An approach based on Machine Learning Algorithms, Geostatistical Technique, and GIS analysis to estimate phosphate ore grade at the Abu Tartur Mine, Western Desert, Egypt

Purpose. This paper aims to estimate phosphate ore grade in the Abu Tartur area, Western Desert, Egypt, using four Machine Learning Algorithms (MLA), Geostatistical Techniques (variogram and kriging models), GIS-analysis. Methods. Four machine-learning techniques include Optimizable Decision Tree (ODT), Support Vector (OSVM), Gaussian Process Regression (OGPR), Artificial Neural Network (ANN) are applied this paper. The constructed variogram models, as well GIS-analysis, provide a clear understanding of all elements distributed very useful at planning mining stages. Findings. Phosphate content has been estimated with high accuracy based on results techniques. most efficient technique for estimating is optimizable which gives correlation coefficients (R) 0.933 0.927 Mean Absolute Errors (MAE) 0.983 training validation data, respectively. In addition, geostatistical GIS methods have shown that percentage P2O5, thickness, Fe% suitable processes, except small pockets require little attention stage. Originality. research attempts develop quick estimation about distribution different constituents within body Practical implications. Grade commonly reduced function approximation. intelligence (AI) techniques, particular chosen type AI can provide, valid methodology grade, proposed models be any other data range used research.