多金属矿产综合信息区域深部成矿预测——以临江市东港地区靶区预测为例

针对现有成矿预测方法存在预测精度低、效率不高的问题,提出多金属矿产综合信息区域深部成矿预测方法。采用地理信息系统(geographic information system,GIS)建立多金属矿综合信息库,数字化处理成矿信息。建立证据权模型,结合信息库,通过计算控矿地质因素的对比度,获取最优缓冲距离,完成区域深部成矿信息提取。基于此,利用遗传算法优化支持向量机参数,基于优化参数后的支持向量机完成成矿预测。实验结果表明:所提方法的最优缓冲距离计算准确率较高,支持向量机参数优化耗时短,且成矿预测精度在90%以上,不受数据状态的影响,预测度也优于传统方法,表明所提方法能够高效完成成矿预测。

Regional Deep metallogenic Prediction based on Comprehensive Information of Polymetallic ores

In order to solve the problems of low prediction accuracy and low efficiency in the existing metallogenic prediction methods, a regional deep metallogenic prediction method based on the comprehensive information of multi-metal deposits is proposed. The comprehensive information database of multi-metal ore is established by GIS, and the metallogenic information is processed digitally. The evidence weight model is established and the contrast of ore-controlling geological factors is calculated by calculating the contrast of ore-controlling geological factors to obtain the optimal buffer distance and complete the extraction of deep metallogenic information in the area. On this basis, the genetic algorithm is used to optimize the parameters of support vector machine, and the metallogenic prediction is completed based on the optimized support vector machine. The experimental results show that the optimal buffer distance of the proposed method is accurate and the support is high. The optimization time of holding vector machine parameters is short, and the accuracy of metallogenic prediction is more than 90%. It is not affected by the data state, and the prediction degree is better than the traditional method, which shows that the proposed method can complete the metallogenic prediction efficiently.