Modeling and Estimating the Land Surface Temperature (LST) Using Remote Sensing and Machine Learning (Case Study: Yazd, Iran)

Abstract

The pressing issue of global warming is particularly evident in urban areas, where urban thermal islands amplify the warming effect. Understanding land surface temperature (LST) changes is crucial in mitigating and adapting to the effect of urban heat islands, and ultimately addressing the broader challenge of global warming. This study estimates LST in the city of Yazd, Iran, where field and high-resolution thermal image data are scarce. LST is assessed through surface parameters (indices) available from Landsat-8 satellite images for two contrasting seasons—winter and summer of 2019 and 2020, and then it is estimated for 2021. The LST is modeled using six machine learning algorithms implemented in R software (version 4.0.2). The accuracy of the models is measured using root mean square error (RMSE), mean absolute error (MAE), root mean square logarithmic error (RMSLE), and mean and standard deviation of the different performance indicators. The results show that the gradient boosting model (GBM) machine learning algorithm is the most accurate in estimating LST. The albedo and NDVI are the surface features with the greatest impact on LST for both the summer (with 80.3% and 11.27% of importance) and winter (with 72.74% and 17.21% of importance). The estimated LST for 2021 showed acceptable accuracy for both seasons. The GBM models for each of the seasons are useful for modeling and estimating the LST based on surface parameters using machine learning, and to support decision-making related to spatial variations in urban surface temperatures. The method developed can help to better understand the urban heat island effect and ultimately support mitigation strategies to improve human well-being and enhance resilience to climate change.

Integrating Remote Sensing and Ground-Based Data for Enhanced Spatial–Temporal Analysis of Heatwaves: A Machine Learning Approach

“…Employing unseen test data and cross-validation methods can help mitigate this risk and ensure improved performance on new datasets [119,120]. Furthermore, regarding the use of the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Built-Up Index (NDBI) for downscaling the TIR bands, an improvement in performance accuracy should be further considered in modeling LST [121,122] In examining the spatial and temporal patterns of heatwaves, our findings highlight a distinct trend across various regions. During daytime heatwaves, peri-urban areas such as Pathum Thani and urban locations like Don Muang in Bangkok are particularly affected, showing significant increases in HWF, HWD, HWM, and HWA.…”

Feasibility of Urban–Rural Temperature Difference Method in Surface Urban Heat Island Analysis under Non-Uniform Rural Landcover: A Case Study in 34 Major Urban Agglomerations in China

“…The MODIS LST, widely employed in SUHII quantification [33][34][35], was sourced from the MOD11A1 and MYD11A1 datasets (Version 6) onboard the Terra and Aqua satellites. These datasets offer daily surface temperature/emissivity product data for each pixel, with a spatial resolution of 1 km and a sinusoidal projection.…”

Spatiotemporal Patterns in the Urban Heat Island Effect of Several Contemporary and Historical Chinese “Stove Cities”

“…Furthermore, there is a focus on simulating urban thermal environments. For instance, Mansourmoghaddam et al employed six machine learning algorithms to model and estimate LST [8].…”