Comparing quantile regression methods for probabilistic forecasting of NO2 pollution levels

Abstract

High concentration episodes for NO2 are increasingly dealt with by authorities through traffic restrictions which are activated when air quality deteriorates beyond certain thresholds. Foreseeing the probability that pollutant concentrations reach those thresholds becomes thus a necessity. Probabilistic forecasting, as oposed to point-forecasting, is a family of techniques that allow for the prediction of the expected distribution function instead of a single future value. In the case of NO2, it allows for the calculation of future chances of exceeding thresholds and to detect pollution peaks. However, there is a lack of comparative studies for probabilistic models in the field of air pollution. In this work, we thoroughly compared 10 state of the art quantile regression models, using them to predict the distribution of NO2 concentrations in a urban location for a set of forecasting horizons (up to 60 hours into the future). Instead of using directly the quantiles, we derived from them the parameters of a predicted distribution, rendering this method semi-parametric. Amongst the models tested, quantile gradient boosted trees show the best performance, yielding the best results for both expected point value and full distribution. However, we found the simpler quantile k-nearest neighbors combined with a linear regression provided similar results with much lower training time and complexity.

Deep Ensemble Machine Learning Framework for the Estimation of PM2.5 Concentrations

“…Logarithmic transformations for the depend variable and quantile-based probabilistic models could be applied in the correction of the heteroscedasticity ( O’Sullivan et al. 2016 ; Tofallis 2009 ; Vasseur and Aznarte 2021 ). Furthermore, our DEML could not directly deal with missing values.…”

“…The biased prediction was expected because of the high variations in the retrieved PM 10 and PM 2:5 concentrations, especially in a certain season like summer when variable atmospheric conditions (Fratianni and Acquaotta 2017) and certain transient air pollution events such as Saharan dust appear frequently in Italy (Mallone et al 2011). Logarithmic transformations for the depend variable and quantilebased probabilistic models could be applied in the correction of the heteroscedasticity (O'Sullivan et al 2016;Tofallis 2009;Vasseur and Aznarte 2021). Furthermore, our DEML could not directly deal with missing values.…”

Uncertainty Quantification for Machine Learning‐Based Ionosphere and Space Weather Forecasting: Ensemble, Bayesian Neural Network, and Quantile Gradient Boosting

“…We chose Gradient Boosting because it is fast (Natras et al., 2022a), performs well on structured input data even for relatively small data sets (Duan et al., 2020), and has proven to be a powerful method in many data science competitions (Chen & Guestrin, 2016). Moreover, Vasseur and Aznarte (2021) compared the performance of 10 ML algorithms with quantile loss for predicting NO 2 pollution and found that Gradient Boosting outperformed the other models with better results for all metrics examined.…”

Deep neural networks for the quantile estimation of regional renewable energy production

“…Natural gradient boosting (NGBoost) is a recent method that uses boosting models for computing probabilistic predictions in regression problems [12,16,53]…”