TY - JOUR
T1 - Automated Classification of Well Test Responses in Naturally Fractured Reservoirs Using Unsupervised Machine Learning
AU - Freites, A.
AU - Corbett, P.
AU - Rongier, G.
AU - Geiger, S.
N1 - Funding Information:
We thank Energi Simulation for supporting Sebastian Geiger’s Chair and Heriot-Watt University for providing the James Watt PhD Scholarship to Alfredo Freites. We thank Schlumberger for the access to ECLIPSE and Petrel softwares. We thank the three anonymous reviewers for their careful and constructive comments, which helped us to improve the manuscript.
Publisher Copyright:
© 2023, The Author(s).
PY - 2023/4
Y1 - 2023/4
N2 - Understanding the impact of fractures on fluid flow is fundamental for developing geoenergy reservoirs. Pressure transient analysis could play a key role for fracture characterization purposes if better links can be established between the pressure derivative responses (p′) and the fracture properties. However, pressure transient analysis is particularly challenging in the presence of fractures because they can manifest themselves in many different p′ curves. In this work, we aim to provide a proof-of-concept machine learning approach that allows us to effectively handle the diversity in fracture-related p′ curves by automatically classifying them and identifying the characteristic fracture patterns. We created a synthetic dataset from numerical simulation that comprised 2560 p′ curves that represent a wide range of fracture network properties. We developed an unsupervised machine learning approach that can distinguish the temporal variations in the p′ curves by combining dynamic time warping with k-medoids clustering. Our results suggest that the approach is effective at recognizing similar shapes in the p′ curves if the second pressure derivatives are used as the classification variable. Our analysis indicated that 12 clusters were appropriate to describe the full collection of p′ curves in this particular dataset. The classification exercise also allowed us to identify the key geological features that influence the p′ curves in this particular dataset, namely (1) the distance from the wellbore to the closest fracture(s), (2) the local/global fracture connectivity, and (3) the local/global fracture intensity. With additional training data to account for a broader range of fracture network properties, the proposed classification method could be expanded to other naturally fractured reservoirs and eventually serve as an interpretation framework for understanding how complex fracture network properties impact pressure transient behaviour.
AB - Understanding the impact of fractures on fluid flow is fundamental for developing geoenergy reservoirs. Pressure transient analysis could play a key role for fracture characterization purposes if better links can be established between the pressure derivative responses (p′) and the fracture properties. However, pressure transient analysis is particularly challenging in the presence of fractures because they can manifest themselves in many different p′ curves. In this work, we aim to provide a proof-of-concept machine learning approach that allows us to effectively handle the diversity in fracture-related p′ curves by automatically classifying them and identifying the characteristic fracture patterns. We created a synthetic dataset from numerical simulation that comprised 2560 p′ curves that represent a wide range of fracture network properties. We developed an unsupervised machine learning approach that can distinguish the temporal variations in the p′ curves by combining dynamic time warping with k-medoids clustering. Our results suggest that the approach is effective at recognizing similar shapes in the p′ curves if the second pressure derivatives are used as the classification variable. Our analysis indicated that 12 clusters were appropriate to describe the full collection of p′ curves in this particular dataset. The classification exercise also allowed us to identify the key geological features that influence the p′ curves in this particular dataset, namely (1) the distance from the wellbore to the closest fracture(s), (2) the local/global fracture connectivity, and (3) the local/global fracture intensity. With additional training data to account for a broader range of fracture network properties, the proposed classification method could be expanded to other naturally fractured reservoirs and eventually serve as an interpretation framework for understanding how complex fracture network properties impact pressure transient behaviour.
KW - Classification
KW - Fractured reservoirs
KW - Machine learning
KW - Well tests
UR - http://www.scopus.com/inward/record.url?scp=85150284624&partnerID=8YFLogxK
U2 - 10.1007/s11242-023-01929-1
DO - 10.1007/s11242-023-01929-1
M3 - Article
AN - SCOPUS:85150284624
SN - 0169-3913
VL - 147
SP - 747
EP - 779
JO - Transport in Porous Media
JF - Transport in Porous Media
IS - 3
ER -