Comparison of daily streamflow forecasts using extreme learning machines and the random forest method

ABSTRACT

Daily streamflow forecasting is a challenging and essential task for water resource management. The main goal of this study was to compare the accuracy of five data-driven models: extreme learning machine (basic ELM), extreme learning machine with kernels (ELM-kernel), random forest (RF), back-propagation neural network (BPNN) and support vector machine (SVR). The results show that the ELM-kernel model provided a superior alternative to the other models, and the basic ELM model had the poorest performance. To further evaluate the predictive capacities of the five models, the estimations of low flow and high flow in the testing dataset were compared. The RF model was slightly superior to the other models in predicting the peak flows, and the ELM-kernel model showed the highest prediction precision of low flows. There was no single model that showed obvious advantages over the other models in this study. Therefore, further exploration is required for the hydrological forecasting problems.     

A multivariate non‐parametric model for synthetic generation of daily streamflow

A p‐order multivariate kernel density model based on kernel density theory has been developed for synthetic generation of multivariate variables. It belongs to a kind of data‐driven approach and is able to avoid prior assumptions as to the form of probability distribution (normal or Pearson III) and the form of dependence (linear or non‐linear). The p‐order multivariate kernel density model is a non‐parametric method for synthesis of streamflow. The model is more flexible than conventional parametric models used in stochastic hydrology. The effectiveness and satisfactoriness of this model are illustrated through its application to the simultaneous synthetic generation of daily streamflow from Pingshan station and Yibin‐Pingshan region (Yi‐Ping region) of the Jinsha River in China. Copyright © 2007 John Wiley & Sons, Ltd.     

Influence of the modified global ocean tide model with local tides of East and South China Seas on load gravity in China and its neighbor area

Introduction With the development of science and technology, the accuracy of gravity measurement is im-proved. The gravity observation with FG5 gravimeter has reached accuracy of μ magnitude. And the high accurate superconducting gravimeter can detect the tiny signal of 10?2 μ magnitude in frequency domain. With the high-accuracy gravity observation on Earth′s surface, the Earth′s tidal parameters can be determined precisely. And the observations can also be used to invert the struc-ture…     

Application of linear and nonlinear techniques in river flow forecasting in the Kilombero River basin,Tanzania / Application de techniques linéaires et non-linéaires à la prévision des débits dans le bassin de la Rivière Kilombero,en Tanzanie

Abstract

Modelling of the rainfall–runoff transformation process and routing of river flows in the Kilombero River basin and its five sub-catchments within the Rufiji River basin in Tanzania was undertaken using three system (black-box) models—a simple linear model, a linear perturbation model and a linear varying gain factor model—in their linear transfer function forms. A lumped conceptual model—the soil moisture accounting and routing model—was also applied to the sub-catchments and the basin. The HEC-HMS model, which is a distributed model, was applied only to the entire Kilombero River basin. River discharge, rainfall and potential evaporation data were used as inputs to the appropriate models and it was observed that sometimes the system models performed better than complex hydrological models, especially in large catchments, illustrating the usefulness of using simple black-box models in datascarce situations.