Related papers: Sea ice floe segmentation in close-range optical i…
The recognition of sea ice is of great significance for reflecting climate change and ensuring the safety of ship navigation. Recently, many deep learning based methods have been proposed and applied to segment and recognize sea ice…
Quantifying kinetic energy (KE) and enstrophy transfer, mixing, and dissipation in the Arctic Ocean is key to understanding polar ocean dynamics, which are critical components of the global climate system. However, in ice-covered regions,…
Visible and Infrared Image Fusion (VIF) has garnered significant interest across a wide range of high-level vision tasks, such as object detection and semantic segmentation. However, the evaluation of VIF methods remains challenging due to…
Understanding the molecular-level structure and dynamics of ice surfaces is crucial for deciphering several chemical, physical, and atmospheric processes. Vibrational sum-frequency generation (SFG) spectroscopy is the most prominent tool…
The discrete element method (DEM) can provide detailed descriptions of sea ice dynamics that explicitly model floes and discontinuities in the ice, which can be challenging to represent accurately with current models. However, floe-scale…
The transport of sea ice over the polar oceans plays an important role in climate. This transport is driven predominantly by turbulent winds, leading to stochastic motion of ice floes. Observed diffusivities and velocity distributions of…
The discrete element method (DEM) is providing a new modeling approach for describing sea ice dynamics. It exploits particle-based methods to characterize the physical quantities of each sea ice floe along its trajectory under Lagrangian…
Eddies within the meso/submeso-scale range are prevalent throughout the Arctic Ocean, playing a pivotal role in regulating freshwater budget, heat transfer, and sea ice transport. While observations have suggested a strong connection…
Interactive segmentation, a computer vision technique where a user provides guidance to help an algorithm segment a feature of interest in an image, has achieved outstanding accuracy and efficient human-computer interaction. However, few…
As Arctic conditions rapidly change, human activity in the Arctic will continue to increase and so will the need for high-resolution observations of sea ice. While satellite imagery can provide high spatial resolution, it is temporally…
Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task.…
We use tools from statistical physics to develop a stochastic theory for the drift of a single Arctic sea-ice floe. Floe-floe interactions are modelled using a Coulomb friction term, with any change in the thickness or the size of the ice…
The Marginal Ice Zone is a highly dynamic region where the atmosphere, ocean, waves and sea ice meet. Waves play a fundamental role in this coupled system, but progress in our understanding of wave-ice interactions is currently hindered by…
Synthetic Aperture Radar (SAR) imagery is the primary data type used for sea ice mapping due to its spatio-temporal coverage and the ability to detect sea ice independent of cloud and lighting conditions. Automatic sea ice detection using…
Sea ice concentration is an important metric used to characterize polar sea ice behavior. Understanding this behavior and accurately representing it is of critical importance for climate science research, and also has important uses in the…
A theoretical model is used to study water waves propagating into and through a region containing thin floating ice, for ice covers transitioning from consolidated (large floe sizes) to fully broken (small floe sizes). The degree of…
Remote sensing semantic segmentation (RSS) is an essential technology in earth observation missions. Due to concerns over geographic information security, data privacy, storage bottleneck and industry competition, high-quality annotated…
At near-grounded glacier termini, calving can lead to the capsize of kilometer-scale unstable icebergs. The transient contact force applied by the capsizing iceberg on the glacier front generates seismic waves that propagate over…
Computer vision and machine learning tools offer an exciting new way for automatically analyzing and categorizing information from complex computer simulations. Here we design an ensemble machine learning framework that can independently…
Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects,…