Yazar "Veysi Kartal" seçeneğine göre listele
Listeleniyor 1 - 6 / 6
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A novel regional forecastable multiscalar standardized drought index (RFMSDI) for regional drought monitoring and assessment(Elsevier BV, 2025-03) Aamina Batool; Veysi Kartal; Zulfiqar Ali; Miklas Scholz; Farman AliDrought is a complex recurrent natural phenomenon. It is the main outcome of climate change. It has long-term impacts on agriculture, human life as well as the environment. Therefore, quantifying drought at the regional level is essential for developing sustainable policies. This study introduced a new drought index for regional drought forecasting called the Regional Forecastable Multiscalar Standardized Drought Index (RFMSDI). The RFMSDI methodology is based on Forecastable Component Analysis (FCA) and K-Component Gaussian Mixture Distribution (K-CGMD). FCA reduce dimension by focus on components that are inherently more predictable. It ensures that reduced data has a built-in ability to predict future trends by selecting the maximized forecastable components. K-CGMD is utilized to model the multimodel time series data. The study application incorporates eight meteorological stations in Türkiye's Elazig province (Baskil, Agin, Elazig, Karakocan, Keban Maden, Palu and Sivrice). The effectiveness of RFMSDI is evaluated by analyzing precipitation data over these meteorological stations of Türkiye. The comparative assessment of the research signifies the superiority of FCA for regional data aggregation. In this research, the comparative assessment of RFMSDI is evaluated against the Standardized Precipitation Index (SPI) by analyzing Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics across different time scales using various machine learning and traditional time series models. The research findings include the following: 1) K-CGMD is a better fitting approach for standardizing RFMSDI and SPI based on reduced BIC values. 2) RFMSDI has superior performance over SPI based on the lower values of RMSE and MAE. 3) Both machine learning and classical methods reveal that RFMSDI outperforms SPI in predicting droughts. 4) SPI shows localized advantages with the ELM training set at 1- and 6-month time scales but RFMSDI offers a more comprehensive and consistent tool for drought prediction, especially when tested on unseen data. In general, the findings endorse the effectiveness of RFMSDI for monitoring drought on a regional level.Öğe Advanced Soft Computing Techniques for Monthly Streamflow Prediction in Seasonal Rivers(MDPI AG, 2025-01-19) Mohammed Achite; Okan Mert Katipoğlu; Veysi Kartal; Metin Sarıgöl; Muhammad Jehanzaib; Enes GülThe rising incidence of droughts in specific global regions in recent years, primarily attributed to global warming, has markedly increased the demand for reliable and accurate streamflow estimation. Streamflow estimation is essential for the effective management and utilization of water resources, as well as for the design of hydraulic infrastructure. Furthermore, research on streamflow estimation has gained heightened importance because water is essential not only for the survival of all living organisms but also for determining the quality of life on Earth. In this study, advanced soft computing techniques, including long short-term memory (LSTM), convolutional neural network–recurrent neural network (CNN-RNN), and group method of data handling (GMDH) algorithms, were employed to forecast monthly streamflow time series at two different stations in the Wadi Mina basin. The performance of each technique was evaluated using statistical criteria such as mean square error (MSE), mean bias error (MBE), mean absolute error (MAE), and the correlation coefficient (R). The results of this study demonstrated that the GMDH algorithm produced the most accurate forecasts at the Sidi AEK Djillali station, with metrics of MSE: 0.132, MAE: 0.185, MBE: −0.008, and R: 0.636. Similarly, the CNN-RNN algorithm achieved the best performance at the Kef Mehboula station, with metrics of MSE: 0.298, MAE: 0.335, MBE: −0.018, and R: 0.597.Öğe Discharge performance of side gates with different shapes(IWA Publishing, 2025-02-10) Veysi Kartal; M. Emin Emiroglu; M. Fatih YukselFlow measurement and water level control in open channels are vital to water management. Lateral intake structures are commonly used for different purposes in civil and environmental engineering applications. Flow characteristics of rectangular, triangular, and semi-circular shapes were experimentally investigated using 357 runs under subcritical flow conditions. Correlation analysis was conducted to determine the effect of various parameters on the discharge coefficient. Upstream Froude number (F1), the ratio of the gate opening to the upstream flow depth, and the gate length to flow depth ratio are influential for all side gates. However, the ratio of the gate opening to the gate length is also influential for triangular side gates. Discharge coefficient of the semi-circular side gate is relatively higher than that of the other tested gates within the range of 0.05Öğe Evaluating variogram models and kriging approaches for analyzing spatial trends in precipitation simulations from global climate models(Springer Science and Business Media LLC, 2025-02-07) Aamina Batool; Sufian Ahmad; Ayesha Waseem; Veysi Kartal; Zulfiqar Ali; Muhammad MohsinClimate change has heightened the irregularity and unpredictability of weather patterns, influencing precipitation patterns. Accurate geographical projections of precipitation and other climatic variables are critical to sustainable water resource management and disaster preparedness. Variogram models are geostatistical techniques used to examine spatial correlation. Therefore, selecting the optimum variogram model for spatial interpolation is challenging. This study used six variogram models to assess spatial trends. Leave-one-out cross-validation (LOOCV) and K-fold cross-validation approaches are used to find the best variogram model based on metrics such as mean absolute error (MAE), root mean square error (RMSE), and mean bias. In this study, correlation data of 22 GCMs within observed data are predicted over 94 locations in Pakistan from 1950 to 2014. For evaluation, ordinary kriging (OK) and universal kriging (UK) are utilized as geostatistical approaches. The study highlights the suitability of the variogram models. Pentaspherical variogram (Pen) model is suggested as suitable model due to its minimum error metrics as well as the Hol effect (Hol) model has been considered beneficial for dealing with complicated data. From the geostatistical approaches, ordinary kriging (OK) yields the best prediction. Moreover, ordinary kriging (OK) and universal kriging (UK) both yield similar outcomes across some correlation-based data of 22 GCMs within observed data. Consequently, the implication of correlation analysis, optimum variogram models, and interpolation techniques enables the precise and accurate approach in the prediction of GCM performance. The efficiency of variogram models and interpolation approaches in managing data variability helps to enhance the consistency and interpretability of climate data.Öğe Improving the Accuracy of Groundwater Level Forecasting by Coupling Ensemble Machine Learning Model and Coronavirus Herd Immunity Optimizer(Springer Science and Business Media LLC, 2025-05-03) Ahmed M. Saqr; Veysi Kartal; Erkan Karakoyun; Mahmoud E. Abd-ElmaboudGroundwater levels are under severe pressure globally due to over-extraction, pollution, and climate change necessitating continuous monitoring for sustainable aquifer management. This study introduces a novel ensemble machine learning (En) model that integrates shallow and deep machine learning (ML) models, optimized through the coronavirus herd immunity optimizer (CHIO), for accurate groundwater level forecasting. This En model was applied to the Ergene River Basin, Türkiye, a region facing severe groundwater depletion and contamination due to intensive agricultural and industrial activities. Groundwater level data spanning 1966 to 2023 on a weekly basis from four wells were used, split into 70% for training and 30% for testing under short- and long-term scenarios. Using the partial autocorrelation function and gamma test the best lag numbers were determined for input data, reflecting aquifer heterogeneity. Score analysis, supported by statistical metrics such as the coefficient of determination (R²) and root mean square error (RMSE), was employed alongside visual aids to assess the developed En model performance. Results demonstrated that deep ML models outperformed shallow ML models achieving R² ~ 0.99 and RMSE ~ 0.5 m. The developed En model outperformed all individual ML models, with score values exceeding 200, and its predictions closely aligned with measured water levels during both testing phases. The findings underscored the developed En model’s contribution to achieving sustainable development goals (SDGs) by enhancing water-use efficiency and addressing environmental, economic, and social sustainability challenges. The proposed approach offers a reliable and adaptable solution for groundwater level forecasting, applicable to other aquifers worldwide.Öğe Innovative drought analysis via groundwater information(Elsevier BV, 2025-09) Veysi KartalDrought hazard has complicated features related to climatic and spatio-temporal characteristics, making it challenging to accurately identify and track. Contemporary approaches to drought monitoring generally use standardized drought indices due to their practical utility. Despite the availability of a various array of drought indices, their application introduces complexities in data mining and decision-making processes, potentially resulting in confused outcomes. However, this research developed a new hybrid drought index Multivariate Cluster Ensemble Drought Evaluation Index (MCEDEI) based on machine learning technique cluster analysis using groundwater data of the KB region of Türkiye to assess the groundwater drought. For the development of MCEDEI, this study used 540-time series observations (range: 1978–2022) of groundwater data from five stations to evaluate drought characteristics. Furthermore, this study used steady-state probability to determine the trend and long-term probabilities of the drought index in the KB region of Türkiye. The results show that the NN (near normal) class was found to be dominant with a probability of 70.41% on a 1-month time scale, while NN was found to be dominant with a high probability of 65.94% on a 3-month time scale. The probability of the NN class was found to be equally high when the time scale was extended to 6, 9 and even 48 months. MD (moderate drought) remains important, and SD (severe drought) increases compared to SW (severe wet) classes. Findings shpw that there are significant changes in groundwater behaviour at different time scales. Short-term stability is characterized by the dominance of the NN class, while long-term scales show a trend towards extreme dry and wet conditions with a decrease in neutrality. As a result, Türkiye may face drought challenges in the future based on the findings.
