Decline Curve Analysis for Production Forecasting Based on Machine Learning

2017 ◽  
Author(s):  
Yunan Li ◽  
Yifu Han
Keyword(s):  
Machine Learning ◽  
Curve Analysis ◽  
Decline Curve Analysis ◽  
Production Forecasting ◽  
Decline Curve

Rescaling Method for Improved Machine-Learning Decline Curve Analysis for Unconventional Reservoirs

SPE Journal ◽  
2021 ◽  
pp. 1-14
Author(s):  
Boxiao Li ◽  
Travis C. Billiter ◽  
Timothy Tokar
Keyword(s):  
Machine Learning ◽  
Error Reduction ◽  
Curve Analysis ◽  
Support Vector ◽  
Mean Deviation ◽  
Production Forecast ◽  
Simple Method ◽  
Decline Curve Analysis ◽  
Curve Fit ◽  
Decline Curve

Summary Decline curve analysis (DCA) has been widely applied in production forecasting of wells in unconventional hydrocarbon reservoirs. However, traditional curve-fit-based methods fall short of forecast accuracy due to three weaknesses: first, they cannot capture the reservoir signals not modeled by the underlying DCA model formulas; second, when predicting the production of a target well, the production history of other wells in the geologic formation (which is valuable information) is not considered; third, the wells’ geographic, geologic, wellbore, well spacing, and completion properties, which are highly relevant to production capability, are not used. More recent approaches have begun replacing traditional DCA with machine-learning methods [e.g., random forest (RF), support vector regression (SVR), etc.] for production forecast. Nevertheless, these methods are still suboptimal in detecting similar production trends in different wells, leading to large forecast error. A new and simple method called dynamic production rescaling (DPR) is developed to improve the accuracy of machine-learning DCA (ML-DCA). By combining DPR with common ML-DCA methods, we observe that the error mean, deviation, and skewness can be significantly reduced by 15 to 35% compared with ML-DCA without DPR. The error reduction is 30 to 60% compared with automatic curve fit of the traditional modified Arps DCA model. DPR has been tested successfully on monthly production data of over 20,000 unconventional horizontal wells in the Permian and Appalachian basins for both long- and short-term forecasts. The significant error reduction is consistent across different basins and formations. DPR is computationally efficient, so a large number of wells can be analyzed automatically and quickly. Moreover, the effectiveness and efficiency of DPR is independent of the underlying machine-learning algorithm, further demonstrating its robustness.

scholarly journals Pre-Drilling Production Forecasting of Parent and Child Wells Using a 2-Segment Decline Curve Analysis (DCA) Method Based on an Analytical Flow-Cell Model Scaled by a Single Type Well

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1525
Author(s):  
Ruud Weijermars ◽  
Kiran Nandlal
Keyword(s):  
Cell Model ◽  
Flow Cell ◽  
Curve Analysis ◽  
Treatment Quality ◽  
Well Performance ◽  
Reservoir Simulations ◽  
Decline Curve Analysis ◽  
Production Forecasting ◽  
Well Spacing ◽  
Decline Curve

This paper advances a practical tool for production forecasting, using a 2-segment Decline Curve Analysis (DCA) method, based on an analytical flow-cell model for multi-stage fractured shale wells. The flow-cell model uses a type well and can forecast the production rate and estimated ultimate recovery (EUR) of newly planned wells, accounting for changes in completion design (fracture spacing, height, half-length), total well length, and well spacing. The basic equations for the flow-cell model have been derived in two earlier papers, the first one dedicated to well forecasts with fracture down-spacing, the second one to well performance forecasts when inter-well spacing changes (and for wells drilled at different times, to account for parent-child well interaction). The present paper provides a practical workflow, introduces correction parameters to account for acreage quality and fracture treatment quality. Further adjustments to the flow-cell model based 2-segment DCA method are made after history matching field data and numerical reservoir simulations, which indicate that terminal decline is not exponential (b = 0) but hyperbolic (with 0 < b< 1). The timing for the onset of boundary dominated flow was also better constrained, using inputs from a reservoir simulator. The new 2-segment DCA method is applied to real field data from the Eagle Ford Formation. Among the major insights of our analyses are: (1) fracture down-spacing does not increase the long-term EUR, and (2) fracture down-spacing of real wells does not result in the rate increases predicted by either the flow-cell model based 2-segment DCA (or its matching reservoir simulations) with the assumed perfect fractures in the down-spaced well models. Our conclusion is that real wells with down-spaced fracture clusters, involving up to 5000 perforations, are unlikely to develop successful hydraulic fractures from each cluster. The fracture treatment quality factor (TQF) or failure rate (1-TQF) can be estimated by comparing the actual well performance with the well forecast based on the ideal well model (albeit flow-cell model or reservoir model, both history-matched on the type curve).

Is Decline Curve Analysis the Right Tool for Production Forecasting in Unconventional Reservoirs?

2021 ◽  
Author(s):  
Oscar Molina ◽  
Laura Santos ◽  
Francisco Herrero ◽  
Agustin Monaco ◽  
Darren Schultz
Keyword(s):  
Curve Analysis ◽  
Stochastic Simulations ◽  
Unconventional Reservoirs ◽  
Sufficient Evidence ◽  
Production Data ◽  
Optimization Approach ◽  
Metaheuristic Algorithm ◽  
Decline Curve Analysis ◽  
Production Forecasting ◽  
Decline Curve

Abstract This study presents a novel metaheuristic algorithm that uses a physics-based model for multi-fractured horizontal wells (MFHW) to accurately predict the estimated ultimate recovery (EUR) for unconventional reservoirs. The metaheuristic algorithm creates a sizeable number of stochastic simulations and keeps the simulation results from those random models that closely reproduce observed production data. Unlike other optimization methods, the proposed algorithm does not aim at finding the exact solution to the problem but a group of sufficiently accurate solutions that help to construct the partial solution to the optimization problem as a function of production history. Results from this work provide sufficient evidence as to why traditional decline curve analysis (DCA) is not a suitable solution for production forecasting in unconventional reservoirs. Two case studies are discussed in this work where results from both modeling strategies are compared. Evolutionary prediction of EUR over time using DCA behaves erratically, regardless of the amount of historical production data available to the regression model. Such erratic behavior can, in turn, yield an erroneous estimation of key economic performance indicators of an asset. In contrast, the proposed metaheuristic algorithm delivers precise and accurate results consistently, achieving a significant reduction of uncertainties as more production data becomes available. In conclusion, the proposed partial optimization approach enables the accurate calculation of important metrics for unconventional reservoirs, including production forecasting and expected productive life of an asset.

Sign in / Sign up

Export Citation Format

Share Document