Prédiction du carbone organique total dans les réservoirs de gaz de schiste à l’aide des réseaux de neurones artificiels, cas du champ de Barnett, nord des Etats Unis.

Abstract

Total organic carbon TOC values the richness of the source rock in organic matter and its predisposition to generate hydrocarbons. The TOC content qualifies the potential of the source rock. The best source of TOC estimation is the direct measurement from the cores in the laboratory, but because of the geological or technical problems during the coring operation the recovery of the cores is not always integral, In addition, the dosage TOC is expensive and time consuming.In our work on Barnett's shale gas field, empirical equations were first used to estimate TOC; the Schmoker method and the Δ logR method, however they did not provide good results comparing with the measured TOC (CC = 0.76, 0.56; RMSE = 1.19, 1.32; MAE = 0.97, 1.06) Others modeling techniques; multiple regression and artificial neural networks (NNA) were applied on classical logs (Gamma ray, Resistivity, Sonic and Density), they give great precision (CC = 0.87, 0.99; RMSE = 0.55, 0.03; MAE = 0.40, 0.02). Thanks to the artificial neural network method with topology MLP (4-13-1) which has a great performance, we can solve the problem of 51 unmeasured points, minimize cost and time saving.