Assembling ensembling: An adventure in approaches across disciplines
When discussing model ensembling or ensemble modeling, a term arises across numerous disciplines, what is meant by it can vary drastically. The very meaning of 'ensemble' - a collection together - conjures different ideas even within disciplines when approaching phenomena. For example, one might think of a set of descriptions of a phenomenon in the world, perhaps a time series or a snapshot of multivariate space, and perhaps that set is comprised of data-independent descriptions, or perhaps it is quite intentionally fit *to* data, or even a suite of data sets with a common theme or intention. Recently, ensemble models have appeared widely across applications, for disease forecasting, environmental suitability modeling, and more. In this piece, we present a typology of the scope of potential perspectives across disciplines to disambiguate terms, concepts, and processes associated with 'ensembles' and 'ensembling'. We do not provide an exhaustive review nor do we recommend that all disciplines must adopt a common suite of terms, but instead focus on facilitating communication, awareness, identification of gaps, and adoption of tools to avoid independent efforts to reinvent the wheel across disciplines. To anchor our discussion, we provide a Shiny App to contain the typology, with a living collection, or compendium, of example publications about ensembles.