Predicting bacterial transport through saturated porous media using an automated machine learning model

Abstract

Escherichia coli, as an indicator of fecal contamination, can move from manure-amended soil to groundwater under rainfall or irrigation events. Predicting its vertical transport in the subsurface is essential for the development of engineering solutions to reduce the risk of microbiological contamination. In this study, we collected 377 datasets from 61 published papers addressing E. coli transport through saturated porous media and trained six types of machine learning algorithms to predict bacterial transport. Eight variables, including bacterial concentration, porous medium type, median grain size, ionic strength, pore water velocity, column length, saturated hydraulic conductivity, and organic matter content were used as input variables while the first-order attachment coefficient and spatial removal rate were set as target variables. The eight input variables have low correlations with the target variables, namely, they cannot predict target variables independently. However, using the predictive models, input variables can effectively predict the target variables. For scenarios with higher bacterial retention, such as smaller median grain size, the predictive models showed better performance. Among six types of machine learning algorithms, Gradient Boosting Machine and Extreme Gradient Boosting outperformed other algorithms. In most predictive models, pore water velocity, ionic strength, median grain size, and column length showed higher importance than other input variables. This study provided a valuable tool to evaluate the transport risk of E.coli in the subsurface under saturated water flow conditions. It also proved the feasibility of data-driven methods that could be used for predicting other contaminants’ transport in the environment.

Estimating bacterial breakthrough behaviors based on bacterial retention profiles in porous media

“…B-I exhibited varying degrees of bacterial retention. The plateau concentrations across the nine BTCs varied from 0.2 to 1, highlighting a broad spectrum of bacterial retention levels in soil (Chen et al, 2023). The R 2 values for the model fits ranged between 0.71 and 0.95, with an average R 2 of 0.87, demonstrating that the traditional method effectively captured most of the BTC and RP dynamics.…”

“…The experimental setup, illustrated in Figure 1a, adheres to the protocol outlined by Zhang et al (2022). According to the literature, the bacterial concentration typically used in column experiments ranges from 10 7 to 10 9 cell mL −1 (F. Chen et al, 2023).…”

“…Following collection, bacterial concentrations in the soil can be determined using various counting methods, including plate count, microscopy count, quantitative polymerase chain reaction (qPCR), bioluminescent count, flow cytometry method, and geometric viability assay (Foght & Aislabie, 2005;Gyawali et al, 2016;Lee et al, 2021;Meyer et al, 2023;Vignola et al, 2018;Yang et al, 2021;Zhang et al, 2022). Research indicates that bacterial concentrations in natural soils, permeable sand aquifers, and organic fertilizers typically range from 10 6 to 10 9 cells per gram (Bressan et al, 2015;F. Chen et al, 2023;DeFlaun et al, 1997;Yadav et al, 2022).…”