Sentence examples for air quality classifications from inspiring English sources

Present a self-organizing map (SOM) framework for creating ambient air quality classifications that group days with similar multipollutant profiles.

In this study, we present the self-organizing map (SOM) as a tool to create ambient air quality classifications because the method offers the benefit of a visual medium (the 'map') that can be useful for understanding classification results [ 15].

We find SOM to be an attractive framework for developing ambient air quality classification because the approach eases interpretation of results by allowing users to visualize classifications on an organized map.

To address our first set of research questions, we apply an unsupervised learning tool known as the self-organizing map (SOM) [Pearce, Waller et al. (2014) explain the use of SOMs for ambient air quality classification] to develop categories of days (i.e., multipollutant day types) based on ambient air quality data that reflect how multipollutant combinations vary in time at our study location.

This is appealing to health investigators because classification of complex multipollutant data into specific categories can elucidate combinatorial patterns of interest and can be used to compare risk of an adverse health outcome observed within one air quality classification to that observed in another.

WHO has just published new guidelines on indoor air quality and recently revised its classification and treatment of childhood pneumonia at health facilities to increase effective lifesaving interventions.

We find SOM to be an attractive framework for classifying day types for ambient air quality characterization because the approach produces classifications equivalent to traditional techniques with the benefit of a map that provides an organized visualization of class profiles.

France has a national standardized classification system for air quality monitoring stations.

Such approaches show promise toward using classification for ambient air quality mixtures research; however, many challenges remain [ 1, 3].

It is important to note that the relatively specific nature of our classification captures transitions in air quality that are rather subtle in nature (e.g., transition from a moderate secondary day to a high secondary day).

Our application of SOM provides an unsupervised approach to producing classification systems for summarizing ambient air quality as a collection of day types.