收稿日期: 2009-02-04
修回日期: 2009-09-08
网络出版日期: 2009-11-10
基金资助
中国科学院知识创新工程重要方向项目“过去2000年东亚季风气候演变及其与人类相互作用研究”(编号:KZCX2-YW-315);国家自然科学基金项目“中国千年气候变化数值模拟与机理研究”(编号:40890054);“近千年来东亚季风年代—世纪尺度变化的模拟与重建资料综合研究”(编号:40672210);“中国东部近千年来土地利用变化对东亚季风气候影响的模拟研究”(编号:40871007)共同资助.
Application of BP Neural Network in Paleoclimatic Reconstruction
Received date: 2009-02-04
Revised date: 2009-09-08
Online published: 2009-11-10
王红丽,顾亚进,刘健,况雪源,提汝媛 . BP神经网络在古气候序列重建中的应用[J]. 地球科学进展, 2009 , 24(11) : 1275 -1279 . DOI: 10.11867/j.issn.1001-8166.2009.11.1275
Researches on the paleoclimatic variabilities in local regions are seriously restricted by the low resolution and uncertainty of the simulated data at present. In order to apply large-scale climate modeling data to paleoclimate research for small region, an effective downscaling method is urgently needed to be built. For this purpose, a triple-layer fitting model of back propagation (BP) neural network was established using relevant meteorological variables as fitting factors. Based on the fitting model, monthly (January and July) and annual mean series of temperature and precipitation were reconstructed in Anhui-Hubei region during the last millennium. Comparison of the fitting series with the observed and simulated records indicates that the fitting series have good precision and reliability. The signals of climate variation in local region on interannual and interdecadal time scales were captured successfully by the BP neural network model. The results show that this downscaling method improves the capacity of research on paleoclimate variability in local regions using large-scale modeling data.
Key words: BP neural network; Paleoclimate; Fitting; Reconstruction
[1]Hu Jianglin, Zhang Liping, Yu Rucong. The study on applying neural network models to prediction of summer precipitation in Hubei Province[J]. Acta Meteorologica Sinica,2001,59(6):776-783.[胡江林,张礼平,宇如聪.神经网络模型预报湖北汛期降水量的应用研究[J]. 气象学报,2001,59(6):776-783.]
[2]Wu Jiansheng. The Back-propagation Neural Network Meteological forecast Model Based on Genetic Algorithms[D]. Guilin:Guangxi Normal University, 2004:5.[吴建生. 基于遗传算法的BP神经网络气象预报建模[D]. 桂林:广西师范大学,2004:5.]
[3]Hsieh W W, Tang B. Applying neural network models to prediction and data analysis in meteorology and oceanography[J].Bulletin of the American Meteorological Society,1998, 79(9): 1 855-1 870.
[4]Hong Y, Hsu K, Sorooshian S, et al. Precipitation estimation from remotely sensed imagery using an artificial neural network cloud classification system[J].Journal of Applied Meteorology,2004, 43(12):1 834-1 853.
[5]Jin Long, Chen Ning, Lin Zhenshan. Study and comparison of ensemble forcasting based on artificial neural network[J].Acta Meteorologica Sinica,1999, 57(2):198-207.[金龙,陈宁,林振山. 基于人工神经网络的集成预报方法研究和比较[J]. 气象学报,1999,57(2):198-207.]
[6]Zhao Suxuan, Luo Jian, Yang Chengyin. Scatheless compression encoding for meteorological grid data based on BP neural network[J].Advances in Earth Science,2008, 23(2): 206-213.[赵苏璇,罗坚,杨成荫.基于BP神经网络的气象格点数据无损压缩方法[J].地球科学进展,2008,23(2):206-213.]
[7]Jin Long, Luo Ying, Guo Guang, et al. Study on mixed model of neural network for farmland flood/drought prediction[J].Acta Meteorologica Sinica,1997, 11(3):364-373.
[8]McCann D. A neural network short-term forecast of significant thunderstorms[J]. Weather and Forecasting,1992, 7:525-534.
[9]Elsken T. Even on finite test sets smaller nets may perform better[J].Neural Networks,1997,10(2) :369-385.
[10]Kuang Xueyuan, Liu Jian, Wang Hongli,et al.Comparison of simulated and reconstructed precipitation in China during the last millennium[J].Advances in Earth Science,2009,24(2):159-171.[况雪源,刘健,王红丽,等.近千年来中国区域降水模拟与重建资料的对比分析[J].地球科学进展,2009,24(2):159-171.]
/
〈 |
|
〉 |