Back

Forecasting Urban Wastewater Microbiome Dynamics Using a Digital Twin Framework

Shrestha Gurung, B. D.; Rayamajhi, M.; Maharjan, N.; Aryal, S.; Yadav, R.; Do, T.; Bhandari, D.; Gnimpieba, E. Z.

2025-07-25 bioinformatics
10.1101/2025.07.21.666059 bioRxiv
Show abstract

Urban wastewater microbiomes are complex and temporally dynamic, offering valuable insight into community-scale microbial ecology and potential public health trends. However, existing wastewater-based studies often remain descriptive, lacking tools for predictive modeling. In this study, we introduce a digital twin framework that forecasts microbial abundance trajectories in urban wastewater using an interpretable generative model, Q-net. Trained on a 30-week longitudinal metagenomic dataset from seven wastewater treatment plants, the model captures temporal microbial dynamics with high fidelity (R2 > 0.97 for key taxa; R2 = 0.998 at the final timepoint). Beyond accurate forecasting, Q-net provides transparent model structure through conditional inference trees and enables simulation of realistic microbial trends under hypothetical scenarios. This work demonstrates the potential of digital twins to move wastewater microbiome studies from static snapshots to dynamic, predictive systems, with broad implications for environmental monitoring and microbial ecosystem modeling.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.