TY - GEN
T1 - Detection and Characterization of Urban Heat Islands with Machine Learning
AU - Bhamjee, Muaaz
AU - Debary, Hiyam
AU - Gaffoor, Zaheed
AU - Govindasamy, Tamara
AU - Mahlasi, Craig
AU - Fiaz, Mustansar
AU - Vos, Etienne
AU - Klein, Levente
AU - Makhanya, Sibusisiwe
AU - Watson, Campbell
AU - Kuehnert, Julian
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Assessing and understanding the urban scale impacts of extreme climate events is a global necessity. Risks associated with heat, where intra-urban dynamics and rural/urban boundary conditions greatly impact its distribution, are of particular interest as the evolution of climate change and ur-banization persists. Characterizing Urban Heat Island (UHI) effects is dependent on the availability of high-resolution near-surface air temperature maps and a description of the Local Climate Zones (LCZs). This study assesses the applicability of state-of-the-art (SOTA) Artificial Intelligence (AI) techniques for UHI detection and characterization. A Geospatial Foundation Model (GFM) is fine-tuned to predict 2 m air temperature at a 1 km resolution for the urban areas of Johannesburg, South Africa, with mean absolute error measures less than 1.5 °C. UHI characterization is further enabled through a Fully Connected Network (FCN) model for LCZs classification for the same region of interest.
AB - Assessing and understanding the urban scale impacts of extreme climate events is a global necessity. Risks associated with heat, where intra-urban dynamics and rural/urban boundary conditions greatly impact its distribution, are of particular interest as the evolution of climate change and ur-banization persists. Characterizing Urban Heat Island (UHI) effects is dependent on the availability of high-resolution near-surface air temperature maps and a description of the Local Climate Zones (LCZs). This study assesses the applicability of state-of-the-art (SOTA) Artificial Intelligence (AI) techniques for UHI detection and characterization. A Geospatial Foundation Model (GFM) is fine-tuned to predict 2 m air temperature at a 1 km resolution for the urban areas of Johannesburg, South Africa, with mean absolute error measures less than 1.5 °C. UHI characterization is further enabled through a Fully Connected Network (FCN) model for LCZs classification for the same region of interest.
KW - AI techniques
KW - Geospatial Foundation Models
KW - Local Climate Zones
KW - Urban Heat Islands
KW - urban scale temperature
UR - http://www.scopus.com/inward/record.url?scp=85204905736&partnerID=8YFLogxK
U2 - 10.1109/IGARSS53475.2024.10641750
DO - 10.1109/IGARSS53475.2024.10641750
M3 - Conference contribution
AN - SCOPUS:85204905736
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 1693
EP - 1699
BT - IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024
Y2 - 7 July 2024 through 12 July 2024
ER -
