APPLICATION OF ARTIFICIAL NEURAL NETWORK IN THE RESTORATION OF TRITIUM CONCENTRATION IN PRECIPITATION
LONG Wen-hua1,2, CHEN Hong-han1, DUAN Qing-mei3, LI Zhi2, PAN Hong-jie2, LIU Rong-yi4
1. China University of Geosciences, Beijing 100083, China; 2. Inner Mongolia Geological Survey, Hohhot 010020, China; 3. Inner Mongolia Institute of Land and Resources Exploration and Development, Hohhot 010020, China; 4. Inner Mongolia Institute of Geo-environment Monitoring, Hohhot 010020, China
Abstract:The artificial neural networks are able to distinguish the complex nonlinear relations between the input/output data. Based on such characteristics, this article selects IAEA/WMO observation data of tritium concentration in atmospheric precipitation from 70 gauging stations in Northern Hemisphere (latitude 22-74°) to establish the restoration model for the annual average concentration of tritium in atmospheric precipitation. With comparison, it is concluded that, the tritium concentration restored by the artificial neural networks can objectively reflect its true value, which provides a new thought for the datum-free areas to restore the tritium concentration in atmospheric precipitation from 1953.
龙文华, 陈鸿汉, 段青梅, 李志, 潘洪捷, 刘荣益. 人工神经网络方法在大气降水氚浓度恢复中的应用[J]. 地质与资源, 2008, 17(3): 208-212.
LONG Wen-hua, CHEN Hong-han, DUAN Qing-mei, LI Zhi, PAN Hong-jie, LIU Rong-yi. APPLICATION OF ARTIFICIAL NEURAL NETWORK IN THE RESTORATION OF TRITIUM CONCENTRATION IN PRECIPITATION. GEOLOGY AND RESOURCES, 2008, 17(3): 208-212.