Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach

Global cloud thermodynamic phase (CP) is normally derived from polar-orbiting satellite imaging data with high spatial resolution. However, constraining conditions and empirical thresholds used in the MODIS (Moderate Resolution Imaging Spectroradiometer) CP algorithm are closely associated with spec...

Full description

Bibliographic Details
Main Authors: Dexin Zhao, Lin Zhu, Hongfu Sun, Jun Li, Weishi Wang
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/13/12/2251
id doaj-4656307cad4a4a4c9e94e8108f619d39
record_format Article
spelling doaj-4656307cad4a4a4c9e94e8108f619d392021-06-30T23:43:59ZengMDPI AGRemote Sensing2072-42922021-06-01132251225110.3390/rs13122251Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning ApproachDexin Zhao0Lin Zhu1Hongfu Sun2Jun Li3Weishi Wang4College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaNational Satellite Meteorological Center, China Meteorological Administration, Beijing 100081, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaCooperative Institute for Meteorological Satellite Study (CIMSS), University of Wisconsin-Madison, Madison, WI 53706, USACollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaGlobal cloud thermodynamic phase (CP) is normally derived from polar-orbiting satellite imaging data with high spatial resolution. However, constraining conditions and empirical thresholds used in the MODIS (Moderate Resolution Imaging Spectroradiometer) CP algorithm are closely associated with spectral properties of the MODIS infrared (IR) spectral bands, with obvious deviations and incompatibility induced when the algorithm is applied to data from other similar space-based sensors. To reduce the algorithm dependence on spectral properties and empirical thresholds for CP retrieval, a machine learning (ML)-based methodology was developed for retrieving CP data from China’s new-generation polar-orbiting satellite, FY-3D/MERSI-II (Fengyun-3D/Moderate Resolution Spectral Imager-II). Five machine learning algorithms were used, namely, k-nearest-neighbor (KNN), support vector machine (SVM), random forest (RF), Stacking and gradient boosting decision tree (GBDT). The RF algorithm gave the best performance. One year of EOS (Earth Observation System) MODIS CP products (July 2018 to June 2019) were used as reference labels to train the relationship between MODIS CP (MYD06 IR) and six IR bands of MERSI-II. CALIOP (Cloud-Aerosol Lidar with Orthogonal Polarization), MODIS, and FY-3D/MERSI-II CP products were used together for cross-validation. Results indicate strong spatial consistency between ML-based MERSI-II and MODIS CP products. The hit rate (HR) of random forest (RF) CP product could reach 0.85 compared with MYD06 IR CP products. In addition, when compared with the operational FY-3D/MERSI CP product, the RF-based CP product had higher HRs. Using the CALIOP cloud product as an independent reference, the liquid-phase accuracy of the RF CP product was higher than that of operational FY-3D/MERSI-II and MYD06 IR CP products. This study aimed to establish a robust algorithm for deriving FY-3D/MERSI-II CP climate data record (CDR) for research and applications.https://www.mdpi.com/2072-4292/13/12/2251FY-3D/MERSI-IIMODIScloud thermodynamic phasemachine learning
collection DOAJ
language English
format Article
sources DOAJ
author Dexin Zhao
Lin Zhu
Hongfu Sun
Jun Li
Weishi Wang
spellingShingle Dexin Zhao
Lin Zhu
Hongfu Sun
Jun Li
Weishi Wang
Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
Remote Sensing
FY-3D/MERSI-II
MODIS
cloud thermodynamic phase
machine learning
author_facet Dexin Zhao
Lin Zhu
Hongfu Sun
Jun Li
Weishi Wang
author_sort Dexin Zhao
title Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
title_short Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
title_full Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
title_fullStr Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
title_full_unstemmed Fengyun-3D/MERSI-II Cloud Thermodynamic Phase Determination Using a Machine-Learning Approach
title_sort fengyun-3d/mersi-ii cloud thermodynamic phase determination using a machine-learning approach
publisher MDPI AG
series Remote Sensing
issn 2072-4292
publishDate 2021-06-01
description Global cloud thermodynamic phase (CP) is normally derived from polar-orbiting satellite imaging data with high spatial resolution. However, constraining conditions and empirical thresholds used in the MODIS (Moderate Resolution Imaging Spectroradiometer) CP algorithm are closely associated with spectral properties of the MODIS infrared (IR) spectral bands, with obvious deviations and incompatibility induced when the algorithm is applied to data from other similar space-based sensors. To reduce the algorithm dependence on spectral properties and empirical thresholds for CP retrieval, a machine learning (ML)-based methodology was developed for retrieving CP data from China’s new-generation polar-orbiting satellite, FY-3D/MERSI-II (Fengyun-3D/Moderate Resolution Spectral Imager-II). Five machine learning algorithms were used, namely, k-nearest-neighbor (KNN), support vector machine (SVM), random forest (RF), Stacking and gradient boosting decision tree (GBDT). The RF algorithm gave the best performance. One year of EOS (Earth Observation System) MODIS CP products (July 2018 to June 2019) were used as reference labels to train the relationship between MODIS CP (MYD06 IR) and six IR bands of MERSI-II. CALIOP (Cloud-Aerosol Lidar with Orthogonal Polarization), MODIS, and FY-3D/MERSI-II CP products were used together for cross-validation. Results indicate strong spatial consistency between ML-based MERSI-II and MODIS CP products. The hit rate (HR) of random forest (RF) CP product could reach 0.85 compared with MYD06 IR CP products. In addition, when compared with the operational FY-3D/MERSI CP product, the RF-based CP product had higher HRs. Using the CALIOP cloud product as an independent reference, the liquid-phase accuracy of the RF CP product was higher than that of operational FY-3D/MERSI-II and MYD06 IR CP products. This study aimed to establish a robust algorithm for deriving FY-3D/MERSI-II CP climate data record (CDR) for research and applications.
topic FY-3D/MERSI-II
MODIS
cloud thermodynamic phase
machine learning
url https://www.mdpi.com/2072-4292/13/12/2251
work_keys_str_mv AT dexinzhao fengyun3dmersiiicloudthermodynamicphasedeterminationusingamachinelearningapproach
AT linzhu fengyun3dmersiiicloudthermodynamicphasedeterminationusingamachinelearningapproach
AT hongfusun fengyun3dmersiiicloudthermodynamicphasedeterminationusingamachinelearningapproach
AT junli fengyun3dmersiiicloudthermodynamicphasedeterminationusingamachinelearningapproach
AT weishiwang fengyun3dmersiiicloudthermodynamicphasedeterminationusingamachinelearningapproach
_version_ 1721350535522549760