Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau

Accurate information on microwave land surface emissivity (MLSE) is important for satellite data assimilation. In this article, a new random forest (RF) algorithm is developed for retrieving MLSE under all-sky conditions. Using Level-1 brightness temperature data from the FengYun-3D (FY-3D) microwav...

Full description

Saved in:
Bibliographic Details
Main Authors: Yonghong Liu, Fuzhong Weng, Fei Tang, Rui Li, Yongming Xu, Yang Han, Jun Yang, Qingyang Liu
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10714024/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200360534147072
author Yonghong Liu
Fuzhong Weng
Fei Tang
Rui Li
Yongming Xu
Yang Han
Jun Yang
Qingyang Liu
author_facet Yonghong Liu
Fuzhong Weng
Fei Tang
Rui Li
Yongming Xu
Yang Han
Jun Yang
Qingyang Liu
author_sort Yonghong Liu
collection DOAJ
description Accurate information on microwave land surface emissivity (MLSE) is important for satellite data assimilation. In this article, a new random forest (RF) algorithm is developed for retrieving MLSE under all-sky conditions. Using Level-1 brightness temperature data from the FengYun-3D (FY-3D) microwave radiation imager in 2022, two global MLSE daily product datasets, clear-sky (FY-3D1) and clear&#x002F;cloudy (FY-3D2), were obtained by using one-dimensional variational method and microwave radiative transfer method, respectively. Based on the global spatiotemporal consistency assessment, a high-quality daily MLSE training dataset for the Tibetan Plateau was selected from the two datasets. Then, ten land surface parameters from routine observation were chosen as input features to the RF model to simulate the MLSE under all-sky conditions in the Tibetan Plateau. The results show that both FY-3D1 and FY-3D2 MLSE datasets are comparable to the international mainstream MLSE products in quality, while the clear sky FY-3D1 is likely to be better than the clear&#x002F;cloudy FY-3D2 MLSE. Land surface roughness, vegetation optical thickness, normalized vegetation index, and land cover type are identified as the most important factors affecting MLSE in the Tibetan Plateau. The RF model can effectively simulate the MLSE in the frequency range of 10.65&#x2013;89.0 GHz under all-sky conditions. The coefficients of determination (<italic>R</italic><sup>2</sup>) for horizontal polarization and vertical polarization range from 0.86 (10.65 GHz) to 0.91 (18.7 GHz) and from 0.60 (10.65 GHz) to 0.74 (89.0 GHz), respectively. The root mean square errors for horizontal polarization and vertical polarization range from 0.017 (23.8 GHz) to 0.023 (10.65 GHz) and from 0.016 (10.65 GHz) to 0.019 (89.0 GHz), respectively. These results indicate that machine learning is likely to be an effective method for future all-sky simulation of MLSE.
format Article
id doaj-art-ede15087ce35454093f83bd20055c50d
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-ede15087ce35454093f83bd20055c50d2025-08-20T02:12:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117190781909410.1109/JSTARS.2024.347835010714024Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan PlateauYonghong Liu0https://orcid.org/0000-0003-4550-7924Fuzhong Weng1Fei Tang2https://orcid.org/0000-0001-6422-3244Rui Li3https://orcid.org/0000-0002-4461-6507Yongming Xu4https://orcid.org/0000-0003-4032-8759Yang Han5https://orcid.org/0000-0003-2049-7678Jun Yang6https://orcid.org/0000-0001-9158-4328Qingyang Liu7https://orcid.org/0009-0005-0612-704XCenter for Earth System Modeling and Prediction, China Meteorological Administration, Beijing, ChinaCenter for Earth System Modeling and Prediction, China Meteorological Administration, Beijing, ChinaKey Laboratory of Transportation Meteorology of China Meteorological Administration, Nanjing Joint Institute for Atmospheric Sciences, Nanjing, ChinaSchool of Earth and Space Sciences, State Key Laboratory of Fire Science, MEM Key Laboratory of Forest Fire Monitoring and Warning, University of Science and Technology of China, Hefei, ChinaSchool of Remote Sensing &amp; Geomatics Engineering, Nanjing University of Information Science &amp; Technology, Nanjing, ChinaCenter for Earth System Modeling and Prediction, China Meteorological Administration, Beijing, ChinaCenter for Earth System Modeling and Prediction, China Meteorological Administration, Beijing, ChinaSchool of Earth and Space Sciences, State Key Laboratory of Fire Science, MEM Key Laboratory of Forest Fire Monitoring and Warning, University of Science and Technology of China, Hefei, ChinaAccurate information on microwave land surface emissivity (MLSE) is important for satellite data assimilation. In this article, a new random forest (RF) algorithm is developed for retrieving MLSE under all-sky conditions. Using Level-1 brightness temperature data from the FengYun-3D (FY-3D) microwave radiation imager in 2022, two global MLSE daily product datasets, clear-sky (FY-3D1) and clear&#x002F;cloudy (FY-3D2), were obtained by using one-dimensional variational method and microwave radiative transfer method, respectively. Based on the global spatiotemporal consistency assessment, a high-quality daily MLSE training dataset for the Tibetan Plateau was selected from the two datasets. Then, ten land surface parameters from routine observation were chosen as input features to the RF model to simulate the MLSE under all-sky conditions in the Tibetan Plateau. The results show that both FY-3D1 and FY-3D2 MLSE datasets are comparable to the international mainstream MLSE products in quality, while the clear sky FY-3D1 is likely to be better than the clear&#x002F;cloudy FY-3D2 MLSE. Land surface roughness, vegetation optical thickness, normalized vegetation index, and land cover type are identified as the most important factors affecting MLSE in the Tibetan Plateau. The RF model can effectively simulate the MLSE in the frequency range of 10.65&#x2013;89.0 GHz under all-sky conditions. The coefficients of determination (<italic>R</italic><sup>2</sup>) for horizontal polarization and vertical polarization range from 0.86 (10.65 GHz) to 0.91 (18.7 GHz) and from 0.60 (10.65 GHz) to 0.74 (89.0 GHz), respectively. The root mean square errors for horizontal polarization and vertical polarization range from 0.017 (23.8 GHz) to 0.023 (10.65 GHz) and from 0.016 (10.65 GHz) to 0.019 (89.0 GHz), respectively. These results indicate that machine learning is likely to be an effective method for future all-sky simulation of MLSE.https://ieeexplore.ieee.org/document/10714024/All-skyfeature selectionFengYun-3D (FY-3D)microwave land surface emissivity (MLSE)random forest (RF)
spellingShingle Yonghong Liu
Fuzhong Weng
Fei Tang
Rui Li
Yongming Xu
Yang Han
Jun Yang
Qingyang Liu
Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
All-sky
feature selection
FengYun-3D (FY-3D)
microwave land surface emissivity (MLSE)
random forest (RF)
title Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
title_full Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
title_fullStr Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
title_full_unstemmed Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
title_short Simulations of Microwave Land Surface Emissivity Using FengYun-3D Microwave Radiation Imager Data: A Case in the Tibetan Plateau
title_sort simulations of microwave land surface emissivity using fengyun 3d microwave radiation imager data a case in the tibetan plateau
topic All-sky
feature selection
FengYun-3D (FY-3D)
microwave land surface emissivity (MLSE)
random forest (RF)
url https://ieeexplore.ieee.org/document/10714024/
work_keys_str_mv AT yonghongliu simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT fuzhongweng simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT feitang simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT ruili simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT yongmingxu simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT yanghan simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT junyang simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau
AT qingyangliu simulationsofmicrowavelandsurfaceemissivityusingfengyun3dmicrowaveradiationimagerdataacaseinthetibetanplateau