Interpretable machine learning for predicting the fate and transport of pentachlorophenol in groundwater.

Pentachlorophenol (PCP) is a commonly found recalcitrant and toxic groundwater contaminant that resists degradation, bioaccumulates, and has a potential for long-range environmental transport. Taking proper actions to deal with the pollutant accounting for the life cycle consequences requires a better understanding of its behavior in the subsurface. We recognize the huge potential for enhancing decision-making at contaminated groundwater sites with the arrival of machine learning (ML) techniques in environmental applications. We used ML to enhance the understanding of the dynamics of PCP transport properties in the subsurface, and to determine key hydrochemical and hydrogeological drivers affecting its transport and fate. We demonstrate how this complementary knowledge, provided by data-driven methods, may enable a more targeted planning of monitoring and remediation at two highly contaminated Swedish groundwater sites, where the method was validated. We evaluated 6 interpretable ML methods, 3 linear regressors and 3 non-linear (i.e., tree-based) regressors, to predict PCP concentration in the groundwater. The modeling results indicate that simple linear ML models were found to be useful in the prediction of observations for datasets without any missing values, while tree-based regressors were more suitable for datasets containing missing values. Considering that missing values are common in datasets collected during contaminated site investigations, this could be of significant importance for contaminated site planners and managers, ultimately reducing site investigation and monitoring costs. Furthermore, we interpreted the proposed models using the SHAP (SHapley Additive exPlanations) approach to decipher the importance of different drivers in the prediction and simulation of critical hydrogeochemical variables. Among these, sum of chlorophenols is of highest significance in the analyses. Setting that aside from the model, tetra chlorophenols, dissolved organic carbon, and conductivity found to be of highest importance. Accordingly, ML methods could potentially be used to improve the understanding of groundwater contamination transport dynamics, filling gaps in knowledge that remain when using more sophisticated deterministic modeling approaches.

DynSus: Dynamic sustainability assessment in groundwater remediation practice.

Decision-making processes for clean-up of contaminated sites are often highly complex and inherently uncertain. It depends not only on hydrological and biogeochemical site variability, but also on the associated health, environmental, economic, and social impacts of taking, or not taking, action. These variabilities suggest that a dynamic framework is required for promoting sustainable remediation. For this, the decision support system DynSus is presented here for integrating a predeveloped contaminant fate and transport model with a sustainability assessment tool. Implemented within a system dynamics framework, the new tool uses model simulations to provide remediation scenario analysis and handling of uncertainty in various data. DynSus was applied to a site in south Sweden, contaminated with pentachlorophenol (PCP). Simulation scenarios were developed to enable a comparison between alternative remediation strategies and combinations of these. Such comparisons are provided for selected sustainability indicators and remediation performance (in terms of concentration at the recipient). This leads to identifying the most critical variables to ensure that sustainable solutions are chosen. Simulation results indicated that although passive practices, e.g., monitored natural attenuation, were more sustainable at first (5-7 years after beginning remediation measures), they failed to compete with more active practices, e.g., bioremediation, over the entire life cycle of the project (from the beginning of remedial action to achieving the target concentration at the recipient). In addition, statistical tools (clustering and genetic algorithms) were used to further assess the available hydrogeochemical data. Taken together, the results reaffirmed the suitability of the simple analytical framework that was implemented in the contaminant transport model. DynSus outcomes could therefore enable site managers to evaluate different scenarios more quickly and effectively for life cycle sustainability in such a complex and multidimensional problem.

INSIDE: An efficient guide for sustainable remediation practice in addressing contaminated soil and groundwater.

Modeling criteria interaction in decision-making problems is complex and often neglected. In complicated problems, like contaminated site remediation projects, independency of involved criteria is not a realistic assumption. INfluence based deciSIon guiDE (INSIDE) is a methodology that enables sustainable decision making and management in contaminated site remediation practice. Unlike most previous decision-support methods, INSIDE considers realistic interactions among all involved criteria. The method not only gives a one-time best option for choosing a remediation method for the project at hand, but also a management plan for further improvements of the system. INSIDE recognizes economic, environmental, social, and technological considerations for the most sustainable practice. Eight criteria are defined based on these aspects and they can be interrelated. This means that a criterion, e.g., remediation time, does not need to belong to any pre-defined category such as economic, environmental, social, or technical, but can interact with other criteria. This allows for a system with many degrees of freedom that is more realistic for practical problem-solving. In INSIDE, the DEcision MAking Trial and Evaluation Laboratory (DEMATEL) and Analytic Network Process (ANP) techniques are combined for assigning weights to criteria and scoring of remediation alternatives, respectively. Thus, the proposed methodology gives a managerial cone of influence versus importance for all involved criteria in the system. The method is applied to a data-scarce case study in Iran to prioritize between remediation methods for a contaminated groundwater aquifer. The results show that human health risk and environmental impacts are more influential than other evaluated criteria. The suggested methodology should be further tested on a variety of actual remediation problems for additional evaluation.

An immunohistochemical study of CD4, CD8, TIA-1 and CD56 subsets in inflammatory skin disease.

BACKGROUND: Antibodies to CD4, CD8, TIA-1, and CD56 are available which perform well in formalin-fixed and paraffin-embedded tissue. While previous studies have investigated CD4 and CD8 subsets in inflammatory skin disease, few have specifically addressed TIA-1 and CD56 reactivity in benign dermatoses. Given that CD8, TIA-1, and CD56 are linked to aggressive lymphoproliferative disorders (i.e. subcutaneous panniculitic T-cell lymphoma, natural killer (NK), and NK/T-cell lymphomas), it would be important to determine their specificity for cutaneous hematologic malignancies. This investigation was undertaken to determine the frequency with which common, benign dermatoses express these four markers. We also sought to determine whether the ratio of CD4- to CD8-positive cells could be used to distinguish among the dermatoses, especially the superficial and deep perivascular ones. METHODS: Formalin-fixed and paraffin-embedded sections from a variety of common inflammatory dermatoses were stained with antibodies to CD4, CD8, TIA-1, and CD56. Positive reactions were scored as a percentage of the entire mononuclear cell infiltrate. RESULTS: All of the dermatoses represented in the study showed TIA-1- and CD56-positive lymphocyte subpopulations. On a case-by-case basis, the percentage of positive cells varied, and while all cases were positive for TIA-1, many were completely negative for CD56. For TIA-1, the percentage of positive cells ranged from 21 to 59%, and for CD56, from < 1 to 9%. The CD4:CD8 ratio ranged from 1.0 to 6.0 but was never less than 1.0. In addition to lymphocytes, TIA-1 also stained polymorphonuclear leukocytes, eosinophils, and mast cells. CONCLUSION: TIA-1- and CD56-positive lymphocytes are common participants in routine inflammatory dermatoses, and therefore these markers are not specific for aggressive lymphoproliferative disorders. Using only immunohistochemical data, the ratio of CD4- to CD8-positive lymphocytes could not be used reliably to separate the superficial and deep perivascular dermatoses from one another. Finally, mast cells are positive for TIA-1 and are commonly seen in normal and inflamed skin, and thus TIA-1 is not specific for cytotoxic T lymphocytes.