The utilization of a GR4J model and wavelet-based artificial neural network for rainfall–runoff modelling

Sezen, Cenk; Partal, Turgay

doi:10.2166/ws.2018.189

Cited by 13 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the PC‐based representation, we chose the GR4J dynamical lumped water balance model (Perrin et al., 2003), due to its relative parsimony and the reports of good performance in other studies (Kunnath‐Poovakka & Eldho, 2019; Pagano et al., 2010; Sezen & Partal, 2019), and because the catchment‐scale data required for its implementation is available (Table A1). Moreover, we coupled to it the lumped CemaNeige snowmelt module (Valéry et al., 2014) to account for snow process dynamics at high altitudes in Andes Mountain range.…”

Section: Study Methodologymentioning

confidence: 99%

Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology

Fuente

Gupta

Condon

2023

Water Resources Research

View full text Add to dashboard Cite

Key to model development is the selection of an appropriate representational system, including both the representation of what is observed (the data), and the formal mathematical structure used to construct the input‐state‐output mapping. These choices are critical, because they completely determine the questions we can ask, the nature of the analyses and inferences we can perform, and the answers we can obtain. Accordingly, a representation that is suitable for one kind of investigation might be limited in its ability to support some other kind. Arguably, how different representational approaches affect what we can learn from data is poorly understood. This paper explores three representational strategies as vehicles for understanding how catchment scale hydrological processes vary across hydro‐geo‐climatologically diverse Chile. Specifically, we test a lumped water‐balance model (GR4J), a data‐based dynamical systems model (LSTM), and a data‐based regression tree model (Random Forest). Insights were obtained regarding system memory encoded in data, spatial transferability by use of surrogate attributes, and informational deficiencies of the data set that limit our ability to learn an adequate input‐output relationship. As expected, each approach exhibits specific strengths, with LSTM providing the best characterization of dynamics, GR4J being the most robust under informationally deficient conditions, and Random Forest regression‐tree method being most supportive of interpretation. Overall, the contrasting nature of the three approaches suggests the value of adopting a multi‐representational framework to more fully extract information from the data and, by doing so, find information that better facilities the goals of robust prediction and improved understanding, ultimately supporting enhanced scientific discovery.

show abstract

Section: Study Methodologymentioning

confidence: 99%

Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology

Fuente

Gupta

Condon

2023

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…Our previous work (Pan et al, 2020) verified that the ACWSC (i.e., parameter θ 1 ) had an "abrupt" point after the prolonged meteorological drought, which assumes that the offset of the estimated θ 1 represents the change in the ACWSC. Meanwhile, θ 1 in each period is recognized as a constant value and does not include the periodicity of the ACWSC that was outlined by many previous works (Nepal et al, 2017;Kunnath-Poovakka and Eldho, 2019;Sezen and Partal, 2019). However, Westra et al (2014) and Pan et al (2020) indicated that the ACWSC had periodic variability that may be due to the seasonal growth and wiling of catchment vegetation.…”

Section: Periodicity Of the Acwscmentioning

confidence: 95%

“…The GR4J model was used to address the response of the ACWSC to prolonged meteorological drought. The model processes a relatively simple structure with relatively low requirements for input data, and it has been widely used in the rainfall-runoff simulation for small and medium-sized catchments (Demirel et al, 2013;Sezen and Partal, 2019;Kunnath-Poovakka and Eldho, 2019). However, the GR4J model is implemented subject to restrictions and limitations due to the inadequate description of the runoff generation and flow confluence processes in large catchments (e.g., larger than 10 000 km 2 ).…”

Section: Limitations Of the Hydrological Modelmentioning

confidence: 99%

Response of active catchment water storage capacity to a prolonged meteorological drought and asymptotic climate variation

Tian

Pan²,

Yin³

et al. 2022

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Studies on the hydrological response to continuous extreme and asymptotic climate change can improve our ability to cope with intensified water-related problems. Most of the literature focused on the runoff response to climate change, while neglecting the impacts of the potential variation in the active catchment water storage capacity (ACWSC) that plays an essential role in the transfer of climate inputs to the catchment runoff. This study aims to systematically identify the response of the ACWSC to a long-term meteorological drought and asymptotic climate change. First, the time-varying parameter is derived to reflect the ACWSC periodic and abrupt variations in both drought and non-drought periods. Second, the change points and varying patterns of the ACWSC are analyzed based on the Bayesian change point analysis with multiple evaluation criteria. Finally, various catchment properties and climate characteristics are used to explore the possible relationship between these variables and the temporal variation characteristics of the ACWSC. The catchments that suffered from a prolonged meteorological drought in southeast Australia were selected as the case study. Results indicate that: (1) the increase in amplitude change in the ACWSC is observed in 83/92 catchments during the prolonged drought period, and significant shifts in the mean value of the ACWSC are detected in 77/92 catchments; (2) the average response time of the ACWSC for all 92 catchments with significant changes is 641.3 d; (3) the values of the ACWSC changed significantly in the catchments with small areas, low elevations, small slope ranges, large forest coverage, and high soil water-holding capacities. This study could enhance our understanding of the variations in catchment property under climate change.

show abstract

“…Our previous work (Pan et al, 2020) has verified that the CWSC (i.e., parameter θ1) had an "abrupt" point after the prolonged meteorological drought, which assumes that the offset of the estimated θ1 represents the change of CWSC. Meanwhile, the θ1 in each period is recognized as a constant value and do not include the periodicity of the CWSC that has been outlined by many previous works (Nepal et al, 2017;Kunnath-Poovakka and Eldho, 2019;Sezen and Partal, 2019).…”

Section: Periodicity Of the Cwscmentioning

confidence: 99%

Response of catchment water storage capacity to the prolonged meteorological drought and asymptotic climate variation

Tian

Pan

Wang

2022

Preprint

View full text Add to dashboard Cite

Abstract. Studies on the hydrological response to continuous extreme and asymptotic climate change can improve our ability to cope the intensified water-related problems. Most of the existing literature focused on the runoff response to different climate change patterns, while neglected the impacts by the potential variation in the catchment water storage capacity (CWSC) that plays an important role in the transfer of climate input to the catchment runoff. This study aims to identify the response of the CWSC to the long-term meteorological drought and asymptotic climate change systematically. Firstly, the time-varying parameter is derived to reflect the CWSC periodic/abrupt variations under both drought and non-drought periods. Secondly, the change points and varying patterns of the CWSC are analysed based on the Bayesian change point analysis with multiple evaluation criteria. Finally, multiple catchment properties and climate characteristics are used to explore the possible relationship between these variables and the temporal variation characteristic of the CWSC. The catchments suffered from prolonged meteorological drought in southeast Australia are selected as the case study. Results indicate that: (1) the increase of CWSC amplitude change has been observed in 83/92 catchments during the prolonged drought period and the significant shifts in the mean value of the CWSC are detected in 77/92 catchments; (2) the median response time of CWSC for all 92 catchments with significant changes is 641.3 days; (3) the values of CWSC are changed significantly in the catchments with small area\\low elevation\\small slope range\\large forest coverage and high soil water holding capacity. This study might enhance our understanding to the variations in catchment property under different climate-changing patterns.

show abstract

The utilization of a GR4J model and wavelet-based artificial neural network for rainfall–runoff modelling

Cited by 13 publications

References 21 publications

Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology

Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology

Response of active catchment water storage capacity to a prolonged meteorological drought and asymptotic climate variation

Response of catchment water storage capacity to the prolonged meteorological drought and asymptotic climate variation

Contact Info

Product

Resources

About