ABSTRACT Peak daily water demand (Kd) is a critical parameter in water supply planning and distribution system design, ensuring that system capacity meets customer water consumption and enhancing investment efficiency. Identifying appropriate indicators requires consideration of local usage patterns and the impacts of climate change. This paper introduces a novel hybrid model that integrates Seasonal Autoregressive Integrated Moving Average (SARIMA) with Artificial Neural Networks (ANN) to forecast Kd using data collected from DMA01 in District 5, Ho Chi Minh City, Vietnam, covering the years 2017–2022, including the COVID-19 period. SARIMA provided initial predictions, with ANN refining residuals to achieve an MAPE of 9%. When applied to DMA01, with 1,730 customers over six years, showed that the Kd value of 2.87 for the next planning period exceeds the Vietnamese standard (1.1–1.4) and is consistent with U.S. and Australian benchmarks. The results of the study highlight its potential to enhance water demand forecasting and to offer a scalable solution for developing regions facing climate challenges.
Minh et al. (Sat,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: