MétaCan
Menu
Back to cohort

Sea Ice Image Semantic Segmentation Using Deep Neural Networks

2020· article· en· W3154253854 on OpenAlexafffund
Benjamin Dowden, Oscar De Silva, Weimin Huang

Bibliographic record

VenueGlobal Oceans 2020: Singapore – U.S. Gulf Coast · 2020
Typearticle
Languageen
FieldEarth and Planetary Sciences
TopicArctic and Antarctic ice dynamics
Canadian institutionsMemorial University of Newfoundland
FundersCanadian Space AgencyMemorial University of Newfoundland
KeywordsComputer scienceSegmentationArtificial intelligenceImage segmentationPixelDeep learningArtificial neural networkRemote sensingProcess (computing)Computer visionPattern recognition (psychology)Geology

Abstract

fetched live from OpenAlex

Semantic segmentation is the process of classifying pixels in an image into different classes. This method is quite established in autonomous vehicles, biomedical image processing, and remote sensing applications. In this paper, we evaluate the applicability of semantic segmentation for sea ice classification using image feeds from on-board an icebreaker. For this purpose, we evaluate SegNet and PSPNet101 neural network architectures to segment images into four classes: ice, ocean, vessel, and sky. The Nathaniel B. Palmer dataset, which captures 2-month footage of the icebreaker completing an Antarctic expedition was used. A subset of the dataset was labeled to generate a 240-image dataset achieving an accuracy of 97.8% classification for the 26 image test dataset. These results validate the applicability of deep learning methods for sea ice detection using images, which can be further improved by classifying the ice type to support marine navigation and mapping applications.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.681
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.225
Teacher spread0.213 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2020
Admission routes2
Has abstractyes

Explore more

Same venueGlobal Oceans 2020: Singapore – U.S. Gulf CoastSame topicArctic and Antarctic ice dynamicsFrench-language works237,207