Home ITCAbout ITCCentres of expertiseCenter of Expertise in Big Geodata ScienceBig Geodata StoriesDownscaling Land Surface Temperature using SAR images: A Machine Learning Framework
Waleed Alzuhair, flickr

Downscaling Land Surface Temperature using SAR images: A Machine Learning Framework

Do you need a geospatial computing platform?

Land Surface Temperature (LST) is significant for climatological and environmental studies. LST products acquired from satellites, however, suffer from the tradeoff between spatial and temporal resolution. Spatial downscaling has emerged as a well explored field aiming to overcome limitations arising from this tradeoff. Previous research on regression based LST downscaling models focused on utilising predictors derived from optical imagery for constructing such spatial downscaling models. Weather-dependent nature of optical imagery data, however, can influence downscaling models and render them ineffective during bad weather conditions like high cloud cover.

To cope with this issue, in our research, we involved predictors derived from the weather-independent Sentinel-1 Synthetic Aperture Radar (SAR) imagery to downscale MODIS LST products. To achieve this we utilised traditional machine learning algorithms such as Random Forest and also proposed novel downscaling architecture based on Convolutional Neural Networks.


Figure 1. Map showing the study area: Zuid-Holland province (left) and various municipalities in Zuid-Holland province (right)

Upon conducting a comparative analysis between the outcomes derived from optical predictors and those obtained from radar predictors, it was noted that radar-based downscaling models exhibited suboptimal performance. This diminished efficacy can be attributed to the more complex nature of radar imagery. Nonetheless, despite a marginal loss in accuracy, the employment of radar predictors enabled the downscaling models to operate independently of weather conditions. This revelation underscores the imperative for further investigation in this domain, especially through the application of more sophisticated and deep neural network architectures, incorporating comprehensive radar datasets (for e.g., incorporating phase information to model temporal variations in LST).

Figure 2. Results of the Case 3 radar-based RF downscaling experiment. Here, (a), (b), and (c) refer to validation Landsat-8 LST (100 m) acquired on 25/03/2020, 10/04/2020, and 28/05/2020, respectively. (d), (e), and (f) refer to the achieved downscaled LST images (100 m) for 25/03/2020, 10/04/2020, and 28/05/2020, respectively. (g), (h) and (i) refer to the histograms and (j), (k), and (l) refer to the scatterplots obtained on comparing downscaled LST images (100 m) to the Landsat-8 validation LST images (100 m)

Given the reliance of this research on machine learning, the necessity for GPUs for training was evident. We were privileged to utilise the Geospatial Computing Platform, which gave us access to ample computational resources for both training and evaluating our models. The presence of standard geospatial and satellite analysis modules, in addition to conventional machine learning frameworks on the computing platform, significantly reduced the time required for environment configuration, thereby allowing for an increased focus on actual experimental research.

My experience with using the platform was exceptionally positive. I am also immensely grateful to the Centre of Expertise in Big Geodata Science (CRIB) team for their quick support with several issues I encountered previously. For researchers working at the intersections of satellite big data, machine learning, and geospatial analysis, the Geospatial Computing Platform stands out as the ideal platform specifically tailored to meet their needs.

For more information: 

Patel, Nishit (2023) Downscaling Land Surface Temperature using SAR images : A Machine Learning framework.


Nishit Patel

I am currently employed as a Geospatial Data Scientist at Amsterdam UMC. My involvement is primarily with the OBCT project, where our team endeavours to analyse and map the relationship between built environments and obesity across the entire European region. This role requires extensive work with satellite images, spatial data, and machine learning techniques. I am deeply passionate about leveraging my existing skills and acquiring new ones to address global challenges. 

dr.ing. H. Aghababaei (Hossein)
Assistant Professor

Dr. Hossein Aghababaei has held the position of Assistant Professor at the Faculty of ITC, University of Twente. His research is focused on Synthetic Aperture Radar (SAR) data analysis, with a particular specialization in Polarimetric SAR (PolSAR) and SAR tomography (TomoSAR). His research interests are closely aligned with applications pertaining to the forestry sector, specifically the investigation of forest structures (3D forest) through the utilization of SAR tomography.

dr. F.B. Osei (Frank)
Assistant Professor

I’m an assistant professor of spatial statistics at the Faculty of Geoinformation Science and Earth Observation (ITC), University of Twente. I have a BSc in Geomatic Engineering and a PhD in computational spatial health statistics. My career goal has been to conduct policy-relevant research in response to the pressing need for “space” and “time” domains in policy development. My skill sets included Geographic Information Sciences, Geo-Health, spatial statistics and simulations, Bayesian networks, Bayesian statistics, spatial data science, etc. I have published my results in journals like Spatial Statistics, International Journal of Health Geographics, Scientific Reports, BMC Medical Research Methodology, etc. My current research focuses on space-time data synthesis and quality which are the backbone of Machine learning, AI and GeoAI.