GeoWarp: Warped Spatial Processes for Inferring Subsea Sediment Properties

• 成果类型: Article
• 署名作者: Bertolacci, Michael; Zammit-Mangion, Andrew; Giraldo, Juan Valderrama; O'Neill, Michael; Bransby, Fraser; Watson, Phil
• 署名单位: University of Western Australia; University of Wollongong; University of Western Australia
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2024.2445874
• 发表日期: 2025
• 页码: 710-722
• 关键词: identification; regression; selection

摘要

For offshore structures like wind turbines, subsea infrastructure, pipelines, and cables, it is crucial to quantify the properties of the seabed sediments at a proposed site. However, data collection offshore is costly, so analysis of the seabed sediments must be made from measurements that are spatially sparse. Adding to this challenge, the structure of the seabed sediments exhibits both nonstationarity and anisotropy. To address these issues, we propose GeoWarp, a hierarchical spatial statistical modeling framework for inferring the 3-D geotechnical properties of subsea sediments. GeoWarp decomposes the seabed properties into a region-wide vertical mean profile (modeled using B-splines), and a nonstationary 3-D spatial Gaussian process. Process nonstationarity and anisotropy are accommodated by warping space in three dimensions and by allowing the process variance to change with depth. We apply GeoWarp to measurements of the seabed made using cone penetrometer tests (CPTs) at six sites on the North West Shelf of Australia. We show that GeoWarp captures the complex spatial distribution of the sediment properties, and produces realistic 3-D simulations suitable for downstream engineering analyses. Through cross-validation, we show that GeoWarp has predictive performance superior to other state-of-the-art methods, demonstrating its value as a tool in offshore geotechnical engineering. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.