GiovanniIacuzzo/water-4.0
WATER 4.0 predicts water leakage in distribution networks using a conditional GAN for scenario generation, an LSTM for leakage prediction, and CPSO for hyperparameter tuning, enabling accurate and probabilistic estimates.
This project helps water utility managers and operations engineers predict water leakage in distribution networks. It takes historical data on pressures, flows, demands, and water levels as input, then generates realistic future scenarios. From these scenarios, it produces accurate, probabilistic estimates of potential water loss (in m³/h) across the network, enabling better resource management.
No commits in the last 6 months.
Use this if you need to forecast water leakage in complex distribution networks and want a probabilistic understanding of potential water loss under various future conditions.
Not ideal if you only need a simple, point-in-time leakage estimate without considering multiple future scenarios or if you lack historical sensor data for your water network.
Stars
11
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GiovanniIacuzzo/water-4.0"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OuyangWenyu/torchhydro
TorchHydro: datasets, and models for watershed hydrological modeling
confidence-duku/bakaano-hydro
A distributed hydrology-guided neural network model for streamflow prediction
mhpi/hydrodl2
Repository for MHPI differentiable hydrological models.
WaterFutures/water-futures-battle
Part of the Battle of Water Networks competition series | WDSA/CCWI 2026, May 18-21, Paphos,...
IBM/Environmental-Intelligence-Suite
IBM Environmental Intelligence Suite