Multi-Contextual Learning : Analyzing Melt Over the Greenland Ice Sheet

Thumbnail Image

Files

10426456.pdf (580.91 KB)

Links to Files

https://ieeexplore.ieee.org/document/10281954/

Permanent Link

https://doi.org/10.1109/IGARSS52108.2023.10281954
 http://hdl.handle.net/11603/35806

Collections

UMBC Faculty Collection
UMBC Information Systems Department
UMBC Student Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0009-0006-1164-003X
 https://orcid.org/0000-0003-0130-6135

Date

2023-07

Type of Work

conference papers and proceedings
postprints
Text

Department

Program

Citation of Original Publication

Kulkarni, Chhaya, Vandana Janeja, and Nicole-Jeanne Schlegel. “Multi-Contextual Learning : Analyzing Melt Over the Greenland Ice Sheet.” In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, 6736–39, 2023. https://doi.org/10.1109/IGARSS52108.2023.10281954.

Rights

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Subjects

Analytical models
Spatial databases
Semantics
Statistical analysis
Data models
Market research
spatiotemporal data
multi-contextual learning
Spatiotemporal phenomena
neighborhood discovery
Greenland ice sheet

Abstract

Climate data related to polar regions has been extensively studied through model simulations, remote sensed images, and statistical analysis. Knowledge discovery tasks, if applied to the Arctic data, can capture the associations, anomalies, and interesting patterns and trends that exist in the data to inform the polar scientists. This can help improve the certainty in the models with better local information. In this study, we propose a framework that develops multi-contextual spatiotemporal neighborhoods, addressing spatial autocorrelation and heterogeneity taking into account data from multiple views or contexts, to identify local homogeneous regions across the entire Greenland Ice Sheet. Using these neighborhoods, we study how local regions in the Greenland ice sheet evolve over time. This framework can expand to include additional contextual variables and help polar scientists study local ice surface melt phenomena across multiple contexts. Novelty of our approach lies in its ability to consider the Greenland data from spatial, temporal and semantic contexts that allows us to build a comprehensive understanding of a specific phenomenon such as snowmelt.