English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The large spatial/frequency scale of hyperspectral and airborne magnetic andgravitational data causes memory issues when using convolutional neuralnetworks for (sub-) surface characterization. Recently developed fullyreversible networks can mostly avoid memory limitations by virtue of having alow and fixed memory requirement for storing network states, as opposed to thetypical linear memory growth with depth. Fully reversible networks enable thetraining of deep neural networks that take in entire data volumes, and createsemantic segmentations in one go. This approach avoids the need to work insmall patches or map a data patch to the class of just the central pixel. Thecross-entropy loss function requires small modifications to work in conjunctionwith a fully reversible network and learn from sparsely sampled labels withoutever seeing fully labeled ground truth. We show examples from land-use changedetection from hyperspectral time-lapse data, and regional aquifer mapping fromairborne geophysical and geological data.

Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing