Development of high resolution air pollution modeling using deep learning and computational fluid dynamics methods in modeling of vehicular emissions

by Tuğçe Akca Güler | Dec 11, 2024

Funding Agency: Tubitak 1001_122Y267

Project Coordinator :  Prof. Dr. S. Levent Kuzu   (Istanbul Technical University)
Investigators:  Prof. Dr. Şeref Naci Engin   (Yıldız Technical University )

Air quality modeling studies are conventionally carried out using dispersion models, aiming to predict pollutant concentrations at ground level or at a specified height. In urban areas, the exclusion of buildings from the modeling domain can lead to prediction errors, particularly in terrains such as streets or avenues where vehicles pass. Additionally, emissions are often estimated using assumptions that may result in unrealistic predictions. The innovative aspects of the proposed project are as follows:  i) Incorporating real terrain conditions, including buildings, into the modeling study, ii) Collecting real-time data on vehicle types, numbers, and speeds for the modeled region and time frame.  Subsequently, the collected data will be used as input for a high-resolution computational fluid dynamics (CFD) model, enabling pollutant predictions at any point within the geometry.  The study will focus on the modeling and calculation of NO, NO₂, and CO emissions to represent traffic emissions. Model results will be validated against data obtained from air quality monitoring stations. A more innovative approach, deep learning, will be employed to estimate vehicle emissions. Images captured from fixed traffic cameras will be processed using the YOLO object detection algorithm to create a comprehensive dataset, including real-time information on vehicle types, speeds, and counts. This approach will enable the dynamic determination of each vehicle's contribution to the pollution level in the region. Total vehicle emissions will be calculated using COPERT, following the most comprehensive methodology, Tier-3. The data obtained will serve as input for the CFD model.


(a) Image labelling and vehicle detection (b) Air quality model

İTÜ Faculty of Civil Engineering

It can be accepted that the history of ITU Civil Engineering Faculty was commenced in 1727 by the establishment of Humbarahane during the era of Damat İbrahim Paşa. However, this attempt was to no avail due to the martyrization of the studwents of this school by the Janissaries.

In 1734, during the grand viziership of Topal Osman Paşa, classes related to Civil Engineering was being taught in Hendesehane, which was founded in Üsküdar. Similarly, this school was also closed after three years due to the opposition of the Janissaries. The reasons of the tragedy that occured in Battle of Chesma, 1770 were inadequacy of the ships and the ignorance of the Ottoman Navy.

Although the Atlantic Map (1513) and the Map of Europe and the Mediterranean Sea (1523) by Piri Reis were the leading pieces of the era, Ottoman viziers were so ignorant that they claimed it was impossible for the Russian Baltic Fleet to reach the Mediterranean Sea assuming that there were no sea connection. With the proposal from Gazi Hasan Paşa and Baron de Tott, Mühendishane-i Bahri-i Humayun was established during the time of Sultan Mustafa III, aiming to train naval construction engineers. Since Ottoman Empire did not have any engineering schools at the time, military engineering classes were taught by French engineers beginning from 1784. French lecturers had to return to their country in 1788 with the increasing suppression from Austria and Russia, which were unwilling for the development and thriving of Ottoman Empire. In 1759, during the Grand Viziership of Koca Ragıp Paşa, Humbarahane was reopened in Karaağaç, Haliç (Golden Horn) and continued to teach even though it was incompetent. In 1792, Lağımcı Ocağı and Humbaracı Ocağı (Guild of Sappers) were established.