Machine learning based identification of dominant controls on runoff dynamics

Oppel, Henning; Schumann, Andreas

doi:10.1002/hyp.13740

Cited by 22 publications

(18 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, by focusing on situations where expert knowledge suggests that hydrology is more important than climate, relationships can be uncovered. For example, watershed drainage pattern helps to predict flood signatures (Oppel & Schumann, 2020), and information on surface waterbodies helps to predict baseflow signatures (Beck et al, 2013).…”

Section: Watershed Processesmentioning

confidence: 99%

A review of hydrologic signatures and their applications

McMillan

2020

WIREs Water

View full text Add to dashboard Cite

Hydrologic signatures are quantitative metrics or indices that describe statistical or dynamical properties of hydrologic data series, primarily streamflow. Hydrologic signatures were first used in eco-hydrology to assess alterations in flow regime, and have since seen wide uptake across a variety of hydrological fields. Their applications include extracting biologically relevant attributes of streamflow data, monitoring hydrologic change, analyzing runoff generation processes, defining similarity between watersheds, and calibrating and evaluating hydrologic models. Hydrologic signatures allow us to extract meaningful information about watershed processes from streamflow series, and are therefore seeing increasing use in emerging information-rich areas such as global-scale hydrologic modeling, machine learning, and large-sample hydrology. This overview paper describes the background and development of hydrologic signature theory, reviews hydrologic signature use across a variety of applications, and discusses ongoing hydrologic signature research including current challenges. This article is categorized under: Science of Water > Science of Water K E Y W O R D S flow indices, flow metrics, hydrologic signatures 1 | INTRODUCTION 1.1 | Discovering the information in streamflow data Streamflow timeseries show patterns: flood peaks and low flow periods, daily changes and seasonal cycles. These patterns are examples of information in streamflow data. The information might describe how the stream reacts to changes in weather, or what magnitudes and rates of change of flow are usual for the stream. Streamflow patterns depend on the physical characteristics of the watershed, telling a story about the path of water from precipitation to streamflow. Flow patterns in turn affect the stream's environment, informing us about riparian conditions and habitats. This paper describes how hydrologists use hydrologic signatures to extract this wealth of information from streamflow. 1.2 | What is a hydrologic signature? Hydrologic signatures are quantitative metrics that describe statistical or dynamic properties of streamflow. They are also known as hydrologic metrics, hydrologic indices, or diagnostic signatures. Hydrologic signatures range from simple

show abstract

Section: Watershed Processesmentioning

confidence: 99%

A review of hydrologic signatures and their applications

McMillan

2020

WIREs Water

View full text Add to dashboard Cite

show abstract

“…A fundamental premise is that these models have much more degrees of freedom than conceptual models facilitating the development and transferability of hydrological relationships and improving scaling relationships. Also, such models have been applied in ungauged catchments based on the assumption that sufficient data exist in hydrologically similar catchments to provide more accurate simulations in ungauged catchments than other calibrated catchment models (Kratzeret et al 2019;Oppel and Schumann 2020). While these approaches attempt to seek "truth" in hydrological modelling, the issue of accurately representing internal hydrological behaviour, and therefore the effects of anthropogenic activities remain elusive.…”

Section: Advances In Hydrological Scaling and Process Conceptualizationmentioning

confidence: 99%

Strategies for smarter catchment hydrology models: incorporating scaling and better process representation

Sidle

2021

Geosci. Lett.

View full text Add to dashboard Cite

Hydrological models have proliferated in the past several decades prompting debates on the virtues and shortcomings of various modelling approaches. Rather than critiquing individual models or modelling approaches, the objective here is to address the critical issues of scaling and hydrological process representation in various types of models with suggestions for improving these attributes in a parsimonious manner that captures and explains their functionality as simply as possible. This discussion focuses mostly on conceptual and physical/process-based models where understanding the internal catchment processes and hydrologic pathways is important. Such hydrological models can be improved by using data from advanced remote sensing (both spatial and temporal) and derivatives, applications of machine learning, flexible structures, and informing models through nested catchment studies in which internal catchment processes are elucidated. Incorporating concepts of hydrological connectivity into flexible model structures is a promising approach for improving flow path representation. Also important is consideration of the scale dependency of hydrological parameters to avoid scale mismatch between measured and modelled parameters. Examples are presented from remote high-elevation regions where water sources and pathways differ from temperate and tropical environments where more attention has been focused. The challenge of incorporating spatially and temporally variable water inputs, hydrologically pathways, climate, and land use into hydrological models requires modellers to collaborate with catchment hydrologists to include important processes at relevant scales—i.e. develop smarter hydrological models.

show abstract

“…The average of all regression results is returned as estimate of the RF. We applied the RF due to its common application in hydrological studies (Yu et al, 2017;Addor et al, 2018;Oppel and Schumann, 2020). Moreover, the use of an ensemble regressor accounts for the recommendations of Elshorbagy et al (2010a).…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

“…Natural and anthropocentric processes have to be reproduced in order to model future events and behaviors (Mount et al, 2016). Hence, 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. However, all water related tasks require pre-processed data.…”

Section: Introductionmentioning

confidence: 99%

On the Automation of Flood Event Separation From Continuous Time Series

Oppel

Mewes

2020

Front. Water

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Machine learning based identification of dominant controls on runoff dynamics

Cited by 22 publications

References 53 publications

A review of hydrologic signatures and their applications

A review of hydrologic signatures and their applications

Strategies for smarter catchment hydrology models: incorporating scaling and better process representation

On the Automation of Flood Event Separation From Continuous Time Series

Contact Info

Product

Resources

About