Abstract
Many countries are concerned about high particulate matter (PM) concentrations caused by rapid industrial development, which can harm both human health and the environment. To manage PM, the prediction of PM concentrations based on historical data is actively being conducted. Existing technologies for predicting PM mostly assess the model performance for the prediction of existing PM concentrations; however, PM must be forecast in advance, before it becomes highly concentrated and causes damage to the citizens living in the affected regions. Thus, it is necessary to conduct research on an index that can illustrate whether the PM concentration will increase or decrease. We developed a model that can predict whether the PM concentration might increase or decrease after a certain time, specifically for PM (fine PM) generated by anthropogenic volatile organic compounds. An algorithm that can select a model on an hourly basis, based on the long short-term memory (LSTM) and artificial neural network (ANN) models, was developed. The proposed algorithm exhibited a higher F1-score than the LSTM, ANN, or random forest models alone. The model developed in this study could be used to predict future regional PM concentration levels more effectively.
Highlights
Occurring particulate matter (PM) is classified as biogenic volatile organic compounds (BVOCs), while artificially occurring PM is classified as anthropogenic volatile organic compounds (AVOCs)
We developed and tested a model that predicts whether the PM concentration would increase or decrease in 3 and 5 h, in terms of AVOC PM2.5
We investigated a probabilistic index concerning whether the PM value would increase or decrease at certain times
Summary
To analyze PM, we utilized data collected in Cheongnyang-ri, Dongdaemun-gu (Location A), and Yangjae 1-dong (Location B) in Seocho-gu, Seoul, South Korea (see Figure 1). To verify the accuracy of the proposed algorithm, the datasets were analyzed and the model was evaluated, based on the two locations displaying differences in temperature and carbon content near the Han River. Location A is approximately 6.3 km above the Han. River, while Location B is roughly 6.2 km below the Han River. For Location B, the reference mean temperatures were 4.65 °C for January–March, 17.39 °C for April–June, 23.28 °C for July–September, and 13.17 °C for October–December. The average temperature of Location A was 1.7 °C higher than that of Location B. The monthly industrial carbon concentration of Location B was approximately 1.03-times higher than that of Location A
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
