奇异性理论在个旧锡铜矿产资源预测中的应用:综合信息集成与靶区圈定

Application of Singularity Theory in Prediction of Tin and Copper Mineral Deposits in Gejiu District,Yunnan,China:Information Integration and Delineation of Mineral Exploration Targets

在致矿弱异常提取和复合异常分解的基础上,进行多元信息综合和集成,绘制成矿后验概率图是矿床资源预测的基本过程.以个旧锡矿为例,介绍一种新的信息集成模型和后验概率图的应用方法.结果表明,个旧锡铜矿床分布受多个控矿要素控制,包括地球化学异常、岩体、有利岩性以及构造条件等.通过证据权所提供的空间相关性统计量可以定量确定控矿要素的最佳控矿距离,并以此为依据形成二态信息图层.对每个图层的叠加可看作一次找矿信息的累积和更新,因此整个信息图层的集成过程可以看作多次信息叠加过程(multiplicative cascade process).由此绘制的后验概率图具有自相似性、奇异性和分形谱系,空间分布服从多重分形统计分布.因此,后验概率图的绘制可以作为致矿地质异常圈定的信息综合和集成方法.

This paper is based on several research projects conducted in Gejiu Sn and Cu mineral districts on regional mineral resource assessment, 3D mineral resource assessment and prediction of deeply buried mineral deposits. New non-linear theory and methods of multifractal singularity have been applied in these projects to map weak anomalies related to deeply buried ores and mineralization halos. The weights of evidence model with corrected posterior probability using a newly developed correction method is applied to integrate various geo-evidential layers to map mineral potentials in the Gejiu area. The binary evidential layers include two layers defined on the basis of geochemical data, with one on distance from intersection of faults and the other on Gejiu Formation. Each addition of a binary layer can be considered as a partition of the study area and redistribution of posterior probability which can be treated as a general multiplicative cascade process and the final product may show multifractal properties with multiple singularities. A power law model was established between posterior probability and undiscovered mineral deposits for the area.