AUTHOR=Sabbaghi Hamid , Tabatabaei Seyed Hassan 

TITLE=Regimentation of geochemical indicator elements employing convolutional deep learning algorithm

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2023.1076302

DOI=10.3389/fenvs.2023.1076302

ISSN=2296-665X

ABSTRACT=Recently, deep learning algorithms have popularly developed for identifying multi elemental geochemical patterns related to various mineralization. The effective recognition of multi elemental geochemical anomalies is essential in mineral exploration and effective recognition is extrermely dependent to integral clustering. Deep learning algorithms can reach to impressive results in comparison to prior methods in the clustering of correlated indicator elements of mineralization for a region of interest due to their superb capability in extracting features from complex data. Although, numerous supervised and unsupervised deep learning algorithms have been executed for recognizing of geochemical anomalies but employing them for clustering of geochemical indicator elements is rarely observed. In this research, a convolutional deep learning (CDL) algorithm was architected to recognize and regimentation of geochemical indicator elements in Takhte-Soleyman district, Iran. Various opinions and experiments were considered to reach the optimum parameters of this architecture. All validators of CDL clustering were in appropriate range, therefore proposed procedure can be regarded for further geoscience works.