Comparative application of two mathematical models to predict sedimentation in Yermasoyia Reservoir,Cyprus

The Yermasoyia Reservoir is located northeast of the town of Limassol, Cyprus. The storage capacity of the reservoir is 13·6 × 10⁶ m³. The basin area of the Yermasoyia River, which feeds the reservoir, totals 122·5 km². This study aims to estimate the mean annual deposition amount in the reservoir, which originates from the corresponding basin. For the estimate of the mean annual sediment inflow into the reservoir, two mathematical models are used alternatively. Each model consists of three submodels: a rainfall‐runoff submodel, a soil erosion submodel and a sediment transport submodel for streams. In the first model, the potential evapotranspiration is estimated for the rainfall‐runoff submodel, and the soil erosion submodel of Schmidt and the sediment transport submodel of Yang are used. In the second model, the actual evapotranspiration is estimated for the rainfall‐runoff submodel, and the soil erosion submodel of Poesen and the sediment transport submodel of Van Rijn are used. The deposition amount in the reservoir is estimated by means of the diagram of Brune, which delivers the trap efficiency of the reservoir. Daily rainfall data from three rainfall stations, and daily values of air temperature, relative air humidity and sunlight hours from a meteorological station for four years (1986–89) were available. The computed annual runoff volumes and mean annual soil erosion rate are compared with the respective measurement data. Copyright © 2006 John Wiley & Sons, Ltd.     

Assessment of sediment transport approaches for sand-bed rivers by means of machine learning

Abstract

The quantification of the sediment carrying capacity of a river is a difficult task that has received much attention. For sand-bed rivers especially, several sediment transport functions have appeared in the literature based on various concepts and approaches; however, since they present a significant discrepancy in their results, none of them has become universally accepted. This paper employs three machine learning techniques, namely artificial neural networks, symbolic regression based on genetic programming and an adaptive-network-based fuzzy inference system, for the derivation of sediment transport formulae for sand-bed rivers from field and laboratory flume data. For the determination of the input parameters, some of the most prominent fundamental approaches that govern the phenomenon, such as shear stress, stream power and unit stream power, are utilized and a comparison of their efficacy is provided. The results obtained from the machine learning techniques are superior to those of the commonly-used sediment transport formulae and it is shown that each of the input combinations tested has its own merit, as they produce similarly good results with respect to the data-driven technique employed.

Editor Z.W. Kundzewicz