Forecasting Smog Clouds With Deep Learning

Valentijn Oldenburg; Juan Cardenas-Cartagena; Matias Valdenegro-Toro

Forecasting Smog Clouds With Deep Learning

Machine Learning 2024-10-04 v1

Authors: Valentijn Oldenburg , Juan Cardenas-Cartagena , Matias Valdenegro-Toro

Abstract

In this proof-of-concept study, we conduct multivariate timeseries forecasting for the concentrations of nitrogen dioxide (NO2), ozone (O3), and (fine) particulate matter (PM10 & PM2.5) with meteorological covariates between two locations using various deep learning models, with a focus on long short-term memory (LSTM) and gated recurrent unit (GRU) architectures. In particular, we propose an integrated, hierarchical model architecture inspired by air pollution dynamics and atmospheric science that employs multi-task learning and is benchmarked by unidirectional and fully-connected models. Results demonstrate that, above all, the hierarchical GRU proves itself as a competitive and efficient method for forecasting the concentration of smog-related pollutants.

Keywords

air quality modeling time series forecasting long short-term memory

Cite

@article{arxiv.2410.02759,
  title  = {Forecasting Smog Clouds With Deep Learning},
  author = {Valentijn Oldenburg and Juan Cardenas-Cartagena and Matias Valdenegro-Toro},
  journal= {arXiv preprint arXiv:2410.02759},
  year   = {2024}
}

Related papers

View all related →