Japanese early-warning for debris flows and slope failures using rainfall indices with Radial Basis Function Network

被引:125
作者
Osanai, Nobutomo [1 ]
Shimizu, Takeshi [2 ]
Kuramoto, Kazumasa [3 ]
Kojima, Shinichi [4 ]
Noro, Tomoyuki [5 ]
机构
[1] MLIT, NILIM, Eros & Sediment Control Div, Tsukuba, Ibaraki 3050804, Japan
[2] PWRI, Volcano & Debris Flow Res Team, Tsukuba, Ibaraki, Japan
[3] Chuden Engn Consultants Co Ltd, Minami Ku, Hiroshima, Japan
[4] MLIT, Fujikawa Sabo Off, Fujimi, Gunma, Japan
[5] PWRI, Snow Avalanche & Landslide Res Ctr, Myoukou, Niigata, Japan
关键词
Landslides; Early-warning system; Debris flows; Slope failures; Radial Basis Function Network;
D O I
10.1007/s10346-010-0229-5
中图分类号
P5 [地质学];
学科分类号
0709 ; 081803 ;
摘要
Early-warning systems for natural disasters are important tools for disaster risk reduction and for achieving sustainable development and livelihoods. In 2005, the Japanese government initiated a new nationwide early-warning system for landslides disasters. The main methodology of the system is to set a criterion for occurrences of debris flows and slope failures based on several rainfall indices (60-min cumulative rainfall and soil-water index) in each 5-km grid mesh covering all of Japan. Because many of the records of mass movements are lacking in scientific precision on timing and location, the system applies Radial Basis Function Network methods to set the criterion based primarily on rainfall data recorded as not triggering disasters. Since the end of March 2007, under torrential rainfall conditions, early-warning information has been disseminated as part of weather news using TV, radio, and the Internet. Because of the increasing worldwide recognition of the importance of early-warning systems for natural disaster reduction, the aim of this article is to introduce the new Japanese early-warning system to the international landslide community. In this article, the method, the system, and the result of its application to landslide disasters in 2009 are presented.
引用
收藏
页码:325 / 338
页数:14
相关论文
共 14 条
  • [1] [Anonymous], 1996, Introduction to radial basis function networks
  • [2] Er MJ, 2002, IEEE T NEURAL NETWOR, V13, P697, DOI 10.1109/TNN.2002.1000134
  • [3] Applying probability determination to refine landslide-triggering rainfall thresholds using an empirical "Antecedent Daily Rainfall Model"
    Glade, T
    Crozier, M
    Smith, P
    [J]. PURE AND APPLIED GEOPHYSICS, 2000, 157 (6-8) : 1059 - 1079
  • [4] HAYKIN Simon., 1999, Neural Networks, V2nd, P256
  • [5] KURAMOTO K, 2001, DOBOKU GAKKAI RONBUN, V672, P117
  • [6] Kuramoto K., 2005, P ANN RES M 2005, P186
  • [7] *MLIT DESC JMA NIL, 2005, MAN METH SE IN PRESS, P21
  • [8] OHYAGI N, 2007, AIR PHOTOGRAPH INTER, P320
  • [9] Okada K., 2005, Sokkoujihou, V69, P67
  • [10] TERADA H, 2001, 5 NAT I LAND INFR MA, P71