Articles | Volume 22, issue 3
https://doi.org/10.5194/acp-22-1861-2022
https://doi.org/10.5194/acp-22-1861-2022
Research article
 | 
08 Feb 2022
Research article |  | 08 Feb 2022

Input-adaptive linear mixed-effects model for estimating alveolar lung-deposited surface area (LDSA) using multipollutant datasets

Pak Lun Fung, Martha A. Zaidan, Jarkko V. Niemi, Erkka Saukko, Hilkka Timonen, Anu Kousa, Joel Kuula, Topi Rönkkö, Ari Karppinen, Sasu Tarkoma, Markku Kulmala, Tuukka Petäjä, and Tareq Hussein

Data sets

SmartSMEAR – About University of Helsinki https://smear.avaa.csc.fi/

Open data Helsinki Region Environmental Services HSY https://www.hsy.fi/avoindata

Download
Short summary
We developed an input-adaptive mixed-effects model, which was automatised to select the best combination of input variables, including up to three fixed effect variables and three time indictors as random effect variables. We tested the model to estimate lung-deposited surface area (LDSA), which correlates well with human health. The results show the inclusion of time indicators improved the sensitivity and the accuracy of the model so that it could serve as a network of virtual sensors.
Altmetrics
Final-revised paper
Preprint