Time filter

Source Type

Nanning, China

Xiao Z.,CAS Institute of Atmospheric Physics | Zhou X.,Guangxi Climate Center | Yang P.,China Meteorological Administration Training Center | Liu H.,China Meteorological Administration Training Center
Frontiers of Earth Science | Year: 2015

This study analyzed the changes in precipitation over summer and autumn across the Yunnan region of China, and undertook a composite analysis of the atmospheric circulations in the troposphere, which included an analysis of the interannual and interdecadal variations. This paper examines in detail the circulation backgrounds of the wet and dry periods in summer and autumn and their correlations with the sea surface temperature. The results indicated that the summer and autumn precipitation across Yunnan has significantly decreased over the past 50 years. Furthermore, since the beginning of the century, the summer and autumn precipitation cycle has been in a low precipitation phase. The overlap of two extremely low rain phases has caused frequent droughts in the region. In addition, the atmospheric circulation fields during these wet and dry periods are very different. These are mainly shown as a meridional wind anomaly in eastern China in the low atmosphere, as a cross-equatorial airflow anomaly, a tropical zonal wind anomaly over the Indian Ocean, and as a related South Asia High and Western Pacific Subtropical High. Further analysis suggested that the SST over the Indian Ocean and the Pacific warm pool critically affect the anomalous summer and autumn precipitation over Yunnan by impacting the monsoon circulations. Future projections for greenhouse gas warming suggest a potential anomalous circulation background between 2010 and 2020 which may result in less precipitation during the wet season or even drought events across the Yunnan region. © 2015 Higher Education Press and Springer-Verlag Berlin Heidelberg Source

Jin J.,East China Normal University | Li M.,East China Normal University | Jin L.,Guangxi Climate Center
Mathematical Problems in Engineering | Year: 2015

When pure linear neural network (PLNN) is used to predict tropical cyclone tracks (TCTs) in South China Sea, whether the data is normalized or not greatly affects the training process. In this paper, min.-max. method and normal distribution method, instead of standard normal distribution, are applied to TCT data before modeling. We propose the experimental schemes in which, with min.-max. method, the min.-max. value pair of each variable is mapped to (-1, 1) and (0, 1); with normal distribution method, each variable's mean and standard deviation pair is set to (0, 1) and (100, 1). We present the following results: (1) data scaled to the similar intervals have similar effects, no matter the use of min.-max. or normal distribution method; (2) mapping data to around 0 gains much faster training speed than mapping them to the intervals far away from 0 or using unnormalized raw data, although all of them can approach the same lower level after certain steps from their training error curves. This could be useful to decide data normalization method when PLNN is used individually. © 2015 Jian Jin et al. Source

Huang Y.,Guangxi Research Institute of Meteorological Disasters Mitigation | Jin L.,Guangxi Climate Center
Meteorology and Atmospheric Physics | Year: 2013

A western North Pacific tropical cyclone (TC) intensity prediction scheme has been developed based on climatology and persistence (CLIPER) factors as potential predictors and using genetic neural network (GNN) model. TC samples during June-October spanning 2001-2010 are used for model development. The GNN model input is constructed from potential predictors by employing both a stepwise regression method and an Isometric Mapping (Isomap) algorithm. The Isomap algorithm is capable of finding meaningful low-dimensional architectures hidden in their nonlinear high-dimensional data space and separating the underlying factors. In this scheme, the new developed model, which is termed the GNN-Isomap model, is used for monthly TC intensity prediction at 24- and 48-h lead times. Using identical modeling samples and independent samples, predictions of the GNN-Isomap model are compared with the widely used CLIPER method. By adopting different numbers of nearest neighbors, results of sensitivity experiments show that the mean absolute prediction errors of the independent samples using GNN-Isomap model at 24- and 48-h forecasts are smaller than those using CLIPER method. Positive skills are obtained as compared to the CLIPER method with being above 12 % at 24 h and above 14 % at 48 h. Analyses of the new scheme suggest that the useful linear and nonlinear prediction information of the full pool of potential predictors is excavated in terms of the stepwise regression method and the Isomap algorithm. Moreover, the GNN is built by integrating multiple individual neural networks with the same expected output and network architecture is optimized by an evolutionary genetic algorithm, so the generalization capacity of the GNN-Isomap model is significantly enhanced, indicating a potentially better operational weather prediction. © 2013 Springer-Verlag Wien. Source

Wu J.,Liuzhou Teacher College | Liu M.,Massey University | Jin L.,Guangxi Climate Center
International Journal of Computational Intelligence and Applications | Year: 2010

In this paper, a hybrid rainfall-forecasting approach is proposed which is based on support vector regression, particle swarm optimization and projection pursuit technology. The projection pursuit technology is used to reduce dimensions of parameter spaces in rainfall forecasting. The particle swarm optimization algorithm is for searching the parameters for support vector regression model and to construct the support vector regression model. The observed data of daily rainfall values in Guangxi (China) is used as a case study for the proposed model. The computing results show that the present model yields better forecasting performance in this case study, compared to other rainfall-forecasting models. Our model may provide a promising alternative for forecasting rainfall application. © 2010 Imperial College Press. Source

Wu J.,Liuzhou Teachers College | Liu M.,Massey University | Jin L.,Guangxi Climate Center
Lecture Notes in Electrical Engineering | Year: 2010

Accurate forecasting of rainfall has been one of the most important issues in hydrological research. In this paper, a novel nonlinear regression ensemble model is proposed for rainfall forecasting. The model employs Least Square Support Vector Machine (LS-SVM) based on linear regression and nonlinear regression. Firstly, Projection Pursuit (PP) technology and Particle Swarm Optimization (PSO) algorithm are used to obtain the main factors of the rainfall, which optimize projection index from high dimensionality to a lower dimensional subspace. Secondly, using different linear regressions extract linear characteristics of the rainfall system, and using different Neural Network (NN) algorithms and different network architectures extract nonlinear characteristics of the rainfall system. Finally, LS-SVM regression is used for nonlinear ensemble model. This technique is implemented to forecast daily rainfall in Guangxi, China. Empirical results show that the prediction by using the LS-SVM ensemble model is generally better than those obtained using other models presented in this study in terms of the same evaluation measurements. The results suggest that our nonlinear ensemble model can be extended to meteorological applications in achieving greater forecasting accuracy and improving prediction quality. © 2010 Springer-Verlag Berlin Heidelberg. Source

Discover hidden collaborations