In-stream <i>Escherichia coli</i> modeling using high-temporal-resolution data with deep learning and process-based models

Contamination of surface waters with microbiological pollutants is a major concern to public health. Although long-term and high-frequency Escherichia coli (E. coli) monitoring can help prevent diseases from fecal pathogenic microorganisms, such monitoring is time-consuming and expensive. Process-driven models are an alternative means for estimating concentrations of fecal pathogens. However, process-based modeling still has limitations in improving the model accuracy because of the complexity of relationships among hydrological and environmental variables. With the rise of data availability and computation power, the use of data-driven models is increasing. In this study, we simulated fate and transport of E. coli in a 0.6 km2 tropical headwater catchment located in the Lao People's Democratic Republic (Lao PDR) using a deep-learning model and a process-based model. The deep learning model was built using the long short-term memory (LSTM) methodology, whereas the process-based model was constructed using the Hydrological Simulation Program–FORTRAN (HSPF). First, we calibrated both models for surface as well as for subsurface flow. Then, we simulated the E. coli transport with 6 min time steps with both the HSPF and LSTM models. The LSTM provided accurate results for surface and subsurface flow with 0.51 and 0.64 of the Nash–Sutcliffe efficiency (NSE) values, respectively. In contrast, the NSE values yielded by the HSPF were −0.7 and 0.59 for surface and subsurface flow. The simulated E. coli concentrations from LSTM provided the NSE of 0.35, whereas the HSPF gave an unacceptable performance with an NSE value of −3.01 due to the limitations of HSPF in capturing the dynamics of E. coli with land-use change. The simulated E. coli concentration showed the rise and drop patterns corresponding to annual changes in land use. This study showcases the application of deep-learning-based models as an efficient alternative to process-based models for E. coli fate and transport simulation at the catchment scale.

In-stream Escherichia Coli Modeling Using high-temporal-resolution data with deep learning and process-based models

Contamination of surface waters through microbiological pollutants is a major concern to public health. Although long-term and high-frequency E. coli monitoring can help prevent diseases from fecal pathogenic microorganisms, this monitoring is time consuming and expensive. Process-driven models are an alternative method for determining fecal pathogenic microorganisms. However, process-based modeling still has limitations in improving the model accuracy because of the complex mechanistic relationships among hydrological and environmental variables. On the other hand, with the rise in data availability and computation power, the use of data-driven models is increasing. Therefore, in this study, we simulated the transport of Escherichia coli (E. coli) in a 0.6 km² tropical headwater catchment located in Lao PDR using a deep learning model and a process-based model. The deep learning model was built using the long short-term memory (LSTM) technique, whereas the process-based model was constructed using the Hydrological Simulation Program–FORTRAN (HSPF). First, we calibrated both models for surface as well as for subsurface flow. Then, we simulated the E. coli transport with 6 min time steps with both the HSPF and LSTM models. The LSTM provided accurate results for surface and subsurface flow, by showing 0.51 and 0.64 of Nash–Sutcliffe Efficiency (NSE), respectively, whereas the NSE values yielded by the HSPF were −0.7 and 0.59 for surface and subsurface flow. The simulated E. coli concentration from LSTM also improved, yielding an NSE of 0.35, whereas the HSPF showed an unacceptable performance, with an NSE value of −3.01. This is because of the limitation of HSPF in capturing the dynamics of E. coli with land-use change. The simulated E. coli concentration showed rise and drop patterns corresponding to annual changes in land use. This study shows the application of deep learning-based models as an efficient alternative to process-based models for E. coil fate and transport simulation at the catchment scale.

Assessing the perturbations of the hydrogeological regime in sloping fens due to roads

Roads in sloping fens constitute a hydraulic barrier for surface and subsurface flow. This can lead to the drying out of downslope areas of the sloping fen as well as gully erosion. Different types of road construction have been proposed to limit the negative implications of roads on flow dynamics. However, so far, no systematic analysis of their effectiveness has been carried out. This study presents an assessment of the hydrogeological impact of three types of road structures in semi-alpine, sloping fens in Switzerland. Our analysis is based on a combination of field measurements and fully integrated, physically based modeling. In the field approach, the influence of roads was examined using tracer tests in which the area upslope of the road was sprinkled with a saline solution. The spatial distribution of electrical conductivity downslope provided a qualitative assessment of the flow paths and, thus, the implications of the road structures on subsurface flow. A quantitative albeit not site-specific assessment was carried out using fully coupled numerical models jointly simulating surface and subsurface flow processes. The different road types were implemented and their influence on flow dynamics was assessed for a wide range of slopes and different hydraulic conductivities of the soil. The models are based on homogenous soil conditions, allowing for a relative ranking of the impact of the road types. For all cases analyzed in the field and simulated using the numerical models, roads designed with an L drain (i.e., collecting water upslope and releasing it in a concentrated manner downslope) constitute the largest perturbations in terms of flow dynamics. The other road structures investigated were found to have less impact. The developed methodologies and results can be used for the planning of future road projects in sloping fens.

Assessing the perturbations of the hydrogeological regime in sloping fens through roads

Roads in sloping fens constitute a hydraulic barrier for surface and subsurface flow. This can lead to a drying out of downslope areas of the sloping fen as well as gully erosion. Different types of road construction have been proposed to limit the negative implications of the roads on flow dynamics. However, so far no systematic analysis of their effectiveness has been carried out. This study presents an assessment of the hydrogeological impact of three types of road structures in semi-alpine, sloping fens in Switzerland. Our analysis is based on a combination of field measurements and fully integrated, physically based modelling. In the field approach, the influence of the road was examined through tracer tests where the upslope of the road was sprinkled with a saline solution. The spatial distribution of electrical conductivity downslope provided a qualitative assessment of the flow paths and thus the implications of the road structures on subsurface flow. A quantitative albeit not site-specific assessment was carried out using numerical models simulating surface and subsurface flow in a fully coupled way. The different road types were implemented in the model and flow dynamics were simulated for a wide range of slopes and hydrogeological conditions such as different hydraulic conductivity of the soil. The results of the field and modelling analysis are coherent. Roads designed with an L-drain collecting water upslope and releasing it in a concentrated manner downslope constitute the largest perturbations. The other investigated road structures were found to have less impact. The developed methodologies and results are useful for the planning of future road projects.

Surface and subsurface contributions to the build-up of forces on bed particles

In nature and in many industrial applications, the boundary of a channel flow is made of solid particles which form a porous wall, so that there is a mutual influence between the free flow and the subsurface flow developing inside the pores. While the influence of the porous wall on the free flow has been well studied, less well characterized is the subsurface flow, due to the practical difficulties in gathering information in the small spaces given by the pores. It is also not clear whether the subsurface flow can host turbulent events able to contribute significantly to the build-up of forces on the particles, potentially leading to their dislodgement. Through large eddy simulations, we investigate the interface between a free flow and a bed composed of spherical particles in a cubic arrangement. The communication between surface and subsurface flow is in this case enhanced, with relatively strong turbulent events happening also inside the pores. After comparing the simulation results with a previous experimental work from a similar setting, the forces experienced by the boundary particles are analysed. While it remains true that the lift forces are largely dependent on the structure of the free flow, turbulence inside the pores can also give a significant contribution. Pressure inside the pores is weakly correlated to the pressure in the free flow, and strong peaks above and below a particle can happen independently. Ignoring the porous layer below the particle from the computations leads then in this case to an underestimation of the lift forces.