The oil and gas industry needs to plug the capability gap with pertinent technology that embraces the current trends to improving productivity. Digital oil fields have to engage the geosciences community and the business decision makers, surfacing knowledge from the plethora of accumulated data, both real-time and historical.
Solutions must integrate not only the data, but extant applications and physical monitoring systems, and enable efficient collaboration between these facets to perform tasks faster and with more effectiveness and efficiency. With improved workflows and computing potential, it is now possible to ascertain the risk assessment and quantification of uncertainty inherent in improving productivity. The cost implied by poor predictions has to be mitigated by improved integration of disciplines and data fusion by adopting soft computing methods such as neural networks, fuzzy logic and probabilistic reasoning instilled into efficient workflows and processes. Reservoir characterization is a crucial player in modern reservoir management, and can lead to improved and timely reservoir decisions and this leads to heightened value of the oil and gas assets.
This paper draws upon a case study that ameliorates the path to knowledge that is derived from available data. Let us look at a reservoir surveillance management solution that embraces a predictive detection and alerting solution to improve production forecasting and planning, and so assist in managing corporate risks and investments. Also, as we walk through a digital oil field workflow, we can focus on some of the soft computing techniques such as neural networks and fuzzy logic that lend credence in reservoir characterization.