Modeling p′p and recent LHC pp total cross-sections

New technique is presented for modeling total cross-section of both pp and $\bar{p}p$ collisions from low to ultra high energy regions using an efficient artificial neural network (ANN). We have used the input (center-of-mass energy, √s, and type of particle P) and output (total cross-section σ_tot) data to build a prediction model by ANN. The neural network has been trained to produce a function that studies the dependence of σ_tot on √s and P. The trained ANN model shows a good performance in matching the trained distributions, predicts cross-sections that are not presented in the training set. The general trend of the predicted values shows a good agreement with the recent Large Hadron Collider (LHC) measurements, where the total cross-section at √s = 7∼{\rm TeV}$ and 8 TeV are measured to be 98.6 mb and 101.7 mb, respectively. The predicted values of the total cross-section at √s = 10∼{\rm TeV} and 14 TeV are found to be 105.8 mb and 111.7 mb, respectively. Those predictions are in good agreement with Block, Cudell and Nakamura.