SUHI intensity in relation to land use changes in urban areas using neural networks and remote sensing

• Published in: International journal of environmental science and technology (Tehran) 2024-09, Vol.21 (13), p.8417-8430
• Main Authors: Mokarram, M., Taripanah, F., Pham, T. M.
• Format: Article
• Language: English
• Subjects: Aquatic Pollution; Earth and Environmental Science; Ecotoxicology; Environment; Environmental Chemistry; Environmental Science and Engineering; Original Paper; Soil Science & Conservation; Waste Water Technology; Water Management; Water Pollution Control
• ISSN: 1735-1472; 1735-2630
• DOI: 10.1007/s13762-024-05584-x

In urban areas, the expansion of urbanization is associated with an increase in thermal pollution. Therefore, it is important to conduct research on the temperature of the earth's surface over time, and how it correlates with vegetation and urban heat islands (UHI). This study utilized vegetation and temperature indices to measure urban temperatures in two metropolises in Iran during July, August, and September of 2001 and 2020. By employing regression analysis, Markov and CA-Markov chains, and artificial neural networks (ANNs), the relationship between land surface temperature (LST), vegetation, and thermal indices was analyzed for predictions of these indices in 2040. The findings revealed that NDVI and PV indices were lower in urban areas than in rural areas, while UI and NDBI indices were higher in urban areas. The indices of NDVI ( R 2  = 0.779), UTFVI ( R 2  = 0.985), and NDBI ( R 2  = 0.847) had a strong correlation with LST in urban areas. Furthermore, with continued urbanization, there will likely be significant temperature changes in 2040 due to land use changes. The multilayer perceptron ANN method proved to be effective in forecasting thermal indices with high accuracy. Such an approach is necessary for supporting detailed planning to prevent thermal pollution from increasing in urban areas.