Machine-Learning Based Modelling of Air Temperature in the Complex Environment of Yerevan City, Armenia.

• DOI: 10.20944/preprints202304.0105.v1
• Publication Date: 2023-04-10T00:35:10Z
• Authors: Garegin Tepanosyan; Shushanik Asmaryan; Vahagn Muradyan; Rima Avetisyan; Azatuhi Hovsepyan; Anahit Khlghatyan; Grigor Ayvazyan; Fabio Dell’Acqua
• Keywords: 570; machine learning (ML); Science; ML-driven partial least-squares regression (PLSR); Q; land surface temperature; multiple independent variables; urban air temperature; urban air temperature; land surface temperature; multiple independent variables; urban heat; remote sensing data; machine learning (ML); ML-driven partial least-squares regression (PLSR); remote sensing data; 11. Sustainability; urban heat; multiple independent variable; remote_sensing_113

Machine Learning (ML) was used to assess and predict urban air temperature (Tair) considering the complexity of terrain features in Yerevan (Armenia). The estimation performed based on PLSR model with a high number (30) input variables. relevant parameters include newly purposed modification spectral index IBI-SAVI, which turned out be strongly impacting Tair prediction together land surface (LST). Cross-validation analysis predictions across station-centered 1000m circular area revealed quite correlation (R2Val = 0.77, RMSEVal 1.58) between predicted measured from test set. It concluded remote sensing is an effective tool estimate distribution where dense network weather stations not available. However, further developments will incorporation additional such as precipitation wind speed, use non-parametric ML techniques.