Historical sea level records offer the opportunity to have a wider perspective on past climate-driven sea level variations and change on multi-year to decadal timescales. This knowledge is essential to understand current changes and improve future sea level predictions in response to climatic shifts. In fact, a recent study suggests that internal climate variability is still substantially impacting sea level in many coastal regions around the globe (Nieves et al., 2021). However, unfortunately, sea level records from tide gauges around the world's coastlines frequently include gaps (with over 50% missing data points at many stations) and biases (due to for example vertical land movements) (Holgate et al., 2013), which limits the study of past local and regional sea level variations. Another limiting factor is that some regions (e.g., coastal regions of Africa and South America) are poorly sampled. At some specific locations, tide gauge data may also represent a variety of regional processes other than climate variations (such as tides or storm surges, among other local factors) (Holgate et al., 2013). Thus, gap filling options for segmented, incomplete or uncertain tide gauge records continue to remain an important challenge (Wenzel & Schröter, 2010), especially for the study of "internally-induced" regional sea level changes (i.e., changes due to internal climate variations) over the past decades (Sérazin et al., 2016).Of all the historical reconstruction methods that have been developed over the years (Carson et al., 2017), machine learning (ML) is a sound strategy for capturing the complex nonlinear behavior in oceanic (but not only) dynamical systems (