Data‐Driven Modeling of 4D Ocean and Coastal Acidification in the Massachusetts and Cape Cod Bays From Surface Measurements

Abstract

A significant portion of atmospheric CO2 emissions is absorbed by the ocean, resulting inacidified seawater and altered carbonate composition that is harmful to marine life. Despite detrimental effects,assessing ocean and coastal acidification (OCA) is difficult due to the scarcity of in situ measurements and thehigh costs of computational modeling. We develop a parsimonious data‐driven framework to model indicatorsof OCA and test it in the Massachusetts Bay and Stellwagen Bank, a region with fishing and tourism industriesaffected by OCA. First, we trained a neural network to predict in‐depth fields for temperature and salinity(x, y, z) using surface quantities from satellites and in situ measurements (x, y). The relationship between 2Dsurface and 3D properties is captured through the in‐depth modes and coefficients obtained from principalcomponent analysis applied to a high‐resolution historical reanalysis data set. Next, we used Bayesianregression methods to estimate region‐specific relationships for in‐depth total alkalinity (TA), dissolvedinorganic carbon (DIC), and aragonite saturation state (ΩAr) as functions of temperature, salinity, andchlorophyll. Lastly, 4D daily field predictions are generated from surface measurements with a spatialresolution of 4 km horizontally and 45 sigma levels vertically. The model's performance is evaluated usingwithheld measurements across depths, locations, and seasons with RMSEs of 1.59°C, 0.31 PSU,37.54 μmol⋅kg-1, and 0.42 for temperature, salinity, TA, DIC, and ΩAr , respectively, at onewithheld location. The framework is useful for understanding OCA and includes uncertainty quantification for future planning and optimal sensor placement.