Creating large scale probabilistic boundaries using Gaussian Processes

作者：

Highlights：

• Production hole data helps to produce more informed geological boundary estimates.

• Boundary estimates can be generated from multiple information sources.

• Presents an iterable, automatic geological boundary estimation method.

• Modelling using a set of smaller boundaries captures local geological variations.

• Sections can be iteratively updated with addition information.

摘要

•Production hole data helps to produce more informed geological boundary estimates.•Boundary estimates can be generated from multiple information sources.•Presents an iterable, automatic geological boundary estimation method.•Modelling using a set of smaller boundaries captures local geological variations.•Sections can be iteratively updated with addition information.

论文关键词：Gaussian processes,Boundary estimation,Machine learning,Data fusion

论文评审过程：Received 28 April 2020, Revised 30 January 2022, Accepted 19 March 2022, Available online 7 April 2022, Version of Record 10 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116959