Machine‐Learning Based Reconstructions of Past Regional Sea Level Variability From Proxy Data. Issue 23 (28th November 2021)

• Record Type: Journal Article
• Authors: Radin, Cristina; Nieves, Veronica
• Is Part Of: Geophysical research letters. Volume 48:Issue 23(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-11-28
• Subjects: Geophysics -- Periodicals; Planets -- Periodicals; Lunar geology -- Periodicals; 550
• DOI: 10.1029/2021GL095382
• Languages: English
• ISSNs: 0094-8276

Abstract

Abstract: The analysis of past regional climate‐related sea level variations has important implications for diagnosing changes in future sea level driven by climate fluctuations. As the climate changes, there is a need for new explanatory variables of within‐region climate factors and for more complex methods able to identify nonlinear relationships, such as machine learning algorithms. This study demonstrates the application of a new machine learning‐based methodology to reconstruct historical sea level tide gauge records from proxy data (i.e., upper‐ocean temperature estimates in open ocean regions), which provide a reasonably good dynamical representation of coastal sea level variations linked to slow and persistent natural processes like internal climate variability. The learning performance of our method was evaluated against observations of multiple stations and across a variety of model reconstructions, as shown and evidenced by the results. Plain Language Summary: Coastal sea level changes in many regions of the world's oceans are still dominated by offshore (natural) processes such as internal climate variability. These local climate factors are reflected in the temperature changes within the upper‐ocean layers of each region, which can be used to reconstruct regional sea level variability from incomplete tide gauge records. However, modeling the complex nonlinear dynamics of these variables requires advanced statistical techniques to produce such responses. We introduce a machine learning framework that allows including the regional ocean's dynamic properties and accounts for such complexity. Our ML‐based reconstructions bring the opportunity to improve analysis of past climate‐driven sea level variability, while exploring multiple variables for automatically modeling and reconstructing coastal sea level changes. Key Points: Proxy data of climate variability used to develop regional sea level analogues Machine Learning to reconstruct historical sea level records Consistent regional‐scale variability revealed in the Machine Learning‐based reconstructions of sea levels