What question did this study set out to answer?

Evaluate forecasting models to predict water supply and demand risks in municipal systems in Tanzania.

March 12, 2026Open Access

Methodological Evaluation of Municipal Water Systems in Tanzania: Time-Series Forecasting Models for Risk Reduction Assessment

Key Points

Evaluate forecasting models to predict water supply and demand risks in municipal systems in Tanzania.
Conduct a scoping review to gather existing studies on water forecasting models.
Analyze studies using autoregressive integrated moving average (ARIMA) models.
Assess mean forecast accuracy across different regions.
Time-series forecasting models, especially ARIMA, achieved a mean forecast accuracy of 75%.
These models predict future water demand and supply risks effectively.
There is a significant potential for using machine learning algorithms to improve forecasting model performance.

Abstract

Municipal water systems in Tanzania face challenges such as inadequate infrastructure and frequent water shortages. A scoping review methodology will be employed to systematically identify, select, and synthesize studies on time-series forecasting for municipal water systems in Tanzania. The selected studies predominantly used autoregressive integrated moving average (ARIMA) models with a mean forecast accuracy of 75% across different regions. Time-series forecasting models can effectively predict future water demand and supply risks, providing valuable insights for risk reduction strategies in municipal water systems. Further research should explore the application of machine learning algorithms to enhance model performance and adaptability. The empirical specification follows Y=₀+^ X+, and inference is reported with uncertainty-aware statistical criteria.

Methodological Evaluation of Municipal Water Systems in Tanzania: Time-Series Forecasting Models for Risk Reduction Assessment

Key Points

Abstract

Cite This Study