Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory
Using of the Chang model for calculation of the snow water equivalent on the basis of measurements of the Earth thermo-microwave radiation by means of scanning polarimeters (SMMR, SSM/I, AMSR-E) from board of orbital satellites does not allow obtaining the accuracy needed hydrological purposes. Low...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Nauka
2016-02-01
|
| Series: | Лëд и снег |
| Subjects: | |
| Online Access: | https://ice-snow.igras.ru/jour/article/view/268 |
| _version_ | 1797878200165990400 |
|---|---|
| author | A. A. Volchek D. A. Kostyuk D. O. Petrov |
| author_facet | A. A. Volchek D. A. Kostyuk D. O. Petrov |
| author_sort | A. A. Volchek |
| collection | DOAJ |
| description | Using of the Chang model for calculation of the snow water equivalent on the basis of measurements of the Earth thermo-microwave radiation by means of scanning polarimeters (SMMR, SSM/I, AMSR-E) from board of orbital satellites does not allow obtaining the accuracy needed hydrological purposes. Low accuracy of the calculations is caused by both simplified character of the mathematical model, and due to significant influence of the surface characteristics (relief, vegetation and complex structure of snow thickness) upon the microwave radiation propagation. This work was aimed at finding a way to increase accuracy of calculations of the snow water equivalent on the Russian Federation territory with its different climate conditions by means of application the neural network approach for processing of results of the passive microwave scanning of the Earth surface. Feed-forward multi-layer artificial neural network was trained by back-propagation algorithm using SSM/I data and results of snow water equivalent in situ measurements obtained at 117 meteorological stations during the period from January 1st, 1988 till December 31st, 1988. Validation was performed using data from the same sources collected during 7 years (1992–1998). Results of performed numerical experiments and obtained values of rootmean-square error (σ = 24.9 мм; r = 0.39±0,01) allow coming to conclusion that the best estimation of water equivalent of a snow cover is provided by artificial neural network using as the input data a set of the SSM/I channels 19.35, 37.0, 85.5 GHz of horizontal and vertical polarizations with meteorological data differentiated by types of the snow survey route.It is shown that low correlation coefficients (< 0.5) as compared with similar studies on small areas is not caused by the chosen mathematical model and its realization but it is due to a strong diversity of climatic conditions and low density of meteorological stations on the land areas covered by our study. For the purpose of further improvement of quality of the snow water equivalent calculations as for diminution of negative influence of the above factors we propose to use the artificial networks ensemble trained by results of direct measurements grouped according to characteristics of the climate conditions, relief and vegetation. |
| first_indexed | 2024-04-10T02:28:54Z |
| format | Article |
| id | doaj.art-1e443e320a9648749eabf7e40871c626 |
| institution | Directory Open Access Journal |
| issn | 2076-6734 2412-3765 |
| language | Russian |
| last_indexed | 2024-04-10T02:28:54Z |
| publishDate | 2016-02-01 |
| publisher | Nauka |
| record_format | Article |
| series | Лëд и снег |
| spelling | doaj.art-1e443e320a9648749eabf7e40871c6262023-03-13T08:01:17ZrusNaukaЛëд и снег2076-67342412-37652016-02-01561435110.15356/2076-6734-2016-1-43-51252Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territoryA. A. Volchek0D. A. Kostyuk1D. O. Petrov2Брестский государственный технический университетБрестский государственный технический университетБрестский государственный технический университетUsing of the Chang model for calculation of the snow water equivalent on the basis of measurements of the Earth thermo-microwave radiation by means of scanning polarimeters (SMMR, SSM/I, AMSR-E) from board of orbital satellites does not allow obtaining the accuracy needed hydrological purposes. Low accuracy of the calculations is caused by both simplified character of the mathematical model, and due to significant influence of the surface characteristics (relief, vegetation and complex structure of snow thickness) upon the microwave radiation propagation. This work was aimed at finding a way to increase accuracy of calculations of the snow water equivalent on the Russian Federation territory with its different climate conditions by means of application the neural network approach for processing of results of the passive microwave scanning of the Earth surface. Feed-forward multi-layer artificial neural network was trained by back-propagation algorithm using SSM/I data and results of snow water equivalent in situ measurements obtained at 117 meteorological stations during the period from January 1st, 1988 till December 31st, 1988. Validation was performed using data from the same sources collected during 7 years (1992–1998). Results of performed numerical experiments and obtained values of rootmean-square error (σ = 24.9 мм; r = 0.39±0,01) allow coming to conclusion that the best estimation of water equivalent of a snow cover is provided by artificial neural network using as the input data a set of the SSM/I channels 19.35, 37.0, 85.5 GHz of horizontal and vertical polarizations with meteorological data differentiated by types of the snow survey route.It is shown that low correlation coefficients (< 0.5) as compared with similar studies on small areas is not caused by the chosen mathematical model and its realization but it is due to a strong diversity of climatic conditions and low density of meteorological stations on the land areas covered by our study. For the purpose of further improvement of quality of the snow water equivalent calculations as for diminution of negative influence of the above factors we propose to use the artificial networks ensemble trained by results of direct measurements grouped according to characteristics of the climate conditions, relief and vegetation.https://ice-snow.igras.ru/jour/article/view/268водный эквивалент снежного покроваискусственная нейронная сетьмикроволновое дистанционное зондированиеснегозапасы |
| spellingShingle | A. A. Volchek D. A. Kostyuk D. O. Petrov Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory Лëд и снег водный эквивалент снежного покрова искусственная нейронная сеть микроволновое дистанционное зондирование снегозапасы |
| title | Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory |
| title_full | Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory |
| title_fullStr | Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory |
| title_full_unstemmed | Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory |
| title_short | Water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the Russian Federation territory |
| title_sort | water equivalent of snow retrieved from data of passive microwave scanning with the use of artificial neural networks over the russian federation territory |
| topic | водный эквивалент снежного покрова искусственная нейронная сеть микроволновое дистанционное зондирование снегозапасы |
| url | https://ice-snow.igras.ru/jour/article/view/268 |
| work_keys_str_mv | AT aavolchek waterequivalentofsnowretrievedfromdataofpassivemicrowavescanningwiththeuseofartificialneuralnetworksovertherussianfederationterritory AT dakostyuk waterequivalentofsnowretrievedfromdataofpassivemicrowavescanningwiththeuseofartificialneuralnetworksovertherussianfederationterritory AT dopetrov waterequivalentofsnowretrievedfromdataofpassivemicrowavescanningwiththeuseofartificialneuralnetworksovertherussianfederationterritory |