基于半监督神经网络的铜矿预测方法

将人工智能技术引入成矿预测研究中，可以提高预测效率，挖掘探测数据与结果之间的隐藏信息.利用半监督学习方法对样本构建要求低的优点，结合其在异常识别方面的应用效果，设计了基于分割准则的孤立森林与深度自编码网络的神经网络结构；基于西藏冈底斯地区的化探元素数据，对研究区内的铜矿进行了成矿预测工作，预测结果与已知矿区数据叠加效果较好，说明本文的神经网络结构能够完成成矿远景区的预测工作. 

Prediction of Copper Mineralization Based on Semi-Supervised Neural Network

The introduction of artificial intelligence technology into metallogenic prediction can improve the prediction efficiency and research the hidden information between the exploration data and the results. In this paper, it designs a brand new semi-supervised neural network structure based on isolation forest with split-selection criterion(SCiForest) and autoencoder, using the advantage of semi-supervised learning method that the samples are easy to construct and the outstanding application effect in anomaly recognition. Based on the geochemical element data of Gangdise area in Tibet, the copper deposits in the study area is predicted. The prediction results are basically within the known mining area, which shows that the neural network structure in this paper can be used to predict the metallogenic prospective area.