CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir
نویسندگان
چکیده
Geared toward the problems of predicting unsteadily changing single oil well production in water flooding reservoir, a machine learning model based on CNN (convolutional neural network) and LSTM (long short-term memory) is established which realizes precise predictions monthly single-well production. This study considering more than 60 dynamic static factors that affect changes production, introduce injection parameters into data set, select 11 main control factors, then, build CNN-LSTM optimized by Bayesian optimization. The effectiveness proposed verified realistic reservoir. experiment results show prediction accuracy over 90%, suggests penitential application an extensive range applications. Production forecasting developed simple, efficient, accurate, can provide guidance for analysis work as good reference development other types reservoirs.
منابع مشابه
Characterization of Reservoir Heterogeneity by Capacitance-resistance Model in Water-flooding Projects
Tedious calculations and simulations are needed to obtain an efficient production scenario and/orproper field development strategy. Capacitance-resistance model (CRM) is proved to be a fastreservoir simulation tool using just the field-available data of production and injection rates. Thisapproach sets a time-constant and a weighting factor (or well-pair connectivity parameter...
متن کاملSensitivity Analysis of Water Flooding Optimization by Dynamic Optimization
This study concerns the scope to improve water flooding in heterogeneous reservoirs. We used an existing, in-house developed, optimization program consisting of a reservoir simulator in combination with an adjoint-based optimal control algorithm. In particular we aimed to examine the scope for optimization in a two-dimensional horizontal reservoir containing a single high permeable streak, ...
متن کاملRapid Estimation of Water Flooding Performance and Optimization in EOR by Using Capacitance Resistive Model
متن کامل
Optimized polymer enhanced foam flooding for ordinary heavy oil reservoir after cross-linked polymer flooding
A successful cross-linked polymer flooding has been implemented in JD reservoir, an ordinary heavy oil reservoir with high permeability zones. For all that, there are still significant volumes of continuous oil remaining in place, which can not be easily extracted due to stronger vertical heterogeneity. Considering selective plugging feature, polymer enhanced foam (PEF) flooding was taken as fo...
متن کاملsensitivity analysis of water flooding optimization by dynamic optimization
this study concerns the scope to improve water flooding in heterogeneous reservoirs. we used an existing, in-house developed, optimization program consisting of a reservoir simulator in combination with an adjoint-based optimal control algorithm. in particular we aimed to examine the scope for optimization in a two-dimensional horizontal reservoir containing a single high permeable streak, as a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Geofluids
سال: 2023
ISSN: ['1468-8115', '1468-8123']
DOI: https://doi.org/10.1155/2023/5467956