US 12,320,945 B2
Probabilistic oil production forecasting
Timothy J. Roberts, Houston, TX (US); Supriya Gupta, Houston, TX (US); and Aria Abubakar, Sugar Land, TX (US)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Appl. No. 16/646,603
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
PCT Filed Sep. 13, 2018, PCT No. PCT/US2018/050882
§ 371(c)(1), (2) Date Mar. 12, 2020,
PCT Pub. No. WO2019/055653, PCT Pub. Date Mar. 21, 2019.
Claims priority of provisional application 62/558,293, filed on Sep. 13, 2017.
Prior Publication US 2020/0257932 A1, Aug. 13, 2020
Int. Cl. G06F 30/20 (2020.01); G01N 33/24 (2006.01); G01V 20/00 (2024.01); G06N 7/01 (2023.01); G06Q 10/063 (2023.01)
CPC G01V 20/00 (2024.01) [G01N 33/241 (2013.01); G06N 7/01 (2023.01); G06Q 10/063 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving historical well-production data;
identifying one or more historical behavior-changing events in the historical well- production data;
determining curve parameters after each of the one or more historical behavior-changing events, wherein determining the curve parameters includes accounting for uncertainty;
determining curve fits for the historical well-production data based on the curve parameters using a plurality of models;
calculating accuracy for each of the models based on a comparison of the curve fits to the historical well-production data;
comparing the accuracy for each of the models using an information criteria that accounts for uncertainty;
selecting one of the models based on the comparison of the accuracy;
determining an estimated ultimate recovery (EUR) for a well using at least the selected one of the models;
predicting curve fits for the historical well-production data as if no further historical behavior-changing events are performed;
comparing the curve fits to the predicted curve fits to determine values of production increases provided by the one or more historical behavior-changing events;
weighing the values of the production increases against costs of the one or more historical behavior-changing events; and
performing a future behavior-changing event in the well based at least partially upon the EUR, the predicted curve fits, and the weighing, wherein the one or more historical behavior-changing events and the future behavior-changing event comprise a well intervention and/or a workover in the well.