English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Abstract. In this study, we propose a data-driven approach for automatically identifyingrainfall-runoff events in discharge time series. Thecore of the concept is to construct and apply discrete multivariateprobability distributions to obtain probabilistic predictions of each timestep that is part of an event. The approach permits any data to serve aspredictors, and it is non-parametric in the sense that it can handle anykind of relation between the predictor(s) and the target. Each choice of aparticular predictor data set is equivalent to formulating a modelhypothesis. Among competing models, the best is found by comparing theirpredictive power in a training data set with user-classified events. Forevaluation, we use measures from information theory such as Shannon entropyand conditional entropy to select the best predictors and models and,additionally, measure the risk of overfitting via cross entropy andKullback–Leibler divergence. As all these measures are expressed in “bit”,we can combine them to identify models with the best tradeoff betweenpredictive power and robustness given the available data. We applied the method to data from the Dornbirner Ach catchment in Austria,distinguishing three different model types: models relying on discharge data,models using both discharge and precipitation data, and recursive models,i.e., models using their own predictions of a previous time step as anadditional predictor. In the case study, the additional use of precipitationreduced predictive uncertainty only by a small amount, likely because theinformation provided by precipitation is already contained in the dischargedata. More generally, we found that the robustness of a model quickly droppedwith the increase in the number of predictors used (an effect well known asthe curse of dimensionality) such that, in the end, the best model was arecursive one applying four predictors (three standard and one recursive):discharge from two distinct time steps, the relative magnitude of dischargecompared with all discharge values in a surrounding 65 h time window andevent predictions from the previous time step. Applying the model reduced theuncertainty in event classification by 77.8 %, decreasing conditionalentropy from 0.516 to 0.114 bits. To assess the quality of the proposedmethod, its results were binarized and validated through a holdout method andthen compared to a physically based approach. The comparison showed similarbehavior of both models (both with accuracy near 90 %), and the cross-validation reinforced the quality of the proposed model. Given enough data to build data-driven models, their potential lies in theway they learn and exploit relations between data unconstrained byfunctional or parametric assumptions and choices. And, beyond that, the useof these models to reproduce a hydrologist's way of identifying rainfall-runoffevents is just one of many potential applications.

Identifying rainfall-runoff events in discharge time series: a data-driven method based on information theory