https://hdl.handle.net/20.500.12573/204 Fri, 08 May 2026 06:28:38 GMT 2026-05-08T06:28:38Z https://hdl.handle.net/20.500.12573/2509 Probabilistic assessment of wind power plant energy potential through a copula-deep learning approach in decision trees Şahin, Kübra Nur; Sutcu, Muhammed In the face of environmental degradation and diminished energy resources, there is an urgent need for clean, affordable, and sustainable energy solutions, which highlights the importance of wind energy. In the global transition to renewable energy sources, wind power has emerged as a key player that is in line with the Paris Agreement, the Net Zero Target by 2050, and the UN 2030 Goals, especially SDG-7. It is critical to consider the variable and intermittent nature of wind to efficiently harness wind energy and evaluate its potential. Nonetheless, since wind energy is inherently variable and intermittent, a comprehensive assessment of a prospective site's wind power generation potential is required. This analysis is crucial for stakeholders and policymakers to make well-informed decisions because it helps them assess financial risks and choose the best locations for wind power plant installations. In this study, we introduce a framework based on Copula-Deep Learning within the context of decision trees. The main objective is to enhance the assessment of the wind power potential of a site by exploiting the intricate and non-linear dependencies among meteorological variables through the fusion of copulas and deep learning techniques. An empirical study was carried out using wind power plant data from Turkey. This dataset includes hourly power output measurements as well as comprehensive meteorological data for 2021. The results show that acknowledging and addressing the non-independence of variables through innovative frameworks like the Copula-LSTM based decision tree approach can significantly improve the accuracy and reliability of wind power plant potential assessment and analysis in other real-world data scenarios. The implications of this research extend beyond wind energy to inform decision-making processes critical for a sustainable energy future. Mon, 01 Jan 2024 00:00:00 GMT https://hdl.handle.net/20.500.12573/2509 2024-01-01T00:00:00Z https://hdl.handle.net/20.500.12573/2497 A NEW RATIONAL CLASSIFICATION APPROACH BY THE NEW MIXED DATA BINARIZATION METHOD Sütçü, Muhammed; Gülbahar, İbrahim Tümay Classification algorithm is a supervised learning technique that is used to identify the category of new observations. However, in some cases, quantitative and qualitative data must be used together. With this approach, we tried to overcome the problems encountered in using quantitative and qualitative data together. In this paper, we model a new classification technique by converting all types of data to binary data because in the real world, data are classified in different types such as binary, numeric, or categorical. By this way, we develop a more accurate and efficient mixed data binarization approach for multi-attribute data classification problems. First, we determine the classes from available dataset and then we classify the new instances into these predetermined classes by using the new proposed data binarization approach. We show how each step of this algorithm could be performed efficiently with a numeric example. Then, we apply the proposed approach on a well-known iris dataset and our model show promising results and improvements over previous approaches.; Sınıflandırma algoritması, yeni gözlemlerin kategorisini belirlemek için kullanılan denetimli bir öğrenme tekniğidir. Ancak bazı durumlarda nicel ve nitel verilerin birlikte kullanılması gerekir. Bu yaklaşımla nicel ve nitel verilerin birlikte kullanılmasında karşılaşılan sorunlar aşılmaya çalışılmıştır. Bu çalışmada, gerçek dünyada veriler ikili, sayısal veya kategorik gibi farklı türlerde sınıflandırıldığından, tüm veri türlerini ikili verilere dönüştürerek yeni bir sınıflandırma tekniği modellenmektedir. Bu sayede çok özellikli veri sınıflandırma problemleri için daha doğru ve verimli bir karma veri ikilileştirme yaklaşımı geliştirilmiştir. Öncelikle mevcut veri setinden sınıfları belirlenmektedir ve ardından yeni önerilen veri ikilileştirme yaklaşımını kullanarak yeni örnekleri bu önceden belirlenmiş sınıflara sınıflandırılmaktadır. Bu algoritmanın her adımının nasıl verimli bir şekilde gerçekleştirilebileceğini sayısal bir örnekle gösterilmiştir. Ardından, önerilen yaklaşımı iyi bilinen bir iris veri kümesine uygulamış ve modelimiz önceki yaklaşımlara göre umut verici sonuçlar ve iyileştirmeler verdiği gösterilmiştir. Sun, 01 Jan 2023 00:00:00 GMT https://hdl.handle.net/20.500.12573/2497 2023-01-01T00:00:00Z https://hdl.handle.net/20.500.12573/2494 Karadeniz Bölgesi’nde Kurak ve Nemli Dönemlerin SPI Yöntemi Kullanılarak Belirlenmesi Öztürk, Yasemin Deniz; Ünlü, Ramazan Karadeniz bölgesi Türkiye’nin en çok yağış alan bölgesidir. Ancak Karadeniz Bölgesi’nde yağışlar hem yıllar arasında hem de bölge içerisinde önemli farklılıklara sahiptir. Bu durum bölgede kuraklıkların yaşanabilmesine ve kurak-nemli dönemlerin birbirini takip etmesine neden olmaktadır. Bu çalışmada yıllık ve 12 aylık SPI değerlerine göre Karadeniz bölgesinde yaşanan kurak ve nemli dönemlerin belirlenmesi amaçlanmıştır. Bölge genelinden seçilen 26 istasyonun 1960-2020 yılları arasındaki ortalama yağış verilerine göre standardize yağış indeksi (SPI) değerleri hesaplanmıştır. Tespit edilen kurak ve nemli dönemlerin eğilimleri MannKendall trend analizi kullanılarak tespit edilmiştir. Ayrıca ısı haritası kullanılarak Karadeniz Bölgesi kıyı ve iç kesimleri olarak ayrılıp kurak ve nemli dönemleri saptanmıştır. Analiz sonuçlarına göre 1966, 1969, 1974-1977, 1984-1986, 1993-1994, 2006-2007 ve 2019- 2020 yıllarının normalden daha az yağış aldığı ve birçok istasyonun kuraklığı şiddetli şekilde olduğu saptanmıştır. 1967, 1988, 1996- 1997, 1999, 2009 ve 2016 yıllarının ise normalden fazla yağış aldığını yani nemli karakterde olduğunu göstermektedir. Mann-Kendall trend analiz sonuçlarına göre Batı Karadeniz Bölgesinin kıyı kesimlerinde azalma eğilimde olduğu saptanmamıştır. Fakat azalışta anlamlılık bulunamamıştır. Orta ve Doğu Karadeniz bölgesinde ise artış eğilimi göstermekle birlikte bu eğilim bazı istasyonlarda anlamlı bulunmuştur. Bölgenin yer şekilleri dolayısıyla genel bir kurak ve genel bir nemli dönem olmadığı, doğu-batı doğrultusu ve kıyı-iç kesimlerde kurak ve nemli dönemlerin farklılık gösterdiği saptanmıştır.; The Black Sea region is the region with the highest rainfall in Türkiye. However, precipitation in the Black Sea region varies considerably both between years and within the region. This situation causes droughts in the region, with dry and wet periods following each other. This study aimed to determine the drought and wet periods in the Black Sea region according to the annual and 12-month SPI values. Standardized Precipitation Index (SPI) values were calculated according to the average precipitation data of 26 meteorology stations selected from the region between 1960 and 2020. The trends of the identified drought and wet periods were determined using Mann-Kendall trend analysis. In addition, using the heat map, the drought and wet periods of the Black Sea Region were determined by dividing coastal and inland areas. The analysis results determined that 1966, 1969, 1974-1977, 1984-1986, 1993- 1994, 2006-2007, and 2019-2020 received less rainfall than normal and many stations had severe drought. It shows that 1967, 1988, 1996-1997, 1999, 2009, and 2016 received more precipitation than normal, that is, it has a humid character. According to the MannKendall trend analysis results, it was not found that there was a decreasing trend in the coastal areas of the Western Black Sea Region. However, there was no significance in the decrease. Although there is an increasing trend in the Central and Eastern Black Sea region, this trend was found to be significant in some stations. Due to the landforms of the region, it was determined that there was not a general dry period or a general wet period and that the drought and wet periods differed in the east-west direction and the coastalinland areas. Mon, 01 Jan 2024 00:00:00 GMT https://hdl.handle.net/20.500.12573/2494 2024-01-01T00:00:00Z https://hdl.handle.net/20.500.12573/2398 Sustainability assessment of denim fabric made of PET fiber and recycled fiber from postconsumer PET bottles using LCA and LCC approach with the EDAS method Fidan, Fatma Şener; Aydoğan, Emel Kızılkaya; Uzal, Niğmet The textile industry is under pressure to adopt sustainable production methods because its contribution to global warming is expected to rise by 50% by 2030. One solution is to increase the use of recycled raw material. The use of recycled raw material must be considered holistically, including its environmental and economic impacts. This study examined eight scenarios for sustainable denim fabric made from recycled polyethylene terephthalate (PET) fiber, conventional PET fiber, and cotton fiber. The evaluation based on the distance from average solution (EDAS) multicriteria decision‐making method was used to rank scenarios according to their environmental and economic impacts, which are assessed using life cycle assessment and life cycle costing. Allocation, a crucial part of evaluating the environmental impact of recycled products, was done using cut‐off and waste value. Life cycle assessments reveal that recycled PET fiber has lower freshwater ecotoxicity and fewer eutrophication and acidification impacts. Cotton outperformed PET fibers in human toxicity. Only the cut‐off method reduces potential global warming with recycled PET. These findings indicated that recycled raw‐material life cycle assessment requires allocation. Life cycle cost analysis revealed that conventional PET is less economically damaging than cotton and recycled PET. The scenarios were ranked by environmental and economic impacts using EDAS. This ranking demonstrated that sustainable denim fabric production must consider both economic and environmental impacts. Integr Environ Assess Manag 2024;20:2347–2365. © 2024 The Author(s). Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC). Mon, 01 Jan 2024 00:00:00 GMT https://hdl.handle.net/20.500.12573/2398 2024-01-01T00:00:00Z