Dataset Information

Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM_2.5, PM₁₀, O₃, NO₂, SO₂, CO) in Seoul, South Korea.

ABSTRACT: Amidst recent industrialization in South Korea, Seoul has experienced high levels of air pollution, an issue that is magnified due to a lack of effective air pollution prediction techniques. In this study, the Prophet forecasting model (PFM) was used to predict both short-term and long-term air pollution in Seoul. The air pollutants forecasted in this study were PM_2.5, PM₁₀, O₃, NO₂, SO₂, and CO, air pollutants responsible for numerous health conditions upon long-term exposure. Current chemical models to predict air pollution require complex source lists making them difficult to use. Machine learning models have also been implemented however their requirement of meteorological parameters render the models ineffective as additional models and infrastructure need to be in place to model meteorology. To address this, a model needs to be created that can accurately predict pollution based on time. A dataset containing three years worth of hourly air quality measurements in Seoul was sourced from the Seoul Open Data Plaza. To optimize the model, PFM has the following parameters: model type, changepoints, seasonality, holidays, and error. Cross validation was performed on the 2017-18 data; then, the model predicted 2019 values. To compare the predicted and actual values and determine the accuracy of the model, the statistical indicators: mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and coverage were used. PFM predicted PM_2.5 and PM₁₀ with a MAE value of 12.6 µg/m³ and 19.6 µg/m³, respectively. PFM also predicted SO₂ and CO with a MAE value of 0.00124 ppm and 0.207 ppm, respectively. PFM's prediction of PM_2.5 and PM₁₀ had a MAE approximately 2 times and 4 times less, respectively, than comparable models. PFM's prediction of SO₂and CO had a MAE approximately five times and 50 times less, respectively, than comparable models. In most cases, PFM's ability to accurately forecast the concentration of air pollutants in Seoul up to one year in advance outperformed similar models proposed in literature. This study addresses the limitations of the prior two PFM studies by expanding the modelled air pollutants from three pollutants to six pollutants while increasing the prediction time from 3 days to 1 year. This is also the first research to use PFM in Seoul, Korea. To achieve more accurate results, a larger air pollution dataset needs to be implemented with PFM. In the future, PFM should be used to predict and model air pollution in other regions, especially those without advanced infrastructure to model meteorology alongside air pollution. In Seoul, Seoul's government can use PFM to accurately predict air pollution concentrations and plan accordingly.

SUBMITTER: Shen J

PROVIDER: S-EPMC7500321 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM2.5, PM10, O3, NO2, SO2, CO) in Seoul, South Korea.

Shen Justin J Valagolam Davesh D McCalla Serena S

PeerJ 20200915

Amidst recent industrialization in South Korea, Seoul has experienced high levels of air pollution, an issue that is magnified due to a lack of effective air pollution prediction techniques. In this study, the Prophet forecasting model (PFM) was used to predict both short-term and long-term air pollution in Seoul. The air pollutants forecasted in this study were PM2.5, PM10, O3, NO2, SO2, and CO, air pollutants responsible for numerous healt ...[more]

PMID: 32983651

Similar Datasets

Project description:Numerous studies have established that acute or chronic exposure to environmental pollutants like particulate matter (PM) leads to the development of accelerated aging related pathologies including pulmonary and cardiovascular diseases, and thus air pollution is one of the major global threats to human health. Air pollutant particulate matter 2.5 (PM2.5)-induced cellular dysfunction impairs tissue homeostasis and causes vascular and cardiopulmonary damage. To test a hypothesis that elevated plasminogen activator inhibitor-1 (PAI-1) levels play a pivotal role in air pollutant-induced cardiopulmonary pathologies, we examined the efficacy of a drug-like novel inhibitor of PAI-1, TM5614, in treating PM2.5-induced vascular and cardiopulmonary pathologies. Results from biochemical, histological, and immunohistochemical studies revealed that PM2.5 increases the circulating levels of PAI-1 and thrombin and that TM5614 treatment completely abrogates these effects in plasma. PM2.5 significantly augments the levels of pro-inflammatory cytokine interleukin-6 (IL-6) in bronchoalveolar lavage fluid (BALF), and this also can be reversed by TM5614, indicating its efficacy in amelioration of PM2.5-induced increases in inflammatory and pro-thrombotic factors. TM5614 reduces PM2.5-induced increased levels of inflammatory markers cluster of differentiation 107 b (Mac3) and phospho-signal transducer and activator of transcription-3 (pSTAT3), adhesion molecule vascular cell adhesion molecule 1 (VCAM1), and apoptotic marker cleaved caspase 3. Longer exposure to PM2.5 induces pulmonary and cardiac thrombosis, but TM5614 significantly ameliorates PM2.5-induced vascular thrombosis. TM5614 also reduces PM2.5-induced increased blood pressure and heart weight. In vitro cell culture studies revealed that PM2.5 induces the levels of PAI-1, type I collagen, fibronectin (Millipore), and sterol regulatory element binding protein-1 and 2 (SREBP-1 and SREBP-2), transcription factors that mediate profibrogenic signaling, in cardiac fibroblasts. TM5614 abrogated that stimulation, indicating that it may block PM2.5-induced PAI-1 and profibrogenic signaling through suppression of SREBP-1 and 2. Furthermore, TM5614 blocked PM2.5-mediated suppression of nuclear factor erythroid related factor 2 (Nrf2), a major antioxidant regulator, in cardiac fibroblasts. Pharmacological inhibition of PAI-1 with TM5614 is a promising therapeutic approach to control air pollutant PM2.5-induced cardiopulmonary and vascular pathologies.

Project description:BackgroundPrenatal exposure to ambient air pollution is linked to a higher risk of unfavorable pregnancy outcomes. However, the association between pregnancy complications and exposure to indoor air pollution remains unclear. The Air Pollution on Pregnancy Outcomes research is a hospital-based prospective cohort research created to look into the effects of aerodynamically exposed particulate matter (PM)10 and PM2.5 on pregnancy outcomes.MethodsThis prospective multicenter observational cohort study was conducted from January 2021 to June 2023. A total of 662 women with singleton pregnancies enrolled in this study. An AirguardK® air sensor was installed inside the homes of the participants to measure the individual PM10 and PM2.5 levels in the living environment. The time-activity patterns and PM10 and PM2.5, determined as concentrations from the time-weighted average model, were applied to determine the anticipated exposure levels to air pollution of each pregnant woman. The relationship between air pollution exposure and pregnancy outcomes was assessed using logistic and linear regression analyses.ResultsExposure to elevated levels of PM10 throughout the first, second, and third trimesters as well as throughout pregnancy was strongly correlated with the risk of pregnancy problems according to multiple logistic regression models adjusted for variables. Except for in the third trimester of pregnancy, women exposed to high levels of PM2.5 had a high risk of pregnancy complications. During the second trimester and entire pregnancy, the risk of preterm birth (PTB) increased by 24% and 27%, respectively, for each 10 μg/m3 increase in PM10. Exposure to high PM10 levels during the second trimester increased the risk of gestational diabetes mellitus (GDM) by 30%. The risk of GDM increased by 15% for each 5 μg/m3 increase in PM2.5 during the second trimester and overall pregnancy, respectively. Exposure to high PM10 and PM2.5 during the first trimester of pregnancy increased the risk of delivering small for gestational age (SGA) infants by 96% and 26%, respectively.ConclusionExposure to high concentrations of PM10 and PM2.5 is strongly correlated with the risk of adverse pregnancy outcomes. Exposure to high levels of PM10 and PM2.5 during the second trimester and entire pregnancy, respectively, significantly increased the risk of PTB and GDM. Exposure to high levels of PM10 and PM2.5 during the first trimester of pregnancy considerably increased the risk of having SGA infants. Our findings highlight the need to measure individual particulate levels during pregnancy and the importance of managing air quality in residential environment.

Dataset Information

Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM_2.5, PM₁₀, O₃, NO₂, SO₂, CO) in Seoul, South Korea.

Publications

Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM<sub>2.5</sub>, PM<sub>10</sub>, O<sub>3</sub>, NO<sub>2</sub>, SO<sub>2</sub>, CO) in Seoul, South Korea.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets