Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach

Generating spatiotemporally continuous land surface temperature (LST) data is in great demand for hydrology, meteorology, ecology, environmental studies, etc. However, the thermal infrared (TIR)-based LST measurements are prone to cloud contamination with missing pixels. To repair the missing pixels...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Weiwei Tan, Chunzhu Wei, Yang Lu, Desheng Xue
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	land surface temperature cloud contamination reconstruction XGBoost MODIS SG filtering Science Q
Acceso en línea:	https://doaj.org/article/55745c8341e749a5a73bd9e8e12a274c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:55745c8341e749a5a73bd9e8e12a274c
record_format	dspace
spelling	oai:doaj.org-article:55745c8341e749a5a73bd9e8e12a274c2021-11-25T18:55:45ZReconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach10.3390/rs132247232072-4292https://doaj.org/article/55745c8341e749a5a73bd9e8e12a274c2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4723https://doaj.org/toc/2072-4292Generating spatiotemporally continuous land surface temperature (LST) data is in great demand for hydrology, meteorology, ecology, environmental studies, etc. However, the thermal infrared (TIR)-based LST measurements are prone to cloud contamination with missing pixels. To repair the missing pixels, a new XGBoost-based linking approach for reconstructing daytime and nighttime Moderate Resolution Imaging Spectroradiometer (MODIS) LST measurements was introduced. The instantaneous solar radiation and two soil-related predictors from China Data Assimilation System (CLDAS) 0.0625°/1-h data were selected as the linking variables to depict the relationship with instantaneous MODIS LST data. Other land surface properties, including two vegetation indices, the water index, the surface albedo, and topographic parameters, were also used as the predictor variables. The XGBoost method was used to fit an LST linking model by the training datasets from clear-sky pixels and was then applied to the MODIS Aqua-Terra LSTs during summer time (June to August) in 2017 and 2018 across China. The recovered LST data was further rectified with the Savitzky–Golay (SG) filtering method. The results showed the distribution of the reconstructed LSTs present a reasonable pattern for different land-cover types and topography. The evaluation results using in situ longwave radiation measurements showed the RMSE varies from 3.91 K to 5.53 K for the cloud-free pixels and from 4.42 K to 4.97 K for the cloud-covered pixels. In addition, the reconstructed LST products correlated well with CLDAS LST data with similar LST spatial patterns. The variable importance analysis revealed that the two soil-related predictors and the elevation variable are key parameters due to their great contribution to the XGBoost model performance.Weiwei TanChunzhu WeiYang LuDesheng XueMDPI AGarticleland surface temperaturecloud contaminationreconstructionXGBoostMODISSG filteringScienceQENRemote Sensing, Vol 13, Iss 4723, p 4723 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	land surface temperature cloud contamination reconstruction XGBoost MODIS SG filtering Science Q
spellingShingle	land surface temperature cloud contamination reconstruction XGBoost MODIS SG filtering Science Q Weiwei Tan Chunzhu Wei Yang Lu Desheng Xue Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
description	Generating spatiotemporally continuous land surface temperature (LST) data is in great demand for hydrology, meteorology, ecology, environmental studies, etc. However, the thermal infrared (TIR)-based LST measurements are prone to cloud contamination with missing pixels. To repair the missing pixels, a new XGBoost-based linking approach for reconstructing daytime and nighttime Moderate Resolution Imaging Spectroradiometer (MODIS) LST measurements was introduced. The instantaneous solar radiation and two soil-related predictors from China Data Assimilation System (CLDAS) 0.0625°/1-h data were selected as the linking variables to depict the relationship with instantaneous MODIS LST data. Other land surface properties, including two vegetation indices, the water index, the surface albedo, and topographic parameters, were also used as the predictor variables. The XGBoost method was used to fit an LST linking model by the training datasets from clear-sky pixels and was then applied to the MODIS Aqua-Terra LSTs during summer time (June to August) in 2017 and 2018 across China. The recovered LST data was further rectified with the Savitzky–Golay (SG) filtering method. The results showed the distribution of the reconstructed LSTs present a reasonable pattern for different land-cover types and topography. The evaluation results using in situ longwave radiation measurements showed the RMSE varies from 3.91 K to 5.53 K for the cloud-free pixels and from 4.42 K to 4.97 K for the cloud-covered pixels. In addition, the reconstructed LST products correlated well with CLDAS LST data with similar LST spatial patterns. The variable importance analysis revealed that the two soil-related predictors and the elevation variable are key parameters due to their great contribution to the XGBoost model performance.
format	article
author	Weiwei Tan Chunzhu Wei Yang Lu Desheng Xue
author_facet	Weiwei Tan Chunzhu Wei Yang Lu Desheng Xue
author_sort	Weiwei Tan
title	Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
title_short	Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
title_full	Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
title_fullStr	Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
title_full_unstemmed	Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach
title_sort	reconstruction of all-weather daytime and nighttime modis aqua-terra land surface temperature products using an xgboost approach
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/55745c8341e749a5a73bd9e8e12a274c
work_keys_str_mv	AT weiweitan reconstructionofallweatherdaytimeandnighttimemodisaquaterralandsurfacetemperatureproductsusinganxgboostapproach AT chunzhuwei reconstructionofallweatherdaytimeandnighttimemodisaquaterralandsurfacetemperatureproductsusinganxgboostapproach AT yanglu reconstructionofallweatherdaytimeandnighttimemodisaquaterralandsurfacetemperatureproductsusinganxgboostapproach AT deshengxue reconstructionofallweatherdaytimeandnighttimemodisaquaterralandsurfacetemperatureproductsusinganxgboostapproach
_version_	1718410523142258688

Reconstruction of All-Weather Daytime and Nighttime MODIS Aqua-Terra Land Surface Temperature Products Using an XGBoost Approach

Ejemplares similares