Monthly Rainfall-Runoff Modeling at Watershed Scale: A Comparative Study of Data-Driven and Theory-Driven Approaches

Chang, Won; Chen, Xi

doi:10.3390/w10091116

Cited by 31 publications

(19 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The discharge and DOC data are from 2006 to 2019. To infer the long record to 2000, we used the machine learning statistical approach Gaussian Process Regression (GPR) 72 , an approach commonly used to infer discharge data [73][74][75] . We trained a discharge model using the odd years of climate and discharge data from 2006 to 2019, and tested the model using even year data.…”

Section: Discussionmentioning

confidence: 99%

Significant stream chemistry response to temperature variations in a high-elevation mountain watershed

Zhi

Williams

Carroll

et al. 2020

Commun Earth Environ

View full text Add to dashboard Cite

High-elevation mountain regions, central to global freshwater supply, are experiencing more rapid warming than low-elevation locations. High-elevation streams are therefore potentially critical indicators for earth system and water chemistry response to warming. Here we present concerted hydroclimatic and biogeochemical data from Coal Creek, Colorado in the central Rocky Mountains at elevations of 2700 to 3700 m, where air temperatures have increased by about 2 °C since 1980. We analyzed water chemistry every other day from 2016 to 2019. Water chemistry data indicate distinct responses of different solutes to inter-annual hydroclimatic variations. Specifically, the concentrations of solutes from rock weathering are stable inter-annually. Solutes that are active in soils, including dissolved organic carbon, vary dramatically, with double to triple peak concentrations occurring during snowmelt and in warm years. We advocate for consistent and persistent monitoring of high elevation streams to record early glimpse of earth surface response to warming.

show abstract

Section: Discussionmentioning

confidence: 99%

Significant stream chemistry response to temperature variations in a high-elevation mountain watershed

Zhi

Williams

Carroll

et al. 2020

Commun Earth Environ

View full text Add to dashboard Cite

show abstract

“…GPR is a nonparametric Bayesian nonlinear regression method that can model random variables with a multivariate normal distribution in continuous time or space (Kirk & Stumpf, 2009). Recent studies have applied GPR to monthly rainfall-runoff predictions for the next time step with acceptable accuracy (W. Chang et al, 2018;Sun et al, 2014). GPR was used as a benchmark in this study as well.…”

Section: Model Benchmarks and Methodsmentioning

confidence: 99%

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

Xiang

Yan²,

Demir

2020

Water Resources Research

467

169

View full text Add to dashboard Cite

Rainfall-runoff modeling is a complex nonlinear time series problem. While there is still room for improvement, researchers have been developing physical and machine learning models for decades to predict runoff using rainfall data sets. With the advancement of computational hardware resources and algorithms, deep learning methods such as the long short-term memory (LSTM) model and sequence-to-sequence (seq2seq) modeling have shown a good deal of promise in dealing with time series problems by considering long-term dependencies and multiple outputs. This study presents an application of a prediction model based on LSTM and the seq2seq structure to estimate hourly rainfall-runoff. Focusing on two Midwestern watersheds, namely, Clear Creek and Upper Wapsipinicon River in Iowa, these models were used to predict hourly runoff for a 24-hr period using rainfall observation, rainfall forecast, runoff observation, and empirical monthly evapotranspiration data from all stations in these two watersheds. The models were evaluated using the Nash-Sutcliffe efficiency coefficient, the correlation coefficient, statistical bias, and the normalized root-mean-square error. The results show that the LSTM-seq2seq model outperforms linear regression, Lasso regression, Ridge regression, support vector regression, Gaussian processes regression, and LSTM in all stations from these two watersheds. The LSTM-seq2seq model shows sufficient predictive power and could be used to improve forecast accuracy in short-term flood forecast applications. In addition, the seq2seq method was demonstrated to be an effective method for time series predictions in hydrology. Key Points:• An hourly runoff model was developed using the LSTM sequence-to-sequence learning method for 24-hr predictions on USGS stations • The proposed model shows better performance than traditional data-driven models and is applicable to different watersheds • The advantages and limitations of seq2seq models and how this model structure could work on the rainfall-runoff modeling is presented Supporting Information:• Supporting Information S1 Correspondence to: Z. Xiang, zhongrun-xiang@uiowa.edu Citation: Xiang, Z., Yan, J., & Demir, I. (2020). A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resources Research, 56, e2019WR025326. https://doi.

show abstract

“…Unlike typical hydrologic models, data-driven approaches do not rely directly on explicit physical knowledge of the process, even if they usually are the first step in developing knowledge about system properties, observing relationships between input and output variables. Using various learning algorithms, data-driven approaches provide a flexible way to model complex phenomena such karst spring discharge [14].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Minimum Karst Spring Discharge Using a Simple Rainfall-Input Model: The Case Study of Capodacqua di Spigno Spring (Central Italy)

Sappa

Filippi

Iacurto

et al. 2019

Water

View full text Add to dashboard Cite

The increasing occurrence of widespread drought phenomena is a global environmental emergency, especially for the effects of ongoing climate change on groundwater availability. Dry years and extreme temperatures are common drivers of current climate impacts all over the world, including, for example, the freshwater supply for drinking and agriculture purposes, ecosystems, forestry, health, etc. In this frame, to ensure temporal water availability in water-stressed areas, sustainable groundwater management is an increasing challenge. Most groundwater in the South-East Latium Region, Central Italy, as in the whole Apennine Mountains chain, is stored in karst aquifers. In this area important water resources are present, but even here in the last decades they are affected by groundwater depletion as a consequence of occurring drought events, the upward trend in the global average temperature and the increase in groundwater extraction. Due to the lack of flow rate data of springs in many areas of Italy, spring response modeling could be a useful tool for supporting proper water resource management. Several research studies proposed methods based on relationships between spring discharges and rainfall data. The goal of this paper is to propose a simple linear model, based on rainfall-discharge cross correlations, in order to be able to simulate the effects of variation in rainfall on water resource connected Capodacqua di Spigno Spring minimum discharge. The results obtained using the developed model has been compared to an existing method that uses the Standard Precipitation Index (SPI) for the estimation of the minimum annual spring discharge.

show abstract

Monthly Rainfall-Runoff Modeling at Watershed Scale: A Comparative Study of Data-Driven and Theory-Driven Approaches

Cited by 31 publications

References 63 publications

Significant stream chemistry response to temperature variations in a high-elevation mountain watershed

Significant stream chemistry response to temperature variations in a high-elevation mountain watershed

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

Evaluation of Minimum Karst Spring Discharge Using a Simple Rainfall-Input Model: The Case Study of Capodacqua di Spigno Spring (Central Italy)

Contact Info

Product

Resources

About