Testing and training data sets for: A novel representation of time-resolved particle emissions from pyrolyzing wood

Biomass burning is responsible for emitting 90% of total primary organic aerosols into the atmosphere. Products from pyrolysis are released to the atmosphere when gas-phase reactions are unable to oxidize them, and even narrow windows of release can produce a large fraction of the overall particle emissions. This work introduces an approach to predict particle emission during high-emitting periods of biomass burning. We trained a regression-based machine learning model to predict particle emission using data from pyrolysis experiments covering seven wood types under controlled conditions. The model considered experimental mass-loss rate (MLR) of the wood, wood density, and heating conditions as features for prediction of measured particle-phase real-time emissions. After training, the experimental mass-loss rate was replaced with modeled MLR from a two-dimensional finite volume model of pyrolysis to predict particle emission rate using only wood properties and the boundary conditions of..., Data collection is described in the associated article and in a related article: M. Fawaz, A. Avery, T.B. Onasch, L.R. Williams, T.C. Bond, Technical note: Pyrolysis principles explain time-resolved organic aerosol release from biomass burning, Atmospheric Chemistry and Physics. 21 (2021) 15605–15618., , # Testing and training data sets for \"A novel representation of time-resolved particle emissions from pyrolyzing wood\"

[https://doi.org/10.5061/dryad.rbnzs7hk6](https://doi.org/10.5061/dryad.rbnzs7hk6)

These files contain measured data from experiments in which solid wood biomass samples, considered thermally thick, were pyrolyzed at different temperatures under nitrogen gas. Mass loss from the wood samples was measured at one-second intervals along with emission rates of pyrolysis products. Further details, especially of the particulate measurement, are contained in the referenced papers.

Testing and training data sets were separated using a k-fold split.

## Description of the data and file structure

Two files are given

PyroPredict_training_set.csv: Data set used to train the gradient boosting regressor machine learning algorithm

PyroPredict_testing_set.csv: Data set used to test the algorithm's output

Each file contains the following columns:

MLR: Mass loss rate (g/s)

CO: Ca...