Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evolution of urban areas and land surface temperature

Sudipan Saha, Tushar Verma, Dario Augusto Borges Oliveira

TL;DR

The paper addresses how urban expansion influences land surface temperature (LST) by analyzing 20-year summer LST time-series on three cities using unsupervised clustering. It constructs pixel-wise LST trajectories of length $T=20$ and applies $k$-means clustering with $k=4$ to detect spatio-temporal LST patterns, then compares these clusters to built-up density derived from Sentinel-2 using the NDBI and IoU. The work reveals city-specific dynamics, including peripheral LST warming and, in Kolkata, a directional shift of the LST center-of-mass, with IoU values highlighting substantial overlap between LST patterns and built-up areas ($0.58$, $0.76$, $0.59$ for Kolkata, Sao Paulo, and Munich respectively). These findings enhance understanding of urban heat island development and offer a scalable framework for linking remote-sensing LST dynamics to urban planning and climate adaptation.

Abstract

With the global population on the rise, our cities have been expanding to accommodate the growing number of people. The expansion of cities generally leads to the engulfment of peripheral areas. However, such expansion of urban areas is likely to cause increment in areas with increased land surface temperature (LST). By considering each summer as a data point, we form LST multi-year time-series and cluster it to obtain spatio-temporal pattern. We observe several interesting phenomena from these patterns, e.g., some clusters show reasonable similarity to the built-up area, whereas the locations with high temporal variation are seen more in the peripheral areas. Furthermore, the LST center of mass shifts over the years for cities with development activities tilted towards a direction. We conduct the above-mentioned studies for three different cities in three different continents.

Evolution of urban areas and land surface temperature

TL;DR

The paper addresses how urban expansion influences land surface temperature (LST) by analyzing 20-year summer LST time-series on three cities using unsupervised clustering. It constructs pixel-wise LST trajectories of length and applies -means clustering with to detect spatio-temporal LST patterns, then compares these clusters to built-up density derived from Sentinel-2 using the NDBI and IoU. The work reveals city-specific dynamics, including peripheral LST warming and, in Kolkata, a directional shift of the LST center-of-mass, with IoU values highlighting substantial overlap between LST patterns and built-up areas (, , for Kolkata, Sao Paulo, and Munich respectively). These findings enhance understanding of urban heat island development and offer a scalable framework for linking remote-sensing LST dynamics to urban planning and climate adaptation.

Abstract

With the global population on the rise, our cities have been expanding to accommodate the growing number of people. The expansion of cities generally leads to the engulfment of peripheral areas. However, such expansion of urban areas is likely to cause increment in areas with increased land surface temperature (LST). By considering each summer as a data point, we form LST multi-year time-series and cluster it to obtain spatio-temporal pattern. We observe several interesting phenomena from these patterns, e.g., some clusters show reasonable similarity to the built-up area, whereas the locations with high temporal variation are seen more in the peripheral areas. Furthermore, the LST center of mass shifts over the years for cities with development activities tilted towards a direction. We conduct the above-mentioned studies for three different cities in three different continents.
Paper Structure (7 sections, 3 figures)

This paper contains 7 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Urbanization and LST
  3. Data Sources and Methods
  4. Results
  5. Analyzed ROIs
  6. Result analysis
  7. Conclusions

Figures (3)

  • Figure 1: Visualization of LST variation in a ROI around Kolkata, India for year: (a) 2004, (b) 2005, (c) 2006, (d) 2021, (e) 2022, (f) 2023. (g) Areas with strong LST temporal variation shown in black. (h) RGB image of the analyzed scene with center of mass in 2004 and 2023 shown in blue and red, respectively. (h) clusters/groups obtained from LST time-series.
  • Figure 2: Visualization of LST variation in a ROI around Sao Paulo, Brazil for year: (a) 2004, (b) 2005, (c) 2022, (d) 2023. (e) Areas with strong LST temporal variation shown in black. (f) RGB image of the analyzed scene with center of mass in 2004 and 2023 shown in blue and red, respectively. (g) clusters/groups obtained from LST time-series.
  • Figure 3: Visualization of LST variation in a ROI around Munich, Germany for year: (a) 2003, (b) 2004, (c) 2021, (d) 2022. e) Areas with strong LST temporal variation shown in black. (f) RGB image of the analyzed scene with center of mass in 2003 and 2022 shown in blue and red, respectively. (g) clusters/groups obtained from LST time-series.