Neural Network Algorithm for Precipitation Estimation from ATMS Radiometer Data.
Saved in:
| Title: | Neural Network Algorithm for Precipitation Estimation from ATMS Radiometer Data. |
|---|---|
| Authors: | Filei, A. A.1 (AUTHOR) andreyvm-61@mail.ru, Andreev, A. I.1 (AUTHOR) |
| Source: | Izvestiya, Atmospheric & Oceanic Physics. Dec2024, Vol. 60 Issue 12, p1443-1457. 15p. |
| Subject Terms: | *Precipitation (Chemistry), *Artificial intelligence, *Microwave measurements, *Image processing, *Reference sources |
| Abstract: | Abstract—This paper presents a neural network method for precipitation estimation using microwave measurements from ATMS radiometer on board Suomi NPP and NOAA-20/21 satellites. The algorithms are based on two fully connected neural networks: the first one is used to detect precipitation clouds and the other one is used to quantify precipitation rate. When training the neural networks, the reference source of information is an array of measurements simulated using the fast radiation transfer model RTTOV in the bands of ATMS instrument and the corresponding precipitation rates taken from ECMWF ERA5 reanalysis data. The validation of the precipitation estimates is carried out using the results of the MIRS and GPROF algorithms for satellite radiometer ATMS, as well as ground-based radar observations from NIMROD. The results of the validation show a high accuracy level consistent with many others works in this research field. Validation is carried out for land and water surface separately. The comparison with the MIRS algorithm shows that the correlation coefficient is more than 0.9, and the RMSE error is approximately 0.78 mm/h for water and 0.84 mm/h for land surface. The same metrics for the GPROF algorithm show that the correlation coefficient is ~0.8 and the RMSE error is approximately 1.27 and 0.9 mm/h for water and land surface, respectively. When compared with ground-based NIMROD radar data, the correlation and the RMSE are 0.47 and 1.37 mm/h, respectively. The results of the validation confirm the performance of the neural network method for precipitation estimation. In addition, further minor refinement of the presented algorithm will make it possible to apply it to measurements of other microwave satellite instruments, including Russian ones, such as MTVZA-GY, installed on Meteor-M satellites. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Abstract—This paper presents a neural network method for precipitation estimation using microwave measurements from ATMS radiometer on board Suomi NPP and NOAA-20/21 satellites. The algorithms are based on two fully connected neural networks: the first one is used to detect precipitation clouds and the other one is used to quantify precipitation rate. When training the neural networks, the reference source of information is an array of measurements simulated using the fast radiation transfer model RTTOV in the bands of ATMS instrument and the corresponding precipitation rates taken from ECMWF ERA5 reanalysis data. The validation of the precipitation estimates is carried out using the results of the MIRS and GPROF algorithms for satellite radiometer ATMS, as well as ground-based radar observations from NIMROD. The results of the validation show a high accuracy level consistent with many others works in this research field. Validation is carried out for land and water surface separately. The comparison with the MIRS algorithm shows that the correlation coefficient is more than 0.9, and the RMSE error is approximately 0.78 mm/h for water and 0.84 mm/h for land surface. The same metrics for the GPROF algorithm show that the correlation coefficient is ~0.8 and the RMSE error is approximately 1.27 and 0.9 mm/h for water and land surface, respectively. When compared with ground-based NIMROD radar data, the correlation and the RMSE are 0.47 and 1.37 mm/h, respectively. The results of the validation confirm the performance of the neural network method for precipitation estimation. In addition, further minor refinement of the presented algorithm will make it possible to apply it to measurements of other microwave satellite instruments, including Russian ones, such as MTVZA-GY, installed on Meteor-M satellites. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 00014338 |
| DOI: | 10.1134/S0001433825700112 |
