Oil production forecasting using deep learning for shale oil wells under variable gas-oil and water-oil ratios

Author(s):  
Pedram Mahzari ◽  
Mehryar Emambakhsh ◽  
Cenk Temizel ◽  
Adrian P. Jones
2021 ◽  
Author(s):  
Robert Downey ◽  
Kiran Venepalli ◽  
Jim Erdle ◽  
Morgan Whitelock

Abstract The Permian Basin of west Texas is the largest and most prolific shale oil producing basin in the United States. Oil production from horizontal shale oil wells in the Permian Basin has grown from 5,000 BOPD in February, 2009 to 3.5 Million BOPD as of October, 2020, with 29,000 horizontal shale oil wells in production. The primary target for this horizontal shale oil development is the Wolfcamp shale. Oil production from these wells is characterized by high initial rates and steep declines. A few producers have begun testing EOR processes, specifically natural gas cyclic injection, or "Huff and Puff", with little information provided to date. Our objective is to introduce a novel EOR process that can greatly increase the production and recovery of oil from shale oil reservoirs, while reducing the cost per barrel of recovered oil. A superior shale oil EOR method is proposed that utilizes a triplex pump to inject a solvent liquid into the shale oil reservoir, and an efficient method to recover the injectant at the surface, for storage and reinjection. The process is designed and integrated during operation using compositional reservoir simulation in order to optimize oil recovery. Compositional simulation modeling of a Wolfcamp D horizontal producing oil well was conducted to obtain a history match on oil, gas, and water production. The matched model was then utilized to evaluate the shale oil EOR method under a variety of operating conditions. The modeling indicates that for this particular well, incremental oil production of 500% over primary EUR may be achieved in the first five years of EOR operation, and more than 700% over primary EUR after 10 years. The method, which is patented, has numerous advantages over cyclic gas injection, such as much greater oil recovery, much better economics/lower cost per barrel, lower risk of interwell communication, use of far less horsepower and fuel, shorter injection time, longer production time, smaller injection volumes, scalability, faster implementation, precludes the need for artificial lift, elimination of the need to buy and sell injectant during each cycle, ability to optimize each cycle by integration with compositional reservoir simulation modeling, and lower emissions. This superior shale oil EOR method has been modeled in the five major US shale oil plays, indicating large incremental oil recovery potential. The method is now being field tested to confirm reservoir simulation modeling projections. If implemented early in the life of a shale oil well, its application can slow the production decline rate, recover far more oil earlier and at lower cost, and extend the life of the well by several years, while precluding the need for artificial lift.


Energies ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 2052 ◽  
Author(s):  
Wardana Saputra ◽  
Wissem Kirati ◽  
Tadeusz Patzek

A recent study by the Wall Street Journal reveals that the hydrofractured horizontal wells in shales have been producing less than the industrial forecasts with the empirical hyperbolic decline curve analysis (DCA). As an alternative to DCA, we introduce a simple, fast and accurate method of estimating ultimate recovery in oil shales. We adopt a physics-based scaling approach to analyze oil rates and ultimate recovery from 14,888 active horizontal oil wells in the Bakken shale. To predict the Estimated Ultimate Recovery (EUR), we collapse production records from individual horizontal shale oil wells onto two segments of a master curve: (1) We find that cumulative oil production from 4845 wells is still growing linearly with the square root of time; and (2) 6401 wells are already in exponential decline after approximately seven years on production. In addition, 2363 wells have discontinuous production records, because of refracturing or changes in downhole flowing pressure, and are matched with a linear combination of scaling curves superposed in time. The remaining 1279 new wells with less than 12 months on production have too few production records to allow for robust matches. These wells are scaled with the slopes of other comparable wells in the square-root-of-time flow regime. In the end, we predict that total ultimate recovery from all existing horizontal wells in Bakken will be some 4.5 billion barrels of oil. We also find that wells completed in the Middle Bakken formation, in general, produce more oil than those completed in the Upper Three Forks formation. The newly completed longer wells with larger hydrofractures have higher initial production rates, but they decline faster and have EURs similar to the cheaper old wells. There is little correlation among EUR, lateral length, and the number and size of hydrofractures. Therefore, technology may not help much in boosting production of new wells completed in the poor immature areas along the edges of the Williston Basin. Operators and policymakers may use our findings to optimize the possible futures of the Bakken shale and other plays. More importantly, the petroleum industry may adopt our physics-based method as an alternative to the overly optimistic hyperbolic DCA that yields an ‘illusory picture’ of shale oil resources.


Author(s):  
Wardana Saputra ◽  
Wissem Kirati ◽  
Tadeusz Patzek

A recent study by the Wall Street Journal reveals that the hydrofractured horizontal wells in shales have been producing less than forecasted by the industry with the empirical hyperbolic decline curve analysis (DCA). As an alternative to DCA, we introduce a simple, fast and accurate method of estimating ultimate recovery (EUR) in oil shales. We adopt a physics-based scaling approach to analyze oil rates and ultimate recovery from 14,888 active horizontal oil wells in the Bakken shale. To predict EUR, we collapse production records from individual horizontal shale oil wells onto two segments of a master curve: (1) We find that cumulative oil production from 4,845 wells is still growing linearly with the square root of time; and (2) 6,401 wells are already in exponential decline after approximately seven years on production. In addition, 2,363 wells have discontinuous production records, because of refracturing or changes in downhole flowing pressure, and are matched with a linear combination of scaling curves superposed in time. The remaining 1,279 new wells with less than 12 months on production have too few production records to allow for robust matches. These wells are scaled with the slopes of other comparable wells in the square-root-of-time flow regime. In the end, we predict that total ultimate recovery from all existing horizontal wells in Bakken will be some 4.5 billion barrels of oil. We also find that wells completed in the Middle Bakken formation, in general, produce more oil than those completed in the Upper Three Forks formation. The newly completed longer wells with larger hydrofractures have higher initial production rates, but they decline faster and have EURs similar to the cheaper old wells. There is little correlation among EUR, lateral length, and the number and size of hydrofractures. Therefore, technology may not help much in boosting production of new wells completed in the poor immature areas along the edges of the Williston Basin. Operators and policy-makers may use our findings to optimize the possible futures of the Bakken shale and other plays. More importantly, petroleum industry may adopt our physics-based method as an alternative to the overly-optimistic hyperbolic DCA that yields an "illusory picture" of shale oil resources.


2020 ◽  
pp. 104833
Author(s):  
Peter B. McMahon ◽  
Joel M. Galloway ◽  
Andrew G. Hunt ◽  
Kenneth Belitz ◽  
Bryant C. Jurgens ◽  
...  

2013 ◽  
Vol 701 ◽  
pp. 440-444
Author(s):  
Gang Liu ◽  
Peng Tao Liu ◽  
Bao Sheng He

Sand production is a serious problem during the exploitation of oil wells, and people put forward the concept of limited sand to alleviate this problem. Oil production with limited sanding is an efficient mod of production. In order to complete limited sand exploitation, improve the productivity of oil wells, a real-time sand monitoring system is needed to monitor the status of wells production. Besides acoustic sand monitoring and erosion-based sand monitoring, a vibration-based sand monitoring system with two installing styles is proposed recently. The paper points out the relationships between sand monitoring signals collected under intrusive and non-intrusive installing styles and sanding parameters, which lays a good foundation for further study and actual sand monitoring in oil field.


Sign in / Sign up

Export Citation Format

Share Document