Ice phenomena on watercourses are commonly occurring effect in winter period. In most places do not cause any complication, but in certain places their occurrence is more frequent and in conjunction with forming ice phenomena into dangerous, as a break-up ice jam or a freeze-up ice jam, can lead to the formation of ice flood. Such places is affected lower Berounka watercourse in section Křivoklát - Vltava confluence. Occurrence and formation of ice phenomena depends on ice regime, which lower Berounka causing frequent problems. Ice regime is the interplay of many factors and ice phenomena are thus generally very difficult to predict because of strongly nonlinear relationships. Artificial neural networks excel in ability to learn on examples, in this case historical data, and ability to apply the knowledge gained on the data present and the future. This work uses multilayer perceptron neural network to realization of ice phenomena prediction based on historical flow and temperature data from the years 1887 - 1940 from the measuring station Křivoklát, which is a place of frequent occurrence of dangerous ice phenomena. The results provided by the learned neural network are comparable to the standard model used in modeling of ice phenomena. Obtained outputs confirmed the possibility of the successful application of neural networks in this area. Their use is possible as e.g. a part of information (warning) system or a system for predicting the occurrence of ice phenomena during winter season, which may lead to the alleviation of their impact on watercourse, surrounding area and residents.
Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:259162 |
Date | January 2016 |
Creators | Šebestová, Lucie |
Contributors | Máca, Petr, Havlíček, Vojtěch |
Publisher | Česká zemědělská univerzita v Praze |
Source Sets | Czech ETDs |
Language | Czech |
Detected Language | English |
Type | info:eu-repo/semantics/masterThesis |
Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0021 seconds