Spatial Disaggregation of Areal Rainfall Using Two Different Artificial Neural Networks Models

Kim, Sung-Won; Singh, Vijay P.

doi:10.3390/w7062707

Cited by 16 publications

(9 citation statements)

References 70 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different statistical and data-driven models have been used for temporal disaggregation of rainfall. A number of recent studies reported promising performance of ANN in temporal disaggregation of rainfall [41][42][43][44][45][46][47]. Zhang et al [43] used ANN for disaggregation of rainfall for West-Central Florida, and reported that the disaggregation of rainfall using ANN is promising.…”

Section: Disaggregation Of Daily Rainfall and Generation Of Projectedmentioning

confidence: 99%

Uncertainty in Rainfall Intensity Duration Frequency Curves of Peninsular Malaysia under Changing Climate Scenarios

Noor

Shahid

Chung

et al. 2018

Water

View full text Add to dashboard Cite

This study developed a methodological framework to update the rainfall intensity-duration-frequency (IDF) curves under climate change scenarios. A model output statistics (MOS) method is used to downscale the daily rainfall of general circulation models (GCMs), and an artificial neural network (ANN) is employed for the disaggregation of projected daily rainfall to hourly maximum rainfall, which is then used for the development of IDF curves. Finally, the 1st quartiles, medians, and 3rd quartiles of projected rainfall intensities are estimated for developing IDF curves with uncertainty level. Eight GCM simulations under two radiative concentration pathways (RCP) scenarios, namely, RCP 4.5 and RCP 8.5, are used in the proposed framework for the projection of IDF curves with related uncertainties for peninsular Malaysia. The projection of rainfall revealed an increase in the annual average rainfall throughout the present century. The comparison of the projected IDF curves for the period 2006–2099 with that obtained using GCM hindcasts for the based period (1971–2005) revealed an increase in rainfall intensity for shorter durations and a decrease for longer durations. The uncertainty in rainfall intensity for different return periods for shorter duration is found to be 2 to 6 times more compared to longer duration rainfall, which indicates that a large increase in rainfall intensity for short durations projected by GCMs is highly uncertain for peninsular Malaysia. The IDF curves developed in this study can be used for the planning of climate resilient urban water storm water management infrastructure in Peninsular Malaysia.

show abstract

Section: Disaggregation Of Daily Rainfall and Generation Of Projectedmentioning

confidence: 99%

Uncertainty in Rainfall Intensity Duration Frequency Curves of Peninsular Malaysia under Changing Climate Scenarios

Noor

Shahid

Chung

et al. 2018

Water

View full text Add to dashboard Cite

show abstract

“…An ANN is a parallel information processing system with a set of neurons arranged in one or more hidden layers [53]. The MLP, which is an explicit form of the ANNs model, consists of three (or more) layers with an input layer (where the data are fed into the model), one (or more) hidden layer (where the data are processed to construct a model), and an output layer (where the results are generated) [54][55][56][57]. The neurons are connected by appropriate weights in each layer to the neurons in continuous layers.…”

Section: Multilayer Perceptron (Mlp) Neural Network Modelmentioning

confidence: 99%

Can Decomposition Approaches Always Enhance Soft Computing Models? Predicting the Dissolved Oxygen Concentration in the St. Johns River, Florida

et al. 2019

Self Cite

View full text Add to dashboard Cite

This study evaluates standalone and hybrid soft computing models for predicting dissolved oxygen (DO) concentration by utilizing different water quality parameters. In the first stage, two standalone soft computing models, including multilayer perceptron (MLP) neural network and cascade correlation neural network (CCNN), were proposed for estimating the DO concentration in the St. Johns River, Florida, USA. The DO concentration and water quality parameters (e.g., chloride (Cl), nitrogen oxides (NOx), total dissolved solid (TDS), potential of hydrogen (pH), and water temperature (WT)) were used for developing the standalone models by defining six combinations of input parameters. Results were evaluated using five performance criteria metrics. Overall results revealed that the CCNN model with input combination III (CCNN-III) provided the most accurate predictions of DO concentration values (root mean square error (RMSE) = 1.261 mg/L, Nash-Sutcliffe coefficient (NSE) = 0.736, Willmott’s index of agreement (WI) = 0.919, R2 = 0.801, and mean absolute error (MAE) = 0.989 mg/L) for the standalone model category. In the second stage, two decomposition approaches, including discrete wavelet transform (DWT) and variational mode decomposition (VMD), were employed to improve the accuracy of DO concentration using the MLP and CCNN models with input combination III (e.g., DWT-MLP-III, DWT-CCNN-III, VMD-MLP-III, and VMD-CCNN-III). From the results, the DWT-MLP-III and VMD-MLP-III models provided better accuracy than the standalone models (e.g., MLP-III and CCNN-III). Comparison of the best hybrid soft computing models showed that the VMD-MLP-III model with 4 intrinsic mode functions (IMFs) and 10 quadratic penalty factor (VMD-MLP-III (K = 4 and α = 10)) model yielded slightly better performance than the DWT-MLP-III with Daubechies-6 (D6) and Symmlet-6 (S6) (DWT-MLP-III (D6 and S6)) models. Unfortunately, the DWT-CCNN-III and VMD-CCNN-III models did not improve the performance of the CCNN-III model. It was found that the CCNN-III model cannot be used to apply the hybrid soft computing modeling for prediction of the DO concentration. Graphical comparisons (e.g., Taylor diagram and violin plot) were also utilized to examine the similarity between the observed and predicted DO concentration values. The DWT-MLP-III and VMD-MLP-III models can be an alternative tool for accurate prediction of the DO concentration values.

show abstract

“…The paper by Kim and Singh [23] entitled Spatial Disaggregation of Areal Rainfall Using Two Different Artificial Neural Networks Models presents the development of two artificial neural network models, namely, the multilayer perceptron and Kohonen self-organizing feature map, for spatial disaggregation of areal precipitation in the Wi-stream catchment in South Korea. For the three-layer multilayer perceptron model, three training algorithms, namely, Levenberg-Marquardt, conjugate gradient and quickprop, are employed to compute areal precipitation.…”

Section: Contributorsmentioning

confidence: 99%

Use of Meta-Heuristic Techniques in Rainfall-Runoff Modelling

Chau

2017

Water

103

View full text Add to dashboard Cite

Each year, extreme floods, which appear to be occurring more frequently in recent years (owing to climate change), lead to enormous economic damage and human suffering around the world. It is therefore imperative to be able to accurately predict both the occurrence time and magnitude of peak discharge in advance of an impending flood event. The use of meta-heuristic techniques in rainfall-runoff modeling is a growing field of endeavor in water resources management. These techniques can be used to calibrate data-driven rainfall-runoff models to improve forecasting accuracies. This Special Issue of the journal Water is designed to fill the analytical void by including papers concerning advances in the contemporary use of meta-heuristic techniques in rainfall-runoff modeling. The information and analyses can contribute to the development and implementation of effective hydrological predictions, and thus, of appropriate precautionary measures.

show abstract

Spatial Disaggregation of Areal Rainfall Using Two Different Artificial Neural Networks Models

Cited by 16 publications

References 70 publications

Uncertainty in Rainfall Intensity Duration Frequency Curves of Peninsular Malaysia under Changing Climate Scenarios

Uncertainty in Rainfall Intensity Duration Frequency Curves of Peninsular Malaysia under Changing Climate Scenarios

Can Decomposition Approaches Always Enhance Soft Computing Models? Predicting the Dissolved Oxygen Concentration in the St. Johns River, Florida

Use of Meta-Heuristic Techniques in Rainfall-Runoff Modelling

Contact Info

Product

Resources

About