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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Convolutional Neural Networks (CNN) possess many positive qualities when itcomes to spatial raster data. Translation invariance enables CNNs to detectfeatures regardless of their position in the scene. However, in some domains,like geospatial, not all locations are exactly equal. In this work, we proposelocalized convolutional neural networks that enable convolutional architecturesto learn local features in addition to the global ones. We investigate theirinstantiations in the form of learnable inputs, local weights, and a moregeneral form. They can be added to any convolutional layers, easily end-to-endtrained, introduce minimal additional complexity, and let CNNs retain most oftheir benefits to the extent that they are needed. In this work we addressspatio-temporal prediction: test the effectiveness of our methods on asynthetic benchmark dataset and tackle three real-world wind predictiondatasets. For one of them, we propose a method to spatially order the unordereddata. We compare the recent state-of-the-art spatio-temporal prediction modelson the same data. Models that use convolutional layers can be and are extendedwith our localizations. In all these cases our extensions improve the results,and thus often the state-of-the-art. We share all the code at a publicrepository.

Localized convolutional neural networks for geospatial wind forecasting