Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A machine-learning inverse model framework for rapid forecasting and history matching in unconventional reservoirs

Journal Article · · Scientific Reports

Model-based optimization for real-time forecasting in unconventional reser-voirs requires novel methods and work?ows since the strategies and work?ows used in conventional reservoirs are either inapplicable, or prohibitively expen-sive and time-consuming. Insu?cient site data and computational expense of high-?delity simulations mean that work?ows with high-?delity simulations are not ideal for usage in comprehensive uncertainty quanti?cation stud-ies that require 1000s of forward model runs. We present an alternative, novel work?ow for unconventional reservoirs, based on the interplay between reduced-order models and machine-learning. Our physics-informed machine-learning (PIML) work?ow addresses the challenges to real-time reservoir management in uncoventionals, namely lack of data (the time-frame for which the wells have been producing), and computational expense of high-?delity modeling. We use the machine-learning paradigm of transfer-learning to bind together fast but less accurate reduced-order models with slow, but accurate high-?delity models and circumvent the di?culties inherent in the current state-of-the-art for unconventionals. Such a PIML work?ow, grounded in physics, is a viable candidate for real-time history matching and production forecasting in a fractured shale gas reservoir. The signi?cance of our approach is that while it is developed for a particu-lar well and site in the Marcelus Shale gas reservoir of the Appalachian basin (MSEEL), it is not wedded to it. We expect the same work?ow can be ap-plied to other shale formations (e.g., Woodford, Barnett, Utica, EagleFord) should site-data become available, using the same set of machine-learning techniques from transfer learning. Some ?ne-tuning (or minimal retraining of the neural networks) will be required to transfer knowledge across shale gas sites/formations but it is a clearly superior alternative to developing a new machine-learning model altogether when considering a di?erent site.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-76RL01830
OSTI ID:
1830370
Report Number(s):
PNNL-SA-159040
Journal Information:
Scientific Reports, Journal Name: Scientific Reports
Country of Publication:
United States
Language:
English

References (33)

Coupled thermo-hydro-mechanical analysis of stimulation and production for fractured geothermal reservoirs journal August 2019
From the Cover: Cozzarelli Prize Winner: Gas production in the Barnett Shale obeys a simple scaling theory journal November 2013
Recovery rates, enhanced oil recovery and technological limits
  • Muggeridge, Ann; Cockin, Andrew; Webb, Kevin
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 372, Issue 2006 https://doi.org/10.1098/rsta.2012.0320
journal January 2014
Recovery Efficiency in Hydraulically Fractured Shale Gas Reservoirs journal March 2017
Does Flowing Pressure Matter? A Statistical Study conference January 2017
Production-Pressure-Drawdown Management for Fractured Horizontal Wells in Shale-Gas Formations journal November 2017
Tactics and Pitfalls in Production Decline Curve Analysis conference March 2013
Optimal planning and modular infrastructure dynamic allocation for shale gas production journal March 2020
Multi-Disciplinary Data Integration for Inverse Hydraulic Fracturing Analysis: A Case Study conference January 2015
Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network journal April 2018
A machine learning approach to predict drilling rate using petrophysical and mud logging data journal March 2019
Geomechanical parameter estimation from mechanical specific energy using artificial intelligence journal April 2019
A geomechanical approach to casing collapse prediction in oil and gas wells aided by machine learning journal January 2021
Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field journal March 2021
An adsorbed gas estimation model for shale gas reservoirs via statistical learning journal July 2017
Predicting production and estimated ultimate recoveries for shale gas wells: A new methodology approach journal November 2017
Modeling of multi-scale transport phenomena in shale gas production — A critical review journal March 2020
Optimization of enhanced oil recovery operations in unconventional reservoirs journal January 2020
A Survey on Transfer Learning journal October 2010
Multi-fidelity machine learning models for accurate bandgap predictions of solids journal March 2017
Efficient Monte Carlo With Graph‐Based Subsurface Flow and Transport Models journal May 2018
Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia journal April 2019
Physics-informed machine learning journal May 2021
Practical Considerations for Well Performance Analysis and Forecasting in Shale Plays journal June 2016
Effect of advective flow in fractures and matrix diffusion on natural gas production journal October 2015
dfnWorks: A discrete fracture network framework for modeling subsurface flow and transport journal November 2015
Upscaled discrete fracture matrix model (UDFM): an octree-refined continuum representation of fractured porous media journal December 2019
Flow and Transport in Tight and Shale Formations: A Review journal January 2017
PFLOTRAN User Manual: A Massively Parallel Reactive Flow and Transport Model for Describing Surface and Subsurface Processes report January 2015
Advancing Graph-Based Algorithms for Predicting Flow and Transport in Fractured Rock journal September 2018
Marcellus Wells' Ultimate Production Accurately Predicted from Initial Production conference May 2016
Dynamics of Production Decline from Shale Gas Reservoirs: Mechanistic or Empirical Models? conference October 2014
Flux: Elegant machine learning with Julia journal May 2018