Lei Ye

TL;DR: Experimental results show that SWLSTM-GPR can obtain high-precision point prediction, appropriate prediction interval and reliable probabilistic prediction results with shorter training time on the wind speed prediction problems.

TL;DR: In this paper, a stochastic simulation method, comprising a copula-based simulation method accounting for flood forecasting uncertainty, a single site daily streamflow simulation method for uncertainty in flood hydrograph, and the Latin hypercube sampling (LHS) method, was proposed to analyze flood control risk due to these uncertainties.

TL;DR: In this article, a hidden Markov model (HMM) and Gaussian Mixture Regression (GMR) were combined for probabilistic monthly streamflow forecasting, and the performance of HMM-GMR was verified based on the mean square error and continuous ranked probability score skill scores.

TL;DR: This study proposes a new method based on the copula-entropy (CE) theory to identify the inputs of an ANN model, which characterizes the dependence between potential model input and output variables directly instead of calculating the marginal and joint probability distributions.

TL;DR: In this article, Pearson Type-III (P3) and kappa (KAP) distributions were compared for point and catchment scales of daily precipitation in the United States, and the performance of KAP distribution best describes the distribution of wet-day precipitation at the point scale, whereas P3 provided the improved goodness of fit over G2.