The accurate monitoring and analysis of PM-2.5 are critical for improving air quality and formulating public health policies. However, environmental data often contain missing values due to equipment failures, data collection errors, or extreme weather conditions, which can hinder reliable analysis and predictions. This study evaluates the performance of various missing data imputation methods for PM-2.5 data in Seoul, Korea, using scenarios with artificially generated missing values during high- and low-concentration periods. The methods compared include FFILL, KNN, MICE, SARIMAX, DNN, and LSTM. The results indicate that KNN consistently achieved stable and balanced performance across different temporal intervals, with an RMSE of 5.65, 9.14, and 9.71 for 6 h, 12 h, and 24 h intervals, respectively. FFILL demonstrated superior performance for short intervals (RMSE 4.76 for 6 h) but showed significant limitations as intervals lengthened. SARIMAX performed well in long-term scenarios, with an RMSE of 9.37 for 24 h intervals, but required higher computational complexity. Conversely, deep learning models such as DNN and LSTM underperformed, highlighting the need for further optimization for time-series data. This study highlights the practicality of KNN as the most effective method for addressing missing PM-2.5 data in mid- to long-term applications due to its simplicity and efficiency. These findings provide valuable insights into the selection of imputation methods for environmental data analysis, contributing to the enhancement of data reliability and the development of effective air quality management policies.

Air pollution, particularly fine particulate matter (PM_2.5), poses significant environmental and public health challenges in South Korea. The National Institute of Environmental Research (NIER) currently relies on numerical models such as the Community Multiscale Air Quality (CMAQ) model for PM_2.5 forecasting. However, these models exhibit inherent uncertainties due to limitations in emission inventories, meteorological inputs, and model frameworks. To address these challenges, this study evaluates and compares the forecasting performance of two alternative models: Long Short-Term Memory (LSTM), a deep learning model, and Seasonal Auto Regressive Integrated Moving Average with Exogenous Variables (SARIMAX), a statistical model. The performance evaluation was focused on Seoul, South Korea, and took place over different forecast lead times (D00–D02). The results indicate that for short-term forecasts (D00), SARIMAX outperformed LSTM in all statistical metrics, particularly in detecting high PM_2.5 concentrations, with a 19.43% higher Probability of Detection (POD). However, SARIMAX exhibited a sharp performance decline in extended forecasts (D01–D02). In contrast, LSTM demonstrated relatively stable accuracy over longer lead times, effectively capturing complex PM_2.5 concentration patterns, particularly during high-concentration episodes. These findings highlight the strengths and limitations of statistical and deep learning models. While SARIMAX excels in short-term forecasting with limited training data, LSTM proves advantageous for long-term forecasting, benefiting from its ability to learn complex temporal patterns from historical data. The results suggest that an integrated air quality forecasting system combining numerical, statistical, and machine learning approaches could enhance PM_2.5 forecasting accuracy.

Particulate matter (PM) in the atmosphere poses significant risks to both human health and the environment. Specifically, PM2.5, particulate matter with a diameter less than 2.5 micrometers, has been linked to increased rates of cardiovascular and respiratory diseases. In South Korea, concerns about PM2.5 exposure have grown due to its potential for causing premature death. This study aims to estimate high-resolution exposure concentrations of PM2.5 across South Korea from 2015 to 2021. We integrated data from the Community Multiscale Air Quality (CMAQ) model with surface air quality measurements, the Weather Research Forecast (WRF) model, the Normalized Difference Vegetation Index (NDVI), and the Multi-Angle Implementation of Atmospheric Correction (MAIAC) Aerosol Optical Depth (AOD) satellite data. These data, combined with multiple regression analyses, allowed for the correction of PM2.5 estimates, particularly in suburban areas where ground measurements are sparse. The simulated PM2.5 concentration showed strong correlations with observed values R (ranging from 0.88 to 0.94). Spatial distributions of annual PM2.5 showed a significant decrease in PM2.5 concentrations from 2015 to 2021, with some fluctuation due to the COVID-19 pandemic, such as in 2020. The study produced highly accurate daily average high-resolution PM2.5 exposure concentrations.

PM-2.5 is a critical pollutant for air quality evaluation and public health policymaking, necessitating accurate data for reliable analysis. However, environmental data often contain missing values due to equipment malfunctions or extreme weather conditions, which undermine the credibility of analysis and predictions. In particular, the frequent fluctuations of PM-2.5 levels in Seoul highlight the importance of addressing missing data issues.This study systematically compares the performance of various missing data imputation methods for PM-2.5 data in Seoul, aiming to identify the optimal approach for medium- and long-term predictions. By generating and evaluating missing data during high- and low-concentration periods, this research differentiates itself from prior studies and enhances practical applicability.A range of statistical and machine learning-based methods, including FFILL, KNN, MICE, SARIMAX, DNN, and LSTM, were applied to impute missing data. The performance of each method was evaluated over 6-hour, 12-hour, and 24-hour intervals using metrics such as RMSE, MAE, and correlation coefficients. The experimental design incorporated real-world air quality conditions by selecting data from periods of significant PM-2.5 variation.KNN demonstrated balanced performance across all time intervals and yielded the best results for medium- and long-term predictions. FFILL showed excellent accuracy over short time intervals but exhibited declining performance as the interval length increased. Conversely, deep learning-based models, such as DNN and LSTM, showed relatively poor performance, indicating the need for further optimization to account for the characteristics of time-series data.This study confirms that KNN is the most suitable method for PM-2.5 missing data imputation due to its simplicity and computational efficiency. These findings enhance the reliability of air quality data analysis and provide a valuable foundation for effective air quality management and policymaking. Furthermore, the results underscore the importance of selecting appropriate imputation methods to improve predictive accuracy and analytical reliability. "This research was supported by Particulate Matter Management Specialized Graduate Program through the Korea Environmental Industry & Technology Institute(KEITI) funded by the Ministry of Environment(MOE)“