Forecasting municipal water demands: Evaluating the impacts of population growth, climate change, and conservation policies on water end-use
Hanyu Liu, Rui Xing, Evan Davies
Abstract
Urban population growth, climate change, and uncertainty about future technologies, behaviors, and policies have made long-term municipal water demand forecasting increasingly complex. This study introduces the Edmonton Water Demand Simulator (EWDS), a novel hybrid model that integrates system dynamics, artificial neural networks, and regression techniques to forecast municipal water demand at a weekly scale through 2100. The EWDS was validated against historical municipal data and applied to scenario-based experiments for Edmonton, Canada. Results quantify the relative and combined impacts of population growth, climate change, technological change, and conservation measures. Population growth emerged as the dominant driver, with a 20 % difference in water demand between high and low growth scenarios by 2100. Climate change increased total demand by 12 %, primarily through higher outdoor water use and longer watering seasons. Conservation efforts reduced per capita demand by up to 15 %. Under high population growth and greater climate change without new conservation efforts, municipal demand was projected to double by 2066, while slower growth and conservation delayed doubling by nearly 30 years. These findings highlight the critical role of conservation in mitigating future demands, while also emphasizing the need to account for demographic and climate-driven changes. The EWDS framework is transferable to other regions with similar demand structures and supports sustainable water management under uncertainty.