(627f) Data Driven Framework for Volatile Organic Compounds (VOCs) Characterization

Air pollution is becoming one of the most serious global health concerns with rising urbanization, industrialization and economic growth. The air pollution has a significant effect on human health. Nearly 90% of people breathe air which has high level of pollutants, and one out of every nine deaths are caused by exposure to air pollution, accounting for more than seven million premature deaths annually (Zhang et al., 2022).

The goal of the study is to develop an in-vitro pediatric lung model to characterize respiratory risks from volatile organic compounds (VOCs), for which a data driven framework is developed with considerable attention to robustness and outlier detection. Machine learning and data driven approaches offer a great opportunity for the evaluations of VOCs by learning the data patterns (Beykal et al., 2022), for which it assists in classifying and analyzing the VOC(s) that affects the lung behavior (Zhang et.al 2022). The tool provides a correlation and a graphical representation between 80 different VOC compounds measured in 2 locations (Manchester - Houston), Texas for 5 days. This is achieved by heat map visualization that correlates between different chemical compounds. Then, clustering analysis is conducted in order to specify the most related and critical VOC chemical compounds subset. Singular value decomposition and PCA analysis are implemented to determine/analyze the interactions and the experimental features that have the most impact from the measured VOCs and minimize the experimental noise (Onel et al., 2018). The concentration-response modeling performed will be useful in the evaluation of respiratory risks from ambient VOCs as it requires careful nonlinear and spatial modeling.

References

Beykal, B., Aghayev, Z., Onel, O., Onel, M., & Pistikopoulos, E. N. (2022). Data-driven Stochastic Optimization of Numerically Infeasible Differential Algebraic Equations: An Application to the Steam Cracking Process. In Y. Yamashita & M. B. T.-C. A. C. E. Kano (Eds.), 14 International Symposium on Process Systems Engineering (Vol. 49, pp. 1579–1584). Elsevier.

Onel, M., Beykal, B., Wang, M., Grimm, F. A., Zhou, L., Wright, F. A., Phillips, T. D., Rusyn, I., & Pistikopoulos, E. N. (2018). Optimal Chemical Grouping and Sorbent Material Design by Data Analysis, Modeling and Dimensionality Reduction Techniques. In A. Friedl, J. J. Klemeš, S. Radl, P. S. Varbanov, & T. B. T.-C. A. C. E. Wallek (Eds.), 28 European Symposium on Computer Aided Process Engineering (Vol. 43, pp. 421–426). Elsevier.

Zhang, R., Johnson, N. M., & Li, Y. (2022). Establishing the exposure–outcome relation between airborne particulate matter and children’s health. Thorax, 77(4), 322 LP – 323.