The Synergy of Data From Profiling Floats, Machine Learning and Numerical Modeling: Case of the Black Sea Euphotic Zone

Abstract

Several important developments in recent decades have greatly advanced our understanding of the biogeochemistry of the ocean and its evolution. The first is attributable to satellites, which continue to provide data on some surface biogeochemical (BGC) properties. The second advancement is the development of sensors for acquiring in situ measurements, particularly by new observational platforms such as the BGC-Argo network (Claustre et al., 2020) and gliders. The third is the advancement in numerical BGC modeling. Unfortunately, each of these advancements suffers from numerous problems. Satellites observe only the ocean surface, whereas the layers beneath could be much more representative of the BGC system than the thin surface layer. BGC-Argo sensors measure properties over large depth ranges; however, sampling locations cannot be determined in advance, and coverage remains insufficient over most of the world's oceans. In addition, the number of sensors is limited.

Combining Neural Networks and Data Assimilation to enhance the spatial impact of Argo floats in the Copernicus Mediterranean biogeochemical model

“…Integration of NN and DA have been tested in several geoscience applications (Buizza et al 2022, Brajard et al 2021, Stanev et al 2022 to infer unresolved spatial scales or reproduce missing data. In our application, the integration of NN, which retrieves a large number of profiles (Pietropolli et al, 2023), and DA, which can apply the correction to all nutrients through error covariances (Teruzzi et al, 2021), allows spatial and multivariate changes to be captured both at the local scale and across the basin to constrain Mediterranean productivity (Figure 10).…”

“…Moreover, in Sauzède et al (2016), MLP serves to infer vertical BGC distribution from OC. High performance in predicting biogeochemical states (e.g., oxygen) from physical profiling floats measurements were achieved in Stanev et al (2022) for the Black Sea.…”