Objective approach for rainstorm based on dual-factor feature extraction and generalized regression neural network
- PDF / 1,924,581 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 90 Downloads / 219 Views
Objective approach for rainstorm based on dual‑factor feature extraction and generalized regression neural network Huang Xiaoyan1 · He Li1 · Zhao Huasheng1 · Huang Ying1 · Wu Yushuang1 Received: 10 September 2018 / Accepted: 21 August 2020 © Springer Nature B.V. 2020
Abstract Rainstorm often causes inland flooding and mudslides that threaten lives and properties. In this study, rainstorm is used as a forecasting object, and an interpretation prediction model for rainstorm based on the European Center for medium-range weather forecasting (ECMWF) numerical prediction model is constructed through the generalized regression neural network method. Model inputs are forecasted through principal component analysis, and dual-factor feature extraction is performed on the primary predictors to obtain new irrelevant variables and optimize network structures. The experimental forecast results of the 24 h aging test using an independent sample of large-scale rainstorm in Guangxi, China from 2012 to 2016, the actual forecast results of selected rainstorm cases with great influence on Guangxi, and different influencing systems show that the new prediction scheme is sophisticated. Thus, the scheme has a certain universal applicability. The results of the comparative analysis between the new program and ECMWF show that the forecasting ability of the new method is more accurate than that of the direct numerical forecasting model. The threat score of the new forecast model for 5 years has a 58.4% increase relative to that of the ECMWF. The forecasting skills are positive and good and can thus improve the rainstorm forecasting ability of ECMWF and provide a better guidance for forecasters. Keywords Rainstorm · Generalized regression neural network (GRNN) · Kernel principal component analysis (KPCA) · Dual-factor feature extraction
1 Introduction Weather forecasts primarily focus on rainstorms, which are persistent global problems because of their complicated processes and large uncertainties; another reason is the absence of methods that accurately describe the rainstorm process; thus, heavy rainfall forecasts, especially the rainstorm forecasts, is difficult to achieve and has low accuracy (Tao et al. 2003; Zhao and Sun 2013). * Huang Xiaoyan [email protected] 1
Guangxi Institute of Meteorological Science, Nanning China, 81 National Road, Nanning 530022, China
13
Vol.:(0123456789)
Natural Hazards
Numerous scholars have developed various rainstorm forecasting methods based on the numerical model and its products to improve the skills of rainstorm forecasting. Global mid-term and regional short-term ensemble forecasting systems have been constructed by the European Center for Medium-Range Weather Forecasting (ECMWF) in Europe, National Centers for Environmental Prediction (NCEP) in USA, China Meteorological Administration in China, and Japan Meteorological Agency in Japan (Molteni et al. 1996; Toth and Kalnay 1993; Toth and Kalnay 1997; Bright and Mullen 2002; Li and Chen 2002; Deng et al. 2010; Wang et al. 2007). These s
Data Loading...
