Multivariate LSTM Modeling for Wastewater Quality Prediction
Abstract
The proposed approach relies on high-frequency multivariate time series collected at the Seine aval (SIAAP 1 ) treatment plant, including pH, temperature, conductivity, and total suspended solids, as well as exogenous variables related to precipitation and measurements from an upstream plant. The objective is to forecast wastewater quality over a 24-hour horizon. A multivariate Long Short-Term Memory (LSTM) recurrent neural network is implemented to capture complex temporal dependencies and nonlinear patterns in the data. The model is trained on one year of data and validated on four months of data (one per season), and is compared with a persistence model and SARIMA models. The evaluation shows an overall superiority of the LSTM model, particularly for variables exhibiting high levels of noise and nonlinearity.
Related
- Short-term metro passenger flow forecasting via decoupled spatio-temporal modeling with a diffusion-convergence graph and Swin-Enhanced LSTM
- Modeling Disease Transmission Dynamics with Population-Weighted Spatial Inference for Wastewater-Based Epidemiology
- Bayesian Spatio-temporal Modeling of Multi-Site Wastewater Surveillance Data
- Generalized Hyperrectangular Prediction Sets in Multivariate Conformal Prediction
- Covariate-dependent Joint Modeling of Multivariate Ordinal Preferences and Its Connections with Comparison Models
BibTeX
@misc{laruelle2026multivariate,
title = {{Multivariate LSTM Modeling for Wastewater Quality Prediction}},
author = {Sophie Laruelle and Innocentia Bénédicta Sossou},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.09996},
eprint = {2610.09996},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05774555v1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Multivariate LSTM Modeling for Wastewater Quality Prediction
AU - Sophie Laruelle
AU - Innocentia Bénédicta Sossou
PY - 2026
DA - 2026/10/07
PB - HAL
DO - 10.48550/arxiv.2610.09996
UR - https://hal.science/hal-05774555v1
AB - The proposed approach relies on high-frequency multivariate time series collected at the Seine aval (SIAAP 1 ) treatment plant, including pH, temperature, conductivity, and total suspended solids, as well as exogenous variables related to precipitation and measurements from an upstream plant. The objective is to forecast wastewater quality over a 24-hour horizon. A multivariate Long Short-Term Memory (LSTM) recurrent neural network is implemented to capture complex temporal dependencies and nonlinear patterns in the data. The model is trained on one year of data and validated on four months of data (one per season), and is compared with a persistence model and SARIMA models. The evaluation shows an overall superiority of the LSTM model, particularly for variables exhibiting high levels of noise and nonlinearity.
ER -