. . . "\u00DAst\u00ED nad Labem" . "13520" . . "RIV/44555601:13520/09:00005107" . "Neruda, Martin" . "Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks"@en . . "Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks"@en . "2009-04-23+02:00"^^ . "The article addresses the modelling of runoff based on precipitation data collected in the S\u00E1zava River and Plou\u010Dnice River basins. Knowledge acquired in previous research in the Plou\u010Dnice River basin was found to be useful in this study. Rainfall and runoff data (both with a 1 hour time step) were obtained from the Czech Hydrometeorological Institute (CHMI). The time period of Aug.1?Sept.11, 2002 was selected, mainly because of the flood event on the 14th of Aug., 2002 in the S\u00E1zava River basin. Calculations were performed with feed-forward neural networks, namely multi-layer perceptron networks trained by back propagation. Network architectures were tested on 1-hour predictions first and then compared with the 6-hour predictions. The role of the accumulated runoff input has been also studied." . . "Neruda, Roman" . "P(WD-44-07-1)" . . "Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks" . "7"^^ . "Environmental Accounting - Sustainable Development Indicators" . "Univerzita Jana Evangelisty Purkyn\u011B v \u00DAst\u00ED nad Labem" . . . "[7249D127EA4B]" . "Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks" . . "324086" . . "Praha" . . "1"^^ . "3"^^ . . . . "artificial neural networks; rainfall-runoff models; Plou\u010Dnice River basin; S\u00E1zava River basin"@en . . "978-80-7414-124-9" . "RIV/44555601:13520/09:00005107!RIV10-MMR-13520___" . . "The article addresses the modelling of runoff based on precipitation data collected in the S\u00E1zava River and Plou\u010Dnice River basins. Knowledge acquired in previous research in the Plou\u010Dnice River basin was found to be useful in this study. Rainfall and runoff data (both with a 1 hour time step) were obtained from the Czech Hydrometeorological Institute (CHMI). The time period of Aug.1?Sept.11, 2002 was selected, mainly because of the flood event on the 14th of Aug., 2002 in the S\u00E1zava River basin. Calculations were performed with feed-forward neural networks, namely multi-layer perceptron networks trained by back propagation. Network architectures were tested on 1-hour predictions first and then compared with the 6-hour predictions. The role of the accumulated runoff input has been also studied."@en . "\u0160rejber, Jan" .