Geomechanical modelling using artificial neural networks combined with geostatistics

The principal minimum horizontal stress (Shmin) plays an important role in reservoir simulation. Experimental formulas were established to determine Shmin along the wellbore. These formulas must be calibrated with LOT data whose number is usually limited or even sometimes unavailable. However, the empirical formulas of one field might not be accurate for others. This study presents a new approach to solve the problem of Shmin estimation by a combination of artificial intelligence and geostatistics. The method consists of using artificial neural network to build a model of Shmin estimation from relevant parameters such as true vertical depth, pore pressure and vertical stress, then combined with Kriging interpolation to obtain the distribution in space of Shmin. Hence, this method can estimate the minimum horizontal stress with a limited amount of available data and therefore we do not need to drill new wells or to find empirical formulas for each survey area. [Received: October 2, 2020; Accepted: December 16, 2020]