DAMIE Dayton Annotated Meltponds in  IceBridge Exploration

A High Resolution Annotated  Aerial Imagery Derived from NASA's Operation IceBridge Campaign

We present the Dayton Annotated Meltponds in IceBridge Exploration (DAMIE), a high-resolution aerial imagery dataset derived from NASA’s Operation IceBridge, focusing on Arctic sea ice surface characterization. This dataset comprises 536 Level 1B images captured in July 2016 over the Chukchi Sea, covering a broad area of seasonal sea ice during the melt period. The images, acquired using the Digital Mapping System (DMS), offer a fine spatial resolution of 10 cm, enabling detailed analysis of surface features.

A subset of 170 images was selected for annotation and includes two semantic classes: meltpond and snow. These annotations were manually verified by domain experts, facilitating the development and benchmarking of image segmentation models. The dataset is split into training, validation, and testing partitions and is provided in PNG format (1000x1000x3) to support a wide range of computer vision and geospatial analysis tasks.

The goal of this dataset is to support advancements in deep learning for remote sensing, particularly in understanding meltpond distribution and its implications for Arctic sea ice modeling and climate research.

Related Article: 

Aqsa Sultana, Vijayan K Asari, Ivan Sudakow, and Lee W. Cooper, "ArcticNet: Meltpond Region Localization in the Arctic," TechRxiv, doi.10.36227/techrxiv.173835285.58180903/v1, pp. 1-12, January 2025.. (TechRxiv)

Data Download

The data set is pre-split into training, validation and testing images, with the following categories: snow and meltponds.

The data set is available for download. If you are interested, please complete the DAMIE Download Request Form

Acknowledgments

The data set is created from the original resource National Snow and Ice Data Center

Contact

If you used our DAMIE data set we would love to hear from you! Please consider sending us a message about your results and any feedback you have.
For additional questions about this data set or inquiries about commercial use, please contact vasari1@udayton.edu