Reconstructing Ocean Heat Content for Revisiting Global Ocean Warming from Remote Sensing Perspectives

Abstract

Global ocean heat content (OHC) is generally estimated using gridded, model and reanalysis data; its change is crucial to understanding climate anomalies and ocean warming phenomena. However, Argo gridded data have short temporal coverage (from 2005 to the present), inhibiting understanding of long-term OHC variabilities at decadal to multidecadal scales. In this study, we utilized multisource remote sensing and Argo gridded data based on the long short-term memory (LSTM) neural network method, which considers long temporal dependence to reconstruct a new long time-series OHC dataset (1993–2020) and fill the pre-Argo data gaps. Moreover, we adopted a new machine learning method, i.e., the Light Gradient Boosting Machine (LightGBM), and applied the well-known Random Forests (RFs) method for comparison. The model performance was measured using determination coefficients (R2) and root-mean-square error (RMSE). The results showed that LSTM can effectively improve the OHC prediction accuracy compared with the LightGBM and RFs methods, especially in long-term and deep-sea predictions. The LSTM-estimated result also outperformed the Ocean Projection and Extension neural Network (OPEN) dataset, with an R2 of 0.9590 and an RMSE of 4.45 × 1019 in general in the upper 2000 m for 28 years (1993–2020). The new reconstructed dataset (named OPEN-LSTM) correlated reasonably well with other validated products, showing consistency with similar time-series trends and spatial patterns. The spatiotemporal error distribution between the OPEN-LSTM and IAP datasets was smaller on the global scale, especially in the Atlantic, Southern and Pacific Oceans. The relative error for OPEN-LSTM was the smallest for all ocean basins compared with Argo gridded data. The average global warming trends are 3.26 × 108 J/m2/decade for the pre-Argo (1993–2004) period and 2.67 × 108 J/m2/decade for the time-series (1993–2020) period. This study demonstrates the advantages of LSTM in the time-series reconstruction of OHC, and provides a new dataset for a deeper understanding of ocean and climate events.

Unabated Global Ocean Warming Revealed by Ocean Heat Content from Remote Sensing Reconstruction

“…In recent years, many studies have reconstructed historical ocean interior information (such as OHC, subsurface temperature, and salinity, etc.) by combining satellite remote sensing data with artificial intelligence methods to reduce its uncertainty and achieve good performance [41][42][43][44][45].…”

A High-Performance Thin-Film Sensor in 6G for Remote Sensing of the Sea Surface

“…Additionally, the survival of human beings and their economic, political, cultural, and social development are closely related to the ocean. Seawater testing is one of the most important ways to determine whether the ecology of the ocean is polluted [4,5]. "Oil in water" is the oil in the water body, which is mainly derived from industrial wastewater, domestic sewage discharge, animal decomposition, and other sources.…”

Subsurface Temperature Reconstruction for the Global Ocean from 1993 to 2020 Using Satellite Observations and Deep Learning

“…The subsurface thermohaline structure can be well predicted based on LSTM and its variants, and the accuracy is higher than methods such as random forests (RFs) [30], recurrent neural network (RNN) [31], support vector regression (SVR), and multilayer perceptron regressor (MLPR) [32]. LSTM is not only suitable for the inversion of ocean subsurface temperature but also has a good application in predicting other ocean internal parameters [33], such as the time series reconstruction of global ocean heat content for the upper 2000 m [34]. Because of ocean data's inherent spatial nonlinearity and temporal dependence, traditional LSTM and CNN cannot fully exploit the temporal and spatial properties of ocean data.…”