Mineral Prospectivity Prediction by Integration of Convolutional Autoencoder Network and Random Forest

The convolutional neural networks used widely in mineral prospectivity prediction usually perform mixed feature extraction for multichannel inputs. This results in redundant features and impacts further improvement of predictive performance. To solve this limitation, this paper utilized convolutiona...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Natural resources research (New York, N.Y.) Jg. 31; H. 3; S. 1103 - 1119
Hauptverfasser:	Yang, Na, Zhang, Zhenkai, Yang, Jianhua, Hong, Zenglin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.06.2022 Springer Nature B.V
Schlagworte:	Artificial neural networks Chemistry and Earth Sciences Classifiers Computer Science Earth and Environmental Science Earth Sciences Feature extraction Fossil Fuels (incl. Carbon Capture) Geography Gold Machine learning Mathematical Modeling and Industrial Mathematics Mineral Resources Neural networks Original Paper Performance enhancement Performance prediction Physics Predictions Statistics for Engineering Support vector machines Sustainable Development Unsupervised learning Feature extraction Random forest Convolutional autoencoder network Mineral prospectivity prediction
ISSN:	1520-7439, 1573-8981
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!