The paper describes an artificial neural network (ANN) model to predict the height of destressed zone (HDZ). This zones are usually considered to be equal to the combined height of caved and fractured zones above the mined panel in longwall mining. The suitable datasets were collected from the literatures to be used for modeling. The data were used to construct a multilayer perceptron (MLP) network to approximate the unknown nonlinear relationship between the input parameters and HDZ. The proposed MLP model predicted the values in enough agreements with the measured ones by a satisfactory correlation of R2=0.989. To approve the capability of proposed ANN model, the obtained results are compared to that of the conventional regression analysis (CRA) method. The calculated performance evaluation indices show the higher level of accuracy of the proposed ANN model compared to CRA. For further evaluation, the ANN model results were compared with the results of available models and the reported in-situ measurements in literatures. Comparative results present a logical agreement between ANN model and available methods. The results remark that the proposed ANN model is a suitable tool in HDZ estimation. At the end of modeling, the parametric study showed that the most effective parameter is the unit weight. The elastic modulus, on the other hand, is the least effective parameter on HDZ in this study.
