TY - GEN
T1 - Stochastic Modelling of Subsurface Stratigraphy from Sparse Measurements and Augmented Training Images
AU - Shi, Chao
AU - Wang, Yu
N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).
PY - 2024
Y1 - 2024
N2 - Exploration and utilization of urban underground space require a sound understanding of subsurface stratigraphy. Image-based machine learning algorithms are appealing to engineering practitioners as they can effectively leverage valuable geological knowledge reflected in training images for stochastic simulations. However, in practice, only limited training images are available, which may not exhaust all the potential stratigraphic patterns at the site of interest. To explicitly tackle this dilemma, in this study, a generative adversarial network (GAN) is employed to generate multiple random image samples from a single training image. The compatibility of generated image samples with site-specific data is ranked based on total information entropy, and the selected image samples can be used to derive a robustness index for adaptive specification of the optimal next sampling location. The performance of the method is demonstrated using real examples from a Hong Kong reclamation site. Results indicate that the proposed framework can efficiently generate multiple image samples with plausible geological patterns, and the adaptively selected training images can improve the stochastic prediction performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
AB - Exploration and utilization of urban underground space require a sound understanding of subsurface stratigraphy. Image-based machine learning algorithms are appealing to engineering practitioners as they can effectively leverage valuable geological knowledge reflected in training images for stochastic simulations. However, in practice, only limited training images are available, which may not exhaust all the potential stratigraphic patterns at the site of interest. To explicitly tackle this dilemma, in this study, a generative adversarial network (GAN) is employed to generate multiple random image samples from a single training image. The compatibility of generated image samples with site-specific data is ranked based on total information entropy, and the selected image samples can be used to derive a robustness index for adaptive specification of the optimal next sampling location. The performance of the method is demonstrated using real examples from a Hong Kong reclamation site. Results indicate that the proposed framework can efficiently generate multiple image samples with plausible geological patterns, and the adaptively selected training images can improve the stochastic prediction performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
KW - Generative adversarial networks
KW - Information entropy
KW - Smart sampling
UR - https://www.scopus.com/pages/publications/105000436256
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105000436256&origin=recordpage
U2 - 10.1007/978-981-97-1257-1_46
DO - 10.1007/978-981-97-1257-1_46
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 978-981-97-1256-4
T3 - Lecture Notes in Civil Engineering
SP - 369
EP - 375
BT - Proceedings of the 18th Conference of the Associated Research Centers for the Urban Underground Space
A2 - Wu, Wei
A2 - Leung, Chun Fai
A2 - Zhou, Yingxin
A2 - Li, Xiaozhao
PB - Springer
CY - Singapore
T2 - 18th Conference of the Associated Research Centers for the Urban Underground Space (ACUUS 2023)
Y2 - 1 November 2023 through 4 November 2023
ER -