A Multi-Convolutional Autoencoder Approach to Multivariate Geochemical Anomaly Recognition

• Published in: Minerals (Basel) 2019-05, Vol.9 (5), p.270
• Main Authors: Chen, Lirong, Guan, Qingfeng, Feng, Bin, Yue, Hanqiu, Wang, Junyi, Zhang, Fan
• Format: Article
• Language: English
• Subjects: Anomalies; Convolution; convolutional autoencoder; Deep learning; Diagenesis; Eigenvalues; Eigenvectors; Euclidean geometry; Geochemistry; Geographic information systems; Geological processes; Geology; Geophysical data; Geophysics; global Moran’s I; Learning; Mapping; Metal concentrations; Mineralization; Multivariate analysis; multivariate geochemical anomalies; Neural networks; Principal components analysis; Remote sensing; Sampling; Sediment samplers; Spatial analysis; Spatial data; Spatial discrimination learning; spatial structure; Variables
• ISSN: 2075-163X; 2075-163X
• DOI: 10.3390/min9050270

The spatial structural patterns of geochemical backgrounds are often ignored in geochemical anomaly recognition, leading to the ineffective recognition of valuable anomalies in geochemical prospecting. In this contribution, a multi-convolutional autoencoder (MCAE) approach is proposed to deal with this issue, which includes three unique steps: (1) a whitening process is used to minimize the correlations among geochemical elements, avoiding the diluting of effective background information embedded in redundant data; (2) the Global Moran’s I index is used to determine the recognition domain of the background spatial structure for each element, and then the domain is used for convolution window size setting in MCAE; and (3) a multi-convolutional autoencoder framework is designed to learn the spatial structural pattern and reconstruct the geochemical background of each element. Finally, the anomaly score at each sampling location is calculated as the difference between the whitened geochemical features and the reconstructed features. This method was applied to the southwestern Fujian Province metalorganic belt in China, using the concentrations of Cu, Mn, Pb, Zn, and Fe2O3 measured from stream sediment samples. The results showed that the recognition domain determination greatly improved the quality of anomaly recognition, and MCAE outperformed several existing methods in all aspects. In particular, the anomalies from MCAE were the most consistent with the known Fe deposits in the area, achieving an area under the curve (AUC) of 0.89 and a forecast area of 17%.