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

As cyclones become more intense due to climate change, the rise of AI-basedmodelling provides a more affordable and accessible approach compared totraditional methods based on mathematical models. This work leverages diffusionmodels to forecast cyclone trajectories and precipitation patterns byintegrating satellite imaging, remote sensing, and atmospheric data, employinga cascaded approach that incorporates forecasting, super-resolution, andprecipitation modelling, with training on a dataset of 51 cyclones from sixmajor basins. Experiments demonstrate that the final forecasts from thecascaded models show accurate predictions up to a 36-hour rollout, with SSIMand PSNR values exceeding 0.5 and 20 dB, respectively, for all three tasks.This work also highlights the promising efficiency of AI methods such asdiffusion models for high-performance needs, such as cyclone forecasting, whileremaining computationally affordable, making them ideal for highly vulnerableregions with critical forecasting needs and financial limitations. Codeaccessible at \url{https://github.com/nathzi1505/forecast-diffmodels}.

Forecasting Tropical Cyclones with Cascaded Diffusion Models