| Monthly Mean Temperature Prediction Based on a Multi－level Mapping Model of Neural Network BP Type |
| |
| 作者姓名： | Yan Shaojin Peng Yongqing Quo Guang |
| |
| 作者单位： | Naming institute of Meteorology，Naming 210044 |
| |
| 摘 要： | In terms of 34-year monthly mean temperature series in 1946-1979, the multi-level mapping model of neural network BP type was applied to calculate the system’s fractual dimension D0 = 2.8, leading to a three-level model of this type with i × j = 3 × 2, k = 1, and the 1980 monthly mean temperture prediction on a long-term basis were pre-pared by steadily modifying the weighting coefficient, making for the correlation coefficient of 97% with the measurements. Furthermore, the weighting parameter was modified for each month of 1980 by means of observations, therefore constructing monthly mean temperature forecasts from January to December of the year, reaching the correlation of 99.9% with the measurements. Likewise, the resulting 1981 monthly predictions on a long-range basis with 1946-1980 corresponding records yielded the correlation of 98% and the month-to month forecasts of 99.4%.
|
| 收稿时间： | 1 August 1994 |
Monthly mean temperature prediction based on a Multi-level mapping model of neural network BP type |
| |
| Yan Shaojin,Peng Yongqing,Quo Guang.Monthly mean temperature prediction based on a Multi-level mapping model of neural network BP type[J].Advances in Atmospheric Sciences,1995,12(2):225-232. |
| |
| Authors: | Yan Shaojin Peng Yongqing Guo Guang |
| |
| Institution: | Nanjing Institute of Meteorology, Nanjing 210044,Nanjing Institute of Meteorology, Nanjing 210044,Nanjing Institute of Meteorology, Nanjing 210044 |
| |
| Abstract: | In terms of 34-year monthly mean temperature series in 1946-1979,the multi-level maPPing model of neural netWork BP type was applied to calculate the system's fractual dimension Do=2'8,leading tO a three-level model of this type with ixj=3x2,k=l,and the 1980 monthly mean temperture predichon on a long-t6rm basis were prepared by steadily modifying the weighting coefficient,making for the correlation coefficient of 97% with the measurements.Furthermore,the weighhng parameter was modified for each month of 1980 by means of observations,therefore constrcuhng monthly mean temperature forecasts from January to December of the year,reaching the correlation of 99.9% with the measurements.Likewise,the resulting 1981 monthly predictions on a long-range basis with 1946-1980 corresponding records yielded the correlahon of 98% and the month-tO month forecasts of 99.4%. |
| |
| Keywords: | Neural network BP-type multilevel mapping model Monthly mean temperature prediction |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
| 点击此处可从《大气科学进展》浏览原始摘要信息 |
| 点击此处可从《大气科学进展》下载免费的PDF全文 |
|
