Geomechanical Properties Estimation Utilizing Artificial Intelligence Prediction Tool

Abstract

Drilling and fracturing are considered to be one of the major costs in the oil and gas industry. Cost may reach tens of millions of dollars and improper design may lead to significant loss of money and time. Reliable fracturing and drilling designs are governed with decent and representative rock mechanical properties. Such properties are measured mainly by analyzing multiple previously cored wells in the same formation. The nature of the conducted tests on the collected plugs are destructive and samples cannot be restored after performing the rock mechanical testing. This may disable further evaluation on the same plugs. This study aims to build an artificial neural network (ANN) model that is capable of predicting the main rock mechanical properties, such as Poisson's ratio and compressive strength from already available lab and field measurements. The log data will be combined together with preliminary lab rock properties to build a smart model capable of predicting advance rock mechanical properties. Hence, the model will provide initial rock mechanical properties that are estimated almost immediately and without undergoing costly and timely rock mechanical laboratory tests. The study will also give an advantage to performing preliminary estimates of such parameters without the need for destructive mechanical core testing. The ultimate goal is to draw a full field geomechanical mapping with this tool rather than having localized scattered data. The AI tool will be trained utilizing representative sets of rock mechanical data with multiple feed-forward backpropagation learning techniques. The study will help in localizing future well location and optimizing multi-stage fracturing designs. These produced data are needed for upstream applications such as wellbore stability, sanding tendency, hydraulic fracturing, and horizontal/multi-lateral drilling.