Interactive Visualization and Representation Analysis Applied to Glacier Segmentation

Bibliographic Data

ID22034544
AuthorsMinxing Zheng (University of Wisconsin–Madison), Xinran Miao (0000-0001-5449-1093, University of Wisconsin–Madison), Kris Sankaran (0000-0002-9415-1971, University of Wisconsin–Madison, corresponding author)
Year2022
Volume11
Issue8
Pages415
Publication date2022-07-22
Open AccessYes
TypeARTICLE
VenueISPRS International Journal of Geo-Information (JOURNAL)
Journal identifiersISSN: 2220-9964 • E-ISSN: 2220-9964
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/ijgi11080415
OpenAlexW4286587727
LanguageEN
References cited20

Interpretability has attracted increasing attention in earth observation problems. We apply interactive visualization and representation analysis to guide the interpretation of glacier segmentation models. We visualize the activations from a U-Net to understand and evaluate the model performance. We built an online interface using the Shiny R package to provide comprehensive error analysis of the predictions. Users can interact with the panels and discover model failure modes. We illustrate an example of how our interface could help guide decisions for improving model performance. Further, we discuss how visualization can provide sanity checks during data preprocessing and model training. By closely examining the problem of glacier segmentation, we are able to discuss how visualization strategies can support the modeling process and the interpretation of prediction results from geospatial deep learning

Data mining · Data science · Data visualization · Geospatial analysis · Human–computer interaction · Interpretability · Machine learning · Preprocessor · Remote sensing · Segmentation · Visual analytics · Visualization · Computer Science · Data Analysis with R · Data Visualization and Analytics · Species Distribution and Climate Change · Artificial Intelligence · Geology

Tools

Open DOIOpen Access