Short-Term Forecasting of Household Water Demand in the UK Using an Interpretable Machine Learning Approach

Abstract

This study utilises a rich UK dataset of smart demand metering data, household 10 characteristics, and weather data to develop a demand forecasting methodology that combines 11 the high accuracy of machine learning models with the transparency of regression methods. 12 For this reason, a Random Forest model is used to predict daily demands one day ahead for groups of properties (mean of 3.8 households/group) with homogenous characteristics. A variety of interpretable machine learning techniques (variable permutation, Accumulated Local Effects plots -ALE, Individual Conditional Expectation curves -ICE) are used to quantify the influence of these predictors (temporal, weather, and household characteristics) on water consumption. Results show that when past consumption data are available, they are the most important explanatory factor. However, when they are not, a combination of household and temporal characteristics can be used to produce a credible model with similar forecasting accuracy. Weather input has overall a mild to no effect on the model's output, although this effect can become significant under certain conditions.

An ensemble stacked model with bias correction for improved water demand forecasting

“…However, model-agnostic interpretability methods (i.e. ones that can be used on any machine learning model) can assist with overcoming this issue by combining the high accuracy of stacked models with the understanding of more transparent and interpretable methods (Molnar, 2019;Xenochristou et al, 2020b).…”

“…families with children, students, young professionals), or even certain habits. Since all of these customer and property characteristics are associated with different patterns and volumes of water use (Xenochristou et al, 2020b), the postcode was considered a valuable indicator of water habits. Finally, the temporal patterns of water use are a well-researched factor in the demand forecasting literature, therefore the type of day (working day vs weekend/holiday) and the season were also used as model inputs (Bakker et al, 2013;Romano and Kapelan, 2014;Anele et al, 2017;Xenochristou et al, 2020b).…”

Advanced Strategies for Monitoring Water Consumption Patterns in Households Based on IoT and Machine Learning

“…According to Koo et al [20], a universal method by which water demand can be predicted has not yet been discovered, as this depends on many factors that can vary. For example, the forecast can be made in the short term (hours, days, or weeks) [21], medium term (between one and two years) [22], or long term (more than two years) [23]. Making a short-term forecast can be essential in the decision-making process of water suppliers, organizations, or companies at the managerial level.…”

Probabilistic Water Demand Forecasting Using Quantile Regression Algorithms

“…In this work, we aim to fill the current gap of not benefitting from quantile regression algorithms and their underlying concepts in the urban water demand forecasting field and, therefore, to propose a new family of urban water demand forecasting algorithms. We also aim to provide the first extensive comparison of such algorithms by using one of the largest datasets used so far in the field (see also the datasets in Duerr et al., 2018; Xenochristou & Kapelan, 2020; Xenochristou et al., 2020, 2021). We additionally consider one of the largest sets of predictor variables and provide large‐scale results on their relative importance.…”

“…PAPACHARALAMPOUS AND LANGOUSIS 10.1029/2021WR030216 2 of 19 applied at scale (Papacharalampous et al, 2019). Therefore, they are befitting and increasingly adopted for solving urban water demand forecasting problems (see, e.g., Duerr et al, 2018;Herrera et al, 2010;Herrera et al, 2011;Lee & Derrible, 2020;Nunes Carvalho et al, 2021;Quilty & Adamowski, 2018;Quilty et al, 2016;Smolak et al, 2020;Xenochristou et al, 2021), and several other water informatics problems (see, e.g., Althoff, Dias, et al, 2020;Althoff, Bazame, & Garcia, 2021;Markonis & Strnad, 2020;Rahman, Hosono, Kisi, et al, 2020;Rahman, Hosono, Quilty, et al, 2020;Sahoo et al, 2019;Scheuer et al, 2021;Tyralis & Papacharalampous, 2017;Xu, Chen, Moradkhani, et al, 2020).…”