The mineral resource estimation process necessitates a precise prediction of the grade based on limited drilling data. Grade is crucial factor in the selection of various mining projects for investment and development. When stationary requirements are not met, geo-statistical approaches for reserve estimation are challenging to apply. Artificial Neural Networks (ANNs) are a better alternative to geo-statistical techniques since they take less processing time to create and apply. For forecasting the iron ore grade at El-Gezera region in El- Baharya Oasis, Western Desert of Egypt, a novel Artificial Neural Network (ANN) model, geo-statistical methods (Variograms and Ordinary kriging), and Triangulation Irregular Network (TIN) were employed in this study. The geo-statistical models and TIN technique revealed a distinct distribution of iron ore elements in the studied area. Initially, the tan sigmoid and logistic sigmoid functions at various numbers of neurons were compared to choose the best ANN model of one and two hidden layers using the Levenberg-Marquardt pure-linear output function. The presented ANN model estimates the iron ore as a function of the grades of Cl%, SiO2%, and MnO% with a correlation factor of 0.94. The proposed ANN model can be applied to any other dataset within the range with acceptable accuracy.