Implications of machine learning on geomechanical characterization and sand management: a case study from Hilal field, Gulf of Suez, Egypt

Abstract

Sand production is one of the major challenges in the oil and gas industry, so a comprehensive geomechanical analysis is necessary to mitigate sand production in mature fields. As the pore pressure drastically decline in depleted reservoirs, the sand production risk becomes more critical and needs to be studied. However, the absence of key logs in many wells is a big challenge in the petroleum industry, and most geologists and engineers use empirical equations to predict missed log intervals. We conducted a comprehensive geomechanical modeling study on a full set of logs from two wells from the Hilal field, Gulf of Suez, Egypt, to infer the geomechanical elements and predict sand production. We have used the multi-arm calipers to calculate the actual depth of damage ratio to validate the geomechanical parameters in the prognosis model and confirm the stress orientations. We used machine learning approach to infer key sonic log in X-10 well to replace the empirical equations. The multi-arm calipers analysis showed an observed anisotropy in the hole diameter size with more enlargement in the ENE direction and fits with the minimum horizontal stress direction in the direction of N 60oE. The later also deduced the maximum horizontal stress direction in N150 ° based on the induced fractures from borehole image data in a nearby field. We developed and compared two sand management models: one using empirical equation and the other using machine learning. The model driven by the Gardner equation suggests sand production from day one, which is not matched with the production data, while the model driven by machine learning suggests no sand production risk, which is matched with the actual production data. Our results demonstrate the advantage of using machine learning technique in geomechanical studies on the classical empirical equations in the area of study that can be applied in other basins. The findings of this study can help with a better understanding of the implications of machine learning on geomechanical characterization and sand management.