.png){kind=icon}
.png){kind=icon}
Return
Machine learning based subsurface modelling using geological exploration data: a comprehensive review
.png){kind=icon}
PRE
AI
DOI：10.1080/17499518.2025.2581567.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The twenty-first century is the century of underground space. The development of underground construction has made it necessary to establish an accurate and high-resolution subsurface model, which is fundamental to optimising engineering design and ensuring construction safety. Traditional stratigraphic methods, such as manual drawing, is time-consuming while geostatistical and probabilistic methods require extensive computational cost. With the prosperity of artificial intelligence and its successful application in a broad range of realms, Machine Learning (ML) has offered a powerful tool for intelligent and high-resolution subsurface modelling. Recently, substantial research papers focused on ML-based subsurface stratigraphy, most of which lay emphasis on the probabilistic methods but lack sufficient and deep insight into ML or DL-based methods. This paper proposed a clear and logical framework to sort out all literature related to this area, which reorganised the scattered past papers and holistically categorised the research topics into three types according to the relative relationships among multiple streams within the existing literature. The future agenda is fully discussed, including emerging opportunities and challenges in the context of ML-based subsurface modelling. Hopefully, this paper could provide a unified governance framework that guides how to properly apply ML in different sub-tasks of intelligent subsurface modelling.
Keywords:
Machine learning
subsurface modelling
stratigraphic uncertainty
site investigation
Journal
G
IF:
0
Papers:
36
Citations:
0