As unconventional resource plays mature and infill drilling increases, wellbore damage can result from fracture-driven interactions (FDI) between wells and significantly impact the productivity of a well. It is important for operators to understand the impact of FDI and the methods to mitigate it. The problem objective is to predict when a child well frac operation will interact and affect a neighbor parent well using data-driven Machine Learning (ML) algorithms. This solution requires extensive subject matter expert (SME) validated data to create a ML training data set that can represent fracture interference events that is difficult and expensive to obtain. This solution provides an automated method to create a frac event ML training dataset using legacy production data.
Horizontal wells are fracked to increase oil and gas productivity. The frac process involves pumping solid proppants mixed with fluids at high pressure into a (child) frac well in order to create the lateral fractures. It is possible for child-well fractures to interact with neighboring (parent) wells and impact ongoing production efficiency. Available legacy data such as well head pressure and fluid rates can indicate when frac interactions have occurred, but the data may be noisy and insufficient to distinguish between valid frac interaction and operational activity.
It is useful to formalize definitions of FDI events to guide FDI classifications that enable ML algorithm prediction based on response measurement or severity of impact. FDIs can be classified depending on factors such as pressure response in a monitor/primary well, production impact in a monitor/primary or active well, and operation impact in a monitor/primary well1. Mild FDIs manifest as parent well pressure changes that represent poro-elastic interactions that fade with time. Stronger FDIs commonly known as ‘frac hits’ affect the productivity of active and primary wells; however, the total effect (positive or negative) varies by play2. Stronger intensity FDIs can also damage downhole equipment and tubulars of the primary well and are the primary focus for operators trying to reduce related operational losses. Infill drilling with reduced well spacing and larger completions after significant reservoir depletion, are factors that can increase FDIs events and the risk of negative impact on infill and primary well production. FDI’s can have negative or positive effects in primary wells before they achieve optimal production. Strategies to mitigate negative FDI’s effects should focus on reservoir depletion surveillance, synchronized field development and optimizing completion efficiency. FDI prevention may include increasing reservoir pressure around the primary well (by pre-loads or refracs) to protect from FDIs and also help to reduce infill well fracture asymmetry and drain the reservoir more uniformly.
