Datum
2020-07-28Schlagwort
004 Informatik 550 Geowissenschaften HochwasserHydrologieForschungsdatenMaschinelles LernenInformation ExtractionZeitreiheAutomationDatenverarbeitungMetadata
Zur Langanzeige
Aufsatz
On the Automation of Flood Event Separation From Continuous Time Series
Zusammenfassung
Can machine learning effectively lower the effort necessary to extract important information from raw data for hydrological research questions? On the example of a typical water-management task, the extraction of direct runoff flood events from continuous hydrographs, we demonstrate how machine learning can be used to automate the application of expert knowledge to big data sets and extract the relevant information. In particular, we tested seven different algorithms to detect event beginning and end solely from a given excerpt from the continuous hydrograph. First, the number of required data points within the excerpts as well as the amount of training data has been determined. In a local application, we were able to show that all applied Machine learning algorithms were capable to reproduce manually defined event boundaries. Automatically delineated events were afflicted with a relative duration error of 20 and 5% event volume. Moreover, we could show that hydrograph separation patterns could easily be learned by the algorithms and are regionally and trans-regionally transferable without significant performance loss. Hence, the training data sets can be very small and trained algorithms can be applied to new catchments lacking training data. The results showed the great potential of machine learning to extract relevant information efficiently and, hence, lower the effort for data preprocessing for water management studies. Moreover, the transferability of trained algorithms to other catchments is a clear advantage to common methods.
Zitierform
In: Frontiers in Water Volume 2 (2020-07-28) , S. Article 18 ; EISSN: 2624-9375Förderhinweis
Gefördert durch den Publikationsfonds der Universität KasselZitieren
@article{doi:10.17170/kobra-202009111783,
author={Oppel, Henning and Mewes, Benjamin},
title={On the Automation of Flood Event Separation From Continuous Time Series},
journal={Frontiers in Water},
year={2020}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2020$n2020 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/11808 3000 Oppel, Henning 3010 Mewes, Benjamin 4000 On the Automation of Flood Event Separation From Continuous Time Series / Oppel, Henning 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/11808=x R 4204 \$dAufsatz 4170 5550 {{Hochwasser}} 5550 {{Hydrologie}} 5550 {{Forschungsdaten}} 5550 {{Maschinelles Lernen}} 5550 {{Information Extraction}} 5550 {{Zeitreihe}} 5550 {{Automation}} 5550 {{Datenverarbeitung}} 7136 ##0##http://hdl.handle.net/123456789/11808
2020-09-11T15:24:19Z 2020-09-11T15:24:19Z 2020-07-28 doi:10.17170/kobra-202009111783 http://hdl.handle.net/123456789/11808 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ flood event separation information extraction time series automation data preprocessing 004 550 On the Automation of Flood Event Separation From Continuous Time Series Aufsatz Can machine learning effectively lower the effort necessary to extract important information from raw data for hydrological research questions? On the example of a typical water-management task, the extraction of direct runoff flood events from continuous hydrographs, we demonstrate how machine learning can be used to automate the application of expert knowledge to big data sets and extract the relevant information. In particular, we tested seven different algorithms to detect event beginning and end solely from a given excerpt from the continuous hydrograph. First, the number of required data points within the excerpts as well as the amount of training data has been determined. In a local application, we were able to show that all applied Machine learning algorithms were capable to reproduce manually defined event boundaries. Automatically delineated events were afflicted with a relative duration error of 20 and 5% event volume. Moreover, we could show that hydrograph separation patterns could easily be learned by the algorithms and are regionally and trans-regionally transferable without significant performance loss. Hence, the training data sets can be very small and trained algorithms can be applied to new catchments lacking training data. The results showed the great potential of machine learning to extract relevant information efficiently and, hence, lower the effort for data preprocessing for water management studies. Moreover, the transferability of trained algorithms to other catchments is a clear advantage to common methods. open access Oppel, Henning Mewes, Benjamin doi:10.3389/frwa.2020.00018 Hochwasser Hydrologie Forschungsdaten Maschinelles Lernen Information Extraction Zeitreihe Automation Datenverarbeitung publishedVersion EISSN: 2624-9375 Frontiers in Water Article 18 Volume 2 false
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: