Outstanding Challenges in the Transferability of Ecological Models.

By K. Yates, Phil J. Bouchet, M. Caley, Kerrie L. Mengersen, C. Randin, Stephen Parnell, A. Fielding, Andrew J. Bamford, S. Ban, A. Márcia Barbosa and 40 more. Trends in Ecology & Evolution, 2018

629 citations recorded by the source corpus.

Predictive models are central to many scientific disciplines and vital for informing management in a rapidly changing world. However, limited understanding of the accuracy and precision of models transferred to novel conditions (their 'transferability') undermines confidence in their predictions. Here, 50 experts identified priority knowledge gaps which, if filled, will most improve model transfers. These are summarized into six technical and six fundamental challenges, which underlie the combined need to intensify research on the determinants of ecological predictability, including species traits and data quality, and develop best practices for transferring models. Of high importance is the identification of a widely applicable set of transferability metrics, with appropriate tools to quantify the sources and impacts of prediction uncertainty under novel conditions.

Subfields: Artificial Intelligence, Ecological Modeling, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/b38e29888ec09c296797e25b73f30df22eb3ac27

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Ecological Modeling

In Nature and Landscape Conservation

Citations in the corpus

Testing species assemblage predictions from stacked and joint species distribution models (2019, methodology): “On the one hand, we calculated un‐ derstorey height diversity (UHD) analogously to FHD, but using 1 m bins restricted to below 12 m (Zellweger et al., 2016) as well as the ratio between the 95th and 25th percentile.”
A standard protocol for reporting species distribution models (2020, background): “If the main modelling objective is to transfer the model to different geographic regions and/or different time periods (Yates et al. 2018), then authors need to report information on the data used in the model transfer, i.e. the environmental data to which the model is projected (Table 1).”