Open AccessPosted Content
A data-driven approach to the forecasting of ground-level ozone concentration.
TLDR
A machine learning approach applied to the forecast of the day-ahead maximum value of the ozone concentration for several geographical locations in southern Switzerland suggests that the trained models effectively learned explanatory cross-dependencies among atmospheric variables, which are described in the ozone photochemistry literature.Abstract:
The ability to forecast the concentration of air pollutants in an urban region is crucial for decision-makers wishing to reduce the impact of pollution on public health through active measures (e.g. temporary traffic closures). In this study, we present a machine learning approach applied to the forecast of the day-ahead maximum value of the ozone concentration for several geographical locations in southern Switzerland. Due to the low density of measurement stations and to the complex orography of the use case terrain, we adopted feature selection methods instead of explicitly restricting relevant features to a neighbourhood of the prediction sites, as common in spatio-temporal forecasting methods. We then used Shapley values to assess the explainability of the learned models in terms of feature importance and feature interactions in relation to ozone predictions; our analysis suggests that the trained models effectively learned explanatory cross-dependencies among atmospheric variables. Finally, we show how weighting observations helps in increasing the accuracy of the forecasts for specific ranges of ozone's daily peak values.read more
Citations
More filters
Journal ArticleDOI
Multi-source and multivariate ozone prediction based on fuzzy cognitive maps and evidential reasoning theory
TL;DR: In this paper , a multi-source and multivariate ozone prediction model based on fuzzy cognitive maps (FCMs) and evidential reasoning theory from the perspective of spatio-temporal fusion, termed as ERC-FCM, is proposed.
Journal ArticleDOI
Spatiotemporal prediction of O3 concentration based on the KNN-Prophet-LSTM model
TL;DR: In this article , a prediction method based on the KNN-Prophet-LSTM hybrid model is established by using the daily pollutant concentration data of Wuhan from January 1, 2014, to May 3, 2021, and considering the characteristics of time and space.
Journal ArticleDOI
A comparison of machine learning methods for ozone pollution prediction
Fouzi Harrou,Ying Sun +1 more
TL;DR: In this paper , the authors evaluated the predictive performance of nineteen machine learning models for ozone pollution prediction and investigate using time-lagged measurements to improve prediction accuracy, showing that dynamic models using timelagged data outperformed static and reduced machine learning.
References
More filters
Journal ArticleDOI
Data mining methods for prediction of air pollution
TL;DR: The paper shows that preselection of the most important features, cooperating with an ensemble of predictors, allows increasing the forecasting accuracy of atmospheric pollution in a significant way.
Journal ArticleDOI
Development of nonlinear empirical models to forecast daily PM2.5 and ozone levels in three large Chinese cities
TL;DR: In this article, empirical regression models for next-day forecasting of PM 2.5 and O 3 air pollution concentrations have been developed and evaluated for three large Chinese cities, Beijing, Nanjing and Guangzhou.
Posted Content
A real-time hourly ozone prediction system using deep convolutional neural network
TL;DR: In this paper, a deep convolutional neural network (CNN) was employed to forecast ozone concentrations over Seoul, South Korea for 2017, using several predictors from the previous day, including the wind fields, temperature, relative humidity, pressure, and precipitation.
Journal ArticleDOI
Linking Air Quality and Human Health Effects Models: An Application to the Los Angeles Air Basin.
Devoun R Stewart,Emily Saunders,Roberto Perea,Rosa M. Fitzgerald,David E. Campbell,William R. Stockwell,William R. Stockwell,William R. Stockwell +7 more
TL;DR: Air quality changes due to several emission control strategies that could be implemented between 2008 and 2030 for the South Coast Air Basin that includes Los Angeles are forecasted.
Posted Content
NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Tony Duan,Anand Avati,Daisy Yi Ding,Khanh K. Thai,Sanjay Basu,Andrew Y. Ng,Alejandro Schuler +6 more
TL;DR: NGBoost generalizes gradient boosting to probabilistic regression by treating the parameters of the conditional distribution as targets for a multiparameter boosting algorithm, and shows how the Natural Gradient is required to correct the training dynamics of the authors' multiparameters boosting approach.
Related Papers (5)
Hybrid Model for Urban Air Pollution Forecasting: A Stochastic Spatio-Temporal Approach
Ana Russo,Amílcar Soares +1 more