Opinion: Why all emergent constraints are wrong but some are useful – a machine learning perspective

Abstract. Global climate change projections are subject to substantial modelling uncertainties. A variety of emergent constraints, as well as several other statistical model evaluation approaches, have been suggested to address these uncertainties. However, they remain heavily debated in the climate science community. Still, the central idea to relate future model projections to already observable quantities has no real substitute. Here we highlight the validation perspective of predictive skill in the machine learning community as a promising alternative viewpoint. Building on this perspective, we review machine learning ideas for new types of controlling factor analyses (CFA). The principal idea behind these CFA is to use machine learning to find climate-invariant relationships in historical data, which also hold approximately under strong climate change scenarios. On the basis of existing data archives, these climate-invariant relationships can be validated in perfect-climate-model frameworks. From a machine learning perspective, we argue that such approaches are promising for three reasons: (a) they can be objectively validated both for past data and future data, (b) they provide more direct – by design physically-plausible – links between historical observations and potential future climates and (c) they can take higher dimensional relationships into account that better characterize the still complex nature of large-scale emerging relationships. We demonstrate these advantages for two recently published CFA examples in the form of constraints on climate feedback mechanisms (clouds, stratospheric water vapour), and discuss further challenges and opportunities using the example of a climate forcing (aerosol-cloud interactions).