Makale Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Data-driven models for significant wave height forecasting: comparative analysis of machine learning techniques(2024) Durap, AhmetAccurate prediction of significant wave height (SWH) is critical for coastal safety, marine operations, and disaster management. Traditional numerical models for wave prediction are computationally intensive and often lack accuracy, prompting a shift towards data-driven methods. This study explores the efficacy of machine learning (ML) models in forecasting SWH in the coastline of North Stradbroke Island, Queensland, Australia. Using a dataset spanning 2010 to 2022, the study employs wave characteristics such as maximum wave height (Hmax), wave periods (Tz, Tp), peak direction, and sea surface temperature (SST) as predictors. Three ML models—Linear Regression, Decision Tree, and Random Forest—were trained and evaluated using performance metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). The Random Forest model demonstrated the best predictive accuracy with the lowest MSE (0.0074) and highest R² (0.958), outperforming both Linear Regression and Decision Tree models. This improvement in prediction accuracy supports the model's application for coastal management, ensuring better forecasting of wave conditions. The proposed approach shows significant advantages, including better handling of non-linearities and reduced computational costs compared to conventional numerical methods, such as SWAN and WAM, making it highly applicable for real-time wave forecasting, particularly for regions with complex coastal dynamics such as North Stradbroke Island.Öğe A new innovative method for model efficiency performance(IWA Publishing, 2022) Şen, Zekai; Şişman, Eyüp; Kızılöz, BurakIn every aspect of scientific research, model predictions need calibration and validation as their representativity of the record measurement. In the literature, there are a myriad of formulations, empirical expressions, algorithms and software for model efficiency assessment. In general, model predictions are curve fitting procedures with a set of assumptions that are not cared for sensitively in many studies, but only a single value comparison between the measurements and predictions is taken into consideration, and then the researcher makes the decision as for the model efficiency. Among the classical statistical efficiency formulations, the most widely used ones are bias (BI), mean square error (MSE), correlation coefficient (CC) and Nash-Sutcliffe efficiency (NSE) procedures all of which are embedded within the visual inspection and numerical analysis (VINAM) square graph as measurements versus predictions scatter diagram. The VINAM provides a set of verbal interpretations and then numerical improvements embracing all the previous statistical efficiency formulations. The fundamental criterion in the VINAM is 1:1 (45 degrees) main diagonal along which all visual, science philosophical, logical, rational and mathematical procedures boil down for model validation. The application of the VINAM approach is presented for artificial neural network (ANN) and adaptive network-based fuzzy inference system (ANFIS) model predictions.Öğe Wet and dry period identification method through serial correlation decomposition(Taylor & Francis Ltd, 2022) Şen, ZekaiThe serial correlation coefficient is the linear dependence procedure used most frequently to identify the short-memory dependence in a given hydrometeorology time series. The serial correlation formulation can be decomposed into four hydrometeorologically important parts: the wet (surplus) spell and dry (deficit) spell (drought) durations in addition to up-crossing and down-crossing components. The only negative values are available for up-crossing and down-crossing cases in the two successive standard variate multiplications, which implies that the first-order serial correlation coefficient has a lower dependence value with more contributions from the up- and down-crossing components. The difference between this methodology and those available in the literature is in the explicit use of the correlation coefficient for the identification of the abovementioned drought features. The validity of this new methodology is revealed through extensive Monte Carlo simulation and actual application to lengthy (1840-2003) Danube River monthly and annual discharges.Öğe Hydroelectric energy potential classification via hypsographical curve concept(Wiley, 2022) Şen, ZekaiHuman activities are directly related to fossil fuel consumption and cause global warming and climate change effects by emitting greenhouse gas into the lower atmosphere. To reduce and adapt to such effects, renewable energy sources such as surface dams, including hydroelectric energy (HE) generation units, are gaining importance. In the current literature, HE potential calculations are based on formulations that are quite simple, clear and do not distinguish between different situations. In this paper, two classification methodologies are proposed for better assessment of HE production. The first one is based on the concept of the hypsographic curve to distinguish different drainage basin features into "Young," "Mature" and "Old." The second classification takes into account the newly defined energy index (EI) principle, which helps to classify the HE generation capability of drainage basins into "Very low," "Low," "Normal," "High" and "Very high." The application of the proposed methodology is presented for three drainage basins from the upstream sub-basins of the Tigris River in Turkey. A comparison of the results shows that the proposed methodologies not only give numerical values but also sets linguistically rational and logical rules for the HE potential of a drainage basin. In the upstream basin of the Tigris River, the EI values vary between 0.705 and 0.122, corresponding to the "High" and "Low" categories, respectively. It is recommended that these two classification procedures be considered before the construction of any dam for HE production.Öğe Extreme value innovative trend analysis methodology(Inderscience Enterprises Limited, 2022) Şen, ZekaiThe main concern of the article is to determine the trend analyses of upper and lower extreme values separately, apart from the classical central trend. The innovative trend analysis (ITA) modification is adapted for extreme value trend analysis using one standard deviation level from the arithmetic mean value. Extreme value trends emerge along completely different monotonous lines. The application of the proposed methodology is presented for the annual total rainfall time series of seven meteorological stations from each geographical and climatological regions of Turkey. In the future, it is recommended to use only the classical central trend extreme value trend analyses for refined forecasts.Öğe Crossing empirical trend analysis (CETA) at risk levels in hydro-meteorological time series(Springer Wien, 2022) Şen, ZekaiTrend identification procedures are used to identify systematic monotonic trendlines in a given hydro-meteorological time series recording to represent time-dependent variations as increases or decreases. Different methodologies have been proposed for such descriptions, but most of them require restrictive assumptions such as normal (Gaussian) probability distribution function (PDF), serial independence, and long sample sizes. In particular, pre-whitening and over-whitening are recommended to meet the need for serial independence, but they cannot transform a serially dependent series into a completely independent one. In this paper, a new trend methodology is proposed based on the characteristics of crossings along any given straight line within the given time series, and the sought-after trend component is the one with the maximum number of crossings. This approach does not require any restrictive assumptions. Unlike previous trend algorithms, the proposed cross-empirical trend analysis (CETA) does not give a single trend, but a series of trends at different levels within the variation range of hydro-meteorological time series records. For the sake of brevity, only three levels are considered in this article, at 10%, 50%, and 90% risk levels. The comparison of the CETA approach is presented with the classical and frequently used Mann-Kendall (MK) trend determination procedure method based on Sen's slope calculation. For very small series correlation coefficients and normal PDF function cases, CETA and the classical technique give almost the same trendline within the +/- 5% error band. The application of this methodology is presented for monthly and annual discharge records of the Danube River and annual precipitation records from seven geographical regions of Turkey.Öğe Flash flood risk and climate analysis in the extreme south of algeria (the case of in-guezzam city)(AGH University of Science and Technology Press, 2022) Zegait, Rachid; Şen, Zekai; Pulido-Bosch, Antonio; Madi, Housseyn; Hamadeha, BachirNatural risks, particularly flood risk, are a topical subject in Algeria and throughout the world, particularly given the last major catastrophic floods in Sudan (2020) and North Africa. With the development of the climate change phenomenon in the world, risk management is becoming increasingly necessary for all the actors concerned (decision-makers, technicians, and the population) to identify protection issues. In 2018, in the extreme south of Algeria, In-Guezzam City suffered a devastating flood that caused significant damage and loss of human and material resources. More than 100 homes collapsed, and approximately 345 families were displaced. Currently, there is no research work to assess the hydrological situation and the risk of flooding in this region. Therefore, the main purpose of this study is to shed light on the risk of flash floods in the extreme south of Algeria with more specific attention to the August 2018 floods as well as the climate trends over the past 30 years using Mann–Kendall test and Sen’s Slope Estimator. The chosen approach involves a hydrological study and hydrodynamic modeling using HEC-RAS software. This latter allows for simulating floods using statistical methods and creating several regional flood hazard maps.Öğe New approach to detect trends in extreme rain categories by the ITA method in northwest Algeria(Taylor and Francis Ltd., 2021) Benzater, Benali; Elouissi, Abdelkader; Dabanlı, İsmail; Harkat, Samra; Hamimed, AbderrahmaneA new approach for the modified method of innovative trend analysis (ITA) was applied to the categories of maximum daily rains coming from 41 pluviometric stations of Macta (northwest Algeria) for the period 1970-2010. Six categories of maximum daily rainfall were considered: light: 0-4 mm/day (A); mild to moderate: 4-16 mm/day (B); moderate to heavy: 16-32 mm/day (C-1); heavy: 32-64 mm/day (C-2); heavy to torrential: 64-128 mm/day (D-1); and torrential: equal to or greater than 128 mm/day (D-2). The results show that during the second period (1990-2010), increasing trends were detected in the middle categories B (most frequent: 20.78%), C-1 (17.85%), C-2 (20.21%) and D-1 (4.92%). In addition, migratory movements and rainy events towards the higher categories were detected (in particular towards C-1 (8.84%)). These results show an increase in extreme rains in the Macta watershed during the period 1990-2010.Öğe Upcycling of industrial iron scale waste for reutilization as anode material in lithium ion batteries(Elsevier Ltd, 2022) Gülcan, Mehmet Feryat; Karahan, Billur DenizIn this work, iron scale is used as the starting raw material to produce anode for lithium ion batteries. In this scope, three different samples are fabricated, then their properties are investigated to evaluate their performances. Firstly, the as received scale is washed with water and milled (Sample 1). Then two different modification methods are applied: physically mixing Sample 1 with carbon (Sample 2) and chemically treating Sample 1 with a polysaccharide contained methanol solution, followed by heat treatment (Sample 3). Galvanostatic tests show that the Sample 2 and Sample 3 exhibit 430 mAh g?1 and 573 mAh g?1, after 200th cycle, respectively. SEM observation reveals that Sample 3 has smaller sized particles with a homogeneous morphology. Raman analysis shows the existence of both graphitized and disordered carbon atoms in Sample 3. The improved performance of Sample 3 is believed to be related to its structural and compositional particularities. The approach presented in this article is expected to set an example for future studies to be carried out within the framework of waste valorisation for energy storage applications.Öğe Extreme rain trend analysis in Macta watershed North West Algeria(Springer, 2021) Benzater, Benali; Elouissi, Abdelkader; Dabanlı, İsmail; Benaricha, Boumediene; Hamimed, AbderrahmaneThe north of Algeria is subject to floods generated directly by extreme rains. Detecting their trends, at different spatial and temporal scales, is a crucial step in the context of climate change. In this article, the Mann-Kendall method was used to detect the trends of maximum daily rains in 41 rainfall stations in the Macta watershed (North West Algeria) for a period of 41 years (1970-2010). The results show contrasting monthly trends; a significant increase, at the 5% (10%) confidence level, was detected in March, May, June, November, and December months, with 29% (7%), 24% (32%), 17% (24%), 12% (0%), and 10% (20%) of stations respectively. In terms of rain intensity, an increase was detected in April, July, August, September, October, and November. It is obvious that the months of August and September, representing the beginning of the autumn season, are marked by the greatest increases in the intensity of the rains justifying the catastrophic floods that hit our basin each year. The same significant upward trends are detected for autumn and winter, accompanied by an increase in quantities in the first season (autumn). Annually, a trend towards a significant increase trend, at 5% (10%) confidence level, in extreme rains with 20% (15%) of stations, was detected. Furthermore, a slight decrease in quantities was observed.Öğe Wet and dry spell feature charts for practical uses(Springer, 2020) Şen, Zekai; Şişman, Eyüp; Dabanlı, İsmailWater resources management is dependent on wet and dry spells occurrences in an alternative manner. Therefore, information about their probabilistic occurrence frequencies and statistical parameters are the most required quantities for optimum and well-balanced operations for water demand. Among the most important dry spells are the meteorological (precipitation) and hydrological (runoff, stream flow, reservoir level, ground water level, etc.) drought occurrences and their future expectations under a certain level of risk (exceedance probability) or return period, which is the inverse of the risk. Firstly, this paper presents detection of wet and dry spell parameters among which are the duration, maximum surplus or deficit, magnitude, and intensity. Secondly, a set ofbeneficialcharts is presented in the new graphical form for each dry (wet) spell characteristic versus different risk levels (0.50, 0.20, 0.10, 0.04 0.02, 0.01, 0.004 and 0.002) corresponding to return periods (2-year, 5-year, 10-year, 25-year, 50-year, 100-year, 250-year and 500-year). These applications of the methodology are presented for New Jersey Statewide annual precipitation and Danube River annual discharge records each with more than 100 years records. Finally, it is found that the mathematical relationship between each wet and dry spell parameter and the return periods abide with exponential function, which appears on semi-logarithmic papers as straight lines. Consequently, it can be generalized for the study area that any drought (wet) parameters variation with the return period appears as exponential function for hydro-meteorological records.Öğe Temperature and precipitation risk assessment under climate change effect in northeast algeria(Springer International Publishing AG, 2020) Boudiaf, Besma; Dabanlı, İsmail; Boutaghane, Hamouda; Şen, ZekaiClimate change impacts on social, economic, industrial, agricultural, and water resource systems tend to increase incrementally with each passing day. Therefore, it is necessary to plan to control its effects, especially with regard to temperature and rainfall events impacting future water resource operation, maintenance and management works. Climate change has a direct influence at the trend of both components temperature and precipitation in increasing or decreasing manner depending on the study area. This paper presents and interprets temperature and rainfall trends for Northeast Algeria. A trend analysis technique was employed along with risk assessment. The modified risks associated with 2-, 5-, 10-, 25-, 50-, 100-, 250, and 500-year return periods are then calculated for each station. This methodology has been applied to precipitation and temperature records for six different meteorological stations in Northeast Algeria. This study confirms that climate change has and will continue to have an impact on temperature and precipitation that should be considered for all infrastructure planning, design, construction, operation, maintenance and optimum management studies in future.Öğe Physical and practical hydrograph recession modeling in karstic sinkholes(IWA Publishing, 2020) Şen, Zekai; Dabanlı, İsmail; Şişman, EyüpKarstic spring discharge is related to the hydraulic head recession through a power function with an exponent <1. In the literature, analytical solutions are available for exponential and non-exponential models based on a set of restrictive physical and mathematical assumptions. The models search for a holistic and deductive solution without basic physical and practical interpretations, simple logical inferences leading to mathematical analytical or empirical formulations. In this paper, an inductive, logical, practical, and instead of holistic modeling, physically plausible piecewise solutions are proposed with detailed inferences and interpretations. In the proposed methodology, the discharge and hydraulic head records are decomposed first into a set of verbal classes and, subsequently, physical meaning for each class is explained leading to simple general but empirical models. For this purpose, Wakula and St. Marks River (Florida) hydrograph records are used for the general solution sinkhole discharge and hydraulic head variations. The solution methodology presented in this paper does not make any distinction between relatively small or large sinkhole heads. The calibration and verification of the methodology is shown with a comparison of the available record values to partial power models. Finally, it is concluded that the proposed methodology is reliable and can be applied to hydraulic head availability with discharge records in any part of the world for karstic aquifer domains.Öğe Innovative flow risk assessment with climate change perspective in Yesilirmak Basin(Parlar Scientific Publications, 2020) Serancam, Uğur; Dabanlı, İsmailSurface temperature increase due to global warming results in polar ice melting, snow cover thinning, changes in precipitation anomaly. All these phenological effects alert engineers, planners and administrators to be more sensitive against climate change-based risk effects on water structures. Vulnerability to natural disasters such as floods and droughts are expected to occur more frequent than past. Therefore, design and potential evaluation of water structures such as transmission channels, water wells, dams and hydraulic power generation facilities need to be re-evaluation. This re-evaluations procedure must be updated by taking into consideration climate change impacts with their risk assessments. For this purpose, the climate change-based risk levels are calculated from historically available records through possible trend tendencies, which are expressed in terms of trend slope. It has been observed that, in general, the climate change impacts are not significant on precipitation and runoff This is due to the low trend slopes in the standardized hydro-meteorological time series. This point has been documented for Yesilirmak basin, where the climate change impact is very limited.Öğe Innovative triangular trend analysis(Springer, 2020) Güçlü, Yavuz Selim; Şişman, Eyüp; Dabanlı, İsmailIn this study, based on the Sen innovative trend analysis (ITA) method, another approach has been developed as innovative triangular trend analysis (ITTA), which helps to identify partial trends within a given time series comparatively with each other. The basis of this methodology is to divide a given time series into a set of equal length sub-series and then to compare them pairwise in the form of a triangular array. In this manner, the trends within the whole series can be identified separately in detail. Consequently, it is possible to make much more realistic assessments depending on these trends. The application of the proposed method is carried out by considering the longest annual rainfall measurement records from 1966 to 2015, inclusive for stanbul, Rize, and Ankara provinces in Turkey. As a result, generally monotonically a negative trend in Ankara, no trend in Florya, and positive trend in Rize are determined by ITA methodology. On the other hand, instability of trends in time series is presented for these stations. Ankara has negative and no trend to the first 10 years and the last 20 years, respectively. Florya has successively positive and negative trends from the first to fifth part. As for Rize, according to ITTA, it has generally positive trends.Öğe Kuraklık riskinin bulanık mantık yardımıyla Türkiye genelinde değerlendirilmesi(2019) Dabanlı, İsmailBu çalışmada meteorolojik ve sosyo-ekonomik veriler kullanılarak elde edilen kuraklık afet ve hassasiyetlik göstergeleri yardımıyla Türkiye genelinde kuraklık riski bulanık mantık çıkarımı (BMÇ) yaklaşımıyla bütüncül olarak değerlendirilmiştir. Kuraklık afetinin tam olarak anlaşılmasında kuraklık risk ve hassasiyetinin önemi bilinse de Türkiye için bütüncül ve yeterli miktarda bilimsel çalışmanın varlığından bahsetmek zordur. Kuraklık Afet Göstergesi (KAG) kuraklığın görülme ihtimaline dayanan standart yağış göstergesi (SYG) (Standardized Precipitation Index-SPI) kullanılarak kuraklık kavramının daha iyi anlaşılmasını kolaylaştırmak için hesaplanmıştır. Bunun yanında, Kuraklık Hassasiyet Göstergesi (KHG) kuraklığın sonuçlarının bağlı olduğu güncel dört adet sosyo-ekonomik veri kullanılarak hesaplanmıştır. BMÇ yardımıyla kuraklık afet ve hassasiyet göstergelerinin, kuraklık riskinin belirlenmesindeki öneminin vurgulanması bu çalışmanın temel hedefidir. Çalışma sonucunda elde edilen bulgulara göre Türkiye genelinde 81 il arasında 5 ilin düşük kuraklık riski taşıdığı, 61 ilin orta kuraklık riskine sahip olduğu, 14 ilde yüksek kuraklık riskinin bulunduğu ve son olarak sadece Konya’da çok yüksek kuraklık riski ortaya çıktığı tespit edilmiştir.Öğe General modeling of karst spring hydrographs and development of a dimensionless karstic hydrograph concept(Springer, 2020) Şen, ZekaiThe response of a karstic-aquifer solution-cavity network subjected to a rainfall event leads to a hydrograph with rapidly increasing rising limb, but comparatively slower recession limb. In published studies, initial (early time) recession limb discharges have been modeled by consideration of the square root (nonlinear) response of the hydraulic head to karstic-sinkhole spring discharge. Late-time recession limb discharges are usually modelled by various mathematical methods such as exponential, quadratic and power functions, and straight line on semi-logarithmic plots. Hence, the recession-limb has been represented by different models, but without any model for the middle-time portion. In this paper, first, for early recession-limb times, a power model is developed by means of a convergence series. The result is compared with the literature models and it is observed that the presented model is significantly better than the previous ones. The literature models used the power 0.5, but this study uses 0.6 (a mathematical explanation for this adaptation is given elsewhere). The final portion of the recession limb is modelled by a straight line. Hence, the two-piece model used for the recession limb is examined. Then, a completely new approach is developed, where the whole karstic-sinkhole spring-discharge hydrograph is modelled mathematically by a single model through the logarithmic normal function. Finally, a dimensionless karstic-sinkhole spring-discharge hydrograph is suggested and its graphical and numerical forms are given for practical use by other researchers.Öğe Piecewise wet and dry spell duration-number relationship and possible climate change impact identification in Turkey(Springer, 2019) Şişman, EyüpWet (dry) spells correspond to successive surplus (deficit) in hydro-meteorology daily, weekly, monthly, or annual records according to above (below) of a given any threshold parameter value such as arithmetic average, median, mod, or quantile precipitation. Researchers generally consider wet (dry) spell durations and their numbers, but this paper also focuses on the climate change impacts. For this purpose, available hydro-meteorological records, obtained from different climatic and geographic regions of Turkey, are divided into two half parts, and the wet and dry spell (month) durations are plotted versus their numbers, where the scatter points appear as decreasing straight lines on semi-logarithmic paper, and their mathematical expressions are in the form of exponential functions. The slopes of these straight lines provide useful information about the climate change impacts on each meteorology station. The physical interpretations and explanations are provided through relevant tables and figures. The application of this procedure is presented for a set of meteorology station monthly rainfall records from different climate regions of Turkey.Öğe A climate change impact: Variation in precipitation patterns, and increased drought risk in Turkey(Sakarya University, 2019) Dabanlı, İsmailSince the industrial revolution, temperature averages have been changing both in local and global scale. These variations are related with the climate and global warming changes. Such typical changes (i.e., increasing heavy precipitation, and declined light or total precipitation) are also observed in Turkey. As expected, decreased precipitation usually promotes drought conditions, and can cause extended dry days or periods. Thus, strong relationship can be considered between precipitation scarcity and drought conditions. In this study, changes in precipitation (i.e., total, bottom/lowest and extreme 10%), dry days length, dry spells (>6 days) and drought severity risk based on Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) were evaluated quantitatively over Turkey from 1971 to 2000 with regards to climate changes. Trend analysis is performed by using Innovative-Şen analysis (ITA) method to evaluate trend behavior of precipitation, lengths of dry days and spells. Results show that changes in dry days (?DD/?T) converge to (-2% ±3%)/0C, while changes in prolonged dry spells change (?DS/?T) are comparatively higher (3% ±5%)/0C. For precipitations, mean values of ?P/?T converges to constant value as (-6% ±8%)/0C, (0% ±2%)/0C and (-1% ±4%)/0C for total, top 10% heavy and lowest 10% precipitations, respectively. These changes are supported by ITA outputs. All results support and point out that prolonged drought risk frequency and severity has been increasing.Öğe Temperature difference relationship among precipitation, dry days, and spells in Turkey(Springer Wien, 2019) Dabanlı, İsmailStrong logical relationships exist between temperature difference and hydro-meteorological variables such as precipitation, dry days, and dry spells. These relationships can be used for knowing how the differences of total and top 10% heavy precipitations, dry days, and dry spells will change with respect to temperature differences? Here, daily precipitation and temperature records over Turkey are considered from 1971 to 2010, inclusive. First 30-year (1971-2000) data are used for training for temperature difference function (Delta T) and the remaining 10-year (2001-2010) is reserved for validation. The temperature difference function is validated by mean relative error, and the results are calculated for total and top 10% heavy precipitation, dry days, and spells as 14.60%, 6.14%, 2.81%, and 11.89%, respectively. The strong relationship exists between temperature difference function and standard deviation of corresponding climatic variables. Results show that standard deviation and mean relative error (MRE) have linear correlation. Also, Delta T model predictions are compared with CMIP5 RCPs projections from 2020 to 2100. The suggested model predictions fall within the range of various atmosphere-ocean global circulation (climate) model (AOGCM) scenario RCP 4.5 and RCP 8.5 projections, in addition to model predictions cross-correlation for RCP 2.6 and RCP 6.0.
