Meteorology-driven variability of air pollution (PM1) revealed with explainable machine learning

Abstract. Air pollution, in particular high concentrations of particulate matter smaller than 1 µm in diameter (PM1), continues to be a major health problem, and meteorology is known to substantially contribute to atmospheric PM concentrations. However, the scientific understanding of the complex mechanisms leading to high pollution episodes is inconclusive, as the effects of meteorological variables are not easy to separate and quantify. In this study, a novel, data-driven approach based on empirical relationships is used to characterise the role of meteorology on atmospheric concentrations of PM1. A tree-based machine learning model is set up to reproduce concentrations of speciated PM1 at a suburban site southwest of Paris, France, using meteorological variables as input features. The contributions of each meteorological feature to modeled PM1 concentrations are quantified using SHapley Additive exPlanation (SHAP) regression values. Meteorological contributions to PM1 concentrations are analysed in selected high-resolution case studies, contrasting season-specific processes. Model results suggest that winter pollution episodes are often driven by a combination of shallow mixed layer heights (MLH), low temperatures, low wind speeds or inflow from northeastern wind directions. Contributions of MLHs to the winter pollution episodes are quantified to be on average ~ 5 µg/m³ for MLHs below 500 m agl. Temperatures below freezing initiate formation processes and increase local emissions related to residential heating, amounting to a contribution of as much as ~ 9 µg/m³. Northeasterly winds are found to contribute ~ 5 µg/m³ to total PM1 concentrations (combined effects of u- and v-wind components), by advecting particles from source regions, e.g. central Europe or the Paris region. However, in calm conditions (i.e. wind speeds

Download Full-text

Meteorology-driven variability of air pollution (PM<sub>1</sub>) revealed with explainable machine learning

Atmospheric Chemistry and Physics ◽

10.5194/acp-21-3919-2021 ◽

2021 ◽

Vol 21 (5) ◽

pp. 3919-3948

Author(s):

Roland Stirnberg ◽

Jan Cermak ◽

Simone Kotthaus ◽

Martial Haeffelin ◽

Hendrik Andersen ◽

...

Keyword(s):

Machine Learning ◽

Air Pollution ◽

Model Performance ◽

Coefficient Of Determination ◽

Large Variability ◽

Major Health Problem ◽

Wind Speeds ◽

Meteorological Influences ◽

High Pollution ◽

Pollution Episodes

Abstract. Air pollution, in particular high concentrations of particulate matter smaller than 1 µm in diameter (PM1), continues to be a major health problem, and meteorology is known to substantially influence atmospheric PM concentrations. However, the scientific understanding of the ways in which complex interactions of meteorological factors lead to high-pollution episodes is inconclusive. In this study, a novel, data-driven approach based on empirical relationships is used to characterize and better understand the meteorology-driven component of PM1 variability. A tree-based machine learning model is set up to reproduce concentrations of speciated PM1 at a suburban site southwest of Paris, France, using meteorological variables as input features. The model is able to capture the majority of occurring variance of mean afternoon total PM1 concentrations (coefficient of determination (R2) of 0.58), with model performance depending on the individual PM1 species predicted. Based on the models, an isolation and quantification of individual, season-specific meteorological influences for process understanding at the measurement site is achieved using SHapley Additive exPlanation (SHAP) regression values. Model results suggest that winter pollution episodes are often driven by a combination of shallow mixed layer heights (MLHs), low temperatures, low wind speeds, or inflow from northeastern wind directions. Contributions of MLHs to the winter pollution episodes are quantified to be on average ∼5 µg/m3 for MLHs below <500 m a.g.l. Temperatures below freezing initiate formation processes and increase local emissions related to residential heating, amounting to a contribution to predicted PM1 concentrations of as much as ∼9 µg/m3. Northeasterly winds are found to contribute ∼5 µg/m3 to predicted PM1 concentrations (combined effects of u- and v-wind components), by advecting particles from source regions, e.g. central Europe or the Paris region. Meteorological drivers of unusually high PM1 concentrations in summer are temperatures above ∼25 ∘C (contributions of up to ∼2.5 µg/m3), dry spells of several days (maximum contributions of ∼1.5 µg/m3), and wind speeds below ∼2 m/s (maximum contributions of ∼3 µg/m3), which cause a lack of dispersion. High-resolution case studies are conducted showing a large variability of processes that can lead to high-pollution episodes. The identification of these meteorological conditions that increase air pollution could help policy makers to adapt policy measures, issue warnings to the public, or assess the effectiveness of air pollution measures.

Download Full-text

A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys

Scientific Reports ◽

10.1038/s41598-021-90237-z ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Jin-Woong Lee ◽

Chaewon Park ◽

Byung Do Lee ◽

Joonseo Park ◽

Nam Hoon Goo ◽

...

Keyword(s):

Machine Learning ◽

Feature Space ◽

Research Strategy ◽

Nsga Ii ◽

Steel Alloys ◽

Non Linear ◽

Data Driven Approach ◽

Processing Information ◽

Set Up ◽

World Industry

AbstractPredicting mechanical properties such as yield strength (YS) and ultimate tensile strength (UTS) is an intricate undertaking in practice, notwithstanding a plethora of well-established theoretical and empirical models. A data-driven approach should be a fundamental exercise when making YS/UTS predictions. For this study, we collected 16 descriptors (attributes) that implicate the compositional and processing information and the corresponding YS/UTS values for 5473 thermo-mechanically controlled processed (TMCP) steel alloys. We set up an integrated machine-learning (ML) platform consisting of 16 ML algorithms to predict the YS/UTS based on the descriptors. The integrated ML platform involved regularization-based linear regression algorithms, ensemble ML algorithms, and some non-linear ML algorithms. Despite the dirty nature of most real-world industry data, we obtained acceptable holdout dataset test results such as R2 > 0.6 and MSE < 0.01 for seven non-linear ML algorithms. The seven fully trained non-linear ML models were used for the ensuing ‘inverse design (prediction)’ based on an elitist-reinforced, non-dominated sorting genetic algorithm (NSGA-II). The NSGA-II enabled us to predict solutions that exhibit desirable YS/UTS values for each ML algorithm. In addition, the NSGA-II-driven solutions in the 16-dimensional input feature space were visualized using holographic research strategy (HRS) in order to systematically compare and analyze the inverse-predicted solutions for each ML algorithm.

Download Full-text

Relation between air pollution episodes and discomfort index in the greater Athens area, Greece

Global NEST Journal ◽

10.30955/gnj.000119 ◽

2013 ◽

Vol 1 (2) ◽

pp. 91-97 ◽

Cited By ~ 1

Keyword(s):

Air Pollution ◽

Nitrogen Dioxide ◽

General Study ◽

Discomfort Index ◽

High Concentrations ◽

Athens Area ◽

Very High ◽

Different Levels ◽

Air Pollution Episodes ◽

Pollution Episodes

An attempt is made for a first general study of the relation between high/very high concentrations of nitrogen dioxide and ozone with the discomfort index (DI) values. The nitrogen dioxide data of «Patision» station and ozone data of «Liosia» and «Marousi» station have been analysed. The relation between air pollution episodes and the corresponding values of DI during the period 1993-1995 have been examined for the Greater Athens Area (GAA). For the warm period of the year, the frequency of the DI values for different levels of air pollution in the GAA is also examined.

Download Full-text

Mutual Information Input Selector and Probabilistic Machine Learning Utilisation for Air Pollution Proxies

Applied Sciences ◽

10.3390/app9204475 ◽

2019 ◽

Vol 9 (20) ◽

pp. 4475 ◽

Cited By ~ 8

Author(s):

Martha A. Zaidan ◽

Lubna Dada ◽

Mansour A. Alghamdi ◽

Hisham Al-Jeelani ◽

Heikki Lihavainen ◽

...

Keyword(s):

Machine Learning ◽

Air Pollution ◽

Mutual Information ◽

Air Pollutant ◽

Bayesian Neural Network ◽

Input Selection ◽

Relevant Variables ◽

Data Driven Approach ◽

Probabilistic Machine Learning ◽

The Cost

An air pollutant proxy is a mathematical model that estimates an unobserved air pollutant using other measured variables. The proxy is advantageous to fill missing data in a research campaign or to substitute a real measurement for minimising the cost as well as the operators involved (i.e., virtual sensor). In this paper, we present a generic concept of pollutant proxy development based on an optimised data-driven approach. We propose a mutual information concept to determine the interdependence of different variables and thus select the most correlated inputs. The most relevant variables are selected to be the best proxy inputs, where several metrics and data loss are also involved for guidance. The input selection method determines the used data for training pollutant proxies based on a probabilistic machine learning method. In particular, we use a Bayesian neural network that naturally prevents overfitting and provides confidence intervals around its output prediction. In this way, the prediction uncertainty could be assessed and evaluated. In order to demonstrate the effectiveness of our approach, we test it on an extensive air pollution database to estimate ozone concentration.

Download Full-text

The Development of the B&R Rig, Structural Space Frame and Tripod Support System with Integrated Boom

10.5957/csys-1995-009 ◽

1995 ◽

Author(s):

Lars Bergstrom ◽

Sven Olof Ridder

Keyword(s):

Structural Testing ◽

Wind Tunnels ◽

Laminar Separation ◽

Wind Speeds ◽

Structural Space ◽

Attached Flow ◽

Institute Of Technology ◽

Set Up ◽

Low Wind Speeds ◽

User Friendly

B&R Designs began business in the early sixties when Sven Ridder and Lars Bergstrom began sailing after studying aeronautical engineering. The principles learnt during their aeronautical studies were applied to sailboats and the goal, for them, has been to take up the structural loads in the most constructive way. Access to the wind tunnels, test tanks and structural testing facilities at the Royal Institute of Technology in Stockholm enabled them to develop and test many ideas. One of these ideas evolved into the B&R rig. The objective was to develop a rig that was more 'user friendly'. Sailboats, thirty years ago and even today, are often fitted with inner forestays and running backstays requiring careful attention by the crew when tacking or jibing. A rig with less demands was the goal, one that was simpler and any mistakes made when tacking or jibing would not jeopardize the boat or crew. Also a simpler rig would require fewer crew members. Safety was another important consideration - a rig that was simple, easy to manage, suitable for a couple or family for cruising. During this rig development period the first application of the rigid boom vang concept was used on Sven Ridder's own sailboat 'Christina Windex'. Calculations and model testing of rigs were carried out. Optimizing the aerodynamic effect in the most favorable way was a very important aim. A series of wind tunnel tests were done to optimize the shape of mast sections. Because of the low wind speeds over a mast, laminar separation occurs very easily. Air scoops were set up on either side of the mast to achieve an attached flow. The best results occurred with an oval shaped mast section, fitted with a sail groove recessed in a V shaped area at the rear of the mast section.

Download Full-text

How do low wind speeds and high levels of air pollution support the spread of COVID-19?

Atmospheric Pollution Research ◽

10.1016/j.apr.2020.10.002 ◽

2020 ◽

Cited By ~ 8

Author(s):

Mario Coccia

Keyword(s):

Air Pollution ◽

Wind Speeds ◽

Low Wind Speeds

Download Full-text

Statistics and Meteorology of Air Pollution Episodes over the South African Highveld Based on Satellite–Model Datasets

Journal of Applied Meteorology and Climatology ◽

10.1175/jamc-d-16-0354.1 ◽

2017 ◽

Vol 56 (6) ◽

pp. 1583-1594 ◽

Cited By ~ 3

Author(s):

Mark R. Jury

Keyword(s):

Air Pollution ◽

South African ◽

Lapse Rate ◽

Weather Data ◽

Industrial Emissions ◽

The South ◽

Dewpoint Temperature ◽

High Concentrations ◽

Air Pollution Episodes ◽

Pollution Episodes

AbstractThe meteorological conditions associated with air pollution episodes on South Africa’s Highveld were studied using Ozone Monitoring Instrument (OMI) and Atmospheric Infrared Sounder (AIRS) satellite estimates, MERRA2 reanalysis model products, and in situ weather data. Surface-layer sulfur dioxide (SO2) and nitrogen dioxide (NO2) display high concentrations during winter (May–July) and provide a focus for statistical analysis of monthly and daily time series. Highveld area-averaged monthly model SO2 was temporally correlated with boundary layer height (correlation coefficient of −0.76) and temperature lapse rate (+0.65) for the period of 1980–2015, but relationships with winds were weak. Daily Highveld area-averaged satellite NO2 was related to dewpoint temperature (−0.59) and exhibited pulsing in the range of 7–24 days for 2005–15. High concentrations of these short-lived locally generated air pollutants were found over and southeast of Johannesburg as a result of urban and industrial emissions. The spatial regression of daily NO2 onto regional sea level air pressure fields for May–July over 2005–15 revealed the slow eastward movement of an anticyclone. At the climatic time scale, Pacific Ocean La Niña conditions favored an increase of May–July SO2 concentrations when sea surface temperatures in the equatorial Atlantic Ocean were warmer than normal. The meteorological pattern underlying the highest-ranked air pollution event of 18–25 July 2008 was characterized by sharp anticyclonic curvature of low-level winds that induce subsidence and consequently a stable lapse rate and low dewpoint temperature (−5°C). The wind vorticity exerted a stronger influence on dispersion than did the surface divergence. This new understanding will underpin better air-quality forecasts over the South African Highveld.

Download Full-text