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

This study presents a comparative analysis of three predictive models with anincreasing degree of flexibility: hidden dynamic geostatistical models (HDGM),generalised additive mixed models (GAMM), and the random forest spatiotemporalkriging models (RFSTK). These models are evaluated for their effectiveness inpredicting PM$_{2.5}$ concentrations in Lombardy (North Italy) from 2016 to2020. Despite differing methodologies, all models demonstrate proficientcapture of spatiotemporal patterns within air pollution data with similarout-of-sample performance. Furthermore, the study delves into station-specificanalyses, revealing variable model performance contingent on localisedconditions. Model interpretation, facilitated by parametric coefficientanalysis and partial dependence plots, unveils consistent associations betweenpredictor variables and PM$_{2.5}$ concentrations. Despite nuanced variationsin modelling spatiotemporal correlations, all models effectively accounted forthe underlying dependence. In summary, this study underscores the efficacy ofconventional techniques in modelling correlated spatiotemporal data,concurrently highlighting the complementary potential of Machine Learning andclassical statistical approaches.

Spatiotemporal modelling of PM$_{2.5}$ concentrations in Lombardy (Italy) -- A comparative study