On digital soil assessment with models and the Pedometrics agenda

The unique selling point of pedometricians still is close to their cradle: ability to map. Irrespective of the many scientific achievements one can ask if offering mapping ability, allbeit in various contexts, is all a pedometrician can do to bring forward soil science's broader agenda. This paper identifies, within some of the hotter issues on the soil science agenda, activities that need the input of pedometricians. Digital soil mapping (DSM) has reached maturity although some issues like the optimal use of legacy data still need attention. The necessary shift from DSM to digital soil function mapping implies an increased need for process knowledge in mapping, but also an increased focus of pedometricians on the strengthening of process models. Most quality issues related to DSM have a counterpart in process modelling, and some of these issues need elaboration to construct well-calibrated and complete models, e.g. by making motivated choices between the inclusion of processes or model reduction. Reaching out to stakeholders is also an issue of increasing interest, as these are confronted with uncertain concurrent models to evaluate future scenarios. Questions are raised such as: Does the need for a state-of-the-art (SOTA) approach imply a choice for one model and how should this be made, or is SOTA implementable as some weighted average of screened concurrent models. Can observations and model results be combined in decision making and what techniques are needed. The above issues are illustrated with existing examples and new material from soil science and beyond. As DSM and process modelling share common ground, mutual benefits can be expected at the interface of both research fields such as (i) increased usage of process knowledge in DSM and (ii) probabilistic approaches to less well understood soil processes. Stakeholders will profit from the development of decision frameworks to choose applicable DSM-techniques and the increased application of ensembles of DSM-methods and models to narrow prediction error bandwidths. Additionally, they will profit from the development of decision support systems filled with outcomes of scenario studies of multiple, uncertain, and concurrent models as these provide an interesting alternative to the application of one selected model. (C) 2011 Elsevier B.V. All rights reserved.