Application of Multilayer Perceptron Neural Network in Geological Modeling of Categorical Variables: A Case Study in Peru.

The objective of this research was to use an Artificial Neural Network Multilayer Perceptron (ANN-MLP) for geological modeling of categorical variables, using a database of 5,654 samples obtained from a diamond drilling campaign in a mine in northern Peru. The ANN-PML architecture consisted of an input layer of 5 neurons, three hidden layers with 100, 50 and 20 neurons respectively, and an output layer with 5 neurons, optimized with the Adam algorithm. Variables analyzed included geographic coordinates (east, north and elevation), copper and molybdenum concentrations, and rock type classification. Five different geological models were generated within a 20×20×20 meter three-dimensional block model, where the estimated volumes for geological models 1 to 5 were 795.1, 4506.7, 1176.1, 333.3 and 24.7 million of tons, respectively. The results were validated by cross-validation, evidencing an efficiency of ANN-MLP with Recall metrics of 0.56, precision of 0.66 and an average F1-Score of 0.58, demonstrating the efficiency and precision of ANN-MLP in geological classification. This research highlights the integration of artificial intelligence in geology especially in geological modeling. [ABSTRACT FROM AUTHOR]