Skip to content

Water level prediction for a reservoir comparing uni- and multivariate models (ARIMA, Prophet, CatBoost Trees and LSTM) and assessing important features.

Notifications You must be signed in to change notification settings

mfriebel/waterlevel_prediction

Repository files navigation

Sustainable water management analytics

In this project the groundwater level of the reservoir Petrignano, Italy is predicted using different time-series models. It uses an dataset from the Acea Group, that was part of an Kaggle Competition. The aim was to identify import features and a reliable model to manage the reservoir sustainable.

Dataset: Acea Smart Water Analytics

About

Water level prediction for a reservoir comparing uni- and multivariate models (ARIMA, Prophet, CatBoost Trees and LSTM) and assessing important features.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published