Real-Time Fluid Identification From Integrating Advanced Mud Gas and Petrophysical Logs

Advanced mud gas logging has been used in the oil industry for about 25 years. However, it has been challenging to predict reservoir fluid properties quantitatively (e.g., gas-oil ratio (GOR)) from only the advanced mud gas data (AMG) while drilling. Recently, machine-learning algorithms have been utilized to derive models from advanced surface data, resulting in the introduction of the first GOR fluid properties prediction models with enhanced accuracy. These models have since been applied to both conventional and unconventional fields with promising outcomes. A real-time service for fluid identification was developed to optimize fluid sampling in exploration wells and support production drilling for the Norwegian operational units. The service utilizes a standard wellbore software platform that integrates a variety of data sources, including AMG data, surface log quality control tools, normalized total gas response, GOR prediction, and petrophysical logs from logging while drilling (LWD). The proposed approach integrates information from downhole and surface logging, providing quantitative information about reservoir fluids that will enable informed and reliable decision making by the operational teams. Specifically, this approach will support well placement, petrophysical log interpretation, and the optimization of production by improving the selection of perforation intervals. Two field cases were presented at the SPWLA 63rd Annual Symposium in 2022 to demonstrate the approach of integrating advanced mud data and petrophysical logs. The first field case is an exploration well with multiple reservoir zones planned as production targets. The integrated approach shows reservoir fluids from all reservoir zones being almost identical. The fluid sampling program was consequently adapted and only sampled at the best reservoir zone for cost efficiency. The second field case is a mature field being produced by pressure support from water, gas, or water alternating gas injections. When a new production well is drilled, there is always a question of whether it encounters any injection gas, whether there is a change in GOR indicated by four-dimensional (4D) seismic gas effects, or simply whether we can trust the computation of higher porosity in sands than initially expected. The latest information from the predictive GOR model solved many puzzles in petrophysical interpretations.