Characterizing interwell connectivity in waterflooded reservoirs using data-driven and reduced-physics models: a comparative study

Date

2017-07-01

Author

Artun, Emre

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

164
views

0
downloads

Waterflooding is a significantly important process in the life of an oil field to sweep previously unrecovered oil between injection and production wells and maintain reservoir pressure at levels above the bubble-point pressure to prevent gas evolution from the oil phase. This is a critical reservoir management practice for optimum recovery from oil reservoirs. Optimizing water injection volumes and optimizing well locations are both critical reservoir engineering problems to address since water injection capacities may be limited depending on the geographic location and facility limits. Characterization of the reservoir connectivity between injection and production wells can greatly contribute to the optimization process. In this study, it is proposed to use computationally efficient methods to have a better understanding of reservoir flow dynamics in a waterflooding operation by characterizing the reservoir connectivity between injection and production wells. First, as an important class of artificial intelligence methods, artificial neural networks are used as a fully data-driven modeling approach. As an additional powerful method that draws analogy between source/sink terms in oil reservoirs and electrical conductors, capacitance-resistance models are also used as a reduced-physics-driven modeling approach. After understanding each method's applicability to characterize the interwell connectivity, a comparative study is carried out to determine strengths and weaknesses of each approach in terms of accuracy, data requirements, expertise requirements, training algorithm and processing times.

Subject Keywords

Software, Artificial Intelligence

URI

https://hdl.handle.net/11511/63952

Journal

NEURAL COMPUTING & APPLICATIONS

DOI

https://doi.org/10.1007/s00521-015-2152-0

Collections

Engineering, Article

Suggestions

OpenMETU
Core

The application of artificial neural networks for the prediction of water quality of polluted aquifer Gumrah, F; Oz, B; Guler, B; Evin, S (2000-04-01) From hydrocarbon reservoirs, beside of oil and natural gas, the brine is also produced as a waste material, which may be discharged at the surface or re-injected into the ground. When the wastewater is injected into the ground, it may be mixed with fresh water source due to to several reasons. Forecasting the pollutant concentrations by knowing the historical data at several locations on a field has a great importance to take the necessary precautions before the undesired situations are happened.
Cyclic behavior of saturated low plastic fine soils Sağlam, Selman; Bakır, Bahadır Sadık; Yılmaz, Mustafa Tolga; Department of Civil Engineering (2011) Weakening and liquefaction of sands with increasing excess pore water pressures under repeated loads is well-known. Occurrence of extensive damage to the built environment also at the sites underlain by fine soils during earthquakes have led the researchers to focus on the seismic response of such soils more recently. The primary objective of this study is to investigate the factors affecting cyclic behavior of saturated low-plastic fine soils through laboratory testing. An extensive laboratory testing prog...
Predicting Frictional Pressure Loss During Horizontal Drilling for Non-Newtonian Fluids SORGUN, MEHMET; Ozbayoglu, M. E. (Informa UK Limited, 2011-01-01) Accurate estimation of the frictional pressure losses for non-Newtonian drilling fluids inside annulus is quite important to determine pump rates and select mud pump systems during drilling operations. The purpose of this study is to estimate frictional pressure loss and velocity profile of non-Newtonian drilling fluids in both concentric and eccentric annuli using an Eulerian-Eulerian computational fluid dynamics (CFD) model. An extensive experimental program was performed in METU-PETE Flow Loop using two ...
Modeling water quality impacts of petroleum contaminated soils in a reservoir catchment Ünlü, Kahraman (2000-05-01) Soil contamination due to spills or leaks of crude oils and refined hydrocarbons is a common problem. Estimation of spill volume is a crucial issue in order to determine the expected contaminating life span of contaminated soils. The direct procedure to determine the amount of hydrocarbon in soil is to measure the concentration of total petroleum hydrocarbon (TPH) in soil samples. The primary objective of this study was to assess the potential effects of oil contaminated soils on the water quality of Devege...
Evaluation of limestone incorporated cement compositions for cementing gas hydrate zones in deepwater environments Hıdıroğlu, İnanç Alptuğ; Parlaktuna, Mahmut; Yaman, İsmail Özgür; Department of Petroleum and Natural Gas Engineering (2017) One of the potential problems which must be overcome during oil or gas exploration in deepwater environments is to complete the drilling operations without decomposing the gas hydrates. Gas hydrates remain stable as long as the thermodynamic conditions are not changed. But, especially by increasing temperature during drilling operations, there is always a possibility of change in thermodynamic conditions, which will cause decomposition. Another factor which may disturb the thermodynamic conditions is the ev...

Citation Formats

E. Artun, “Characterizing interwell connectivity in waterflooded reservoirs using data-driven and reduced-physics models: a comparative study,” NEURAL COMPUTING & APPLICATIONS, pp. 1729–1743, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/63952.