PyLEnM: A Machine Learning Framework for Long-Term Groundwater Contamination Monitoring Strategies.

In this study, we have developed a comprehensive machine learning (ML) framework for long-term groundwater contamination monitoring as the Python package PyLEnM (Python for Long-term Environmental Monitoring). PyLEnM aims to establish the seamless data-to-ML pipeline with various utility functions, such as quality assurance and quality control (QA/QC), coincident/colocated data identification, the automated ingestion and processing of publicly available spatial data layers, and novel data summarization/visualization. The key ML innovations include (1) time series/multianalyte clustering to find the well groups that have similar groundwater dynamics and to inform spatial interpolation and well optimization, (2) the automated model selection and parameter tuning, comparing multiple regression models for spatial interpolation, (3) the proxy-based spatial interpolation method by including spatial data layers or in situ measurable variables as predictors for contaminant concentrations and groundwater levels, and (4) the new well optimization algorithm to identify the most effective subset of wells for maintaining the spatial interpolation ability for long-term monitoring. We demonstrate our methodology using the monitoring data at the Savannah River Site F-Area. Through this open-source PyLEnM package, we aim to improve the transparency of data analytics at contaminated sites, empowering concerned citizens as well as improving public relations.

The effect of bicarbonate on the microbial dissolution of autunite mineral in the presence of gram-positive bacteria.

Bacteria are key players in the processes that govern fate and transport of contaminants. The uranium release from Na and Ca-autunite by Arthrobacter oxydans strain G968 was evaluated in the presence of bicarbonate ions. This bacterium was previously isolated from Hanford Site soil and in earlier prescreening tests demonstrated low tolerance to U(VI) toxicity compared to other A. oxydans isolates. Experiments were conducted using glass serum bottles as mixed bioreactors and sterile 6-well cell culture plates with inserts separating bacteria cells from mineral solids. Reactors containing phosphorus-limiting media were amended with bicarbonate ranging between 0 and 10 mM and meta-autunite solids to provide a U(VI) concentration of 4.4 mmol/L. Results showed that in the presence of bicarbonate, A. oxydans G968 was able to enhance the release of U(VI) from Na and Ca autunite at the same capacity as other A. oxydans isolates with relatively high tolerance to U(VI). The effect of bacterial strains on autunite dissolution decreases as the concentration of bicarbonate increases. The results illustrate that direct interaction between the bacteria and the mineral is not necessary to result in U(VI) biorelease from autunite. The formation of secondary calcium-phosphate mineral phases on the surface of the mineral during the dissolution can ultimately reduce the natural autunite mineral contact area, which bacterial cells can access. This thereby reduces the concentration of uranium released into the solution. This study provides a better understanding of the interactions between meta-autunite and microbes in conditions mimicking arid and semiarid subsurface environments of western U.S.