INTEGRATING GEOLOGY AND GEOSTATISTECAL METHODS FOR EFFECTIVE RESERVIR PREDICTION

Abstract

Geological information is often available at various scales but an integrational perspective is often missing. Apart from that, there is an underutilization of machine learning in geosciences. With the recent developments in machine learning and data sciences, the risks and uncertainty involved in exploration, development and production projects can be greatly reduced. With the advancement and understanding of the subsurface variation in rock and fluid properties and the availability of high-performance computing, the use of software to solve complex earth problem has become a routine. There is a need for a free source platform where multi-scale geological information can be integrated, optimized and visualized with minimum uncertainty. PRIME is an Integrated platform for solving Petrophysical and Rock Physical challenges for today’s exploration and development activities. More than the conventional solutions, PRIME aims to integrate machine learning in the most natural way for predicting the hydrocarbon that is; yet to be found. PRIME is used to analyze the seismic and well data. It determines the value and accordingly applies quantitative methods to predict fluid, rock, and pressure properties. With PRIME, seismic related data can be integrated with pressure and log data. PRIME can be used to identify many other types of geological variations, and porosity, based on the well data and seismic data