
Ecological Indicators, Journal Year: 2024, Volume and Issue: 169, P. 112836 - 112836
Published: Nov. 14, 2024
Language: Английский
Ecological Indicators, Journal Year: 2024, Volume and Issue: 169, P. 112836 - 112836
Published: Nov. 14, 2024
Language: Английский
Journal of Contaminant Hydrology, Journal Year: 2024, Volume and Issue: 269, P. 104480 - 104480
Published: Dec. 10, 2024
Language: Английский
Citations
6Frontiers in Big Data, Journal Year: 2025, Volume and Issue: 7
Published: Jan. 15, 2025
Atmospheric ozone chemistry involves various substances and reactions, which makes it a complex system. We analyzed data recorded by Switzerland's National Air Pollution Monitoring Network (NABEL) to showcase the capabilities of machine learning (ML) for prediction concentrations (daily averages) document general approach that can be followed anyone facing similar problems. evaluated artificial neural networks compared them linear as well non-linear models deduced with ML. The main analyses training were performed on atmospheric air from 2016 2023 at NABEL station Lugano-Università in Lugano, TI, Switzerland. As first step, we used techniques like best subset selection determine measurement parameters might relevant concentrations; general, identified these methods agree chemistry. Based results, constructed predict Lugano period between January 1, 2024, March 31, 2024; then, output our actual measurements repeated this procedure two stations situated northern Switzerland (Dübendorf-Empa Zürich-Kaserne). For stations, predictions made aforementioned 2023, December 2023. In most cases, lowest mean absolute errors (MAE) provided model 12 components (different powers combinations NO 2 , X SO non-methane volatile organic compounds, temperature radiation); MAE predicted was low 9 μgm −3 . Zürich Dübendorf, MAEs around 11 13 respectively. tested periods, accuracy approximately 1 Since values are all lower than standard deviations observations conclude using ML very helpful do not necessarily outperform simpler models.
Language: Английский
Citations
0Water Conservation Science and Engineering, Journal Year: 2025, Volume and Issue: 10(1)
Published: March 10, 2025
Language: Английский
Citations
0Applied Water Science, Journal Year: 2025, Volume and Issue: 15(5)
Published: April 29, 2025
Language: Английский
Citations
0Results in Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 102306 - 102306
Published: May 1, 2025
Language: Английский
Citations
0Ecological Indicators, Journal Year: 2024, Volume and Issue: 169, P. 112836 - 112836
Published: Nov. 14, 2024
Language: Английский
Citations
0