Collaborative Research: CAIG: Weakly Supervised Learning to Address Label-Data Irregularities in Sea-Ice Classification

NSF Award Search · 01002526DB NSF RESEARCH & RELATED ACTIVIT · $805,132 · view on nsf.gov ↗

Abstract

Arctic sea ice plays a crucial role in regulating global climate. Accordingly, monitoring sea ice conditions and mapping its properties, such as type, extent, and concentration, are important for climate monitoring as well as marine navigation and near- or off-shore operations. This project will address data availability and bottlenecks in manually producing maps of sea ice by applying artificial intelligence (AI) methods to the problem. The project will introduce novel AI driven methods to effectively learn from existing label data, despite its irregularities, in order to automate sea ice classification. The intellectual merits of the proposed project are novel weakly supervised techniques that are aware of irregularities with existing label data for sea ice classification and provide methodological solutions to address these irregularities for improved sea ice classification performance. For Ill-formed Labels (i.e., coarse polygon-level annotations that fail to reflect spatial detail at the pixel-level required for typical methods) the sea ice classification problem will be reformulated and addressed with polygon-level data as a multi-instance, multi-label proportion learning problem. For Inaccurate Labels (i.e., uncertain annotations due to human subjectivity, ambiguous concentration ranges, or class trimming protocols) confidence-aware sample selection and uncertainty quantification will be embedded directly into model training via a hybrid strategy that combines loss

Key facts

NSF award ID
2531101
Awardee
University of Colorado at Denver (CO)
SAM.gov UEI
MW8JHK6ZYEX8
PI
Farnoush Banaei-Kashani
Primary program
01002526DB NSF RESEARCH & RELATED ACTIVIT
All programs
Artificial Intelligence (AI)
Estimated total
$805,132
Funds obligated
$805,132
Transaction type
Standard Grant
Period
09/01/2025 → 08/31/2028