediqi, Rahmatullah; Yildiz, Osman; Akturk, Gaye; Kostecki, Jakub; Gortych, Marta
    This study investigates the effects of climate change on streamflow in the Ayazma river basin located in the Marmara region of Turkey using a hydrological model. Regional Climate Model (RCM) outputs from CNRM-CM5/RCA4, EC-EARTH/RACMO22E and NorESM1-M/HIRHAM5 with the RCP4.5 and RCP8.5 emission scenarios were utilized to drive the HBV-Light (Hydrologiska Byrans Vattenbalansavdelning) hydrological model. A trend analysis was performed with the Mann-Kendall trend test for precipitation and temperature projections. A meteorological drought assessment was presented using the Standardized Precipitation-Evapotranspiration Index (SPEI) method for the worst-case scenario (i.e., RCP8.5). The calibrated and validated hydrological model was used for streamflow simulations in the basin for the period 2022-2100. The selected climate models were found to produce high precipitation projections with positive anomalies ranging from 22 to 227 mm. The increase in annual mean temperatures reached up to 1.8 degrees C and 2.6 degrees C for the RCP4.5 and RCP8.5 scenarios, respectively. The trend results showed statistically insignificant upward and downward trends in precipitation and statistically significant upward trends in temperatures at 5% significance level for both RCP scenarios. It was shown that there is a significant increase in drought intensities and durations for SPEI greater than 6 months after mid- century. Streamflow simulations showed decreasing trends for both RCP scenarios due to upward trend in temperature and, hence, evapotranspiration. Streamflow peaks obtained with the RCP8.5 scenario were generally lower than those obtained with the RCP4.5 scenario. The mean values of the streamflow simulations from the CNRM-CM5/RCA4 and NorESM1-M/HIRHAM5 outputs were approximately 2 to 10% lower than the observation mean. On the other hand, the average value obtained from the EC-EARTH/RACMO 22E outputs was significantly higher than the observation average, up to 32%. The results of this study can be useful for evaluating the impact of climate change on streamflow and developing sustainable climate adaptation options in the Ayazma river basin.
  • [ X ]
    Öğe
    Investigating the climate change effects on annual average streamflows in the Euphrates-Tigris basin using the climate elasticity method
    (Gazi Univ, Fac Engineering Architecture, 2021) Alivi, Abdulrezzak; Yildiz, Osman; Akturk, Gaye
    This study was conducted to investigate the response of streamflows (Q) to changes in precipitation (P), potential evapotranspiration (E-p) and drought index within the Euphrates-Tigris basin. For this purpose, 37 sub-basins that are not affected by dams were identified within the basin. Here, the sensitivity of annual average streamflows to precipitation, E-p and drought index was evaluated by the climate elasticity method proposed by Schaake [1]. With this method, the average values of the precipitation and E-p sensitivity coefficients of the streamflow (epsilon(P) and epsilon(Ep), respectively) throughout the basin were calculated as 1.50 and -0.50, respectively. Therefore, it is observed that a 10% increase (decrease) in precipitation would lead to an average increase (decrease) of 15% in streamflow, on the other hand, a 10% increase (decrease) in Ep would result in an average decrease (increase) of 5% in streamflow across the basin. Moreover, the average value of sensitivity coefficient of streamflow to drought index (epsilon((sic))) was determined as -0.47, which means that a 10% increase in the drought index will result in an average decrease of 4.7% in streamflow within the basin. Additionally, it is observed that there is a nonlinear inverse correlation between the climate change sensitivity coefficients (i.e., epsilon(P), |epsilon(Ep)| and |epsilon((sic))|) and the flow coefficient (Q/P) values of the sub-basins indicating that the decrease in streamflow would increase the sensitivity of streamflow to climatic changes. Finally, it was determined that there exist relative increases in epsilon(P), |epsilon(Ep)| and |epsilon((sic))| values from high to low elevations across the basin.

| Kırıkkale Üniversitesi | Kütüphane | Rehber | OAI-PMH |

Bu site Creative Commons Alıntı-Gayri Ticari-Türetilemez 4.0 Uluslararası Lisansı ile korunmaktadır.


Kırıkkale Üniversitesi, Kırıkkale, TÜRKİYE
İçerikte herhangi bir hata görürseniz lütfen bize bildirin

DSpace 7.6.1, Powered by İdeal DSpace

DSpace yazılımı telif hakkı © 2002-2025 LYRASIS

  • Çerez Ayarları
  • Gizlilik Politikası
  • Son Kullanıcı Sözleşmesi
  • Geri Bildirim