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

Three-dimensional distribution characteristics of multiple pollutants in the soil at a steelworks mega-site based on multi-source information

Soil pollution at steelworks mega-sites has become a severe environmental issue worldwide. However, due to the complex production processes and hydrogeology, the soil pollution distribution at steelworks is still unclear. This study scientifically cognized the distribution characteristics of polycyclic aromatic hydrocarbons (PAHs), volatile organic compounds (VOCs), and heavy metals (HMs) at a steelworks mega-site based on multi-source information. Specifically, firstly, 3D distribution and spatial autocorrelation of pollutants were obtained by interpolation model and local indicators of spatial associations (LISA), respectively. Secondly, the characteristics of horizontal distribution, vertical distribution, and spatial autocorrelations of pollutants were identified by combining multi-source information such as production processes, soil layers, and properties of pollutants. Horizontal distribution showed that soil pollution in steelworks mainly occurred in the front end of the steel process chain. Over 47% of PAHs and VOCs pollution area were distributed in coking plants and over 69% of HMs in stockyards. Vertical distribution indicated that HMs, PAHs, and VOCs were enriched in the fill, silt, and clay layers, respectively. Spatial autocorrelation of pollutants was positively correlated with their mobility. This study clarified the soil pollution characteristics at steelworks mega-sites, which can support the investigation and remediation of steelworks mega-sites.

Contaminant sorption on soil and indoor materials and its possible impact on transients in vapor intrusion- An example based upon trichloroethylene (TCE)

Although building materials are well recognized as potential sources and sinks of indoor volatile organic compounds (VOCs), knowledge about how they affect indoor air concentrations and measurements in vapor intrusion scenarios is limited. This study investigates the potential influence of sorption processes on indoor air contamination in vapor intrusion, relying upon laboratory measurements at relevant concentration levels, and applying these in a numerical transient vapor intrusion model. It was found that the sink effect of adsorption on building materials can lower indoor air concentrations or delay their achieving a steady state, thus cautioning that these processes can affect observed indoor air concentration variability. Building materials can also serve as secondary sources of pollutants in vapor intrusion mitigation scenarios, which might affect the evaluation of the efficiency of mitigation efforts. For example, it was predicted that in a cinderblock structure it could take up to 305 hours to reduce indoor trichloroethylene (TCE) concentrations by 50% due to the re-emission of TCE from the cinderblock, whereas it would take only 1.4 hours without the re-emission process.

Exploring the nonlinear partitioning mechanism of volatile organic contaminants between soil and soil vapor using machine learning

Traditional phase equilibrium models usually depend on simplified assumptions and empirical parameters, which are difficult to obtain during regular site investigations. As a result, they often under- or over-estimate soil vapor concentrations for assessing the risks of volatile organic compound (VOC)-contaminated sites. In this study, we develop several machine learning models to predict soil vapor concentrations using 2225 soil-soil vapor data pairs collected from seven contaminated sites in northern China. Compared to the classic dual equilibrium desorption model, the random forest (RF) model can provide more accurate predictions of soil vapor concentrations by at least 1-2 orders of magnitude. Among the employed covariates, soil concentration and organic carbon-water partition coefficient are two of the most significant explanatory covariates affecting soil vapor concentrations. Further examination of the developed RF model reveals the phase equilibrium behavior of VOCs in soil is that: the soil vapor concentration increases with soil concentration at different rates in the first two intervals but remains almost unchanged in the last interval; the solid-vapor partitioning interface may still exist at up to 15% mass water content in our simulations. These findings can help site investigators perform more accurate risk assessments at VOC-contaminated sites.

Database examination, multivariate analysis, and machine learning: Predictions of vapor intrusion attenuation factors

Traditional soil vapor intrusion (VI) models usually rely on preset conceptual scenarios, simplifying the influences of limiting environmental covariates in determining indoor attenuation factors relative to subsurface sources. This study proposed a technical framework and applied it to predict VI attenuation factors based on site-specific parameters recorded in the United States Environmental Protection Agency (USEPA)'s and the California Environmental Protection Agency (CalEPA)'s VI databases, which can overcome the limitations of traditional VI models. We examined the databases with multivariate analysis of variance to identify effective covariates, which were then employed to develop VI models with three machine learning algorithms. The results of multivariate analysis show that the effective covariates include soil texture, source depth, foundation type, lateral separation, surface cover, and land use. Based on these covariates, the predicted attenuation factors by these new models are generally within one order of magnitude of the observations recorded in the databases. Then the developed models were employed to generate the generic indoor attenuation factors to subsurface vapor (i.e., the 95th percentile of selected dataset), the values of which are different between the USEPA's and CalEPA's databases by one order of magnitude, although comparable to recommendations by the USEPA and literature, respectively. Such a difference may reflect the significant regional disparity in factors such as building structures or operational conditions (e.g., indoor air exchange rates), which necessitates generating generic VI attenuation factors on a state-specific basis. This study provides an alternative for VI risk screens on a site-specific basis, especially in states with a good collection of datasets. Although the proposed technical framework is used for the VI databases, it can be equally applied to other environmental science problems.