Geochemical anomaly recognition based on Gaussian mixture model

In order to find the optimal method for identifying geochemical anomalies in geochemical exploration, the Gaussian mixture model and the deep autoencoder network were compared in this paper. Based on the determination of the optimal L value of the Gaussian mixture model and the structure of the deep...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) S. 821 - 824
Hauptverfasser: Wang, Haijun, Xue, Linfu, Ran, Xiangjin
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.03.2021
Schlagworte:
Anomaly detection
Correlation
Data models
Deep Autoencoder Network
Gaussian mixture model
Geochemical Anomalies Detection
Geochemical Exploration
Mineralization
Smart cities
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In order to find the optimal method for identifying geochemical anomalies in geochemical exploration, the Gaussian mixture model and the deep autoencoder network were compared in this paper. Based on the determination of the optimal L value of the Gaussian mixture model and the structure of the deep autoencoder network, geochemical anomaly detection was carried out in the Yawan-Daqiao area, Gansu Province, China. The experimental results show that the geochemical data modeling results of the Gaussian mixture model and the deep autoencoder network are highly consistent with the mineralization characteristics of the study area, and the separated geochemical anomalies have a highly consistent spatial relationship with the known deposit positions in the study area.
DOI:10.1109/ICITBS53129.2021.00204