Saved in:
Bibliographic Details
Main Authors: Oldenburg, Valentijn, Cardenas-Cartagena, Juan, Valdenegro-Toro, Matias
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.02759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914963630587904
author Oldenburg, Valentijn
Cardenas-Cartagena, Juan
Valdenegro-Toro, Matias
author_facet Oldenburg, Valentijn
Cardenas-Cartagena, Juan
Valdenegro-Toro, Matias
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Forecasting Smog Clouds With Deep Learning
Oldenburg, Valentijn
Cardenas-Cartagena, Juan
Valdenegro-Toro, Matias
Machine Learning
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.
title Forecasting Smog Clouds With Deep Learning
topic Machine Learning
url https://arxiv.org/abs/2410.02759