Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bestami Taşar has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    COMPARATIVE EVALUATION OF MACHINE LEARNING-BASED MODELS FOR RAINFALL–RUNOFF PREDICTION

    by Bestami Taşar

    Accurate rainfall–runoff prediction is important in hydrological modeling. However, watershed processes are nonlinear and dynamic. This study examined the effect of different input configurations on daily streamflow prediction using data-driven methods. A total of 1,826 daily observations covering the period 01/01/2020–09/13/2025 were used. The dataset was split into 1,461 for training and 365 for testing. Three model sets were developed and evaluated using Multiple Linear Regression (MLR), Multilayer Perceptron (MLP), M5 Model Tree (M5 TREE), and Random Tree (RT). Model performance was assessed using RMSE, MAE, MAPE, NSE, R, and R². The results showed that prediction accuracy improved as the input structure became more comprehensive. Model Set 3 produced the best overall results. MLP3 achieved the lowest RMSE (3.582 m³/s) and the highest NSE (0.974) and R² (0.974). M5 TREE3 produced the lowest MAE (2.118 m³/s) and MAPE (4.601%). In contrast, RT models showed weaker and less stable performance. Overall, the results showed that input configuration is as important as algorithm selection in rainfall–runoff modeling. The findings also indicated that nonlinear machine learning models can provide more reliable predictions when suitable lagged variables are included.

  • Open Access

    Examination of Flow in a Chute Spillway During Flood Conditions Using a 3D Numerical Model

    by Hakan Varçin, Fatih Üneş, Ercan Gemici, Bestami Taşar

    Dams are built for many purposes, one of the most important of which is to reduce the impact of floods. They release water downstream in a controlled manner through spillway structures. Spillways are critical structures that must be designed with low‐risk criteria to withstand floods that occur once every thousand years. This paper presents a three‐dimensional CFD simulation of the flow over a prototype spillway and validates the results with experimental data. The spillway belongs to the Çatalan Dam, which was constructed in 1985 for hydroelectric power generation. A 1:100 physical model of the Çatalan Dam spillway was built based on Froude similarity, and velocities in the discharge channel were measured at specific cross‐sections and points. The numerical model used the Volume of Fluid (VOF) method and the k‐ε Standard model. The velocity values from the numerical model were compared with experimental velocity values, showing good agreement. Additionally, pressure values were obtained from the numerical model, and cavitation index values were computed accordingly. The results indicated no cavitation risk in the prototype spillway, as the index values remained above 0.2 at all points in the cross‐sections.

  • Open Access

    Investigation of the Temperature Performance of Bitumen Modified with Egg Shell Waste

    by İbrahim Erginer, Ömer Faruk Cansız, Ali Tuncay Özyılmaz, Nurullah Karaca, Bestami Taşar

    This study was conducted to improve the heat performance of bitumen. The effect of eggshells on the performance of bitumen was investigated. Eggshell waste was ground and mixed with bitumen at 1%, 2%, and 3% by weight. Sulfuric acid was used as a catalyst for maximum interaction of eggshells with bitumen. The high heat performance and rutting resistance of modified bitumen formed at 160 °C were determined by the Dynamic Shear Rheometer (DSR) test. In addition, the low heat performance of modified bitumen was determined with the Bending Beam Rheometer (BBR) test. It was determined that the high heat performance of modified bitumen increased by 16.22% and the low heat performance (creep values) by 11.43% compared to pure bitumen. In addition, it was determined that the rutting resistance values of modified bitumen increased compared to pure bitumen.

  • Open Access

    3D Modeling of A Novel Curved Submerged Vane With Variable Profile for the Protection of Meandering River Beds

    by Bestami Taşar, Fatih Üneş, Ercan Gemici, Hakan Varçin

    Due to scour problems caused by flooding or high and turbulent flow in the riverbed, river regulation structures are important on the outer meander. Submerged vanes are a new method for meandering open channels and river regulation. In this study, initially, using a flow discharge of 20 L/s, the numerical results of the no‐vane (V0) and three‐array with six submerged vanes (V1) in meandering open channel flows have been calibrated with experimental results. Then, the submerged vane cases with no angle (CV1) and 20° angle (CV2–CV3) were investigated numerically. In the presented numerical models, continuity, momentum, and turbulence model equations were used. The k–ε model was used for turbulence viscosity. The results of the numerical model were compared with the experimental model results. Additionally, flow velocities and depth were analyzed using numerical models. In the outer meander, the three‐array with curved vane structures (CV1, CV2 and CV3) affected the flow velocity by 77%–92% in the region behind the vane. The flow velocities were investigated along with depth using the numerical modeling and found that the mean velocity was reduced by 54%–83% along the depth. As an effective method of reducing flow velocities and directing flows, it is also recommended that submerged vane structures be used.


  • Open Access

    Amik Ovasında Buharlaşma Tahmini için Çoklu Çıktılı Yapay Sinir Ağları Modeli

    by Samed Göçmen, Fatih Üneş, Bestami Taşar, Ömer Faruk Cansız

    Yeryüzü su seviyesinde önemli miktarda kayıplara sebep olan buharlaşma, su kaynakları mühendisliğinin projelendirilmesi, suyun idaresi ve kontrolü gibi konularda önem taşımaktadır. Bu çalışma, Amik Ovası'nda aylık buharlaşma tahminini geliştirmek amacıyla çoklu çıktılı yapay sinir ağları (YSA) modelini kullanmaktadır. Geleneksel tahmin yöntemlerine kıyasla YSA’nın daha düşük hata oranı ile tahmin yapabildiği görülmüştür. Veriler 1970-2025 yılları arasında toplanmış ve model eğitiminde kullanılmak üzere ön işleme tabi tutulmuştur. Modelin doğruluğu R², KOH ve YOH gibi istatistiksel ölçütler ile değerlendirilmiştir. Sonuçlar, YSA modelinin buharlaşma tahmininde başarılı olduğunu ve özellikle yarı kurak bölgelerde uygulanabilirliğini göstermektedir. Modelin farklı iklim bölgelerinde test edilmesi önerilmektedir. Öte yandan çoklu çıktılı yapay sinir ağları (YSA) modeli buharlaşma çalışmalarında ilk defa denenmesine rağmen oldukça iyi sonuçlar vermiştir.


  • Forecasting of Suspended Sediment in River Using Artificial Intelligence Methods

    by Fatih Üneş, Bestami Tasar, Hakan Varçin

    Accurate estimation of the amount of suspended sediment in the river is important for protecting and managing water structures. By accurately estimating the amount of suspended matter in streams, important information is obtained by determining the life of water structures, water pollution, and river transportation. In this study, the West Branch Neversink River near Claryville, USA, was chosen as the study area. 567 real-daily data measured between 2021-2023 were used as the study data. As input parameters of the model; air temperature, precipitation, stream flow and turbidity were selected and sediment amount was estimated. Multi Linear Regression (MLR), M5 Decision Tree (M5 Tree) and Artificial Neural Network (ANN) models were used in sediment estimation. Model results were evaluated according to statistical criteria. As a result, ANN model showed best performance.

  • Open Access

    Kıyıya Dik Kum Barlarının Bitiş Noktasının Yapay Zeka Yöntemleriyle Tahmini

    by Mert Sabancıoğlu, Fatih Üneş, Mustafa Demirci, Bestami Taşar, Yunus Ziya Kaya

    Kıyıya dik katı madde sonucu oluşan kumbar parametrelerinin tahmini, kıyı yapılarının tasarımı için oldukça önemlidir. Bu çalışmada, kıyıya dik kum barlarının bitiş noktasının kıyı çizgisine olan mesafesi (Xs) tahmini için deneysel veriler kullanılmıştır. Deneylerde 5 farklı ortalama tane çapı d50=0,25, 0,32, 0,45, 0,62 ve 0,80 mm ve 1/8, 1/10 ve 1/15 olmak üzere 3 farklı taban eğimi kullanılmıştır. Bar bitiş noktasının kıyı çizgisine olan mesafesinin tahmini için farklı kıyı eğimleri, farklı tane çaplarındaki kıyı malzemeleri, farklı dalga periyodu ve dalga dikliği girdi parametresi olarak kullanılarak çoklu doğrusal regresyon, destek vektör regresyonu, basit üyelik fonksiyonları ve bulanık kural oluşturma tekniği (Simple Membership Functions and Fuzzy Rule Generation Technique–SMRGT) ve uyarlamalı ağ tabanlı sistemi yöntemleri ile modeller oluşturulmuştur. Model sonuçlarına göre uyarlamalı ağ tabanlı bulanık çıkarım sistemi modelinin diğer iki modele göre daha düşük hata değerleri verdiği ve determinasyon katsayısına göre daha başarılı olduğu görülmüştür.

  • Open Access

    Adana İli Referans Evapotranspirasyon Miktarının Bulanık Smrgt, Anfis ve Çoklu Doğrusal Regresyon Kullanılarak Tahmini

    by Serkan Demi̇rEl, Yunus Ziya Kaya, Bestami Taşar, Fatih Üneş, Mustafa Demi̇rCi̇

    Hidrolik tasarım süreci ve tarımsal sulama yönetiminde evapotranspirasyonun tahmini oldukça önemlidir. Bu çalışmada günlük evapotranspirasyon miktarı tahmini için ortalama sıcaklık (S), bağıl nem (N), rüzgâr hızı (R), solar radyasyon (SR) parametreleri kullanılmıştır. Penman-Monteith, FAO (Food and Agriculture Organization) tarafından önerilen standart bir metottur. Bu metoda göre günlük evapotranspirasyon tahmini yapılmış (ET0), referans olarak da Penman Monteith yöntemi kabul edilmiştir. Günlük evapotranspirasyon miktarının tahmini için Basit Üyelik Fonksiyonları ve Bulanık Kural Oluşturma Tekniği (Bulanık SMRGT) ve Adaptif Sinirsel Bulanık Çıkarım sistemi (ANFİS) yöntemleri kullanılmıştır. Elde edilen değerler klasik bir yöntem olan Çoklu Doğrusal Regresyon (ÇDR) sonuçları ile karşılaştırılmıştır. Modellerin tahmin sonuçları referans evapotranspirasyon değerleri ile kıyaslanmış ve her iki modelin de kararlı sonuçlar verdiği gözlenmiştir.


  • Open Access

    Experimental and Numerical Study on Flow Control Using 3-Array Submerged Vane in Laboratory Channel Bend

    by Bestami Taşar, Fatih Üneş, Ercan Gemici, Martina Zelenakova

    Regulation structures such as submerged vane are needed to reduce and eliminate environmental damage due to increased flooding in rivers. In particular, scours on the outer bank due to increased flow velocities cause the river bed to change and deteriorate. In this study, the effect on flow velocities was investigated experimentally by using 3-array submerged vane structures in areas close to the outer bank. The experimental vane results were performed in the open channel setup. The Computational Fluid Dynamics (CFD) results obtained with the numerical model were also verified and compared with experimental results. It has been observed that the CFD model gives results close to the real experimental results. The standard-based k-ε model was used as the turbulence model. In the outer meander, the 3-array submerged vane with a 3-vane structure was found to affect the flow velocity by 16–27% in the region behind the vane. The flow velocities were investigated along with depth using the CFD and found that the mean velocity was reduced by 14–21% along the depth. It is also recommended that submerged vane structures can be applied as an effective method in reducing flow velocities and directing flows.