Abstract
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.
Highlights
Machine-learning has proven its capability in a vast range of applications, especially in those cases when a certain pattern has to be revealed from a huge data archive in order to reproduce it afterwards
Our results showed that a training data set of 35 manually separated flood events was needed to train Artificial neuronal networks (ANN), only the Extreme Learning Machine (ELM) and KNN should be used with less available data
In this article we demonstrated how machine learning can be used to automate the task of hydrograph separation from continuous time series
Summary
Machine-learning has proven its capability in a vast range of applications, especially in those cases when a certain pattern has to be revealed from a huge data archive in order to reproduce it afterwards. Natural and anthropocentric processes have to be reproduced in order to model future events and behaviors (Mount et al, 2016). Machine learning (ML) has been applied in a broad range of applications, like streamflow simulation (Shortridge et al, 2016), the interpretation of remote sensing images (Mountrakis et al, 2011), modeling of evapotranspiration (Tabari et al, 2012), rainfall forecasting (Yu et al, 2017), process analysis (Oppel and Schumann, 2020), and many more. All water related tasks require pre-processed data. A typical example is the need for direct runoff flood events that have to be extracted from continuous time series of discharge
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
