SDG 13 · İklim Eylemi · SDG · Erzincan Binali Yıldırım Üniversitesi

Yazarlar

Yayınlar

Yeniden eskiye Eskiden yeniye

ArticleAçık Erişim2026/r/ebyu/19324
Teknoloji, Yenilenebilir Enerji ve Sürdürülebilir Büyüme Ekseninde Çevre Kalitesi: CS-ARDL Analizi
Şakalak, Ayşenur; Akın, Fatih; Dinçer, Selin
Amaç: Bu çalışmada, 1990-2022 döneminde G-7 ülkelerinde yenilenebilir enerji, sürdürülebilir büyüme ve araştırma-geliştirme (Ar-Ge) harcamalarının çevre kalitesi üzerindeki etkilerinin incelenmesi amaçlanmaktadır. Yöntem: Çalışmada yenilenebilir enerji, sürdürülebilir büyüme ve Ar-Ge harcamalarının çevre kalitesi üzerindeki etkileri incelenirken panel CS-ARDL yöntemi kullanılmıştır. Bulgular: DH eşbütünleşme testi sonuçları, karbon emisyonları ile incelenen değişkenler arasında uzun dönemli bir eşbütünleşme ilişkisi bulunduğunu doğrulamaktadır. CS-ARDL analizi bulguları, ekonomik büyümenin başlangıçta karbon emisyonlarını artırdığını, ancak belirli bir gelir seviyesinden sonra bu etkinin tersine dönerek emisyonları azalttığını göstermektedir. Bu sonuç, Çevresel Kuznets Eğrisi (ÇKE) hipotezinin G-7 ülkeleri için geçerliliğini desteklemektedir. Ayrıca, yenilenebilir enerji tüketimi ve Ar-Ge harcamalarının karbon emisyonlarını azaltıcı yönde etkide bulunduğu tespit edilmiştir. Özgünlük: G-7 ülkeleri hem ekonomik büyüklükleri hem de Ar-Ge yatırımları bakımından küresel ölçekte öncü konumda yer almaktadır. Bu ülkelerin çevre üzerindeki etkilerinin kapsamlı ve güncel verilerle analiz edilmesi, yalnızca akademik literatüre katkı sağlamakla kalmayıp, aynı zamanda politika yapıcılar için pratik ve uygulanabilir öneriler sunma potansiyeli taşımaktadır. Dolayısıyla bu çalışma, G-7 ülkeleri özelinde yenilenebilir enerji, sürdürülebilir büyüme, teknoloji ve çevre kalitesi arasındaki ilişkileri inceleyerek literatüre özgün bir katkı sunmayı amaçlamaktadır.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/19308
LandTrendr Algoritması ve Makine Öğrenme Kullanılarak Orman Tahribatı ve İyileşme Süreçlerinin Sınıflandırılması: Milas-Bodrum Örneği
Taş, Mehmet Akif
Bu çalışma, zengin orman varlığına rağmen Türkiye'nin yangına en hassas bölgelerinden olan Muğla'nın Milas-Bodrum yöresindeki orman dinamiğini, 2013-2024 periyodu için uzaktan algılama ve makine öğrenmesi yöntemleriyle analiz etmektedir. Analizde, 49 adet Landsat 8 görüntüsünden oluşan zaman serisi verileri kullanılmıştır. Normalize Edilmiş Yanma Oranı (NBR) indeksine dayalı bu veriler, LandTrendr algoritması ile işlenmiş ve ardından Random Forest makine öğrenmesi modeliyle her yıl için "Sağlıklı Orman", "Bozulma" ve "İyileşme" olmak üzere, ekosistemin durumunu yansıtan üç dinamik sınıfa ayrılmıştır. Kantitatif bulgular, 2014-2021 arasında "Bozulma" oranının %24'e gerilediği bir iyileşme döneminin, 2021'deki büyük yangınla dramatik şekilde kesintiye uğradığını ortaya koymuştur. Hem sağlıklı hem de iyileşmekte olan ormanları etkileyen bu olay, "Bozulma" oranını tek bir yılda %47'ye fırlatmış; ancak 2024 itibarıyla "İyileşme" kategorisi tekrar %29'a ulaşarak yeni bir rejenerasyon döngüsünün başladığını teyit etmiştir. Bu çalışma, geleneksel sınıflandırmaların ötesine geçerek, makine öğrenmesi ve zaman serisi analizinin büyük afetlerin ekosistem etkilerini belgelemek ve iyileşme süreçlerini izlemek için sunduğu güçlü metodolojik çerçeveyi ortaya koymaktadır.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/19281
Projection of Light Pollution and Environmental Impact Estimation Based on Population and GDP: The Case of Türkiye
Elveren, Müjgan; Yilmaz, Abdulvahap
Artificial Light at Night (ALAN) prediction can inform the development of strategies to minimise future light pollution and mitigate its adverse health, ecological, and environmental impacts. Population growth and GDP expansion significantly influence ALAN dynamics. This study quantifies changes in light pollution across Türkiye for 2012, 2017, and 2022, and predicts and maps potential changes in ALAN for 2027 and 2037 using the MOLUSCE plugin (MLP-ANN) in QGIS version 2.18, incorporating population and GDP as driving variables. The predicted and observed ALAN maps for 2022 show a satisfactory level of agreement, with an overall kappa coefficient of 0.63 and a general accuracy of 73.16%. The predicted and observed ALAN maps for 2022 exhibit an overall kappa coefficient of 0.63 and a general accuracy of 73.16%. Based on this validation, potential changes in ALAN according to Bortle classes were projected for 2027 and 2037. From 2022 onwards, ALAN intensity in the light suburban zone (20.1–19.1 mag/arcsec²) is projected to increase by 34,792.87 km², while the suburban–urban transition zone (19.1–18 mag/arcsec²) is expected to expand by 2,979.80 km² by 2037. The predicted spatial patterns provide critical insights into future urbanisation trends and light pollution dynamics. The contraction of rural areas and expansion of suburban zones pose notable risks to environmental sustainability. Gains and losses among Bortle classes indicate that ALAN dynamics can be managed through spatial planning and that ALAN projections can serve as early-warning and scenario-based decision-support tools. Integrating ALAN maps into Environmental Impact Assessment (EIA) processes and spatial planning policies can help preserve dark-sky areas and mitigate the impacts of light pollution.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/19206
Landslide Susceptibility Analysis of Kara Dere Basin (Erzincan) Using Analytical Hierarchy Process Method
Kopar, İbrahim; Yanik, Muhammet Enes
Landslides, as one of the primary natural hazards, are significant mass movements that cause considerable casualties and property damage. The objective of this study is to perform a landslide susceptibility analysis of the Kara Dere Basin, located in the northwest of the Erzincan Plain, and to spatially delineate potential risk areas. In this research, the Analytic Hierarchy Process (AHP), a Multi-Criteria Decision-Making (MCDM) method, and Geographic Information Systems (GIS) technology were utilized. Within the scope of the model, eleven different landslide-conditioning parameters were evaluated: slope, precipitation, lithology, NDVI, slope curvature, distance to streams, land use, elevation, great soil groups, aspect, and distance to roads. As a result of the weighting process applied via the AHP method, slope (25.10%) and precipitation (19.20%) were identified as the most influential factors in landslide occurrence. For the validation of the susceptibility map produced, the historical landslide inventory in the study area was randomly partitioned, utilizing 70% as training data and 30% as independent testing data. The validation procedure, performed using the Receiver Operating Characteristic (ROC) curve and the Area Under the Curve (AUC) technique, yielded an AUC value of 0.799, demonstrating that the model possesses a scientifically acceptable and reliable predictive capacity. According to the spatial analysis results, it was determined that 43% of the basin consists of high and very high-risk areas, 34% of moderate-risk areas, and 23% of low and very low-risk areas. The most susceptible regions were identified as the high-gradient terrains in the north and northeast of the basin. Furthermore, while certain sections of the Erzincan-Kelkit highway were observed to be located in high-risk zones, it was verified that the Ahmetli Village disaster housing, constructed following a historical landslide event, is appropriately situated in a low-risk area. It is anticipated that the resulting susceptibility map will serve as a crucial scientific baseline for future regional and spatial planning, as well as disaster risk management strategies.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/19030
Çevresel phillips eğrisi hipotezinin geçerliliğinin analizi: cıvets ülkeleri örneği
Akın, Fatih
Bu çalışma, CIVETS ülkeleri (Kolombiya, Endonezya, Vietnam, Mısır, Türkiye ve Güney Afrika) için 1991-2022 döneminde çevresel Phillips eğrisinin geçerliliğini incelemektedir. Ekolojik ayak izi bağımlı değişken, işsizlik oranı temel açıklayıcı değişken, ekonomik büyüme ve yenilenebilir enerji tüketimi ise kontrol değişkenleri olarak modele dâhil edilmiştir. Uzun dönem analizinde panel DOLSMG yöntemi uygulanmış, nedensellik ilişkilerinin belirlenmesinde Canning ve Pedroni (2008) panel nedensellik testi kullanılmıştır. Bulgular, ekonomik büyümenin ekolojik ayak izi üzerinde pozitif ve anlamlı etkisi olduğunu, yenilenebilir enerji tüketiminin ise ekolojik ayak izini azalttığını göstermektedir. Ayrıca işsizlik oranının ekolojik ayak izi üzerindeki düşürücü etkisi, ekonomik durgunluk dönemlerinde çevresel baskının azaldığını ortaya koymaktadır. Çevresel Phillips eğrisi Kolombiya, Vietnam, Türkiye, Güney Afrika ve panel geneli için geçerli, Endonezya ve Mısır için geçerli bulunmamıştır. Nedensellik analizine göre, işsizlik ile yenilenebilir enerji tüketimi ve ekolojik ayak izi arasında çift yönlü; ekonomik büyümeden ekolojik ayak izi, yenilenebilir enerji ve işsizliğe tek yönlü; ekolojik ayak izinden yenilenebilir enerjiye ise tek yönlü nedensellik mevcuttur.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/19026
Heterogeneous Effects of Green Technology Innovations on Renewable Energy Supply Share: A Dynamic Panel Evidence
Balkar, Oğuz Emre; Özenoğlu, Yunus Emre; Alkan, Okan
This study examines the determinants of renewable energy efficiency (REE) in a balanced panel of 17 countries (1995–2021), focusing on green technology innovations (GTI), economic growth (EG), and energy taxation (ET). The analysis accounts for heterogeneity, common shocks, and dynamic adjustment by combining two-way fixed effects with dependence-robust and dynamic common correlated effects (CCE) estimators using Driscoll–Kraay inference. The results show strong persistence in REE and a robust positive association between GTI and REE in the preferred common-factor framework, while the average effects of EG and ET are weaker and model-sensitive. Dumitrescu–Hurlin panel causality tests indicate feedback between REE and EG and bidirectional linkages between REE and ET at the level, whereas innovation dynamics are asymmetric. Overall, the evidences support innovation-centered transition strategies and emphasizes evaluating policy instruments over multi-year horizons given strong persistence and cross-country heterogeneity.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/18238
Adaptive hybrid control algorithm for integrated wind-solar energy systems: Enhancing efficiency and minimizing environmental impact
Can, Erol
This study introduces a three-tier adaptive control strategy designed for hybrid wind - solar energy systems, with the goal of optimizing energy capture, stabilizing the DC bus voltage, and enhancing overall system performance under varying environmental conditions. The control framework incorporates a TSR-based Maximum Power Point Tracking (MPPT) method for the wind turbine, a temperature-sensitive Perturb-and-Observe (P&O) MPPT for the photovoltaic array, and a real-time energy coordination system that dynamically adjusts the power allocation between wind and solar sources based on their instantaneous availability. A conventional Proportional-Integral (PI) controller manages the DC bus voltage, minimizing fluctuations and ensuring seamless integration with energy storage or the grid. The proposed approach is adaptable to both off-grid and grid-connected microgrids and is computationally efficient for real-time application. Simulation results from four typical scenarios - including high wind/low solar, low wind/high solar, intermittent generation, and balanced generation - show system efficiencies consistently exceeding 92%, along with a substantial reduction in voltage ripple when compared to traditional MPPT techniques. These findings validate the effectiveness of the coordinated control strategy in maintaining power quality, system reliability, and stable energy output, offering a scalable and practical solution for integrating renewable energy into microgrid systems.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/18035
A thermal-aware and self-adapting method for accurate state of charge estimation in lithium-ion batteries
Can, E. R. O. L.
Accurate state-of-charge (SOC) estimation remains a key challenge for lithium-ion batteries (LIBs) operating under varying thermal and load conditions, particularly in electric vehicles and grid-scale energy storage systems. Conventional model-based estimators such as EKF and UKF typically assume fixed parameters and neglect coupled electro-thermal dynamics, which degrades estimation accuracy under temperature fluctuations and aging effects. To address these limitations, this paper proposes a Thermal-Aware Hierarchical Self-Tuning Square Root Unscented Kalman Filter (TA-HST-SRUKF) for real-time SOC estimation. The proposed framework explicitly incorporates a lumped thermal model into the SOC estimation loop and employs a hierarchical self-tuning mechanism to adapt process and measurement noise covariances online. In addition, the square-root formulation enhances numerical stability and reduces computational burden, making the approach suitable for embedded battery management systems. Compared with conventional EKF- and UKF-based methods, the proposed TA-HST-SRUKF demonstrates improved robustness and accuracy across a wide temperature range and varying operating conditions. Simulation results confirm lower estimation errors and better adaptability without increasing computational complexity. The proposed method provides an effective and practical solution for highaccuracy SOC estimation in thermally dynamic and aging-prone battery applications.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/11552
Climatic Variables as Drivers of Pterocarpus erinaceus (Fabaceae): Distribution and the Implications of Climate Change
Sari, İdris; Ismael, Bio; Ullah, Fazal; Agoundé, Gafarou; Yildiz, Faruk
Pterocarpus erinaceus is an ecologically and economically important tree species native to the Sahel region of West Africa, facing severe threats due to overexploitation, habitat degradation, and climate change. This study assesses the impact of key climatic variables on the species' current distribution and projects potential range shifts across Africa under mid-21st century climate scenarios. Using an ensemble modeling approach that combines various algorithms and utilizes 37 comprehensive climatic variables, the analysis revealed significant patterns of highly suitable habitat, concentrated primarily in West Africa. Projections under low and medium emission scenarios for 2040–2060 and 2080–2100 periods predict a reduction in climatically unsuitable areas and a potential expansion of suitable habitats, suggesting that the species may be somewhat resilient to medium-term climate changes. The primary climatic factors limiting the species' distribution were identified as the Mean Temperature of the Driest Quarter and the Climatic Moisture Index. These results underscore the species' ecophysiological dependence on specific temperature and moisture regimes. Crucially, while our projections suggest the species exhibits resilience and potential habitat expansion under medium-term climate change, its realization is contingent upon mitigating persistent anthropogenic pressures. Therefore, to ensure the species' long-term persistence and maintain the ecological integrity of the West African Savanna Biome, conservation strategies must prioritize aggressive, in situ actions focused on sustainable management, controlled harvesting, and the protection of current and future suitable habitats, rather than focusing solely on long-term climate change adaptation measures.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/11502
Association between environmental literacy and carbon footprint awareness among future healthcare professionals
Aydın Kahraman, Handan; Bozcu Kartal, Ebru
Climate change poses significant threats to global health, necessitating a healthcare workforce equipped to handle these challenges. This study aimed to evaluate the level of environmental literacy among nursing students and to determine its predictive impact on their carbon footprint awareness. This descriptive, cross-sectional study was conducted with 402 undergraduate nursing students at a public university in eastern Türkiye. Data were collected using a Personal Information Form, the Environmental Literacy Scale for Adults (ELSA) to assess environmental consciousness, concern, and awareness, and the Carbon Footprint Awareness Scale (CFAS) to measure climate-conscious daily behaviors. Participants demonstrated high environmental literacy (mean ELSA score: 79.01 ± 10.35) and substantial awareness (mean CFAS score: 68.19 ± 9.69). A strong, positive correlation existed between environmental literacy and carbon footprint awareness (r = 0.694; p < 0.001). Regression analysis indicated that environmental literacy is a significant predictor, explaining 48% of the variance in carbon footprint awareness (R2=0.480; F = 371.608; p < 0.001). Environmental literacy strongly predicts carbon footprint awareness. Integrating comprehensive planetary health and environmental literacy strategies into nursing curricula is essential to foster a generation of nurses conscious of their carbon footprint and capable of leading sustainable healthcare practices.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/11464
Hybrid VMD-EMD Enhanced Machine Learning Models for Daily Reference Evapotranspiration Forecasting
Acar, Reşat; Katipoğlu, Okan Mert; Çırağ, Burak
Getting accurate daily estimates of reference evapotranspiration (ET₀) is essential for hydrological modeling, irrigation planning, and climate research. This study evaluated the performance of four machine learning models: Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Deep Neural Network (DNN), and Light Gradient Boosting Machine (LGBM) for daily ET₀ prediction. Feature selection was implemented using Partial Autocorrelation (PACF) and Autocorrelation (ACF) analysis on the basis of an 8-day lag structure, while the CatBoost feature importance framework was implemented to identify the most important inputs. Moreover, the methodologies of decomposition-based preprocessing, Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD) were implemented on the lagged inputs to build the hybrid models augmented with intrinsic constituents. These augmented hybrid models were created to improve the data representation as well as predictive capability. Model performance was evaluated using key statistical metrics, including RMSE, MAE, NSE, KGE, R2, and bias-related indicators. CatBoost produced the lowest RMSE (1.57 mm/day) and MAE (1.13 mm/day), and the highest NSE (0.67), KGE (0.78), and R2 (0.67), along with the lowest AIC score (627.15), indicating strong and reliable predictive performance. Furthermore, the VMD based CatBoost model yielded even greater improvements, highlighting the added value of decomposition enhanced learning. On the contrary, DNN showed the weakest results, with the highest RMSE (2.39 mm/day) and lowest NSE (0.23). These findings suggest that CatBoost and its hybrid variants are highly effective and reliable tools for daily ET₀ prediction, particularly in data limited environments and mountainous regions.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/11209
National-Scale Estimation of Brake-Wear Particulate Emissions From On-Road Vehicles in Türkiye: A 2024 Inventory with Uncertainty and Mitigation Scenarios
Demirci, Oğuz Kürşat
This research article develops a screening-level national inventory of airborne brake-wear particulate emissions from on-road vehicles in Türkiye for the year 2024. The scope is limited to brake wear only and does not include tyre wear, road wear, resuspension, or concentration and exposure modelling. The inventory combines TurkStat vehicle-kilometre statistics with EMEP/EEA Tier-2 brake-wear emission factors, including passenger-car powertrain differentiation to reflect regenerative-braking effects. Under nominal baseline assumptions, annual emissions are estimated at 5.67 kt•y-1 for PM10 and 2.26 kt•y-1 for PM2.5. Monte Carlo framework that propagates bounded uncertainty in total activity, vehicle-category composition, passenger-car powertrain shares, guidebook-anchored emission factors, and particle-size fractions, the national totals are characterised by a median (95% interval) of 5.67 (4.87-7.19) kt•y-1 for PM10 and 2.26 (1.87-2.90) kt•y-1 for PM2.5 Passenger cars account for approximately 45% of national PM10 emissions, followed by light commercial vehicles and tractor units. Illustrative, assumptiondependent scenario analysis indicates that PM10 could decrease to 4.95 kt•y-1 under partial uptake of low-emission brake technologies, to 5.28 kt•y-1 with greater use of auxiliary braking in heavy-duty vehicles, and to 5.47 kt•y-1 under a passenger-car fleet share of 10% HEV and 10% BEV. These scenario outcomes should be interpreted as indicative screening-level projections rather than empirical or policyevaluation results. Overall, the study provides a transparent brake-wear-only national baseline and a comparative framework for examining how selected assumptions influence estimated PM emissions in Türkiye.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/10985
An adaptive hybrid energy management system for UAVs integrating fuzzy logic, solar forecasting and real-time control
Can, Erol
This study presents a hybrid energy management system (EMS) for unmanned aerial vehicles (UAVs), integrating flexible photovoltaic (PV) panels with a high-capacity lithium-polymer (Li-Po) battery to enhance flight endurance and energy resilience. The proposed EMS features a multi-layered adaptive control architecture, combining fuzzy logic-based decision-making, short-term solar irradiance prediction using machine learning and closed-loop proportional-integral-derivative (PID) motor control. This architecture dynamically allocates power based on real-time solar irradiance, battery state of charge (SOC) and propulsion load. The approach aims to minimise battery stress while ensuring stable UAV operation under variable environmental conditions. Simulation results indicate that, without PV support, the UAV battery depletes in approximately 28 min. However, incorporating an 80 W PV panel extends the endurance to 37 min, and a 160 W effective PV configuration increases the flight time to over 50 min, while maintaining the SOC above 20%. This corresponds to a 79% improvement in endurance and nearly a 50% reduction in net battery energy consumption. The EMS effectively mitigates deep discharge cycles, improving battery health and operational lifespan. These findings demonstrate that the proposed hybrid EMS provides a scalable, adaptive and computationally efficient solution for balancing renewable and stored energy. It outperforms conventional static or single-source control strategies, particularly under fluctuating solar conditions.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/10873
Physically constrained air–sea heat flux driven modeling of sea surface temperature using atmospheric and oceanographic variables with explainable AI
Katipoğlu, Okan Mert; Bazrafshan, Ommolbanin; Mohammadi, Mojtaba; Alsumaiei, Abdullah A.
This study aims to develop a robust multivariate regression framework for accurately predicting monthly Sea Surface Temperature (SST) using a core set of ten primary atmospheric and oceanographic variables, including relative humidity, specific humidity, temperature, mean square slope of waves, mean wave direction, 2-meter air temperature, top net solar radiation, total precipitation, mean evaporation rate, and potential evaporation. The originality of this research lies in the simultaneous integration of meteorological and oceanographic parameters into multiple machine learning architectures, coupled with a detailed interpretability analysis using SHAP values, which provide a comprehensive understanding of the influence of variables on SST prediction. The dataset was split into 60 % for training, 20 % for testing, and 20 % for validation. Four machine learning models: Random Forest, CatBoost, one-dimensional Convolutional Neural Network, and Support Vector Machine were optimized using RandomizedSearchCV, with MinMaxScaler applied to ensure consistent feature scaling across models. Model performance was evaluated using Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, Coefficient of Determination, and Explained Variance metrics. Meanwhile, SHAP analysis identified the most influential features as 2-meter air temperature, mean evaporation rate, mean square slope of waves, air temperature, and specific humidity. Results revealed that the Support Vector Machine achieved the highest accuracy overall, followed by CatBoost, confirming that combining meteorological and oceanographic predictors significantly enhances SST forecasting performance. The physical consistency analyses, supported by the bulk air–sea heat flux formulations for sensible and latent heat fluxes, confirm that the machine-learning model’s most influential predictors: near-surface air temperature, specific humidity, and evaporation-related variables are fully consistent with the fundamental thermodynamic controls governing SST. This research not only advances SST prediction accuracy but also provides a transparent interpretability framework, making it a valuable reference for climate modeling, marine resource management, and environmental monitoring applications.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/10859
Beyond Conventional Methods: Predicting Novel Modified Groundwater Drought Indices with Advanced Computing Paradigms
Katipoğlu, Okan Mert; Kartal, Veysi; Aktürk, Gaye; Kilinc, Huseyin Cagan; Elshaboury, Nehal; Yamany, Mohamed S.; Pande, Chaitanya Baliram
To achieve accurate and reliable predictions of groundwater drought, it is essential to incorporate relevant meteorological variables and apply advanced predictive methodologies capable of modeling their complex interrelationships. In this study, groundwater drought prediction models were developed based on the seven modified drought indices, which are obtained from groundwater levels and multiple meteorological parameters. The analysis focuses on four districts in Türkiye (Tekirdağ-Çorlu, Tekirdağ-Çerkezköy, Amasya-Merzifon, and Amasya-Centre), which are hereafter referred to collectively as the study areas. Three machine learning models were applied such as a standalone Artificial Neural Network (ANN) and two hybrid models, ANN integrated with Shuffled Frog Leaping Algorithm (SFLA-ANN) and Firefly Algorithm (FFA-ANN). The hybrid metaheuristic algorithms were chosen for their ability to model nonlinear and complex relationships between meteorological variables and groundwater levels, which traditional statistical methods cannot fully capture. Modified drought indices were employed to represent the groundwater drought better. The findings indicate that the hybrid FFA-ANN model generally provides the highest predictive accuracy for most indices, with coefficient of determination values frequently exceeding 0.90. In contrast, the ANN model occasionally outperforms the hybrid FFA-ANN model in terms of root mean square error (RMSE) for specific stations within the study areas. These results highlight the robustness of hybrid ANN approaches, especially FFA-ANN, in predicting groundwater drought under changing climate conditions. The novelty of this study is the modification of meteorological drought indices widely used to represent groundwater drought and the application of hybrid metaheuristic ANN models to estimate these indices in Türkiye. The results demonstrated that such models provide a reliable framework for predicting groundwater drought and provide decision-makers with advanced tools for water resources management, irrigation planning, and climate adaptation strategies.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/10817
Prediction of soil moisture via feature selection, model optimization, and climate data integration
Katipoğlu, Okan Mert; Kartal, Veysi; Akiner, Muhammed Ernur; Terzioğlu, Zeynep Özge; Kılıç, Zeyneb
Soil moisture is vital for water resource management and agricultural productivity. With the growing availability of reanalysis data and advanced machine learning methods, it is essential to explore reliable, scalable models for long-term estimation. Comparing different algorithms enables a comprehensive assessment of their strengths and limitations in modeling complex soil moisture dynamics under varying climatic and agricultural conditions. In this study, soil moisture data for the period 1950–2022 from six stations in the Konya Closed Basin of Türkiye were estimated using Echo State Networks (ESN), Adaptive Boosting (AdaBoost), Deep Neural Networks (DNN), and Light Gradient Boosting Machine (LGBM). Precipitation (PR), solar radiation (RSDS), wind speed (WS), mean temperature (Tave), maximum temperature (Tmax), minimum temperature (Tmin), and potential evapotranspiration (ET0) values calculated by the Thornthwaite equation were used as input variables of the models, and soil moisture (SM) was determined as the output variable. Model performance was evaluated using statistical metrics and visualizations derived from training, validation, and test datasets. In addition, a feature selection approach was used to identify the most effective parameters for soil moisture estimation. The analysis showed that the DNN model achieved the highest accuracy, with R2 values ranging from 0.87 to 0.97. The second most successful model was AdaBoost or ESN, while the LGBM model showed higher deviations than the others. These findings reveal that artificial intelligence-based models can effectively estimate soil moisture.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/10802
Assessment of future hydrometeorological variability in the Konya Basin, Türkiye using bias-corrected CMIP6 projections
Katipoğlu, Okan Mert; Kartal, Veysi; Akiner, Muhammed Ernur; Bazrafshan, Ommolbanin; Spor, Pinar; Çelik, Mehmet Ali
This study presents bias-corrected projections of soil moisture, precipitation, Temperature and evapotranspiration in the Konya Basin, derived using CMIP6 data under SSP1-2.6, SSP2-4.5, and SSP5-8.5 scenarios. Bias correction methods, including Delta, Quantile Mapping, and Empirical Quantile Mapping, were applied to the raw model outputs. Historical data from CMIP6 (1950–2014) and future projections (2015–2100) were corrected using ERA5 reanalysis data (1940–2024) to improve accuracy. Nine global climate models ACCESS-CM2, CESM2, CMCC-ESM2, EC-Earth3-CC, MIROC6, GFDL-ESM4, MPI-ESM1-2-LR, MRI-ESM2-0, and NorESM2-LM were evaluated, and ACCESS-CM2 provided the most reliable results for all three SSP scenarios. The data were divided into four time periods: the reference period (2015–2024), near future (2025–2049), mid-future (2050–2074), and far future (2075–2100). Relative errors were calculated as (Observed - Predicted)/Observed × 100, with temperature trends incorporated for comparative assessments. For spatial analysis, Universal Co-Kriging was employed to generate predictive maps for each future period, using elevation as a secondary variable. Therefore, the Universal Co-Kriging parameters determined through a trial-and-error approach namely, the use of a Gaussian kernel, standard neighborhood structure with 5 maximum and 2 minimum neighbors, and a 45-degree sectoral division in four directions proved to be the most effective combination for accurately mapping the spatial distribution of soil moisture, precipitation, temperature, and evapotranspiration in the Konya Basin. The study provides valuable insights into the future variability of hydrometeorological variables in the Konya Basin, offering critical information for water resource management and climate adaptation strategies.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/10765
Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria
Katipoğlu, Okan Mert; Achite, Mohammed; Kartal, Veysi; Çelik, Mehmet Ali; Pandey, Kusum
Hydrological drought forecasting in semi-arid basins is challenging due to the combined influence of meteorological forcing, large-scale atmospheric teleconnections, and basin memory processes, which are rarely jointly analysed within a leakage-free predictive framework. This study addresses this gap by evaluating gradient-boosted trees and neural forecasting models for one-month-ahead prediction of the Standardized Runoff Index (SRI) in two sub-basins of the Wadi Sahaouat Basin, Algeria. The models include gradient-boosted regression trees (GBRT), A-N-BEATS, A-N-HiTS, and TiDE, representing distinct forecasting architectures. Predictors consist of the Standardised Precipitation Index (SPI), seven teleconnection indices (NAO, AO, EAWR, SCAND, MEI, SOI, WeMO), and their one- to three-month lags. Two scenarios are tested: Scenario 1 uses SPI and teleconnection lags only, while Scenario 2 additionally includes lagged SRI values (SRI_lag1–3) to represent hydrological memory. A train-only Variance Inflation Factor (VIF > 10) procedure is applied to remove multicollinearity without data leakage. In Basin 1, SRI lags were excluded due to strong collinearity with SPI lags (r = 0.984), resulting in identical inputs for both scenarios. In Basin 2, SRI lags were retained to assess their predictive contribution. GBRT achieved the best overall performance across both basins and scenarios, with mean RMSE, NSE, and KGE values of 0.0682, 0.9907, and 0.8945, respectively. TiDE ranked second overall, with a mean RMSE of 0.1166, followed by A-N-HiTS in third place with a mean RMSE of 0.1203 and A-N-BEATS with the weakest overall performance, with a mean RMSE of 0.2159. These results indicate that gradient-boosted trees remain highly competitive with neural models for small monthly hydrological datasets and that the value of hydrological memory is basin-dependent and varies according to its independence from concurrent meteorological forcing.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2026/r/ebyu/10703
Machine learning and traffic simulation for corridor-level optimization in Intelligent Transportation Systems: reducing travel times, delays, and carbon dioxide emissions
Deniz, Fatih Ahmet; Çolak, Muhammed Ali
Increased individual vehicle ownership has led to longer travel times, increased delays, and higher CO2 emissions in traffic networks. This study aims to optimize intersection designs, lane counts, and signal timings within an Intelligent Transportation System (ITS)-based traffic corridor to reduce travel time, minimize delays and decrease instantaneous CO2 emissions. To achieve this, the current conditions of a seven-intersection corridor were simulated, resulting in 27,647 different scenarios with various combinations of vehicle volumes, intersection properties, lane configurations, and signalization. Incorporating real intersection vehicle count data and signal timings further enhanced the accuracy of the simulations, providing a more realistic representation of traffic flow and helping to refine the optimization of intersection designs, lane counts, and signal settings. In total, 27,648 scenarios, including the baseline scenario, were analyzed, resulting in three datasets that focus on delay time, instantaneous CO2 emissions, and total travel time. These datasets were modeled using various algorithms, including linear regression, support vector regression, elastic net, decision trees, random forests, AdaBoost, gradient boosting, XGBoost, and CatBoost. Among these models, CatBoost was found to be the most effective in explaining delay time, instantaneous CO2 emissions, and total travel time. Feature importance analysis using CatBoost revealed the optimal designs for reducing travel time, minimizing delays, and lowering emissions: modern roundabouts at the Dortyol and Old Police School intersections, and a grade-separation at the Terzibaba intersection. The findings demonstrate that integrating machine learning with traffic simulation can support ITS by improving traffic flow, reducing congestion, and lowering CO2 emissions.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2026/r/ebyu/10684
THE RELATIONSHIP BETWEEN EXTERNAL DEBT AND ENVIRONMENTAL QUALITY IN TÜRKIYE: A FRACTIONAL FREQUENCY FOURIER ARDL BOUNDS TEST APPROACH
Akın, Fatih
As efforts to achieve global sustainability goals intensify, it is increasingly important to understand the environmental consequences of countries’economic policies, particularly the impact o fmacroeconomic variables such as external debt. This study analyses the impact of Türkiye’s external debt on environmental sustainability for 1970–2023 using the Fractional Frequency Fourier Autoregressive Distributed Lag (FFF-ARDL) method. Moreover, the variables of economic growth, renewable energy consumption (REN), and non-renewable energy (NREN) consumption were included in the model, and the Environmental Kuznets Curve (EKC) hypothesis was tested. Carbon dioxide (CO2) emissions were used as a proxy for environmental sustainability. The long-run coefficient findings indicate that increases in external debt reduce CO2 emissions, while economic growth initially increases emissions but then declines after a certain income threshold, confirming the EKC hypothesis. Moreover, REN energy consumption decreases CO2 emissions, whereas NREN energy consumption increases them. The Fourier Toda-Yamamoto test results indicate unidirectional causality running from CO2 emissions, REN, and external debt to NREN consumption. There is also unidirectional causality running from economic growth, REN, and NREN consumption to external debt. These findings suggest that Türkiye’s external debt management and the transition toward REN sources are crucial for reducing CO2 emissions.
RDL Kalıcı Kaydıİncele