Environmental Health Insights (Mar 2017)

Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK

  • Xun Liu,
  • Daji Wu,
  • Gebreab K Zewdie,
  • Lakitha Wijerante,
  • Christopher I Timms,
  • Alexander Riley,
  • Estelle Levetin,
  • David J Lary

DOI
https://doi.org/10.1177/1178630217699399
Journal volume & issue
Vol. 11

Abstract

Read online

This article describes an example of using machine learning to estimate the abundance of airborne Ambrosia pollen for Tulsa, OK. Twenty-seven years of historical pollen observations were used. These pollen observations were combined with machine learning and a very complete meteorological and land surface context of 85 variables to estimate the daily Ambrosia abundance. The machine learning algorithms employed were Least Absolute Shrinkage and Selection Operator (LASSO), neural networks, and random forests. The best performance was obtained using random forests. The physical insights provided by the random forest are also discussed.