A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data
Clouds are one of the major uncertainties of the climate system. The study of cloud processes requires information on cloud physical properties, in particular liquid water path (LWP). This parameter is commonly retrieved from satellite data using look-up table approaches. However, existing LWP retri...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/21/3475 |
| _version_ | 1827703709782507520 |
|---|---|
| author | Miae Kim Jan Cermak Hendrik Andersen Julia Fuchs Roland Stirnberg |
| author_facet | Miae Kim Jan Cermak Hendrik Andersen Julia Fuchs Roland Stirnberg |
| author_sort | Miae Kim |
| collection | DOAJ |
| description | Clouds are one of the major uncertainties of the climate system. The study of cloud processes requires information on cloud physical properties, in particular liquid water path (LWP). This parameter is commonly retrieved from satellite data using look-up table approaches. However, existing LWP retrievals come with uncertainties related to assumptions inherent in physical retrievals. Here, we present a new retrieval technique for cloud LWP based on a statistical machine learning model. The approach utilizes spectral information from geostationary satellite channels of Meteosat Spinning-Enhanced Visible and Infrared Imager (SEVIRI), as well as satellite viewing geometry. As ground truth, data from CloudNet stations were used to train the model. We found that LWP predicted by the machine-learning model agrees substantially better with CloudNet observations than a current physics-based product, the Climate Monitoring Satellite Application Facility (CM SAF) CLoud property dAtAset using SEVIRI, edition 2 (CLAAS-2), highlighting the potential of such approaches for future retrieval developments. |
| first_indexed | 2024-03-10T15:24:42Z |
| format | Article |
| id | doaj.art-8897eb5e940a4e6489266bee2572ad97 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:24:42Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8897eb5e940a4e6489266bee2572ad972023-11-20T18:08:47ZengMDPI AGRemote Sensing2072-42922020-10-011221347510.3390/rs12213475A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI DataMiae Kim0Jan Cermak1Hendrik Andersen2Julia Fuchs3Roland Stirnberg4Institute of Meteorology and Climate Research, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, GermanyInstitute of Meteorology and Climate Research, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, GermanyInstitute of Meteorology and Climate Research, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, GermanyInstitute of Meteorology and Climate Research, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, GermanyInstitute of Meteorology and Climate Research, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, GermanyClouds are one of the major uncertainties of the climate system. The study of cloud processes requires information on cloud physical properties, in particular liquid water path (LWP). This parameter is commonly retrieved from satellite data using look-up table approaches. However, existing LWP retrievals come with uncertainties related to assumptions inherent in physical retrievals. Here, we present a new retrieval technique for cloud LWP based on a statistical machine learning model. The approach utilizes spectral information from geostationary satellite channels of Meteosat Spinning-Enhanced Visible and Infrared Imager (SEVIRI), as well as satellite viewing geometry. As ground truth, data from CloudNet stations were used to train the model. We found that LWP predicted by the machine-learning model agrees substantially better with CloudNet observations than a current physics-based product, the Climate Monitoring Satellite Application Facility (CM SAF) CLoud property dAtAset using SEVIRI, edition 2 (CLAAS-2), highlighting the potential of such approaches for future retrieval developments.https://www.mdpi.com/2072-4292/12/21/3475liquid water pathgeostationary satelliteSEVIRICM SAF CLAAS-2CloudNetmachine learning |
| spellingShingle | Miae Kim Jan Cermak Hendrik Andersen Julia Fuchs Roland Stirnberg A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data Remote Sensing liquid water path geostationary satellite SEVIRI CM SAF CLAAS-2 CloudNet machine learning |
| title | A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data |
| title_full | A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data |
| title_fullStr | A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data |
| title_full_unstemmed | A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data |
| title_short | A New Satellite-Based Retrieval of Low-Cloud Liquid-Water Path Using Machine Learning and Meteosat SEVIRI Data |
| title_sort | new satellite based retrieval of low cloud liquid water path using machine learning and meteosat seviri data |
| topic | liquid water path geostationary satellite SEVIRI CM SAF CLAAS-2 CloudNet machine learning |
| url | https://www.mdpi.com/2072-4292/12/21/3475 |
| work_keys_str_mv | AT miaekim anewsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT jancermak anewsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT hendrikandersen anewsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT juliafuchs anewsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT rolandstirnberg anewsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT miaekim newsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT jancermak newsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT hendrikandersen newsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT juliafuchs newsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata AT rolandstirnberg newsatellitebasedretrievaloflowcloudliquidwaterpathusingmachinelearningandmeteosatseviridata |