Title: OLAP technology and machine learning as the tools for validation of the numerical models of convective clouds

Authors: Elena N. Stankova; Andrey V. Balakshiy; Dmitry A. Petrov; Vladimir V. Korkhov; Andrey V. Shorov

Addresses: Saint Petersburg State University, 7-9, Universitetskaya nab., 199034 St. Petersburg, Russia ' Saint Petersburg State University, 7-9, Universitetskaya nab., 199034 St. Petersburg, Russia ' Saint Petersburg State University, 7-9, Universitetskaya nab., 199034 St. Petersburg, Russia ' Saint Petersburg State University, 7-9, Universitetskaya nab., 199034 St. Petersburg, Russia ' Saint Petersburg Electrotechnical University 'LETI' (SPbETU) ul. Professora Popova 5, 197376, St. Petersburg, Russia

Abstract: In the present work we use the technologies of machine learning and OLAP for more accurate forecasting of such phenomena as a thunderstorm, hail, heavy rain, using the numerical model of convective cloud. Three methods of machine learning: support vector machine, logistic regression and ridge regression are used for making the decision on whether or not a dangerous convective phenomenon occurs at present atmospheric conditions. The OLAP technology is used for development of the concept of multidimensional data base intended for distinguishing the types of the phenomena (thunderstorm, heavy rainfall and light rain). Previously developed complex information system is used for collecting the data about the state of the atmosphere and about the place and at the time when dangerous convective phenomena are recorded.

Keywords: online analytical processing; OLAP; online analytical processing; machine learning; validation of numerical models; numerical model of convective cloud; weather forecasting; thunderstorm; multidimensional data base; data mining.

DOI: 10.1504/IJBIDM.2019.096793

International Journal of Business Intelligence and Data Mining, 2019 Vol.14 No.1/2, pp.254 - 266

Received: 03 Feb 2017
Accepted: 16 Feb 2017
Published online: 11 Dec 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article