地球科学进展 ›› 2009, Vol. 24 ›› Issue (11): 1275 -1279. doi: 10.11867/j.issn.1001-8166.2009.11.1275

研究简报 上一篇    下一篇

BP神经网络在古气候序列重建中的应用
王红丽 1,2,顾亚进 3,刘健 1*,况雪源 4,提汝媛 1,2   
  1. 1.中科院南京地理与湖泊研究所 湖泊与环境国家重点实验室,江苏南京210008;2.中国科学院研究生院,北京100049; 3.南京信息工程大学大气科学学院,江苏南京210044;4.南京大学大气科学学院,江苏南京210093
  • 收稿日期:2009-02-04 修回日期:2009-09-08 出版日期:2009-11-10
  • 通讯作者: 刘健(1966-),女,四川合江人,研究员,主要从事古气候模拟及季风气候演变研究. E-mail:jianliu@niglas.ac.cn
  • 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

WANG Hongli 1,2, GU Yajin 3, LIU Jian 1, KUANG Xueyuan 4, TI Ruyuan 1,2   

  1. 1.State Key Laboratory of Lake Science and Enviroment, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China; 2. Graduate University of Chinese Academy of Sciences, Beijing100049, China; 3. School of Atmospheric Sciences, Nanjing University of Information Science and Technology, Nanjing210044, China; 4.School of Atmopheric Sciences, Nanjing University,Nanjing210093, China
  • Received:2009-02-04 Revised:2009-09-08 Online:2009-11-10 Published:2009-11-10

当前小区域的古气候变化研究受模拟资料分辨率和可靠性的严重制约。为了将大区域的气候模拟资料应用到小区域的古气候研究中去,亟待建立有效的降尺度方法。为此以徽鄂地区为例,建立了一个3层BP神经网络拟合模型,利用相关气象要素作为拟合因子,拟合并重建了该地区近千年来1月、7月和年平均的温度和降水序列,通过与观测及模拟资料的对比分析发现,该模型拟合及重建的近千年气候序列有较高的精度和可靠性,能反映小区域气候的年际和年代际变化信号,提高了模拟资料对小区域气候变化的刻画能力。

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.

中图分类号: 

[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.]

[1] 苏绕绕, 赵珍. 16世纪末以来北运河水系演变及驱动因素[J]. 地球科学进展, 2021, 36(4): 390-398.
[2] 梁承弘, 鹿化煜. 风成沉积物叶蜡氢同位素在揭示东亚季风区干湿变化中的原理及应用[J]. 地球科学进展, 2021, 36(1): 45-57.
[3] 杨军怀,夏敦胜,高福元,王树源,陈梓炫,贾佳,杨胜利,凌智永. 雅鲁藏布江流域风成沉积研究进展[J]. 地球科学进展, 2020, 35(8): 863-877.
[4] 武雪超, 郝青振, Marković Slobodan B, 付玉, 娜米尔, 宋扬, 郭正堂. 多瑙河黄土与古环境研究进展[J]. 地球科学进展, 2020, 35(4): 363-377.
[5] 陈立雷,李凤,刘健. 海洋沉积物中 GDGTs和长链二醇的古气候—环境指示意义研究进展[J]. 地球科学进展, 2019, 34(8): 855-867.
[6] 侯笛,张俊杰,邢磊,周阳. 长链烷基二醇在海洋环境重建中的研究进展[J]. 地球科学进展, 2019, 34(2): 140-147.
[7] 党皓文,马小林,杨策,金海燕,翦知湣. 重建高分辨率深海环境变化:冷水竹节珊瑚无机地球化学方法[J]. 地球科学进展, 2019, 34(12): 1262-1272.
[8] 王鑫,张金辉,贾佳,王蜜,王强,陈建徽,王飞,李再军,陈发虎. 中亚干旱区第四系黄土和干旱环境研究进展[J]. 地球科学进展, 2019, 34(1): 34-47.
[9] 宗秀兰, 宋友桂, 李越. 蚯蚓方解石颗粒——一种新的古气候信息记录载体[J]. 地球科学进展, 2018, 33(9): 983-993.
[10] 陈科贵, 李进, 黄长兵, 陈愿愿, 王刚, 刘阳. BP神经网络在富钾卤水中的应用研究[J]. 地球科学进展, 2018, 33(6): 614-622.
[11] 王兆夺, 黄春长, 周亚利, 庞奖励, 查小春. 关中东部全新世黄土—古土壤序列粒度组分变化特征及古气候意义[J]. 地球科学进展, 2018, 33(3): 293-304.
[12] 李育, 刘媛. 干旱区内流河流域长时间尺度水循环重建与模拟——以石羊河流域为例[J]. 地球科学进展, 2017, 32(7): 731-743.
[13] 李兴文, 张鹏, 强小科, 敖红. 三门峡会兴沟剖面黄土—古土壤序列的岩石磁学研究[J]. 地球科学进展, 2017, 32(5): 513-523.
[14] 王瑞, 余克服, 王英辉, 边立曾. 珊瑚礁的成岩作用[J]. 地球科学进展, 2017, 32(3): 221-233.
[15] 吕璇, 刘志飞. 大洋红层的分布、组成及其科学研究意义综述[J]. 地球科学进展, 2017, 32(12): 1307-1318.
阅读次数
全文


摘要