Search for: All records

Antarctic sea ice modeling has become essential due to the exacerbating effects of climate change on the region, with the aim of utilizing present and past data to predict the future. However, a setback lies in the grand scale of the data needed to make these predictions best, spanning both spatial and temporal axes. As a result, dimension reduction is necessary to capture the most important patterns of variability – a pre-processing step for future predictions. The utilization of Machine Learning tools, such as autoencoders, has been investigated as an alternative to linear dimension reduction methods, such as EOFs. Input data includes satellite observed gridded data in the Antarctic region from 1979 to 2022. Different versions of the autoencoder model are investigated, with varying components in its architecture, including activation function (linear and ReLU), bottleneck units (compressed dimensions), and added layers. It is found that the seven-layered and five-layered ReLU models outperform other configurations across all bottleneck units, including when compared with EOFs. These models also contain a higher explained variance ratio: at 11 compressed dimensions, the seven-layered autoencoder can capture 18.7% more variance than the 11 EOF modes explain. The ReLU activation function also allows the model to detect nonlinear patterns, providing an additional benefit to the improved RMSE and variance ratio. The findings demonstrate that the autoencoder model serves as a worthy alternative to EOFs, likely extracting more predictable variance in the sea ice field. The result is crucial for understanding sea ice spatiotemporal variability and its predictability in the Antarctic. 

Abstract Rock dissolution is a common subsurface geochemical reaction affecting pore space properties, crucial for reservoir stimulation, carbon storage, and geothermal energy. Predictive models for dissolution remain limited due to incomplete understanding of the mechanisms involved. We examine the influence of flow, transport, and reaction regimes on mineral dissolution using 29 time‐resolved data from 3D rocks. We find that initial pore structure significantly influences the dissolution pattern, with reaction rates up to two orders of magnitude lower than batch conditions, given solute and fluid‐solid boundary constraints. Flow unevenness determines the location and rate of dissolution. We propose two models describing expected dissolution patterns and effective reaction rates based on dimensionless metrics for flow, transport, and reaction. Finally, we analyze feedback between evolving flow and pore structure to understand conditions that regulate/reinforce dissolution hotspots. Our findings underscore the major impact of flow arrangement on reaction‐front propagation and provide a foundation for controlling dissolution hotspots.