A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data

To monitor environmental and biological processes, Land Surface Temperature (LST) is a central variable, which is highly variable in space and time. This particularly applies to the Antarctic Dry Valleys, which host an ecosystem highly adapted to the extreme conditions in this cold desert. To predic...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lilian-Maite Lezama Valdes, Marwan Katurji, Hanna Meyer
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/9598b374fd564188aa71ef7766ce2044
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9598b374fd564188aa71ef7766ce2044
record_format dspace
spelling oai:doaj.org-article:9598b374fd564188aa71ef7766ce20442021-11-25T18:55:17ZA Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data10.3390/rs132246732072-4292https://doaj.org/article/9598b374fd564188aa71ef7766ce20442021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4673https://doaj.org/toc/2072-4292To monitor environmental and biological processes, Land Surface Temperature (LST) is a central variable, which is highly variable in space and time. This particularly applies to the Antarctic Dry Valleys, which host an ecosystem highly adapted to the extreme conditions in this cold desert. To predict possible climate induced changes on the Dry Valley ecosystem, high spatial and temporal resolution environmental variables are needed. Thus we enhanced the spatial resolution of the MODIS satellite LST product that is sensed sub-daily at a 1 km spatial resolution to a 30 m spatial resolution. We employed machine learning models that are trained using Landsat 8 thermal infrared data from 2013 to 2019 as a reference to predict LST at 30 m resolution. For the downscaling procedure, terrain derived variables and information on the soil type as well as the solar insolation were used as potential predictors in addition to MODIS LST. The trained model can be applied to all available MODIS scenes from 1999 onward to develop a 30 m resolution LST product of the Antarctic Dry Valleys. A spatio-temporal validation revealed an R<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula> of 0.78 and a RMSE of 3.32 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mo>∘</mo></msup></semantics></math></inline-formula>C. The downscaled LST will provide a valuable surface climate data set for various research applications, such as species distribution modeling, climate model evaluation, and the basis for the development of further relevant environmental information such as the surface moisture distribution.Lilian-Maite Lezama ValdesMarwan KaturjiHanna MeyerMDPI AGarticledownscalingLand Surface TemperatureAntarcticaMcMurdo Dry ValleysMODISmachine learningScienceQENRemote Sensing, Vol 13, Iss 4673, p 4673 (2021)
institution DOAJ
collection DOAJ
language EN
topic downscaling
Land Surface Temperature
Antarctica
McMurdo Dry Valleys
MODIS
machine learning
Science
Q
spellingShingle downscaling
Land Surface Temperature
Antarctica
McMurdo Dry Valleys
MODIS
machine learning
Science
Q
Lilian-Maite Lezama Valdes
Marwan Katurji
Hanna Meyer
A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
description To monitor environmental and biological processes, Land Surface Temperature (LST) is a central variable, which is highly variable in space and time. This particularly applies to the Antarctic Dry Valleys, which host an ecosystem highly adapted to the extreme conditions in this cold desert. To predict possible climate induced changes on the Dry Valley ecosystem, high spatial and temporal resolution environmental variables are needed. Thus we enhanced the spatial resolution of the MODIS satellite LST product that is sensed sub-daily at a 1 km spatial resolution to a 30 m spatial resolution. We employed machine learning models that are trained using Landsat 8 thermal infrared data from 2013 to 2019 as a reference to predict LST at 30 m resolution. For the downscaling procedure, terrain derived variables and information on the soil type as well as the solar insolation were used as potential predictors in addition to MODIS LST. The trained model can be applied to all available MODIS scenes from 1999 onward to develop a 30 m resolution LST product of the Antarctic Dry Valleys. A spatio-temporal validation revealed an R<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula> of 0.78 and a RMSE of 3.32 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mo>∘</mo></msup></semantics></math></inline-formula>C. The downscaled LST will provide a valuable surface climate data set for various research applications, such as species distribution modeling, climate model evaluation, and the basis for the development of further relevant environmental information such as the surface moisture distribution.
format article
author Lilian-Maite Lezama Valdes
Marwan Katurji
Hanna Meyer
author_facet Lilian-Maite Lezama Valdes
Marwan Katurji
Hanna Meyer
author_sort Lilian-Maite Lezama Valdes
title A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
title_short A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
title_full A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
title_fullStr A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
title_full_unstemmed A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data
title_sort machine learning based downscaling approach to produce high spatio-temporal resolution land surface temperature of the antarctic dry valleys from modis data
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/9598b374fd564188aa71ef7766ce2044
work_keys_str_mv AT lilianmaitelezamavaldes amachinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
AT marwankaturji amachinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
AT hannameyer amachinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
AT lilianmaitelezamavaldes machinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
AT marwankaturji machinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
AT hannameyer machinelearningbaseddownscalingapproachtoproducehighspatiotemporalresolutionlandsurfacetemperatureoftheantarcticdryvalleysfrommodisdata
_version_ 1718410541326663680