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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The detection and analysis of transient astronomical sources is of greatimportance to understand their time evolution. Traditional pipelines identifytransient sources from difference (D) images derived by subtractingprior-observed reference images (R) from new science images (N), a process thatinvolves extensive manual inspection. In this study, we present TransientViT, ahybrid convolutional neural network (CNN) - vision transformer (ViT) model todifferentiate between transients and image artifacts for the KilodegreeAutomatic Transient Survey (KATS). TransientViT utilizes CNNs to reduce theimage resolution and a hierarchical attention mechanism to model featuresglobally. We propose a novel KATS-T 200K dataset that combines the differenceimages with both long- and short-term images, providing a temporallycontinuous, multidimensional dataset. Using this dataset as the input,TransientViT achieved a superior performance in comparison to othertransformer- and CNN-based models, with an overall area under the curve (AUC)of 0.97 and an accuracy of 99.44%. Ablation studies demonstrated the impact ofdifferent input channels, multi-input fusion methods, and cross-inferencestrategies on the model performance. As a final step, a voting-based ensembleto combine the inference results of three NRD images further improved themodel's prediction reliability and robustness. This hybrid model will act as acrucial reference for future studies on real/bogus transient classification.

TransientViT: A novel CNN - Vision Transformer hybrid real/bogus transient classifier for the Kilodegree Automatic Transient Survey