Univariate Long-Term Municipal Water Demand Forecasting

05/18/2021
by   Blake VanBerlo, et al.
0

This study describes an investigation into the modelling of citywide water consumption in London, Canada. Multiple modelling techniques were evaluated for the task of univariate time series forecasting with water consumption, including linear regression, Facebook's Prophet method, recurrent neural networks, and convolutional neural networks. Prophet was identified as the model of choice, having achieved a mean absolute percentage error of 2.51 averaged across a 5-fold cross validation. Prophet was also found to have other advantages deemed valuable to water demand management stakeholders, including inherent interpretability and graceful handling of missing data. The implementation for the methods described in this paper has been open sourced, as they may be adaptable by other municipalities.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

03/01/2020

Data Pre-Processing and Evaluating the Performance of Several Data Mining Methods for Predicting Irrigation Water Requirement

Recent drought and population growth are planting unprecedented demand f...
04/16/2021

Probabilistic water demand forecasting using quantile regression algorithms

Machine and statistical learning algorithms can be reliably automated an...
12/23/2020

Global Models for Time Series Forecasting: A Simulation Study

In the current context of Big Data, the nature of many forecasting probl...
02/06/2020

Progressive Cleaning and Mining of Uncertain Smart Water Meter Data

Several municipalities have recently installed wireless 'smart' water me...
05/09/2020

Probabilistic Multi-Step-Ahead Short-Term Water Demand Forecasting with Lasso

Water demand is a highly important variable for operational control and ...
06/21/2019

Accurate Robotic Pouring for Serving Drinks

Pouring is the second most frequently executed motion in cooking scenari...
12/12/2018

Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks

Purpose: To perform and evaluate water and fat signal separation of whol...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.