Prediction of climatic changes caused by land use changes in urban area using artificial neural networks

THEORETICAL AND APPLIED CLIMATOLOGY, sa.2023, ss.1-15, 2023 (SCI-Expanded)

Yayın Türü: Makale / Tam Makale
Basım Tarihi: 2023
Doi Numarası: 10.1007/s00704-023-04386-4
Dergi Adı: THEORETICAL AND APPLIED CLIMATOLOGY
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, IBZ Online, PASCAL, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Artic & Antarctic Regions, BIOSIS, CAB Abstracts, Environment Index, Geobase, Index Islamicus, INSPEC, Pollution Abstracts, Veterinary Science Database
Sayfa Sayıları: ss.1-15
Akdeniz Üniversitesi Adresli: Evet

The aim of this study was to investigate the use of artificial neural networks (ANNs) as a simulation tool to predict thermal

changes in urban areas. Istanbul Airport, which is a recently constructed mega project in Istanbul, was selected as the study

area. In the study, the texture transfer method which allows creating synthetic images is used as a new image processing

technique. This method allows land-use changes to be represented by texture pixels transfers that represent similar land-use

types before the construction phase of a project. According to the results, while the surface temperature predictions for the

warmed and cooled points were obtained with 79% and 54% accuracy respectively for one-to-one overlapping, 97% accuracy

rates were reached within 300 m. This study revealed that the effect on the urban climate from surface changes that might

occur in cities can be predicted by employing an ANN algorithm.