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

Atmospheric simulations for urban cities can be computationally intensivebecause of the need for high spatial resolution, such as a few meters, toaccurately represent buildings and streets. Deep learning has recently gainedattention across various physical sciences for its potential to reducecomputational cost. Super-resolution is one such technique that enhances theresolution of data. This paper proposes a convolutional neural network (CNN)that super-resolves instantaneous snapshots of three-dimensional airtemperature and wind velocity fields for urban micrometeorology. Thissuper-resolution process requires not only an increase in spatial resolutionbut also the restoration of missing data caused by the difference in thebuilding shapes that depend on the resolution. The proposed CNN incorporatesgated convolution, which is an image inpainting technique that infers missingpixels. The CNN performance has been verified via supervised learning utilizingbuilding-resolving micrometeorological simulations around Tokyo Station inJapan. The CNN successfully reconstructed the temperature and velocity fieldsaround the high-resolution buildings, despite the missing data at loweraltitudes due to the coarseness of the low-resolution buildings. This resultimplies that near-surface flows can be inferred from flows above buildings.This hypothesis was assessed via numerical experiments where all input valuesbelow a certain height were made missing. This research suggests thepossibility that building-resolving micrometeorological simulations become morepractical for urban cities with the aid of neural networks that enhancecomputational efficiency.

Super-Resolution of Three-Dimensional Temperature and Velocity for  Building-Resolving Urban Micrometeorology Using Physics-Guided Convolutional  Neural Networks with Image Inpainting Techniques