Characterization of vapor intrusion sites with a deep learning-based data assimilation method

Jun Man; Yuanming Guo; Junliang Jin; Jianyun Zhang; Yijun Yao; Jiangjiang Zhang

doi:10.1016/j.jhazmat.2022.128600

Characterization of vapor intrusion sites with a deep learning-based data assimilation method

J Hazard Mater. 2022 Jun 5:431:128600. doi: 10.1016/j.jhazmat.2022.128600. Epub 2022 Mar 3.

Authors

Jun Man¹, Yuanming Guo², Junliang Jin³, Jianyun Zhang³, Yijun Yao⁴, Jiangjiang Zhang⁵

Affiliations

¹ Key Laboratory of Soil Environment and Pollution Remediation, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, China; University of Chinese Academy of Sciences, Beijing 100049, China.
² Nanjing University of Science and Technology, Nanjing 210094, China.
³ Yangtze Institute for Conservation and Development, Hohai University, Nanjing 210024, China.
⁴ Key Laboratory of Soil Environment and Pollution Remediation, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, China; University of Chinese Academy of Sciences, Beijing 100049, China. Electronic address: yijun_yao@issas.ac.cn.
⁵ Yangtze Institute for Conservation and Development, Hohai University, Nanjing 210024, China. Electronic address: zhangjiangjiang@hhu.edu.cn.

PMID: 35255335
DOI: 10.1016/j.jhazmat.2022.128600

Abstract

Appropriate characterization of site soils is essential for accurate risk assessment of soil vapor intrusion (VI). In this study, we develop a data assimilation method based on deep learning (i.e., ES_(DL)) to estimate the distribution of soil properties with limited measurements. Two hypothetical VI scenarios are employed to demonstrate site characterization using the ES_(DL) method, followed by validation with a laboratory sandbox experiment and then one practical site application. The results show that the ES_(DL) method can provide reasonable estimates of the effective diffusion coefficient distributions and corresponding emission rates (into the building) in all four cases. The spatial heterogeneity of site soils can be characterized by considerably enough measurements (i.e., 15 sampling points in the first hypothetical case); otherwise, layered characterization is recommended at the cost of neglecting horizontal heterogeneity of site soils. This new method provides an alternative to characterize VI sites with relatively fewer sampling efforts.

Keywords: Data assimilation; Machine learning; Site characterization; Soil heterogeneity; Vapor intrusion.