A data-driven approach to the forecasting of ground-level ozone concentration
Institute for Applied Sustainability to the Built Environment, University of Applied Sciences and Arts of Southern Switzerland（瑞士南部应用科学与艺术大学建筑环境应用可持续性研究所）
Dario Marvin, Lorenzo Nespoli, Davide Strepparava, Vasco Medici
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.
A Lagrangian column model has been developed to simulate the mean (monthly and annual) three-dimensional structure in ozone and nitrogen oxides concentrations in the boundary layer within and immediately around an urban area. Short time-scale photochemical processes of ozone, as well as emissions and deposition to the ground are simulated. The results show that the average surface ozone concentration in the urban area is lower than the surrounding rural areas by typically 50%. Model results are compared with observations.
University of Houston（休斯顿大学）；Houston Advanced Research Center（休斯顿高级研究中心）
Issues regarding air quality and related health concerns have prompted this study, which develops an accurate and computationally fast, efficient hybrid modeling system that combines numerical modeling and machine learning for forecasting concentrations of surface ozone. Currently available numerical modeling systems for air quality predictions (e.g., CMAQ, NCEP EMP) can forecast 24 to 48 hours in advance. In this study, we develop a modeling system based on a convolutional neural network (CNN) model that is not only fast but covers a temporal period of two weeks with a resolution as small as …
This study uses a deep learning approach to forecast ozone concentrations over Seoul, South Korea for 2017. We employ a deep convolutional neural network (CNN). We apply this method to predict the hourly ozone concentration on each day for the entire year using several predictors from the previous day, including the wind fields, temperature, relative humidity, pressure, and precipitation, along with in-situ ozone and NO2 concentrations. We refer to a history of all observed parameters between 2014 and 2016 for training the predictive models. Model-measurement comparisons for the 25 monitoring …
Chapman's model for ozone concentration is studied. In this nonlinear model, the photodissociation coefficients for $O_{2}$ and $O_{3}$ are time-depending due to earth-rotation. From the Kapitsa's method, valid in the high frequency limit, we find the criterion for the existence of equilibrium solutions. These solutions are depending on the frequency, and require a rotation period $T$ which satisfies $T<T_{1}$ or $T>T_{2}$. Where the critical periods $T_{1}$ and $T_{2}$, with $T_{2}>T_{1}$, are a function of the parameters of the system (reaction rates and photodissociation coefficients). Conj…
Ground-level ozone in Kiev for an episode of its high concentration in August 2000 was simulated with the model of the urban air pollution UAM-V (Urban Airshed Model). The study of total ozone over Kiev and its concentration changes with height in the troposphere is made on the basis of ground-based observations with the infrared Fourier spectrometer at the Main Astronomical Observatory of National Academy of Sciences of Ukraine as a part of the ESA-NIVR-KNMI no 2907. In 2008 the satellite Aura-OMI data OMO3PR on the atmosphere ozone profiles became available. Beginning in 2005, these data inc…
Tropospheric ozone (O3) is a greenhouse gas which can absorb heat and make the weather even hotter during extreme heatwaves. Besides, it is an influential ground-level air pollutant which can severely damage the environment. Thus evaluating the importance of various factors related to the O3 formation process is essential. However, O3 simulated by the available climate models exhibits large variance in different places, indicating the insufficiency of models in explaining the O3 formation process correctly. In this paper, we aim to identify and understand the impact of various factors on O3 fo…
The study of total ozone columns above Kiev and variations of ozone concentrations in the troposphere at different altitudes above Kiev was carried out using ground-based Fourier Transform InfraRed (FTIR) spectrometric observations that are taken on a routine basis at the Main Astronomical Observatory of the National Academy of Sciences of Ukraine (MAO NASU). This study was performed within the framework of the international ESA-NIVR-KNMI OMI-AO project no.2907 entitled OMI validation by ground-based remote sensing: ozone columns and atmospheric profiles during the time frame 2005-2008. The in…
This study investigates the hourly concentrations of Ground-level Ozone (O3), Nitric Oxide (NO), Nitrogen Dioxide (NO2), and Oxides of Nitrogen (NOx) in ambient air, along with the various meteorological parameters viz., ambient temperature, relative humidity, wind speed, and solar radiation over one year, from August 2020 to July 2021 for an industrial and commercial site in Madhya Pradesh, a central state in India. We also analyze the chemical coupling between the O3 and ambient NO, NO2, and NOx at both sites during the daytime. We focus on understanding how the concentration of the oxidant …
Social-distancing to combat the COVID-19 pandemic has led to widespread reductions in air pollutant emissions. Quantifying these changes requires a business as usual counterfactual that accounts for the synoptic and seasonal variability of air pollutants. We use a machine learning algorithm driven by information from the NASA GEOS-CF model to assess changes in nitrogen dioxide (NO$_{2}$) and ozone (O$_{3}$) at 5,756 observation sites in 46 countries from January through June 2020. Reductions in NO$_{2}$ correlate with timing and intensity of COVID-19 restrictions, ranging from 60% in severely …
Tropospheric Ozone Formation Potential and Related Design Considerations for Radiative Coolers
Oak Ridge National Laboratory（橡树岭国家实验室）；University “G. d’Annunzio” of Chieti-Pescara（基耶蒂-佩斯卡拉“G. d’Annunzio”大学）；Auburn University（奥本大学）；Princeton University（普林斯顿大学）
Observational time series data often exhibit both cyclic temporal trends and autocorrelation and may also depend on covariates. As such, there is a need for flexible regression models that are able to capture these trends and model any residual autocorrelation simultaneously. Modelling the autocorrelation in the residuals leads to more realistic forecasts than an assumption of independence. In this paper we propose a method which combines spline-based semi-parametric regression modelling with the modelling of auto-regressive errors. The method is applied to a simulated data set in order to sho…
We explore possibilities of improving the spatial structure of NOx emissions employed in a continental scale chemistry transport model (CTM) by using satellite measurements of nitrogen dioxide and ground-based observations of near surface ozone. In this study, we combine the tropospheric NO2 columns derived from SCIAMACHY measurements, the data from the EMEP ozone-monitoring network and the calculations performed with the CHIMERE CTM in the framework of an advanced inverse modelling scheme. All data used in the study correspond to the period of June-August 2003. The main distinctive feature of…
This study is focused on the effects of cosmic rays (solar activity) and halogenated molecules (mainly chlorofluorocarbons-CFCs) on atmospheric O3 depletion and global climate change. Brief reviews are first given on the cosmic-ray-driven electron-induced-reaction (CRE) theory for O3 depletion and the warming theory of CFCs for climate change. Then natural and anthropogenic contributions are examined in detail and separated well through in-depth statistical analyses of comprehensive measured datasets. For O3 loss, new statistical analyses of the CRE equation with observed data of total O3 and …
Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a daily prediction method of PM2.5 concentration by using data-driven ordinary differential equation (ODE) models. Specifically, based on the historical PM2.5 concentration, this method combines genetic programming and orthogonal least square method to evolve the ODE models, which describe the transport of PM2.5 and then uses the data-driven ODEs to predict the air quality in the future. Experiment results show that the ODE models obtain similar prediction results as t…
We present a simple framework to easily pre-select the most essential data for accurately forecasting the concentration of the pollutant PM$_{10}$, based on pollutants observations for the years 2002 until 2006 in the metropolitan region of Lisbon, Portugal. Starting from a broad panoply of different data sets collected at several meteorological stations, we apply a forward stepwise regression procedure that enables us not only to identify the most important variables for forecasting the pollutant but also to rank them in order of importance. We argue the importance of this variable ranking, s…
