Uncertainty Quantification of Rainfall-runoff Simulations Using the Copula-based Bayesian Processor: Impacts of Seasonality, Copula Selection and Correlation Coefficient

Liu, Zhangjun; Zhang, Jingwen; Wen, Tianfu; Cheng, Jingqing

doi:10.1007/s11269-022-03287-x

Cited by 5 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the global water scarcity crisis, the precise and logical prediction of the rainfall-runoff (r-r) phenomenon stands as a significant hydro-environmental challenge (Lang et al, 2008;Nourani et al, 2019a;Wen et al, 2020;Liu et al, 2022). The dependable simulation of the r-r process is crucial, with undeniable impacts on water and drought management, irrigation, potable water resources, agriculture, industry, flood control, reservoir operations, and flood warning systems, among others (Nourani et al, 2019b;Zhao et al, 2022;Li et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Molajou,

Nourani,

Tajbakhsh

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper introduces a novel hybrid approach for predicting the rainfall-runoff (r-r) phenomenon across different data division scenarios (50%-50%, 60%-40%, and 75%-25%) within two distinct watersheds, encompassing both monthly and daily scales. Additionally, the effectiveness of this newly proposed hybrid method is evaluated in multi-step ahead prediction (MSAP) scenarios. The proposed method comprises three primary steps. Initially, to address the non-stationarity of the runoff and rainfall time series, these series are decomposed into multiple sub-time series using the wavelet (WT) decomposition method. Subsequently, in the second step, the decomposed sub-series are utilized as input data for the M5 model tree, a decision tree-based model. The M5 model tree classifies the samples of decomposed runoff and rainfall time series into distinct classes. Finally, each class is modeled using an artificial neural network (ANN). The results demonstrate the superior efficiency of the proposed WT-M5-ANN method compared to other available hybrid methods. Specifically, the calculated R2 was 0.93 for the proposed WT-M5-ANN method, whereas it was 0.89 and 0.81 for the WT-ANN and WT-M5 methods, respectively, for the Lobbs Hole Creek watershed at the daily scale.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Molajou,

Nourani,

Tajbakhsh

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Climate Change Impacts on Rainwater Tank’s Potential Water Savings, Efficiency and Reliability Presenting Relationship Between ‘Seasonality Index’ and Water Savings Efficiency

Imteaz

Khan

Yilmaz

et al. 2023

Water Resour Manage

View full text Add to dashboard Cite

The paper presents potential impacts of climate change on rainwater tanks outcomes such as water savings, reliability and water savings efficiency under two projected climate change scenarios; RCP4.5 and RCP8.5 utilising a case study using rainfall data from four stations within the city of Brisbane, Australia. Historical rainfall data were collected from the Australian Bureau of Meteorology website for the selected stations. Projected daily rainfall data were collected from Australian government data portal for the same stations within Brisbane. Using an earlier developed daily water balance model, eTank potential annual water savings were calculated for several weather and climate change scenarios with varied roof areas and rainwater demandValues of ‘Seasonality Index (SI)’, a commonly used factor representing rainfall variability within a year, were explored to validate earlier developed relationships between SI and water savings efficiency through rainwater tanks. It is found that in most cases water savings in future periods are expected to decrease and such decrease is not necessarily attributed to the expected decrease in rainfall amounts in future, rather also affected by future reductions in rainwater tank reliability. Linear relationships between potential future water savings and reliabilities for all the stations are found. Relationship between SI and water savings efficiency was established, and it is found that the relationship slightly varies with an earlier developed relationship using historical data. Compared to earlier established relationship, for lower SI values water savings efficiency is expected to become better, while for higher SI values the water savings efficiency is expected to become worse. Also, an increase of roof area from 100 m2 to 200 m2 will cause an average increase of water savings efficiency by 25% and an increase of rainwater usage from 200 L/day to 300 L/day will cause an average increase of water savings efficiency by 20%.

show abstract

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Molajou,

Nourani,

Tajbakhsh

et al. 2024

Water Resour Manage

View full text Add to dashboard Cite

This paper introduces a novel hybrid approach for predicting the rainfall-runoff (r-r) phenomenon across different data division scenarios (50%-50%, 60%-40%, and 75%-25%) within two distinct watersheds, encompassing both monthly and daily scales. Additionally, the effectiveness of this newly proposed hybrid method is evaluated in multi-step ahead prediction (MSAP) scenarios. The proposed method comprises three primary steps. Initially, to address the non-stationarity of the runoff and rainfall time series, these series are decomposed into multiple sub-time series using the wavelet (WT) decomposition method. Subsequently, in the second step, the decomposed sub-series are utilized as input data for the M5 model tree, a decision tree-based model. The M5 model tree classifies the samples of decomposed runoff and rainfall time series into distinct classes. Finally, each class is modeled using an artificial neural network (ANN). The results demonstrate the superior efficiency of the proposed WT-M5-ANN method compared to other available hybrid methods. Specifically, the calculated R 2 was 0.93 for the proposed WT-M5-ANN method, whereas it was 0.89 and 0.81 for the WT-ANN and WT-M5 methods, respectively, for the Lobbs Hole Creek watershed at the daily scale.

show abstract

Uncertainty Quantification of Rainfall-runoff Simulations Using the Copula-based Bayesian Processor: Impacts of Seasonality, Copula Selection and Correlation Coefficient

Cited by 5 publications

References 45 publications

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Climate Change Impacts on Rainwater Tank’s Potential Water Savings, Efficiency and Reliability Presenting Relationship Between ‘Seasonality Index’ and Water Savings Efficiency

Multi-Step-Ahead Rainfall-Runoff Modeling: Decision Tree-Based Clustering for Hybrid Wavelet Neural- Networks Modeling

Contact Info

Product

Resources

About