Regimentation of geochemical indicator elements employing convolutional deep learning algorithm

Recently, deep learning algorithms have been popularly developed for identifying multi-element geochemical patterns related to various mineralization occurrences. Effective recognition of anomalies is essential mineral exploration, and effective extremely dependent on integral clustering. Deep can achieve impressive results in comparison the prior methods clustering indicator elements correlated a region interest due their superb capability extracting features from complex data. Although numerous supervised unsupervised executed anomalies, employing them rarely observed. In this research, convolutional (CDL) algorithm was architected recognize regiment Takht-e Soleyman District, Iran. Various opinions experiments were considered reach optimum parameters architecture. Fortunately, achieved root mean square error (RMSE) values appropriate range (<20%) which display predicted variables (Pb as pioneer first group Ag second group) through independent that are so close actual values. Also, great R 2 adj calculated (more than 90%) last stage regimentation confirms accuracy performance study area.