Asaad Y. Shamseldin

A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi–Sugeno fuzzy system

Abstract With a plethora of watershed rainfall-runoff models available for flood forecasting and more than adequate computing power to operate a number of such models simultaneously, we can now combine the simulation results from the different models to produce the combination forecasts. In this paper, the first-order Takagi–Sugeno fuzzy system is introduced and explained as the fourth combination method (besides other three combination methods tested earlier, i.e. the simple average method (SAM), the weighted average method (WAM), and the neural network method (NNM)) to combine together the simulation results of five different conceptual rainfall-runoff models in a flood forecasting study on eleven catchments. The comparison of the forecast simulation efficiency of the first-order Takagi–Sugeno combination method with the other three combination methods demonstrates that the first-order Takagi–Sugeno method is just as efficient as both the WAM and the NNM in enhancing the flood forecasting accuracy. Considering its simplicity and efficiency, the first-order Takagi–Sugeno method is recommended for use as the combination system for flood forecasting.

Methods for combining the outputs of different rainfall–runoff models

Abstract The present paper promotes the concept of combining the estimated output of different rainfall–runoff models to produce an overall combined estimated output to be used as an alternative to that obtained from a single individual rainfall–runoff model. Three methods of combining model outputs are considered, namely the simple average method (SAM), the weighted average method (WAM) and the neural network method (NNM). The estimated discharges of five rainfall–runoff models for 11 catchments are used to test the performance of these three combination methods. The results confirm that better discharge estimates can be obtained by combining the model outputs of different models.

Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting

This paper traces two decades of neural network rainfall-runoff and streamflow modelling, collectively termed ‘river forecasting’. The field is now firmly established and the research community involved has much to offer hydrological science. First, however, it will be necessary to converge on more objective and consistent protocols for: selecting and treating inputs prior to model development; extracting physically meaningful insights from each proposed solution; and improving transparency in the benchmarking and reporting of experimental case studies. It is also clear that neural network river forecasting solutions will have limited appeal for operational purposes until confidence intervals can be attached to forecasts. Modular design, ensemble experiments, and hybridization with conventional hydrological models are yielding new tools for decision-making. The full potential for modelling complex hydrological systems, and for characterizing uncertainty, has yet to be realized. Further gains could also emerge from the provision of an agreed set of benchmark data sets and associated development of superior diagnostics for more rigorous intermodel evaluation. To achieve these goals will require a paradigm shift, such that the mass of individual isolated activities, focused on incremental technical refinement, is replaced by a more coordinated, problem-solving international research body.

A real-time combination method for the outputs of different rainfall-runoff models

Abstract Application of the concept of combining the estimated forecast output of different rainfall-runoff models to yield an overall combined estimated output in the context of real-time river flow forecasting is explored. A Real-Time Model Output Combination Method (RTMOCM) is developed, based on the structure of the Linear Transfer Function Model (LTFM) and utilizing the concept of the Weighted Average Method (WAM) for model output combination. A multiple-input single-output form of the LTFM is utilized in the RTMOCM. This form of the LTFM model uses synchronously the daily simulation-mode model-estimated discharge time series of the rainfall-runoff models selected for combination, its inherent updating structure being used for providing updated combined discharge forecasts. The RTMOCM is applied to the daily data of five catchments, using the simulation-mode estimated discharges of three selected rainfall-runoff models, comprising one conceptual model (Soil Moisture Accounting and Routing Procedure—S...

Statistical downscaling of watershed precipitation using Gene Expression Programming (GEP)

Investigation of hydrological impacts of climate change at the regional scale requires the use of a downscaling technique. Significant progress has already been made in the development of new statistical downscaling techniques. Statistical downscaling techniques involve the development of relationships between the large scale climatic parameters and local variables. When the local parameter is precipitation, these relationships are often very complex and may not be handled efficiently using linear regression. For this reason, a number of non-linear regression techniques and the use of Artificial Neural Networks (ANNs) was introduced. But due to the complexity and issues related to finding a global solution using ANN-based techniques, the Genetic Programming (GP) based techniques have surfaced as a potential better alternative. Compared to ANNs, GP based techniques can provide simpler and more efficient solutions but they have been rarely used for precipitation downscaling. This paper presents the results of statistical downscaling of precipitation data from the Clutha Watershed in New Zealand using a non-linear regression model developed by the authors using Gene Expression Programming (GEP), a variant of GP. The results show that GEP-based downscaling models can offer very simple and efficient solutions in the case of precipitation downscaling.

Hydrodynamic Forces Generated on a Spherical Sediment Particle during Entrainment

The objective of this research is to study the relationship between the coherent flow structures and the hydrodynamic forces leading to entrainment of a spherical bed sediment particle for a rough bed uniform turbulent flow. Two types of experiments, namely, movable and fixed balls, were conducted using spherical roughness-element beds with particle image velocimetry to measure the instantaneous flow-velocity field. Miniature piezoelectric pressure sensors were used to capture the instantaneous pressure on the surface of the sphere. Movable ball experiments reveal the predominance of large sweep structures at the instant of entrainment. Fixed ball experiments carried out at entrainment conditions show the importance of both vertical and horizontal pressure gradients on the ball leading to entrainment. Probability distribution function plots of pressures based on quadrant analysis of velocities also reveal the higher probability of occurrence of high magnitude force induced by sweep ( Q4 ) events.

A nearest neighbour linear perturbation model for river flow forecasting

Abstract The non-parametric nearest neighbour method (NNM) for river flow forecasting is explored and developed further as the nearest neighbour linear perturbation model (NNLPM), which combines the nearest neighbour concept with the concept of perturbations from a mean value, as used in the linear perturbation model (LPM). The NNLPM model is tested on six catchments and its results are compared with those of the simple linear model (SLM) and the linear perturbation model (LPM). The results indicate that the NNLPM is a more reliable indicator of the discharge forecast than either the SLM or the LPM in the case of non-seasonal catchments.

A Comparative Study of Three Neural Network Forecast Combination Methods for simulated river flows of different Rainfall-runoff models

Abstract The performances of three artificial neural network (NN) methods for combining simulated river flows, based on three different neural network structures, are compared. These network structures are: the simple neural network (SNN), the radial basis function neural network (RBFNN) and the multi-layer perceptron neural network (MLPNN). Daily data of eight catchments, located in different parts of the world, and having different hydrological and climatic conditions, are used to enable comparisons of the performances of these three methods to be made. In the case of each catchment, each neural network combination method synchronously uses the simulated river flows of four rainfall—runoff models operating in design non-updating mode to produce the combined river flows. Two of these four models are black-box, the other two being conceptual models. The results of the study show that the performances of all three combination methods are, on average, better than that of the best individual rainfall—runoff model utilized in the combination, i.e. that the combination concept works. In terms of the Nash-Sutcliffe model efficiency index, the MLPNN combination method generally performs better than the other two combination methods tested. For most of the catchments, the differences in the efficiency index values of the SNN and the RBFNN combination methods are not significant but, on average, the SNN form performs marginally better than the more complex RBFNN alternative. Based on the results obtained for the three NN combination methods, the use of the multi-layer perceptron neural network (MLPNN) is recommended as the appropriate NN form for use in the context of combining simulated river flows.

Modification of the probability-distributed interacting storage capacity model

Abstract This paper is concerned with the review and modification of the structure of the conceptual rainfall-runoff model known as the probability-distributed interacting storage capacity (PDISC) model. The significance of the fundamental assumption of the equal-storage redistribution mode used in this model is critically investigated by adopting a more general linear-storage redistribution mode. The investigation is performed using the daily data of six catchments. The results reveal that the original assumption of the equal-storage redistribution mode may not be an optimum in some catchments. Further development of the water-balance module of the PDISC model is also explored. The surface-runoff generation mechanism of the model is modified by incorporating into the model structure a quick-runoff component. The results suggest that this modification can significantly improve the performance of the model. The results of the PDISC model are also compared with that of another established lumped conceptual rainfall-runoff model known as the soil moisture accounting and routing procedure (SMAR). Neither of the two models has worked consistently better than the other under all situations.

Use of Gene Expression Programming for Multimodel Combination of Rainfall-Runoff Models

AbstractThis paper deals with the application of an innovative method for combining estimated outputs from a number of rainfall-runoff models using gene expression programming (GEP) to perform symbolic regression. The GEP multimodel combination method uses the synchronous simulated river flows from four conventional rainfall-runoff models to produce a set of combined river flow estimates for four different catchments. The four selected models for the multimodel combinations are the linear perturbation model (LPM), the linearly varying gain factor model (LVGFM), the soil moisture accounting and routing (SMAR) model, and the probability-distributed interacting storage capacity (PDISC) model. The first two of these models are black-box models, the LPM exploiting seasonality and the LVGFM employing a storage-based coefficient of runoff. The remaining two are conceptual models. The data of four catchments with different geographical locations and hydrological and climatic conditions are used to test the perfor...