Published March 10, 2021 | Version v3
Dataset Open

Gap-filling Satellite Land Surface Temperature Over Heatwave Periods with Machine Learning

  • 1. University of Tartu

Description

The frequency of heatwave events has increased in recent decades because of global warming. Satellite observed Land Surface Temperature (LST) is a widely used parameter for assessing heatwaves. It provides a wide spatial coverage compared to surface air temperature measured at weather stations. However, LST quality is limited by cloud contamination. Because heatwaves have a limited temporal frame, having a full and cloud-free complement of LST for that period is necessary. In this letter, we explore gap-filling of LST using spatial features like land cover, elevation and vegetation indices in a machine learning approach. We use a seamless open and free daily vegetation index product which is paramount to the success of our study.  We create a Random Forest model that provides a ranking of features relevant for predicting LST. We compare the output of our model to an established spatiotemporal gap-filling algorithm to validate the predictive capability of our model. This study validates machine learning as a suitable tool for filling gaps in satellite LST. In addition, we acknowledge that while time is an important factor in predicting LST, additional information on vegetation can improve the predictions of a model.

 

Please refer to latest version.

 

 

Files

filled_lst_EST-HW-2010.zip

Files (891.1 MB)

Name Size Download all
md5:ebe77bb513ca41513dc4ac2ddc4b10ce
8.6 MB Preview Download
md5:a9ebc928feba7cd149c6d847392c6488
6.4 MB Preview Download
md5:708aee5091d953da92c9dd604ef0b1f9
6.7 MB Preview Download
md5:ea3074d844bcc8f23aa83fea69fdcf25
927.0 kB Preview Download
md5:cb4ebb68c0049e13da1a4c67d1cb2571
720 Bytes Preview Download
md5:528138106566e8e4c159fad3a410b205
868.4 MB Preview Download