This article is devoted to the mechanisms of neural network training for forecasting the meteorological situation when using GIS. The structural scheme of the GIS under consideration is proposed as a project solution and the main elements allowing to implement neural networks and their training are defined. The stochastic method is chosen as a tool for neural network training as it suggests the most probable outcome of the event based on the previous sample. The article gives an example of testing neural network training as an application program «Data Processor». The results described in the article allow us to judge about the applicability of the selected neural network training method for forecasting meteorological conditions and using data in geoinformation decision-making systems.

Vagizov Marcel Ravilevich, Candidate of Technical Sciences, acting head of the Department of Information systems and technologies of the Federal State Budgetary Educational Institution of Higher Education
«St. Petersburg State Forest Technical University». Letter U, 5, Institutsky lane, Saint Petersburg, 194021, Russia. Е-mail: bars-tatarin@yandex.ru.

Istomin Evgeny Petrovich, Doctor of Technical Sciences, head of the Department of Applied Informatics of the Federal State Budgetary Educational Institution of Higher Education «Russian state hydrometeorological University». 79, Voronezhskaya street, Saint Petersburg, 192007, Russia. E-mail: biom@bk.ru.

Kolbina Olga Nikolaevna, Candidate of Technical Sciences, associate Professor of the Department of Applied Informatics of the Federal State Budgetary Educational Institution of Higher Education «Russian state hydrometeorological University». 79, Voronezhskaya street, Saint Petersburg, 192007, Russia. E-mail: olya_kolbina@mail.ru.

Kochnev Alexander Sergeevich, student of the Saint Petersburg national research University of information technologies, mechanics and optics. 49, Kronverksky Prospekt, Saint Petersburg, 197101, Russia. E-mail: opybook@mail.ru.

Mikheev Valery Leonidovich, PhD in law, rector of the Federal state budgetary educational institution of higher education «Russian state hydrometeorological University». 79, Voronezhskaya street, Saint Petersburg, 192007, Russia. E-mail: v.mikheev-rshu@yandex.ru.

Yagotintseva Natalia Vladimirovna, Candidate of Technical Sciences, associate Professor of the Department of Applied Informatics, Federal state budgetary educational institution of higher education «Russian state hydrometeorological University». 79, Voronezhskaya street, Saint Petersburg, 192007, Russia. E-mail: yagotintceva@yandex.ru.

1. Bagrov A.N., Bykov F.L., Gordin V.A. Complex forecast of surface meteorological values // Meteorology and Hydrology. 2014. No. 5. P. 5-16.
2. Bykov F.L. Statistical correction of COSMO model weather forecasts using neural networks // Meteorology and hydrology. 2020. No. 3. P. 5-20.
3. Yaremenko I.A. Method of the distributed processing of the meteorological information on the basis of the artificial neural networks technologies of the A.F. Mozhaysky Military and Space Academy of Labor. 2020. No. S674. P. 263-270.
4. Istomin E.P., Fokicheva A.A., Korshunov A.A., Slesareva L.S. Management of the hydrometeorological risks in the socio-economic systems (in Russian) // Scientific notes of the Russian State Hydrometeorological University. 2016. No. 44. P. 219-224.
5. Kramareva L.S., Andreev A.I., Bloshchinskiy V.D., Kuchma M.O., Davidenko A.N., Pustatintsev I.N., Shamilova Yu. 2019. V. 24, No. 6. P. 50-59.
6. Models and methods of information systems research : Monograph / Under edition of A.D. Homonenko. St. Petersburg : Lan, 2019. 204 с.
7. Istomin E.P., Sokolov A.G. Organization theory: a system approach textbook for students of higher educational institutions. 2nd ed., with amendments and additions. Saint-Petersburg : Andreevsky publishing house, 2011. 420 p. (Organizational systems, vol. 1).
8. Panfilov P.N. Introduction into neural networks. Modern trading. 2001. No. 2. P. 12-17.
9. Galimyanov F.A. Comparative Analysis of Algorithms of Implementing the Method of Error Reverse Propagation for Training the Neural Network // Scientific and Technical Bulletin of the Volga Region. 2020. No. 2, Р. 69-71.
10. Database of meteorological risks / E.P. Istomin, Ya.A. Petrov, A.A. Fokicheva, N.V. Yagotintseva. Certificate of RU 2019620208, 04.02.2019 ; Application No. 2018621294 of 18.09.2018.