BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Methods for dealing with sparse and incomplete environmental datas
 ets - Ann Gledson and Doug Lowe | University of Manchester
DTSTART:20210316T110000Z
DTEND:20210316T123000Z
UID:TALK155401@talks.cam.ac.uk
CONTACT:Tudor Suciu
DESCRIPTION:Whilst the importance of quantifying the impacts of detrimenta
 l air quality remains a global priority for both researchers and policy ma
 kers\, transparent methodologies that support the collection and manipulat
 ion of such data are currently lacking. In support of the Britain Breathin
 g citizen science project\, aiming to investigate the possible interaction
 s between meteorological or air quality events and seasonal allergy sympto
 ms\, we have built a comprehensive data-set\, and a web application: ‘Mi
 ne the Gaps’\, which present daily air quality\, pollen and weather read
 ings from the Automatic Urban and Rural Network (AURN) and Met Office moni
 toring stations in the years 2016 to 2019 inclusive\, for the United Kingd
 om. \n\nMeasurement time series are rarely fully complete so we have used 
 machine learning techniques to fill in gaps in these records to ensure as 
 good coverage as possible. To address sparse regional coverage\, we propos
 e a simple baseline method called concentric regions. ‘Mine the Gaps’ 
 can be used for graphically exploring and comparing the imputed dataset an
 d the regional estimations. The application code is designed to be reusabl
 e and flexible so it can be used to interrogate other geographical dataset
 s. \n\nIn this talk we will cover the development of these datasets - disc
 ussing some of the choices that we made\, as well as how reliable the impu
 tation and estimation processes are for the different meteorological and a
 ir quality measurements. We will also demonstrate the ‘Mine the Gaps’ 
 application.\n\nThe datasets that we discuss in this talk are available to
  download at https://zenodo.org/record/4416028 and https://zenodo.org/reco
 rd/4475652.  The data processing toolkit is written in python (and uses sc
 ikit-learn for the machine learning processes) and is available at https:/
 /zenodo.org/record/4545257. The regional estimation code is written in pyt
 hon and available at https://zenodo.org/record/4518866. The ‘Mine the Ga
 ps’ application is written in Python\, using the Django web framework an
 d can be accessed at http://minethegaps.manchester.ac.uk. The code reposit
 ory will be linked to from the website when it is released.\n
LOCATION:https://zoom.us/j/6708259482?pwd=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09
END:VEVENT
END:VCALENDAR