Muberra Erdogan

Muberra Erdogan

Auto-generated profile, based on publicly available information

Muberra Erdogan

Department of Biosystem Engineering, Agriculture Faculty, Tokat Gaziosmanpasa University, Tokat, Turkey

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 May 2023 in Hydrological Sciences Journal
Verified
Journal Article
Closed access
DSDilek Sabanci
Dilek Sabanci
KYKadri Yurekli
Kadri Yurekli
MCMehmet Murat Comert
Mehmet Murat Comert
Serhat KILIÇARSLANSerhat KILIÇARSLAN
Serhat KILIÇARSLAN
MEMuberra Erdogan
Muberra Erdogan
In this study, it was aimed to estimate the reference evapotranspiration (ET0) due to some limitations of the FAO-56 Penman-Monteith (FAO 56-PM) approach by using alternative machine learning models such as Long Short-Term Memory (LSTM), Artificial Neural Networks (ANN), Radial Basis Functions Regression (RBFreg), Sequential Minimal Optimization Regression (SMOreg), and Multivariate Adaptive Regression Splines (MARS). It makes an important contribution to the estimation success of the ET0 of 12 stations with variable climate characteristics in the Central Anatolian Region (CAR) would be. The performances of the selected models were compared with the R2, MAE, and RMSE error metrics which were frequently cited in the literature, and also with the PI index which was changed depending on Relative Root Mean Square Error (RRMSE) and Correlation Coefficient (r). LSTM, ANN, and MARS models provided the best performance in 8, 3, and 1 stations, respectively. As a result, the R2, MAE, RMSE, and PI values of the selected models from each station vary in the range of 0.987-0.999, 1.948-4.567, 2.671-6.659, and 1.544-4.018, respectively.

15 March 2025 in Natural Hazards
Verified
Journal Article
Open access
PDF file
MKMuberra Erdogan Karaagacli
Muberra Erdogan Karaagacli
KYKadri Yurekli
Kadri Yurekli
MCMehmet Murat Comert
Mehmet Murat Comert
NMNurcan Menevse
Nurcan Menevse
This study aimed to shed light on the extent to which the changing climate would affect the fire risk in forests in Turkey. For this purpose, statistical approaches and indices were applied to some climate parameters in 39 provinces with forest presence. A statistically significant increasing trend according to Şen approaches, named ITA and IPTA, was detected in the temperature datasets of almost all provinces between May and October, which was referred to as the “forest fire period” in Turkey. The annual Lang index showed that there was a tendency towards desertification and aridification in the provinces. The monthly Lang index also pointed out semi-arid and arid climates from May to September in almost all provinces. The Ångström index classifying fire risk showed the probability of fire increasing between June and September for many provinces. These findings draw attention to the impact of climate change on possible forest fires in Turkey.


5 September 2025 in Natural Hazards
Verified
Journal Article
Open access
PDF file
MKMuberra Erdogan Karaagacli
Muberra Erdogan Karaagacli
KYKadri Yurekli
Kadri Yurekli
MCMehmet Murat Comert
Mehmet Murat Comert
NMNurcan Menevse
Nurcan Menevse

30 December 2025 in Journal of Agricultural Faculty of Gaziosmanpasa University
Verified
Journal Article
Closed access
MKMüberra Erdoğan Karaağaçlı
Müberra Erdoğan Karaağaçlı
MCMehmet Murat Cömert
Mehmet Murat Cömert
KYKadri Yürekli
Kadri Yürekli
The source of water, the basic need of all living things in nature, is rainfall. When the same amount of rainfall is insufficient or does not fall globally, some regions experience drought problems. In some areas, floods occur due to excessive rainfall. Apart from the normal process of drought and flood, human interventions such as global warming also play an active role in the occurrence of both natural disasters. In order to track drought, several moisture indices have been developed in the literature. Moisture conditions and the extent of a water deficit in a particular area are usually ascertained using moisture indices, characterizing the equilibrium between water inflows and outflows. In this study, Thornthwaite moisture index (TMI) was used to evaluate moisture deficit. The study was conducted in the provinces of Tokat, Kayseri, Ankara, Konya, Karaman, Afyon, Denizli and Burdur. The first effort for this purpose was made according to the Innovative Polygon Trend Analysis (IPTA) of seasonal variation of rainfall and potential evapotranspiration (PET) values. Regular polygons were not obtained at any station in both data sets. Although precipitation data showed a general decreasing trend in all stations during the summer months except June, PET values had the opposite pattern. The monthly TMI index for all stations showed that there was a moisture deficit from April (except for the Afyon station) to October. A striking finding in the annual TMI results was that negative values were detected at all stations. These findings will contribute to relevant decision makers in water-related planning and awareness studies.

10 December 2019 in Turkish Journal of Agriculture - Food Science and Technology
Verified
Journal Article
Open access
PDF file
MEMüberra Erdoğan
Müberra Erdoğan
KYKadri Yürekli
Kadri Yürekli
MCMehmet Murat Cömert
Mehmet Murat Cömert
Standardized Precipitation Index (SPI) is used to determine dry and humid periods according to the cumulative probability method at different time scales. . In this study, the rainfall data between the years of 1980-2018 belonging to of Kayseri Meteorology Station was simulated by CLIGEN stochastic climatic data generator. SPI indices calculated by using observed and simulated precipitation were evaluated with the statistical methods at the time scales of 3-, 6-, 9- and 12- months. The SPI values of 3-, 6-, 9- and 12- month which are observed and simulated with CLIGEN are close to each other and the performance of the model is very high in calculating the SPI values of these time series. However, as the time period increased, the model's representative ability decreased.