Detection of multivariate geochemical anomalies associated with gold deposits by using distance anomaly factors

Abstract

The outliers of the statistical population are usually far from most samples in the observation space. Therefore, the total distance from a sample to all remaining samples in the population can be used to quantitatively represent the anomaly level of the sample. The greater the total distance between the sample and all the remaining samples, the more likely the sample is to be an outlier. Accordingly, the total distance of each sample in the population can be used to define a distance anomaly factor for each sample for outlier detection. The spatial distance between each pair of samples in the population can be measured by different distance measures, such as the Mahalanobis distance, Manhattan distance, Euclidean distance, and kernel Euclidean distance. According to different distances, different distance anomaly factors can be defined for each sample in outlier detection. These distance anomaly factors are potentially useful in geoscientific data procession. For demonstration purposes, the distance anomaly factors were used to detect multivariate geochemical anomalies associated with gold deposits from the stream sediment survey data in the Jinchanggouliang district, Inner Mongolia, China. Receiver operating characteristic curve and area under the curve were used to evaluate the performance of distance anomaly factors for geochemical anomaly detection. The results show that the distance anomaly factors perform better than continuous restricted Boltzmann machine and one-class support vector machine in the detection of multivariate geochemical anomalies associated with gold deposits. The Youden index was used to determine the optimal threshold to separate geochemical anomalies from geochemical background. The geochemical anomalies detected by the distance anomaly factors occupy 6.2–14.4% of the study area while contain 70–91% of the known gold deposits. The geochemical anomalies detected by the continuous restricted Boltzmann machine occupy respectively 3.1% of the study area while contain 52% of the known gold deposits. The geochemical anomalies detected by the one-class support vector machine occupy respectively 8.5% of the study area while contain 70% of the known gold deposits. Therefore, the distance anomaly factors are potentially useful techniques for geochemical anomaly detection.