Vol. 29, issue 04, article # 13

Abstract:

To reconstruct the data of hydrophysical parameter observations, a model based on a neural network with the teacher has been suggested. The indices of global climate modes of the ocean–atmosphere system were applied as the model input. The processes of the model teaching and adaptation, which allow one to find the most accurate solution of the problem of modeling, is described. The comparison of modeled monthly average Danube's runoff with data of observation demonstrated their good correspondence. Missed in some years observation data on sea water transparency (depth of white disc visibility) were reconstructed. The proximity of reconstructed and observed depths of white disc visibility was noted. Some features of interannual variability of reconstructed data on sea water transparency caused by both climatic factors during 1950–1962 and changes in the chlorophyll а concentration during 1998–2010 were found.

Keywords:

transparency, neural network, runoff, hydrometeorological conditions, Black Sea

References:

1. Kukushkin A.S. Mnogoletnjaja i sezonnaja izmenchivost' raspredelenija prozrachnosti v poverhnostnyh vodah severo-zapadnoj chasti Chernogo morja // Optika atmosf. i okeana. 2013. V. 26, N 2. P. 113–123.
2. Kukushkin A.S., Voskresenskaja E.N., Maslova V.N. Osobennosti formirovanija polja prozrachnosti v poverhnostnom sloe severo-zapadnoj chasti Chernogo morja v zimne-vesennij period // Optika atmosf. i okeana. 2010. V. 23, N 8. P. 730–736; Kukushkin A.S., Voskresenskaya E.N., Maslova V.N. The Features of Transparency Field Generation in the Upper Sea Layer of the Northwestern Black Sea in the Winter-Spring Period // Atmos. Ocean. Opt. 2011. V. 24, N 1. P. 95–101.
3. Kukushkin A.S. Vlijanie raspredelenij gidrologicheskih i gidrobiologicheskih parametrov na strukturu polja prozrachnosti v verhnem sloe pelagiali Chernogo morja // Meteorol. i gidrol. 2013. N 7. P. 74–86.
4. Osovskij S. Nejronnye seti dlja obrabotki informacii. M.: Finansy i statistika, 2002. 344 p.
5. Efimov V.V., Pososhkov V.L. Primenenie metoda iskusstvennyh nejronnyh setej dlja regionalizacii prognoza osadkov v Prichernomorskom regione // Morskoj gidrofiz. zh. 2006. N 3. P. 23–35.
6. Pososhkov V.L. Ispol'zovanie iskusstvennyh nejronnyh setej dlja statisticheskogo ocenivanija rjada srednesutochnyh osadkov // Sistemy kontrolja okruzhajushhej sredy. Sevastopol': MGI NAN Ukrainy, 2002. P. 146–152.
7. Pososhkov V.L., Prusov A.V. Primenenie metoda samoorganizujushhihsja otobrazhenij priznakov k analizu jekstremal'nyh osadkov // Sistemy kontrolja okruzhajushhej sredy. Sevastopol': MGI NAN Ukrainy, 2003. P. 118–123.
8. Efimov V.V., Shokurov M.V. Ispol'zovanie iskusstvennoj nejronnoj seti dlja statisticheskogo ocenivanija temperatury poverhnosti Chernogo morja // Trudy Mezhdunar. konf., posvjashhennoj 75-letiju akademika G.I. Marchuka i 20-letiju Instituta vychislitel'noj matematiki. M.: IVM RAN, 2000. V. 2. P. 267–274.
9. Polonskij A.B., Voskresenskaja E.N., Pososhkov V.L. Statisticheskij prognoz srednemesjachnogo stoka chernomorskih rek na osnove cirkuljacionnyh atmosfernyh processov // Dopovіdі NAN Ukraїni. 2010. N 11, P. 95–101.
10. Lubkov A.S., Voskresenskaja E.N., Kukushkin A.S. Vosstanovlenie znachenij prozrachnosti morskoj vody na osnove modelirovanija metodom nejronnyh setej // HX Mezhdunar. simp. «Optika atmosfery i okeana. Fizika atmosfery». Sbornik trudov [Jelektronnyj resurs]. Tomsk: IOA SO RAN, 2014. P. 238–241.
11. Northern Hemisphere Teleconnection Patterns // Climate Prediction Center. URL: http://www.cpc.ncep.noaa.gov/data/teledoc/telecontents.shtml (дата обращения 10.12.2014).
12. Pacific Decadal Oscillation (PDO) / Joint Institute for the Study of the Atmosphere and Ocean (JISAO). URL: http://jisao.washington.edu/pdo/PDO.latest data obrashhenija 10.12.2014).
13. Southern Oscillation Index. Archives / Australia's official weather forecasts & weather radar Bureau of Meteorology. URL: http://www.bom.gov.au/climate/current/soihtm1.shtml (data obrashhenija 10.12.2014).
14. Haykin S. Neural networks, a comprehensive foundation. N.Y.: Macmillan College Publishing Company, 1994. 823 p.
15. Rosenblatt F. Principles of neurodynamics: Perceptrons and the theory of brain mechanisms. N.Y.: Spartan, 1962. 626 p.
16. Monin A.S. Gidrodinamika atmosfery, okeana i zemnyh nedr. SPb.: Gidrometeoizdat, 1999. 524 p.
17. Muleta M.K. Model performance sensitivity to objective function during automated calibrations // J. Hydrologic Engin. 2012. V. 17, N 6. P. 756–767.
18. Kolmogorov A.N. O predstavlenii nepreryvnyh funkcij neskol'kih peremennyh v vide superpozicij nepreryvnyh funkcij odnogo peremennogo i slozhenija // Dokl. AN SSSR. 1957. V. 114, N 5. P. 953–956.
19. Hecht-Nielsen R. Neurocomputing. Amsterdam: Addison Wesley, 1991. 433 p.