EYElif Yavuz

Elif Yavuz

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Elif Yavuz has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Predictive Modeling of Vehicle Emissions Using Deep Learning Techniques and AERMOD

    by Elif Yavuz, Alihan Öztürk, Nedime Gaye Nur Balkanlı, Şeref Naci Engin, S. Levent Kuzu

  • İSTANBUL'DA KENTSEL ARKA PLANDA ATMOSFERIK SIYAH KARBON KONSANTRASYON DEĞIŞIMININ DEĞERLENDIRILMESI

    by Zehra Çolak, Burcu Onat, Melike Servin Coşgun, Burcu Uzun Ayvaz, Coşkun Ayvaz, S. Levent Kuzu, Elif Yavuz, Hilal Çetin, Zeynep Fidan, Ülkü Alver Şahin

    Siyah karbon (Black Carbon, BC), eksik bir yanma ürünüdür ve ince partikül madde bileşeni olup solunduğunda insan sağlığı için zararlıdır. Ayrıca BC iklim değişikliğinde kısa ömürlü iklim zorlayıcısı (short lived climate force) olarak tanımlanmakta ve CO2’den sonra önemli bir ısı tutma etkisine sahiptir. Dünyanın diğer kentlerinde atmosferik BC konsantrasyon değişimi oldukça yaygın çalışılmışken, Türkiye’de sadece İstanbul’da kısıtlı sayıda trafik alanlarında çalışma bulunmaktadır. Bu çalışmada, İstanbul’da ilk kez kent arkaplanda BC’nin değişimleri ve diğer parametrelerle ilişkisi mevsimsel olarak incelenmiştir. BC ölçümleri tek dalga boyunda (880 nm) tek kanallı AE51 aethalometre ile yapılmıştır. Mevsimsel ortalama BC konsantrasyon değişimleri yaz, sonbahar, kış ve ilkbahar dönemlerinde sırasıyla 1,97 ± 3,10 µg/m3, 1,77 ± 2,36 µg/m3, 3,33 ± 4,29 µg/m3, 3,22 ± 3,25 µg/m3 olarak ölçüldü. En yüksek konsantrasyon kışın gözlendi. BC ile partikül madde ve trafikle ilgili kirleticiler (NOX gibi) arasında pozitif yüksek korelasyonlar olduğu tespit edildi. BC’nin gün içi saatlik değişimleri incelendiğinde trafiğin yoğun olduğu sabah ve akşam saatlerinde İstanbul trafiğinin bölgesel emisyonlara katkısı olduğu görüldü. Rüzgâr hızı, PBLH gibi meteorolojik parametrelerin ve mevsimsel konsantrasyon üzerinde önemli bir etkisi olduğu ve trafik kaynağının kentsel arka plan bölgesinde her mevsim önemli bir BC kaynağı olduğu söylenebilir. Kentsel ortamlarda BC’nin mekânsal dağılımının anlaşılması için uzun süreli mevsimsel farklar ortaya konulmasını ve hem sabit hem mobil ölçümlerle izlenmesini tavsiye ediyoruz.


  • Open Access

    Development of Artificial Intelligent-Based Methodology to Prepare Input for Estimating Vehicle Emissions

    by Elif Yavuz, Alihan Öztürk, Nedime Gaye Nur Balkanlı, Şeref Naci Engin, S. Levent Kuzu

    Machine learning has significantly advanced traffic surveillance and management, with YOLO (You Only Look Once) being a prominent Convolutional Neural Network (CNN) algorithm for vehicle detection. This study utilizes YOLO version 7 (YOLOv7) combined with the Kalman-based SORT (Simple Online and Real-time Tracking) algorithm as one of the models used in our experiments for real-time vehicle identification. We developed the “ISTraffic” dataset. We have also included an overview of existing datasets in the domain of vehicle detection, highlighting their shortcomings: existing vehicle detection datasets often have incomplete annotations and limited diversity, but our “ISTraffic” dataset addresses these issues with detailed and extensive annotations for higher accuracy and robustness. The ISTraffic dataset is meticulously annotated, ensuring high-quality labels for every visible object, including those that are truncated, obscured, or extremely small. With 36,841 annotated examples and an average of 32.7 annotations per image, it offers extensive coverage and dense annotations, making it highly valuable for various object detection and tracking applications. The detailed annotations enhance detection capabilities, enabling the development of more accurate and reliable models for complex environments. This comprehensive dataset is versatile, suitable for applications ranging from autonomous driving to surveillance, and has significantly improved object detection performance, resulting in higher accuracy and robustness in challenging scenarios. Using this dataset, our study achieved significant results with the YOLOv7 model. The model demonstrated high accuracy in detecting various vehicle types, even under challenging conditions. The results highlight the effectiveness of the dataset in training robust vehicle detection models and underscore its potential for future research and development in this field. Our comparative analysis evaluated YOLOv7 against its variants, YOLOv7x and YOLOv7-tiny, using both the “ISTraffic” dataset and the COCO (Common Objects in Context) benchmark. YOLOv7x outperformed others with a mAP@0.5 of 0.87, precision of 0.89, and recall of 0.84, showing a 35% performance improvement over COCO. Performance varied under different conditions, with daytime yielding higher accuracy compared to night-time and rainy weather, where vehicle headlights affected object contours. Despite effective vehicle detection and counting, tracking high-speed vehicles remains a challenge. Additionally, the algorithm’s deep learning estimates of emissions (CO, NO, NO2, NOx, PM2.5, and PM10) were 7.7% to 10.1% lower than ground-truth.


  • Open Access

    Investigation of the Near Future Solar Energy Changes Using a Regional Climate Model over Istanbul, Türkiye

    by Yusuf Duran, Elif Yavuz, Bestami Özkaya, Yüksel Yalçin, Çağatay Variş, S. Levent Kuzu

    This study aims to assess potential changes in radiation values at the solar power plant facility in Istanbul using the RegCM. This analysis seeks to estimate the extent of the solar radiation changes and evaluate the production capacity of solar power in Istanbul in the future. The research involved installing an off-grid rooftop solar energy system. Meteorological parameters (temperature, etc.) and the system’s outputs were monitored to evaluate the energy production and its relationship with these parameters. The performance of the Regional Climate Model version 5.0 (RegCMv5) in accurately representing surface solar radiation and temperature patterns was assessed by comparing it with measured monocrystalline solar panel output data. The impact of different cumulus convection schemes was examined on the sensitivity of the RegCM by analyzing surface solar radiation data over the initial three months. Long-term simulations were conducted with the representational concentration path (RCP) scenarios of 2.6, 4.5, and 8.5 spanning from 2023 to 2050 with convection schemes yielding the best results. All scenarios project a slight decrease in incoming surface radiation.


  • Open Access

    Investigation of aerosol direct radiative forcing during a dust storm using a regional climate model over Turkiye

    by Elif Yavuz, Levent Kuzu, Serdar Uğurdoğan, Arslan Saral

    Dust particles originating from arid zones can be transported long distances and change the radiation budget. Understanding atmospheric aerosols and their radiative forcing is important to determine their global and regional climate effects. The aim of this study is to simulate the dust transport event that occurred on March 22, 2018, using RegCM-4.5 and investigate the radiative forcing effect of Saharan dust particles. The model was run with the 4 dust bin chemistry option and the direct effect of aerosols on the regional radiation balance was investigated. Validation of the model was made by a comparison between simulated aerosol optical depth (AOD) and MODIS satellite data. The radiative forcing at the top and surface was calculated at all sky conditions. During the dust episode, the shortwave radiative forcing was ranging between -3 and -50 W/m2 at surface and -2 and -22 W/m2 at top of atmosphere while the longwave radiative forcing was between 0.5 and 8 W/m2 at surface and 0.2 and 2 W/m2 at top of atmosphere over Turkiye. In Istanbul it produced a cooling up to -18 W/m2 at surface and -9 W/m2 at top of atmosphere, a warming up to 3.5 W/m2 at surface and 0.6 W/m2 at top of atmosphere.