Computer models are powerful tools that allow us to analyze problems in unprecedented detail and to conduct experiments impossible with the real system. Reliance on computer models in science and policy decisions has been challenged by philosophers of science on methodological and epistemological grounds. This challenge is examined for the case of climate models by reviewing what they are and what climate scientists do with them, followed by an analysis of how they can be used to construct new trustworthy knowledge. A climate model is an executable computer code that solves a set of mathematical equations assumed to represent the climate system. Climate modelers use these models to simulate present and past climates and forecast likely and plausible future evolutions. Model uncertainties and model calibration are identified as the two major concerns. Climate models of different complexity address different question. Their interplay helps to weed out model errors, identify robust features, understand the climate system, and build confidence in the models, but is no guard against flaws in the underlying physics. (C) 2010 John Wiley & Sons, Ltd. WIREs Clim Change 2010 1 565-580
