How important are choice of model selection method and spatial autocorrelation of presence data for distribution modelling by MaxEnt

By Rune Halvorsen, Dr. Sabrina Mazzoni, John Wirkola Dirksen, Erik Næsset, Terje Gobakken, M. Ohlson. 2016

94 citations recorded by the source corpus.

How researchers see this paper

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

Bunching up the background betters bias in species distribution models (2019, methodology): “When modeling real distributions, subset variable selection seems to produce more parsimonious models than lasso regularization (Halvorsen et al. 2016).”
Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data (2018, background): “Ecological applications range from species distribution models (Halvorsen et al., 2016; Quillfeldt et al., 2017; Wieland et al., 2017), predicting ﬂoristic (Muenchow et al., 2013a) and faunal composition to disentangling the relationships between species and their environment (Muenchow et al.,…”