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

. Severe haze or low-visibility events caused by abundantatmospheric aerosols have become a serious environmental issue in manycountries. A framework based on deep convolutional neural networkscontaining more than 20 million parameters called HazeNet has beendeveloped to forecast the occurrence of such events in two Asian megacities:Beijing and Shanghai. Trained using time-sequential regional maps of up to16 meteorological and hydrological variables alongside surface visibilitydata over the past 41 years, the machine has achieved a good overallperformance in identifying haze versus non-haze events, and thus theirrespective favorable meteorological and hydrological conditions, with avalidation accuracy of 80 % in both the Beijing and Shanghai cases, exceedingthe frequency of non-haze events or no-skill forecasting accuracy, and an F1score specifically for haze events of nearly 0.5. Its performance is clearlybetter during months with high haze frequency, i.e., all months exceptdusty April and May in Beijing and from late autumn through all of winter inShanghai. Certain valuable knowledge has also obtained from the training,such as the sensitivity of the machine's performance to the spatial scale offeature patterns, that could benefit future applications using meteorologicaland hydrological data. Furthermore, an unsupervised cluster analysis usingfeatures with a greatly reduced dimensionality produced by the trainedHazeNet has, arguably for the first time, successfully categorized typicalregional meteorological–hydrological regimes alongside local quantitiesassociated with haze and non-haze events in the two targetedcities, providing substantial insights to advance our understandings of thisenvironmental extreme. Interesting similarities in associated weather andhydrological regimes between haze and false alarm clusters or differencesbetween haze and missing forecasting clusters have also been revealed,implying that factors, such as energy-consumption variation and long-rangeaerosol transport, could also influence the occurrence of hazes,even under unfavorable weather conditions.

atmospheric chemistry and physics

Forecasting and identifying the meteorological and hydrological conditions favoring the occurrence of severe hazes in Beijing and Shanghai using deep learning