Enhanced Downscaling of Urban Land Surface Temperatures Using a Land Cover–Enhanced Nonlinear Model with Landsat-8/9 and Sentinel-2 Imagery

Urban surface temperatures are increasing because of climate change and rapid urbanisation, contributing to the urban heat island (UHI) effect and significantly influencing local climates. Satellite-derived land surface temperature (LST) plays a vital role in analysing urban thermal patterns. However, current satellite thermal infrared (TIR) sensors have a low spatial resolution, making it difficult to accurately capture the complex thermal variations within urban areas. This limitation affects the assessments of UHI effects and hinders effective mitigation strategies. We proposed a hybrid model named “geospatial machine learning” (GeoML) to address these challenges, combining random forest and kriging downscaling techniques. This method utilises high spatial resolution data from Sentinel-2 to enhance the LST derived from Landsat 8/9 data. Tested in Perth, Australia, GeoML generated an enhanced LST with good agreement with ground-based measurements, with a Pearson’s correlation coefficient of 0.85, a root mean square error (RMSE) of 2.7 °C, and a mean absolute error (MAE) of less than 2.2 °C. Validation with LST derived from another TIR sensor also provided promising outputs. The results were compared with the high-resolution urban thermal sharpener (HUTS) downscaling methods, which GeoML outperformed, demonstrating its effectiveness as a valuable tool for urban thermal studies involving high-resolution LST data.

A physical model-based method for retrieving urban land surface temperatures under cloudy conditions

All cities of the world have undergone rapid urbanization. Consequently, urban areas encounter higher surface and air temperatures than the surrounding nonurbanized areas and exhibit urban heat island (UHI) effect. Surface temperature derived from remote sensing data has been used for analyzing the UHI effect over a number of cities. This study has been carried out to predict the land-surface temperature (LST) of Jaipur city, India. Remote sensing data from Moderate-Resolution Imaging Spectroradiometer (MODIS) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) sensors have been used for the prediction. 10-year linear time series (LTS) model has been developed using enhanced vegetation index (EVI), elevation, and LST for the prediction of future LST. Model output has been validated using LST data of the year 2014. A comparison of model-estimated LST and measured LST shows that mean absolute error (MAE) varies from 0.292 to 0.353 and mean absolute percentage error (MAPE) varies from 0.098 to 0.123. High correlation exists between the model-estimated LST and measured LST with an average R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value of 0.95. LTS model developed in this study can be used for many studies involving LST, and it can be a significant tool for the prediction of UHI effect at any location.

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.

Optical sensors cannot penetrate clouds and can cause serious missing data problems in optical-based Land Surface Temperature (LST) products. Under cloudy conditions, microwave observations are usually utilized to derive the land surface temperature. However, microwave sensors usually have coarse spatial resolutions. High-Resolution (HR) LST data products are usually desired for many applications. Instead of developing and launching new high-resolution satellite sensors for LST observations, a more economical and practical way is to develop proper methodologies to derive high-resolution LSTs from available Low-Resolution (LR) datasets. This study explores different algorithms to downscale low-resolution LST data to a high resolution. The existing regression-based downscaling methods usually require simultaneous observations and ancillary data. The Super-Resolution Reconstruction (SRR) method developed for traditional image enhancement can be applicable to high-resolution LST generation. For the first time, we adapted the SRR method for LST data. We specifically built a unique database of LSTs for the example-based SRR method. After deriving the LST data from the coarse-resolution passive microwave observations, the AMSR-E at 25 km and/or AMSR-2 at 10 km, we developed an algorithm to downscale them to a 1 km spatial resolution with the SRR method. The SRR downscaling algorithm can be implemented to obtain high-resolution LSTs without auxiliary data or any concurrent observations. The high-resolution LSTs are validated and evaluated with the ground measurements from the Surface Radiation (SURFRAD) Budget Network. The results demonstrate that the downscaled microwave LSTs have a high correlation coefficient of over 0.92, a small bias of less than 0.5 K, but a large Root Mean Square Error (RMSE) of about 4 K, which is similar to the original microwave LST, so the errors in the downscaled LST could have been inherited from the original microwave LSTs. The validation results also indicate that the example-based method shows a better performance than the self-similarity-based algorithm.

Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies.

Under the trend of rapid urbanization, the urban heat island (UHI) effect has become a hot issue for scholars to study. In order to better alleviate UHI effect, it is important to understand the effect of landuse/landcover (LULC) and landscape patterns on the urban thermal environment from perspective of landscape ecology. This research aims to quantitatively investigate the effect of LULC landscape patterns on UHI effects more accurately based on a landscape metrics analysis. In addition, we also explore the complex relationship between land surface temperature (LST) and vegetation cover. Taking Zhengzhou City of China as a case study, an integrated method which includes the geographic information system (GIS), remote-sensing (RS) technology, and landscape metrics was employed to facilitate the analysis. Landsat data (2000–2014) were applied to investigate the spatiotemporal evolution patterns of LST and LULC. The results indicated that the mean LST value increased by 2.32°C between 2000 and 2014. The rise of LST was consistent with the trend of rapid urbanization in Zhengzhou City, which resulted in sharp increases in impervious surfaces (IS) and substantial losses of vegetation cover. Furthermore, the investigation of LST and vegetation cover demonstrated that fractional vegetation cover (FVC) had a stronger negative effect on LST than normalized differential vegetation index (NDVI). In addition, LST was obviously correlated with LULC landscape patterns, and both landscape composition and spatial configuration affected UHI effects to varying degrees. This study not only illustrates a feasible way to investigate the relationship between LULC and urban thermal environment but also suggests some important measures to improve urban planning to reduce UHI effects for sustainable development.

The local climate of cities is changing, and one of the primary reasons for this change is rapid urbanization. The Lahore district is situated in the Punjab province of Pakistan and is mainly comprised of Lahore city. This city is among the fastest expanding cities in Pakistan. Due to this rapid urbanization, the natural land surfaces are being altered, harming the local environment and thus causing the urban heat island (UHI) effect. For the analysis of the UHI effect, the fundamental and essential step is assessing the land surface temperature (LST). Therefore, the current investigation assessed LST to evaluate the UHI effect of the Lahore district. This study used the remote sensing data retrieved from the Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model (ASTER GDEM) and Moderate-Resolution Imaging Spectroradiometer (MODIS) sensor. Different new generation algorithms were initially used, but a convolutional neural network (CNN) model was used based on the accuracy. The model was developed by utilizing the past 19 years’ LST values along with elevation, road density (RD), and enhanced vegetation index (EVI) as input parameters for analyzing and predicting the LST. The LST data of the year 2020 was used for the validation of the outcomes of the CNN model. Among the model predicted LST and observed LST, a high correlation was noticed. The mean absolute percentage error (MAPE), mean absolute error (MAE), and mean squared error (MSE) for the considered two different periods (January and May) were also computed for both the training and validation processes. The prediction error for most parts of the district was within 0.1 K of the observed values. Hence, the formulated CNN model can be utilized as an essential tool for analyzing and predicting LST and thus for the evaluation of the UHI effect at any location.

Examining urban thermal environment dynamics and relations to biophysical composition and configuration and socio-economic factors: A case study of the Shanghai metropolitan region

Urban temperatures are typically, but not necessarily, elevated compared to their rural surroundings. This phenomenon of urban heat islands (UHI) exists both above and below the ground. These zones are coupled through conductive heat transport. However, the precise process is not sufficiently understood. Using satellite-derived land surface temperature and interpolated groundwater temperature measurements, we compare the spatial properties of both kinds of heat islands in four German cities and find correlations of up to 80%. The best correlation is found in older, mature cities such as Cologne and Berlin. However, in 95% of the analyzed areas, groundwater temperatures are higher than land surface temperatures due to additional subsurface heat sources such as buildings and their basements. Local groundwater hot spots under city centers and under industrial areas are not revealed by satellite-derived land surface temperatures. Hence, we propose an estimation method that relates groundwater temperatures to mean annual land-surface temperatures, building density, and elevated basement temperatures. Using this method, we are able to accurately estimate regional groundwater temperatures with a mean absolute error of 0.9 K.

The urban heat island (UHI) effect has been recognized as one of the most significant terrestrial surface climate-related consequences of urbanization. However, the traditional definition of the urban–rural (UR) division and the newly established local climate zone (LCZ) classification for UHI and urban climate studies do not adequately express the pattern and intensity of UHI. Moreover, these definitions of UHI find it hard to capture the human activity-induced anthropogenic heat that is highly correlated with urban functional zones (UFZ). Therefore, in this study, with a comparison (theory, technology, and application) of the previous definition (UR and LCZ) of UHI and integration of computer programming technology, social sensing, and remote sensing, we develop a new urban functional zone-based urban temperature zoning system (UFZC). The UFZC system is generally a social-based, planning-oriented, and data-driven classification system associated with the urban function and temperature; it can also be effectively used in city management (e.g., urban planning and energy saving). Moreover, in the Beijing case, we tested the UFZC system and preliminarily analyzed the land surface temperature (LST) difference patterns and causes of the 11 UFZC types. We found that, compared to other UFZCs, the PGZ (perseveration green zone)-UFZC has the lowest LST, while the CBZ (center business district zone)-UFZC and GCZ (general commercial zone)-UFZC contribute the most and stable heat sources. This implies that reducing the heat generated by the function of commercial (and industrial) activities is an effective measure to reduce the UHI effect. We also proposed that multi-source temperature datasets with a high spatiotemporal resolution are needed to obtain more accurate results; thus providing more accurate recommendations for mitigating UHI effects. In short, as a new and finer urban temperature zoning system, although UFZC is not intended to supplant the UR and LCZ classifications, it can facilitate more detailed and coupled urban climate studies.

Rapid urban development between the 1960 and 2010 decades have changed the urban landscape and pattern in the Kowloon Peninsula of Hong Kong. This paper aims to study the changes of urban morphological parameters between the 1985 and 2010 and explore their influences on the urban heat island (UHI) effect. This study applied a mono-window algorithm to retrieve the land surface temperature (LST) using Landsat Thematic Mapper (TM) images from 1987 to 2009. In order to estimate the effects of local urban morphological parameters to LST, the global surface temperature anomaly was analysed. Historical 3D building model was developed based on aerial photogrammetry technique using aerial photographs from 1964 to 2010, in which the urban digital surface models (DSMs) including elevations of infrastructures and buildings have been generated. Then, urban morphological parameters (i.e. frontal area index (FAI), sky view factor (SVF)), vegetation fractional cover (VFC), global solar radiation (GSR), Normalized Difference Built-Up Index (NDBI), wind speed were derived. Finally, a linear regression method in Waikato Environment for Knowledge Analysis (WEKA) was used to build prediction model for revealing LST spatial patterns. Results show that the final apparent surface temperature have uncertainties less than 1 degree Celsius. The comparison between the simulated and actual spatial pattern of LST in 2009 showed that the correlation coefficient is 0.65, mean absolute error (MAE) is 1.24 degree Celsius, and root mean square error (RMSE) is 1.51 degree Celsius of 22,429 pixels.

Land surface temperature (LST) is an important parameter that is highly responsive to surface energy fluxes and has become valuable to many disciplines. However, it is difficult to acquire satellite LSTs with both high spatial and temporal resolutions due to tradeoffs between them. Thus, various algorithms/models have been developed to enhance the spatial or the temporal resolution of thermal infrared (TIR) data or LST, but rarely both. The Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) is the widely-used data fusion algorithm for Landsat and MODIS imagery to produce Landsat-like surface reflectance. In order to extend the STARFM application over heterogeneous areas, an enhanced STARFM (ESTARFM) approach was proposed by introducing a conversion coefficient and the spectral unmixing theory. The aim of this study is to conduct a comprehensive evaluation of the ESTARFM algorithm for generating ASTER-like daily LST by three approaches: simulated data, ground measurements and remote sensing products, respectively. The datasets of LST ground measurements, MODIS, and ASTER images were collected in an arid region of Northwest China during the first thematic HiWATER-Multi-Scale Observation Experiment on Evapotranspiration (MUSOEXE) over heterogeneous land surfaces in 2012 from May to September. Firstly, the results of the simulation test indicated that ESTARFM could accurately predict background with temperature variations, even coordinating with small ground objects and linear ground objects. Secondly, four temporal ASTER and MODIS data fusion LSTs (i.e., predicted ASTER-like LST products) were highly consistent with ASTER LST products. Here, the four correlation coefficients were greater than 0.92, root mean square error (RMSE) reached about 2 K and mean absolute error (MAE) ranged from 1.32 K to 1.73 K. Finally, the results of the ground measurement validation indicated that the overall accuracy was high (R2 = 0.92, RMSE = 0.77 K), and the ESTARFM algorithm is a highly recommended method to assemble time series images at ASTER spatial resolution and MODIS temporal resolution due to LST estimation error less than 1 K. However, the ESTARFM method is also limited in predicting LST changes that have not been recorded in MODIS and/or ASTER pixels.

Urban heat redistribution is mainly result of surface energy process. Surface energy process is also contributed in urban environment. Urban heat island (UHI) is mainly defined when urban temperature is elevated compared to surrounding rural area. Both in above and below the ground UHI is observed. This is happened due to conductive heat transport. How the Land surface temperature and ground water temperature are affected by the urban land use in Bangalore is the primary plan of investigation. Landsat data of 1999 and 2009 are used to understand the LU/LC changes. In this present study we used satellite derived Land surface temperature and field collected Ground water temperature which was analyzed using interpolation method and Supervised Classification Change Detection technique applied for change analysis. Here investigation was done for a period of one decade (1999/2009) on LST changes over different land use. Moreover, relationship between NDVI and LST was also considered. To understand urban surface, we estimated Normalized Difference Built-Up Index (NDBI) and Built up Area Index (BUAI); with this we are trying to find relationship with ground water temperature. Changing land use pattern, mostly expansion of built-up area has effect over land surface temperature in Bangalore urban district. The correlation between LST and the Ground water temperature (GWT); has been studied on 2009 data and found 80% correlation between them. In result, it is showing that GWT is less than LST but wherever LST is high there GWT is also high. In city core area like residential, outside industrial and road, GWT and LST both show high but near to lake or park area both show low temperature. Results show that during years 1999 to 2009 that LST and GWT directly affected due to rapid urban growth which reflects over built-up area enlarged from 39 to 57%. We can understand that urbanization has an impact on both on LST and GWT. The study showed that land use land cover change has important role of increasing GWT which is a marker of the strength of urban heat island effect and can be utilized to evaluate the extent of the urban heat island effect.KeywordsGround water temperatureLand surface temperatureBuilt up area indexSub surface urban heat islandRemote sensing

Rapid urbanization has the potential to significantly alter local microclimates through the urban heat islands (UHI) effect. This study examines the spatial and temporal changes in land surface temperature (LST) in Krakow, Poland, from 2002 to 2023 in relation to changes in urban land cover. Multispectral satellite imagery from the Landsat 7/8/9 and Sentinel‑2 missions (clear-sky August scenes at ~5-year intervals) was processed using Google Earth Engine to derive LST and spectral indices. The normalized difference vegetation index (NDVI) and normalized difference built-up index (NDBI) were computed to quantify vegetation loss and built-up area expansion, respectively. A supervised land cover classification (random forest) identified five classes – vegetation, water, built-up areas, roads, and bare soil – providing land cover maps for each analysis year. Satellite-derived LST was validated against in situ ground temperature measurements from 17 sensors deployed across the city in summer 2023. The results reveal pronounced surface warming in Krakow’s urban core and in newly urbanized districts, corresponding to areas of intensive development and vegetation decline. Statistically, LST was negatively correlated with NDVI and positively correlated with NDBI, confirming that reduced green cover and increased impervious surfaces exacerbate surface heating. The satellite LST showed strong agreement with ground measurements, supporting the reliability of the remote sensing approach. Our integrated methodology and findings underscore the impact of urbanization on the city’s microclimate and the critical role of green infrastructure in mitigating UHI effects. This approach provides a framework for evidence-based urban planning and climate adaptation strategies in other Central European cities.