Articles | Volume 11, issue 11
https://doi.org/10.5194/amt-11-6203-2018
https://doi.org/10.5194/amt-11-6203-2018
Research article
 | 
19 Nov 2018
Research article |  | 19 Nov 2018

Machine learning for improved data analysis of biological aerosol using the WIBS

Simon Ruske, David O. Topping, Virginia E. Foot, Andrew P. Morse, and Martin W. Gallagher

Model code and software

simonruske/AMT-2018-126: Code release upon acceptance (Version 1.0.0) S. Ruske https://doi.org/10.5281/zenodo.1478082

simonruske/UVLIF: Pre-release of software (Version 0.0.1) S. Ruske https://doi.org/10.5281/zenodo.1478098

Download
Short summary
Pollen, bacteria and fungal spores are common in the environment, can have very important implications for public health and may influence the weather. Biological sensors potentially could be used to monitor quantities of these types of particles. However, it is important to transform the measurements from these instruments into counts of these biological particles. The paper tests a variety of approaches for achieving this aim on data collected in a laboratory.