Predicting ambient PM2.5 concentrations in Ulaanbaatar, Mongolia with machine learning approaches

evalPM: a framework for evaluating machine learning models for particulate matter prediction

Air pollution through particulate matter (PM) is one of the largest threats to human health. To understand the causes of PM pollution and enact suitable countermeasures, reliable predictions of future PM concentrations are required. In the scientific literature, many methods exist for machine learning (ML)-based PM prediction, though their quality is difficult to compare because, among other things, they use different data sets and evaluate the resulting predictions differently. For a new data set, it is not apparent which of the existing prediction methods is best suited. In order to ease the assessment of said models, we present evalPM, a framework to easily create, evaluate, and compare different ML models for immission-based PM prediction. To achieve this, the framework provides flexibility regarding data sets, input features, target variables, model types, hyperparameters, and model evaluation. It has a modular design consisting of several components, each providing at least one required flexibility. The individual capabilities of the framework are demonstrated using 16 different models from the related literature by means of temporal prediction of PM concentrations for four European data sets, showing the capabilities and advantages of the evalPM framework. In doing so, it is shown that the framework allows fast creation and evaluation of ML-based PM prediction models.

Impact of lifetime air pollution exposure patterns on the risk of chronic disease

Long-term exposure to air pollution can lead to cardiovascular disease, metabolic syndrome, and chronic respiratory disease. However, from a lifetime perspective, the critical period of air pollution exposure in terms of health risk is unknown. This study aimed to evaluate the impact of air pollution exposure at different life stages. The study participants were recruited from community centers in Northern Taiwan between October 2018 and April 2021. Their annual averages for fine particulate matter (PM2.5) exposure were derived from a national visibility database. Lifetime PM2.5 exposures were determined using residential address information and were separated into three stages (<20, 20-40, and >40 years). We employed exponentially weighted moving averages, applying different weights to the aforementioned life stages to simulate various weighting distribution patterns. Regression models were implemented to examine associations between weighting distributions and disease risk. We applied a random forest model to compare the relative importance of the three exposure life stages. We also compared model performance by evaluating the accuracy and F1 scores (the harmonic mean of precision and recall) of late-stage (>40 years) and lifetime exposure models. Models with 89% weighting on late-stage exposure showed significant associations between PM_2.5 exposure and metabolic syndrome, hypertension, diabetes, and cardiovascular disease, but not gout or osteoarthritis. Lifetime exposure models showed higher precision, accuracy, and F1 scores for metabolic syndrome, hypertension, diabetes, and cardiovascular disease, whereas late-stage models showed lower performance metrics for these outcomes. We conclude that exposure to high-level PM_2.5 after 40 years of age may increase the risk of metabolic syndrome, hypertension, diabetes, and cardiovascular disease. However, models considering lifetime exposure showed higher precision, accuracy, and F1 scores and lower equal error rates than models incorporating only late-stage exposures. Future studies regarding long-term air pollution modelling are required considering lifelong exposure pattern. .¹.

Embedded Generative Air Pollution Model with Variational Autoencoder and Environmental Factor Effect in Ulaanbaatar City

Air pollution is one of the most pressing modern-day issues in cities around the world. However, most cities have adopted air quality measurement devices that only measure the past pollution levels without paying attention to the influencing factors. To obtain preliminary pollution information with regard to environmental factors, we developed a variational autoencoder and feedforward neural network-based embedded generative model to examine the relationship between air quality and the effects of environmental factors. In the model, actual SO2, NO2, PM2.5, PM10, and CO measurements from 2016 to 2020 were used, which were assembled from 15 differently located ground monitoring stations in Ulaanbaatar city. A wide range of weather and fuel measurements were used as the data for the influencing factors, and were collected over the same period as the air pollution data were recorded. The prediction results concerned all measurement stations, and the results were visualized as a spatial–temporal distribution of pollution and the performance of individual stations. A cross-validated R2 was used to estimate the entire pollution distribution through the regions as SO2: 0.81, PM2.5: 0.76, PM10: 0.89, and CO: 0.83. Pearson’s chi-squared tests were used for assessing each measurement station, and the contingency tables represent a high correlation between the actual and model results. The model can be applied to perform specific analysis of the interdependencies between pollution and environmental factors, and the performance of the model improves with long-range data.

Features Exploration from Datasets Vision in Air Quality Prediction Domain

Air pollution and its consequences are negatively impacting on the world population and the environment, which converts the monitoring and forecasting air quality techniques as essential tools to combat this problem. To predict air quality with maximum accuracy, along with the implemented models and the quantity of the data, it is crucial also to consider the dataset types. This study selected a set of research works in the field of air quality prediction and is concentrated on the exploration of the datasets utilised in them. The most significant findings of this research work are: (1) meteorological datasets were used in 94.6% of the papers leaving behind the rest of the datasets with a big difference, which is complemented with others, such as temporal data, spatial data, and so on; (2) the usage of various datasets combinations has been commenced since 2009; and (3) the utilisation of open data have been started since 2012, 32.3% of the studies used open data, and 63.4% of the studies did not provide the data.