Southern Ocean Marginal Ice Zone Photographs from a 2019 Winter Research Cruise (SA Agulhas II)

Vos, Marc de; Ramjukadh, Carla-Louise; Liesker, Christina Gabriele; Villiers, Mardené De; Lyttle, Casey Tara

doi:10.1594/pangaea.905497

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A secondary objective for this investigation was to compare estimates made by the existing numerical sea ice concentration models with a set of recent in situ observations. A 2019 research expedition to the MIZ in the Southern Ocean collected a large set of geotagged images of the sea ice conditions [9]. This kind of comparison is ideal for understanding the validity of the existing models in the Southern Ocean where extensive in situ observation data is lacking.…”

Section: Evaluation Interfacesmentioning

confidence: 99%

Sea ice concentration estimation techniques using machine learning: an end-to-end workflow for estimating concentration maps from SAR images

Dominicus

Mishra

Rautenbach

2021

New Methodologies for Understanding Radar Data

View full text Add to dashboard Cite

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 context of maritime navigation. An end-to-end workflow for generating learned concentration estimation models from synthetic aperture radar data, trained on existing passive microwave data, is presented here. A novel objective function was introduced to account for uncertainty in the passive microwave measurements, which can be extended to account for arbitrary sources of error in the training data, and a recent set of in-situ observations was used to evaluate the reliability of the chosen passive microwave concentration estimation model. Google Colaboratory was used as the development platform, and all notebooks, training data, and trained models are available on GitHub. This chapter is an overview of the most interesting aspects of this investigation, and a detailed report is also available on GitHub.

show abstract

Section: Evaluation Interfacesmentioning

confidence: 99%