A deep-learning estimate of the decadal trends in the Southern Ocean carbon storage

Constraining the trend in the ocean CO2 sink during 2000-2022

The ocean will ultimately store most of the CO2 emitted to the atmosphere by human activities. Despite its importance, estimates of the 2000-2022 trend in the ocean CO2 sink differ by a factor of two between observation-based products and process-based models. Here we address this discrepancy using a hybrid approach that preserves the consistency of known processes but constrains the outcome using observations. We show that the hybrid approach reproduces the stagnation of the ocean CO2 sink in the 1990s and its reinvigoration in the 2000s suggested by observation-based products and matches their amplitude. It suggests that process-based models underestimate the amplitude of the decadal variability in the ocean CO2 sink, but that observation-based products on average overestimate the decadal trend in the 2010s. The hybrid approach constrains the 2000-2022 trend in the ocean CO2 sink to 0.42 ± 0.06 Pg C yr-1 decade-1, and by inference the total land CO2 sink to 0.28 ± 0.13 Pg C yr-1 decade-1.

Increased methane emissions from oil and gas following the Soviet Union's collapse

Global atmospheric methane concentrations rose by 10 to 15 ppb/y in the 1980s before abruptly slowing to 2 to 8 ppb/y in the early 1990s. This period in the 1990s is known as the "methane slowdown" and has been attributed in part to the collapse of the former Soviet Union (USSR) in December 1991, which may have decreased the methane emissions from oil and gas operations. Here, we develop a methane plume detection system based on probabilistic deep learning and human-labeled training data. We use this method to detect methane plumes from Landsat 5 satellite observations over Turkmenistan from 1986 to 2011. We focus on Turkmenistan because economic data suggest it could account for half of the decline in oil and gas emissions from the former USSR. We find an increase in both the frequency of methane plume detections and the magnitude of methane emissions following the collapse of the USSR. We estimate a national loss rate from oil and gas infrastructure in Turkmenistan of more than 10% at times, which suggests the socioeconomic turmoil led to a lack of oversight and widespread infrastructure failure in the oil and gas sector. Our finding of increased oil and gas methane emissions from Turkmenistan following the USSR's collapse casts doubt on the long-standing hypothesis regarding the methane slowdown, begging the question: "what drove the 1992 methane slowdown?"

A unified deep learning framework for water quality prediction based on time-frequency feature extraction and data feature enhancement

Deep learning methods exhibited significant advantages in mapping highly nonlinear relationships with acceptable computational speed, and have been widely used to predict water quality. However, various model selection and construction methods resulted in differences in prediction accuracy and performance. Hence, a unified deep learning framework for water quality prediction was established in the paper, including data processing module, feature enhancement module, and data prediction module. In the established model, the data processing module based on wavelet transform method was applied to decomposing complex nonlinear meteorology, hydrology, and water quality data into multiple frequency domain signals for extracting self characteristics of data cyclic and fluctuations. The feature enhancement module based on Informer Encoder was used to enhance feature encoding of time series data in different frequency domains to discover global time dependent features of variables. Finally, the data prediction module based on the stacked bidirectional long and short term memory network (SBiLSTM) method was employed to strengthen the local correlation of feature sequences and predict the water quality. The established model framework was applied in Lijiang River in Guilin, China. The maximum relative errors between the predicted and observed values for dissolved oxygen (DO), chemical oxygen demand (CODMn) were 12.4% and 20.7%, suggesting a satisfactory prediction performance of the established model. The validation results showed that the established model was superior to all other models in terms of prediction accuracy with RMSE values 0.329, 0.121, MAE values 0.217, 0.057, SMAPE values 0.022, 0.063 for DO and CODMn, respectively. Ablation tests confirmed the necessity and rationality of each module for the established model framework. The established method provided a unified deep learning framework for water quality prediction.

The Four-Dimensional Carbon Cycle of the Southern Ocean

The Southern Ocean plays a fundamental role in the global carbon cycle, dominating the oceanic uptake of heat and carbon added by anthropogenic activities and modulating atmospheric carbon concentrations in past, present, and future climates. However, the remote and extreme conditions found there make the Southern Ocean perpetually one of the most difficult places on the planet to observe and to model, resulting in significant and persistent uncertainties in our knowledge of the oceanic carbon cycle there. The flow of carbon in the Southern Ocean is traditionally understood using a zonal mean framework, in which the meridional overturning circulation drives the latitudinal variability observed in both air-sea flux and interior ocean carbon concentration. However, recent advances, based largely on expanded observation and modeling capabilities in the region, reveal the importance of processes acting at smaller scales, including basin-scale zonal asymmetries in mixed-layer depth, mesoscale eddies, and high-frequency atmospheric variability. Assessing the current state of knowledge and remaining gaps emphasizes the need to move beyond the zonal mean picture and embrace a four-dimensional understanding of the carbon cycle in the Southern Ocean.