Using IOT and sensors, today it is possible to collect data pertaining to downhole conditions (for example temperature, pressure and geophysical makeup), drill bit performance and reservoir dynamics. These data sets can serve as input to Deep Learning algorithms that can in turn operate and manage the exploration assets. Using feedback loops and sensor data intelligent software can manipulate parameters such as individual pump strokes, rate of penetration and chemical injection rates to maintain optimal production and efficiency.
Oil and Gas
Over the past decade, the use of machine learning, predictive analytics, and other artificial intelligence-based technologies in the oil and gas industry has grown immensely as the drop in oil price has prompted a drive to reduce costs and minimize unplanned downtime. The primary application of these technologies is in the ‘Upstream’ areas of Exploration, Development and Production.
A trained deep learning software can monitor many variables such such pressure differential in a reservoir, equipment ratings, seismic vibrations, strata permeability and thermal gradients. Taken together, these input data sets can be used to determine not only the optimal direction of the drill bit, but also how it should be controlled (that is, rate of penetration) as it bores through the ground. Systems can also be designed to take in real time human feedback as training and course-correct in near real time.
Deep Learning systems can also be used to trigger warnings regarding potential catastrophic events including and linked events such as as a lost circulation, stuck pipe or blowouts.
Deep Learning can be combined with traditional analytics and operations research (OR) to improve efficiencies in the transport, refining and distribution of oil and gas. Macro data such as economic conditions and weather patterns to forecast demand can help with better judged pricing decisions.