TY - JOUR
T1 - Optimization of subsurface models with multiple criteria using Lexicase Selection
AU - He, Yifan
AU - Aranha, Claus
AU - Hallam, Tony
AU - Chassagne, Romain
N1 - Funding Information:
AH and RC would like to thank the sponsors of Edinburgh Time-Lapse Project (ETLP) Phase VII (AkerBP, BP, CGG, Chevron/Ithaca Energy, CNOOC, Equinor, ConocoPhillips, ENI, Petrobras, Norsar, Woodside, Taqa, Halliburton, ExxonMobil, OMV and Shell) for funding this work and Equinor for provision of the public data set. RC acknowledges the Japanese Society for Promotion of Science (JSPS) for the fellowship L19544 which initiated this work. YH acknowledges the Japanese Society for Promotion of Science (JSPS) for support under grant 17K12690 We also acknowledge Schlumberger for the use of their Eclipse software and the Python open source community.
Publisher Copyright:
© 2022 The Authors
PY - 2022
Y1 - 2022
N2 - Seismic History Matching (SHM) is a key problem in the geosciences community, requiring optimal parameters of a subsurface model that match the observed data from multiple in-situ measurements. Therefore, the SHM problems are usually solved with Multi-Objective Evolutionary Algorithms (MOEAs). This group of algorithms optimize multiple objectives simultaneously, considering the trade-off between objectives. However, SHM requires the solutions that are good on all objectives rather than a trade-off. In this study, we propose a Differential Evolution algorithm using Lexicase Selection to solve the SHM problems. Unlike the MOEAs, this selection method pushes the solutions to perform well on all objectives. We compared this method with two MOEAs, namely Non-dominated Sorting Genetic Algorithm II and Reference Vector-guided Evolutionary Algorithm, on two SHM problems. The results show that this method generates more solutions near the ground truth.
AB - Seismic History Matching (SHM) is a key problem in the geosciences community, requiring optimal parameters of a subsurface model that match the observed data from multiple in-situ measurements. Therefore, the SHM problems are usually solved with Multi-Objective Evolutionary Algorithms (MOEAs). This group of algorithms optimize multiple objectives simultaneously, considering the trade-off between objectives. However, SHM requires the solutions that are good on all objectives rather than a trade-off. In this study, we propose a Differential Evolution algorithm using Lexicase Selection to solve the SHM problems. Unlike the MOEAs, this selection method pushes the solutions to perform well on all objectives. We compared this method with two MOEAs, namely Non-dominated Sorting Genetic Algorithm II and Reference Vector-guided Evolutionary Algorithm, on two SHM problems. The results show that this method generates more solutions near the ground truth.
KW - Lexicase Selection
KW - Multi-Objective Evolutionary Algorithm
KW - Multi-objective optimization
KW - Seismic History Matching
UR - http://www.scopus.com/inward/record.url?scp=85129646202&partnerID=8YFLogxK
U2 - 10.1016/j.orp.2022.100237
DO - 10.1016/j.orp.2022.100237
M3 - Article
SN - 2214-7160
VL - 9
JO - Operations Research Perspectives
JF - Operations Research Perspectives
M1 - 100237
ER -