Ever growing understanding of general ecological, biogeochemical and climatic processes is allowing for the construction of a growing list of end-to-end models. While many of these are taking the form of generic modelling frameworks, no one approach defines end-to-end ecosystem modelling. There is a wide range of scales, resolutions, forcings, components and represented processes. Examples drawn from existing models can be used to give guidance on best practice approaches for creating end-to-end models. In particular, it is clear that defaulting to the finest resolution and greatest complexity in all the dimensions (e.g. spatial, temporal, taxonomic, process detail) is not beneficial. There is also a lot of value, during model development and implementation, in trying different model types, assumptions and formulations; there is no one "best" model. Maintaining a diversity of approaches is important given that end-to-end models are most effective when used as strategic tools, to address questions that are at scales where there is still a lot of uncertainty about how systems function. There are still many challenges facing the end-to-end modelling field, particularly when long simulation periods are called for, but perhaps the greatest ones are: non-stationarity introduced by shifting climate, biodiversity and evolution; representing human responses; and handling uncertainty. (C) 2009 Elsevier B.V. All rights reserved.
