EOR surfactants are usually formulated at the initial reservoir temperature. Is this a correct approach? Field data from three Single-Well Chemical Tracer pilots in North Africa are used to answer this question. The objectives are, first, to provide a realistic image of the temperature variations inside the water-flooded reservoir; second, to demonstrate the impact of such temperature variations on the surfactant performances; and last, to introduce a new methodology for estimating the target temperature window for surfactant formulations. During pre-SWCTT pilot tests, water injection, shut-in and back-production were performed. The bottom-hole temperature was monitored to evaluate the reservoir temperature changes (initially at 120°C) and to calibrate a thermal model. The thermal parameters were applied to the reservoir model to simulate 30 years of water injection (with its surface temperature varying between 20°C and 60°C) and to obtain a full picture of the temperature variations inside the reservoir. Multi-well surfactant injection was modelled assuming that the surfactant is only efficient within ±10°C around the design temperature. The impact of this assumption on the additional oil recovery was analyzed for several scenarios. The rock thermal transmissivity was found to be the key parameter for properly reproducing the observed data gathered in the North African pre-SWCTT tests. The measured temperature during the back-production phase demonstrated the accuracy of the thermal model parametrization. It proved that the heat exchange between the reservoir and the injected fluid is considerably less than what industry expects: the injected water temperature inside the reservoir remains far below the initial reservoir temperature even after 11 days of shut-in. When simulating various historical bottom-hole injection temperatures and pre-flush durations, the thermal model showed an average cooling radius of 275m, larger than the industry recommended well-spacing for the EOR 5-spot patterns. This was mainly due to the significant temperature difference between the historical injected water and the initial reservoir temperature. Several simulations were performed for 3 representative bottom-hole injection temperatures of 20°C, 40°C and 60°C, varying the surfactant design temperature range between the injection temperature and the initial reservoir temperature. The results showed that regardless of the injection temperature, the simulated additional oil recovery is highest when the design temperature range is close to the injection bottom-hole temperature. This is an important subject since in the EOR industry, the surfactants are usually formulated at the initial reservoir temperature and thus, the impact of the reservoir cooling on the surfactant efficiency is seldom considered. In a water flooded reservoir, the injected chemicals are unlikely to encounter the initial reservoir temperature. This results in a dramatic loss of surfactant performance especially when there is a considerable difference between the initial reservoir and the injected fluid temperatures.

Leveraging the recent developments in the Machine Learning (ML) technology, the objective of this work was to use Artificial Neural Networks to build proxy models to classical reservoir simulation tools for two distinct chemical EOR applications. Once built and calibrated (trained), these ML-based proxy models were used to efficiently identify optimal scenarios to be further considered in the corresponding EOR developments, therefore demonstrating how these techniques can complement classical tools to enhance the decision-making process. Two numerical simulation models were built and calibrated to reproduce lab-measured data from a real surfactant-polymer coreflood experiment (Application #1) or historical data from a real oilfield (Application #2). Different scenarios were then simulated: Application #1: various sequences of injection were explored (chemical concentrations and slug sizes)Application #2: different surfactant-polymer injection configurations were investigated on a large-scale multi-pattern configuration Simulated outputs were used to train Artificial Neural Network models, which were checked for their predictivity on unseen data. These ML-based proxy models were finally used to rapidly identify other optimal scenarios for each application based on several economic indicators. For the first application, numerical model calibration was obtained using one real coreflood experiment: measured pressure signal was well reproduced by the simulator, as well as oil and surfactant production. Several numerical simulations were then performed to evaluate the oil recovery from different injection sequences. Both surfactant and polymer concentrations were varied as well as the slug's durations. For the second application, a history-matched sector model representing the current status of a real oilfield after several years of waterflooding was used. Several scenarios were simulated to evaluate oil recovery associated with distinct sequences of EOR injection consisting of surfactant and polymer agents of various slug volumes and concentrations. Using a train/test split approach, 80% of the simulations were used to train one Artificial Neural Network for each application. The remaining simulations (20%), used as blind tests, confirmed the predictivity of the trained models on unseen data. The ANN models were finally used to predict outcomes from new scenarios not investigated by numerical simulation. This enabled us to identify optimal scenarios with regards to classical economic indicators. These scenarios were then numerically simulated to confirm the predictions from the ANN models, therefore validating the whole approach. This work illustrates how modern machine learning techniques such as Artificial Neural Networks can be used to enhance the numerical simulation tool while solving specific optimization problems (here related to chemical EOR application). Such techniques, becoming increasingly accessible thanks to open-source programming languages, provide a powerful lever to become more efficient when using reservoir simulators as a tool to guide decision-making processes in the oil industry.

Soft Skills - To what extent is deepwater drilling driven by culture? Deepwater drilling is a high-risk operation. It involves going below water depths of 500 ft to explore for oil and gas. If there are any issues with the subsurface equipment, divers cannot intervene because human beings are physically incapable of tolerating such depths. But water pressure is not the only thing a person working in deep water needs to worry about. There will also be significant challenges to maintaining a work/life balance. The extent of these challenges could depend on one’s culture and roots. What, then, is culture? Culture is based on the cumulated beliefs and behaviors characteristic of a particular group. Such a group could be as small as a family or as large as a country. Geert Hofstede, a Dutch sociologist, conducted extensive surveys of employees of different nationalities working for multinational companies and published his findings in a book in 1980. He identified the following five key dimensions of culture: Uncertainty avoidance Power distance Masculinity Individualism Long-term orientation He developed an index for each of these dimensions. Let’s see how deepwater operations rank according to these indices.