• Home
  • Search
  • Improving 3-day deterministic air pollution forecasts using machine learning algorithms
  • Cite Icon27
  • https://doi.org/10.5194/acp-24-807-2024Copy DOI Icon

Improving 3-day deterministic air pollution forecasts using machine learning algorithms

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract. As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms – random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) – to improve 1, 2, and 3 d deterministic forecasts of PM10, NOx, and O3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60 %, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations.

Similar Papers
  • PDF
  • Research Article
  • Citations56

Application of ANN, XGBoost, and Other ML Methods to Forecast Air Quality in Macau

  • Mar 17, 2023
  • Sustainability
  • Thomas M T Lei +2
  • Research Article
  • Citations2

Protocol for the development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data.

  • Jan 07, 2025
  • medRxiv : the preprint server for health sciences
  • Jiawen Deng +2
  • Research Article

Machine learning models to predict skeletal-related events in bone metastasis from advanced cancer.

  • Jun 01, 2025
  • Journal of Clinical Oncology
  • Hirotaka Miyashita +1
  • Research Article

Predicting non-compliance to pancreatic enzyme supplementation therapy in chronic pancreatitis: A machine learning-based approach.

  • Dec 27, 2025
  • Indian journal of gastroenterology : official journal of the Indian Society of Gastroenterology
  • Anjali Srikanth Mannava +7
  • PDF
  • Research Article
  • Citations42

Prediction of shear behavior of glass FRP bars-reinforced ultra-highperformance concrete I-shaped beams using machine learning

  • Aug 30, 2023
  • International Journal of Mechanics and Materials in Design
  • Asif Ahmed +6
  • Research Article
  • Citations5

Application of Machine Learning to Interpret Steady-State Drainage Relative Permeability Experiments

  • Mar 22, 2023
  • SPE Reservoir Evaluation & Engineering
  • Eric Sonny Mathew +4
  • Research Article
  • Citations13

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

  • Apr 18, 2024
  • Transportation Geotechnics
  • Xuefeng An +5
  • Research Article
  • Citations17

Machine learning algorithm to predict the in-hospital mortality in critically ill patients with chronic kidney disease

  • May 19, 2023
  • Renal Failure
  • Xunliang Li +6
  • PDF
  • Research Article
  • Citations11

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

  • May 23, 2023
  • Energies
  • Sun-Feel Yang +2
  • Conference Article

Nanomaterial-Enhanced Organic-Rich Shales: Data-Driven Insights into Wettability Predictions for Underground Hydrogen Storage Design

  • Sep 16, 2025
  • Zeeshan Tariq +3
  • Research Article
  • Citations77

Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

  • Nov 13, 2023
  • BMC medical research methodology
  • Yinan Huang +3
  • Research Article

Development and comparison of machine learning models for predicting moderate-to-severe tinnitus in patients with hearing loss

  • Jan 12, 2026
  • Frontiers in Neurology
  • Chenguang Zhang +6
  • Research Article
  • Citations4

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review

  • Nov 23, 2022
  • Journal of Neurological Surgery. Part B, Skull Base
  • Darrion B Yang +7
  • Conference Article
  • Citations5

Evaluating explainable artificial intelligence (XAI): algorithmic explanations for transparency and trustworthiness of ML algorithms and AI systems

  • Jun 06, 2022
  • Utsab B Khakurel +1
  • PDF
  • Research Article
  • Citations36

Hybrid systems using residual modeling for sea surface temperature forecasting

  • Jan 11, 2022
  • Scientific Reports
  • Paulo S G De Mattos Neto +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.