No abstract

No abstract

SignificanceSince the 19th century, rising greenhouse gas concentrations have caused the ocean to absorb most of the Earth’s excess heat and warm up. Before the 1990s, most ocean temperature measurements were above 700 m and therefore, insufficient for an accurate global estimate of ocean warming. We present a method to reconstruct ocean temperature changes with global, full-depth ocean coverage, revealing warming of 436 ×normal1021 J since 1871. Our reconstruction, which agrees with other estimates for the well-observed period, demonstrates that the ocean absorbed as much heat during 1921–1946 as during 1990–2015. Since the 1950s, up to one-half of excess heat in the Atlantic Ocean at midlatitudes has come from other regions via circulation-related changes in heat transport.

Oceanographic observations are limited by sampling rates, while ocean models are limited by finite resolution and high viscosity and diffusion coefficients. Therefore, both data from observations and ocean models lack information at small and fast scales. Methods are needed to either extract information, extrapolate, or upscale existing oceanographic data sets, to account for or represent unresolved physical processes. Here we use machine learning to leverage observations and model data by predicting unresolved turbulent processes and subsurface flow fields. As a proof of concept, we train convolutional neural networks on degraded data from a high-resolution quasi-geostrophic ocean model. We demonstrate that convolutional neural networks successfully replicate the spatiotemporal variability of the subgrid eddy momentum forcing, are capable of generalizing to a range of dynamical behaviors, and can be forced to respect global momentum conservation. The training data of our convolutional neural networks can be subsampled to 10-20% of the original size without a significant decrease in accuracy. We also show that the subsurface flow field can be predicted using only information at the surface (e.g., using only satellite altimetry data). Our results indicate that data-driven approaches can be exploited to predict both subgrid and large-scale processes, while respecting physical principles, even when data are limited to a particular region or external forcing. Our in-depth study presents evidence for the successful design of ocean eddy parameterizations for implementation in coarse-resolution climate models.Plain Language Summary Models of the ocean and ocean observations are imperfect. Due to this imperfection, simulations of the ocean and our observations are not quite the same as the true ocean currents. We, therefore, need ways to make our ocean data more realistic and complete and to make it more similar to the actual ocean. Scientists have traditionally approached this problem in a pen-and-paper style, considering physical theories and mechanisms. This study instead uses machine learning, which focuses on data as opposed to equations on a black board. We successfully use a particular type of machine learning algorithm, called a convolutional neural network, to make the most of current oceanographic data. This type of neural network works well even if ocean data are limited to a particular area. Future work will involve combining machine learning with physical theories of the ocean.