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

Land-use regression (LUR) models are important for the assessment of airpollution concentrations in areas without measurement stations. While many suchmodels exist, they often use manually constructed features based on restricted,locally available data. Thus, they are typically hard to reproduce andchallenging to adapt to areas beyond those they have been developed for. Inthis paper, we advocate a paradigm shift for LUR models: We propose theData-driven, Open, Global (DOG) paradigm that entails models based on purelydata-driven approaches using only openly and globally available data. Progresswithin this paradigm will alleviate the need for experts to adapt models to thelocal characteristics of the available data sources and thus facilitate thegeneralizability of air pollution models to new areas on a global scale. Inorder to illustrate the feasibility of the DOG paradigm for LUR, we introduce adeep learning model called MapLUR. It is based on a convolutional neuralnetwork architecture and is trained exclusively on globally and openlyavailable map data without requiring manual feature engineering. We compare ourmodel to state-of-the-art baselines like linear regression, random forests andmulti-layer perceptrons using a large data set of modeled $\text{NO}_2$concentrations in Central London. Our results show that MapLUR significantlyoutperforms these approaches even though they are provided with manuallytailored features. Furthermore, we illustrate that the automatic featureextraction inherent to models based on the DOG paradigm can learn features thatare readily interpretable and closely resemble those commonly used intraditional LUR approaches.

MapLUR: Exploring a new Paradigm for Estimating Air Pollution using Deep Learning on Map Images