1. This paper presents a systematic review of the literature related to the application and characterization of ANN-based metamodels for building performance simulation.
2. It provides an insight into the methodology of metamodel generation and ANN theory, as well as a critical review of different stages for the generation of ANN-based metamodels.
3. The current limitations and areas for further investigation are discussed.
The article is generally reliable and trustworthy, providing a comprehensive overview of the use of artificial neural networks (ANNs) metamodels in building performance simulation (BPS). The authors provide an in-depth systematic review of the up-to-date literature related to the application and characterization of ANN-based metamodels for BPS, including a general insight into the methodology of metamodel generation and ANN theory, as well as a critical review of different stages for the generation of ANN-based metamodels. The article also discusses current limitations and areas for further investigation.
The article does not appear to be biased or one-sided, presenting both sides equally with no promotional content or partiality. All claims made are supported by evidence from relevant sources, while possible risks are noted throughout. There do not appear to be any unsupported claims or missing points of consideration, although there may be some unexplored counterarguments that could have been included in order to provide a more comprehensive overview.