Author(s): Biniam Abrha Tsegay; Ali Khajavian; Nicolas Peleato

Linked Author(s):

Keywords: Data augmentation; Generative modeling; Smart water meters; Water demand prediction

Abstract: Urban Water Distribution Systems (WDS) require accurate demand forecasting for effective planning and resource management. However, traditional forecasting models often fail under different environmental changes that alter consumption patterns beyond their training scope. This study proposes an Environment-Aware Conditional Variational Autoencoder(Time-VAE), a generative framework that produces realistic, weather-conditioned synthetic water demand data to enhance forecasting robustness. Validated on the FP7 DAIAD dataset (Alicante, Spain; 1,099 users), Random Forest models trained on augmented data achieved 48.9% mean RMSE reduction (169.56 vs 331.64 L/hr) with a 92% success rate across 25 trial combinations of 100 users. Results demonstrate that weather-conditioned synthetic data augmentation effectively improves water demand forecasting under data-scarce conditions.

DOI:

Year: 2026