Probabilistic modeling and uncertainty estimation of urban water consumption under an incompletely informational circumstance

摘要: With a booming development characterized by new urbanization in current China, urban water consumption attracts growing concerns. An efficient and probabilistic prediction of plays vital role for planning toward sustainable development, especially megacities limited resources. However, the data insufficiency issue commonly exists nowadays seriously restricts further simulation. In this article, we proposed consolidated framework under an incompletely informational circumstance to deal with challenge. The model was constructed based on state-of-the-art Bayesian neural networks (BNNs) technique. Three dominated influencing factors were identified included into BNN model. Future impact generated using variety methods including quadratic polynomial model, regression auto-regressive moving average combination Grey Verhulst Thereafter, projection (2013–2020) uncertainty estimates done. Results showed that matched well observations. Through reducing dependence large amount information constructing means incorporating estimation, approach can work better than conventional support resources management circumstance.