Optimizing Multi-Stage Hydraulic Fracturing Treatments for Economical Production in Permian Basin Using Machine Learning

Wang, Yanfang; Chen, Jianhua; Kam, Seung Ihl; Bao, Anqi

doi:10.1109/icmla52953.2021.00173

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chaikine et al reported that the developed model could predict individual well production with a 14.9% average error which can be decreased exponentially with multiple well aggregations. Other references for hydraulic fracturing design optimization are Mutalova et al [140], Wang et al [141], and Hryb et al [142]. Fracture-interaction studies have been combined with machine learning techniques, such as fracture interference [143] and automated hydraulic fracturing [144].…”

Section: Data Analytics Approachmentioning

confidence: 99%

Fracture Modeling of Shale Oil and Gas Reservoirs in Texas

Gao,

Ali,

Soliman

2023

Energies

View full text Add to dashboard Cite

Formation fracturing is the method of choice for developing shale oil and gas reservoirs that constitute a gigantic resource in the U.S.A. and many other countries but are characterized by a low permeability in the nano-Darcy range. The oil production of Texas has increased by about 5 million B/D in 15 years as a result of shale exploitation by massive multistage hydraulic fracturing. The mathematical modeling of this fracturing process is complex and can be approached in several ways. This paper first gives a concise description of the fracturing process as carried out in Texas. Included are the ranges of the key reservoir properties, as well as the injection fluid volumes and pressure, the composition of the injected fluid, proppant type, and volume, and other relevant data. Also included are the number of fracture stages, methods of zonal isolation, and diagnostic techniques used. An important variable considered is flowback, in particular, fluid retention and oil and gas production. High-salinity water production is discussed. Given the above variables, the currently used fracture simulators are briefly considered and compared, both the geomechanics-based and fracture-propagation-based. No single simulator can model the complete process. The directions currently being followed are briefly described. Also discussed is the simulation of the re-fracturing process and its range of success in increasing oil recovery from about the original ~5% to ~8%. Future processes such as plasma fracturing are mentioned, and their future applicability is discussed for further increasing oil recovery.

show abstract