A Machine Learning Snowfall Retrieval Algorithm for ATMS
This article describes the development of a machine learning (ML)-based algorithm for snowfall retrieval (Snow retrievaL ALgorithm fOr gpM–Cross Track, SLALOM-CT), exploiting ATMS radiometer measurements and using the CloudSat CPR snowfall products as references. During a preliminary analysis, diffe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/6/1467 |
| _version_ | 1797442618304495616 |
|---|---|
| author | Paolo Sanò Daniele Casella Andrea Camplani Leo Pio D’Adderio Giulia Panegrossi |
| author_facet | Paolo Sanò Daniele Casella Andrea Camplani Leo Pio D’Adderio Giulia Panegrossi |
| author_sort | Paolo Sanò |
| collection | DOAJ |
| description | This article describes the development of a machine learning (ML)-based algorithm for snowfall retrieval (Snow retrievaL ALgorithm fOr gpM–Cross Track, SLALOM-CT), exploiting ATMS radiometer measurements and using the CloudSat CPR snowfall products as references. During a preliminary analysis, different ML techniques (tree-based algorithms, shallow and convolutional neural networks—NNs) were intercompared. A large dataset (three years) of coincident observations from CPR and ATMS was used for training and testing the different techniques. The SLALOM-CT algorithm is based on four independent modules for the detection of snowfall and supercooled droplets, and for the estimation of snow water path and snowfall rate. Each module was designed by choosing the best-performing ML approach through model selection and optimization. While a convolutional NN was the most accurate for the snowfall detection module, a shallow NN was selected for all other modules. SLALOM-CT showed a high degree of consistency with CPR. Moreover, the results were almost independent of the background surface categorization and the observation angle. The reliability of the SLALOM-CT estimates was also highlighted by the good results obtained from a direct comparison with a reference algorithm (GPROF). |
| first_indexed | 2024-03-09T12:44:33Z |
| format | Article |
| id | doaj.art-11edfe807e554f7ba13c13e4ee7df50e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:44:33Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-11edfe807e554f7ba13c13e4ee7df50e2023-11-30T22:13:27ZengMDPI AGRemote Sensing2072-42922022-03-01146146710.3390/rs14061467A Machine Learning Snowfall Retrieval Algorithm for ATMSPaolo Sanò0Daniele Casella1Andrea Camplani2Leo Pio D’Adderio3Giulia Panegrossi4National Research Council of Italy, Institute of Atmospheric Sciences and Climate (CNR-ISAC), 00133 Rome, ItalyNational Research Council of Italy, Institute of Atmospheric Sciences and Climate (CNR-ISAC), 00133 Rome, ItalyNational Research Council of Italy, Institute of Atmospheric Sciences and Climate (CNR-ISAC), 00133 Rome, ItalyNational Research Council of Italy, Institute of Atmospheric Sciences and Climate (CNR-ISAC), 00133 Rome, ItalyNational Research Council of Italy, Institute of Atmospheric Sciences and Climate (CNR-ISAC), 00133 Rome, ItalyThis article describes the development of a machine learning (ML)-based algorithm for snowfall retrieval (Snow retrievaL ALgorithm fOr gpM–Cross Track, SLALOM-CT), exploiting ATMS radiometer measurements and using the CloudSat CPR snowfall products as references. During a preliminary analysis, different ML techniques (tree-based algorithms, shallow and convolutional neural networks—NNs) were intercompared. A large dataset (three years) of coincident observations from CPR and ATMS was used for training and testing the different techniques. The SLALOM-CT algorithm is based on four independent modules for the detection of snowfall and supercooled droplets, and for the estimation of snow water path and snowfall rate. Each module was designed by choosing the best-performing ML approach through model selection and optimization. While a convolutional NN was the most accurate for the snowfall detection module, a shallow NN was selected for all other modules. SLALOM-CT showed a high degree of consistency with CPR. Moreover, the results were almost independent of the background surface categorization and the observation angle. The reliability of the SLALOM-CT estimates was also highlighted by the good results obtained from a direct comparison with a reference algorithm (GPROF).https://www.mdpi.com/2072-4292/14/6/1467neural networksdeep learningmachine learningconvolutional neural networksmicrowave radiometerssatellite precipitation retrieval |
| spellingShingle | Paolo Sanò Daniele Casella Andrea Camplani Leo Pio D’Adderio Giulia Panegrossi A Machine Learning Snowfall Retrieval Algorithm for ATMS Remote Sensing neural networks deep learning machine learning convolutional neural networks microwave radiometers satellite precipitation retrieval |
| title | A Machine Learning Snowfall Retrieval Algorithm for ATMS |
| title_full | A Machine Learning Snowfall Retrieval Algorithm for ATMS |
| title_fullStr | A Machine Learning Snowfall Retrieval Algorithm for ATMS |
| title_full_unstemmed | A Machine Learning Snowfall Retrieval Algorithm for ATMS |
| title_short | A Machine Learning Snowfall Retrieval Algorithm for ATMS |
| title_sort | machine learning snowfall retrieval algorithm for atms |
| topic | neural networks deep learning machine learning convolutional neural networks microwave radiometers satellite precipitation retrieval |
| url | https://www.mdpi.com/2072-4292/14/6/1467 |
| work_keys_str_mv | AT paolosano amachinelearningsnowfallretrievalalgorithmforatms AT danielecasella amachinelearningsnowfallretrievalalgorithmforatms AT andreacamplani amachinelearningsnowfallretrievalalgorithmforatms AT leopiodadderio amachinelearningsnowfallretrievalalgorithmforatms AT giuliapanegrossi amachinelearningsnowfallretrievalalgorithmforatms AT paolosano machinelearningsnowfallretrievalalgorithmforatms AT danielecasella machinelearningsnowfallretrievalalgorithmforatms AT andreacamplani machinelearningsnowfallretrievalalgorithmforatms AT leopiodadderio machinelearningsnowfallretrievalalgorithmforatms AT giuliapanegrossi machinelearningsnowfallretrievalalgorithmforatms |