{"id":2902,"date":"2026-06-23T10:51:05","date_gmt":"2026-06-23T10:51:05","guid":{"rendered":"https:\/\/artelnics.com\/case_studies\/acciona-water-flow-forecasting\/"},"modified":"2026-08-21T20:20:23","modified_gmt":"2026-08-21T20:20:23","slug":"acciona-water-flow-forecasting","status":"publish","type":"case_studies","link":"https:\/\/artelnics.com\/case_studies\/acciona-water-flow-forecasting\/","title":{"rendered":"Forecasting water flows across distribution networks"},"content":{"rendered":"
\n
\n

Machine-learning models estimate future water flow by station and hour to support planning in distribution networks.<\/p>\n

\n Water and utilities<\/span>
\n Time-series forecasting<\/span>
\n Operational planning<\/span>\n <\/div>\n

Challenge<\/h2>\n

Network operators need short-term forecasts of water demand at different stations to plan resources, detect unusual behavior and operate the network with more confidence.<\/p>\n

Data<\/h2>\n

The forecasting service used historical flow data together with weather information, calendar variables and holidays. The system organized predictions by station and forecast horizon.<\/p>\n

Solution<\/h2>\n

Artelnics designed a forecasting workflow that trains predictive models for each station and hour, producing multi-day flow predictions that can be consumed by operational systems.<\/p>\n

\n
Forecast horizon<\/strong><\/p>\n

Hourly predictions several days ahead.<\/p>\n<\/div>\n

Inputs<\/strong><\/p>\n

Historical flows, weather variables and calendar effects.<\/p>\n<\/div>\n<\/div>\n

Results<\/h2>\n

The system provides structured forecasts for network planning and gives operators a quantitative view of expected demand before it happens.<\/p>\n

Illustrations<\/h2>\n
\"Forecast
Water flow forecast chart<\/figcaption><\/figure>\n<\/article>\n