In-stream Escherichia coli 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 timeconsuming 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 led by Ather Abbas, PhD student at the Ulsan National Institute of Science & Technology (UNIST) in Korea, fate and transport of E. coli was simulated in the 0.6 km² Houay Pano tropical headwater catchment located Lao PDR, using both a deep-learning model and a process-based model. 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.

The paper has been published open access in the journal Hydrology & Earth System Sciences Discussions.

More news


Escherichia coli concentration, multiscale monitoring over the decade 2011–2021 in the Mekong River basin, Lao PDR

Bacterial pathogens in surface waters may threaten human health, especially in developing countries, where untreated surface water is often used for domestic needs. The objective of the long-term multiscale monitoring of Escherichia coli concentration in stream water, and that of associated variables (temperature, electrical conductance, dissolved oxygen concentration and saturation, pH, oxidation-reduction potential, turbidity, and […]



Groundwater irrigation reduces overall poverty but increases socioeconomic vulnerability in a semiarid region of southern India

The development of irrigation is generally considered an efficient way to reduce poverty in rural areas, although its impact on the inequality between farmers is more debated. In fact, assessing the impact of water management on different categories of farmers requires resituating it within the different dimensions of the local socio-technical context. This study, led […]



Distribution of Burkholderia pseudomallei within a 300‑cm deep soil profile: implications for environmental sampling

The environmental distribution of Burkholderia pseudomallei, the causative agent of melioidosis, remains poorly understood. This study performed in Lao PDR and supervised by Alain Pierret (IRD-iEES Paris) and Olivier Ribolzi (IRD-GET), in the frame of the PhD of Khemngeun Pongmala, provides novel information about a putative association of soil biogeochemical heterogeneity and the vertical distribution […]