Assessing the effects of pseudo-absences on predictive distribution model performance

Despite its theoretical relationship, the effect of body size on the performance of species distribution models (SDM) has only been assessed in a few studies of terrestrial taxa. We aim to assess the effect of body size on the performance of SDM in river fish. We study seven Chilean freshwater fish, using models trained with three different sets of predictor variables: ecological (Eco), anthropogenic (Antr) and both (Eco+Antr). Our results indicate that the performance of the Eco+Antr models improves with fish size. These results highlight the importance of two novel predictive layers: the source of river flow and the overproduction of biotopes by anthropogenic activities. We compare our work with previous studies that modeled river fish, and observe a similar relationship in most cases. We discuss the current challenges of the modeling of riverine species, and how our work helps suggest possible solutions.

Download Full-text

Wildfire ignition-distribution modelling: a comparative study in the Huron–Manistee National Forest, Michigan, USA

International Journal of Wildland Fire ◽

10.1071/wf11178 ◽

2013 ◽

Vol 22 (2) ◽

pp. 174 ◽

Cited By ~ 65

Author(s):

Avi Bar Massada ◽

Alexandra D. Syphard ◽

Susan I. Stewart ◽

Volker C. Radeloff

Keyword(s):

Random Forests ◽

Model Performance ◽

Machine Learning Algorithms ◽

Environmental Data ◽

Distribution Model ◽

National Forest ◽

Similar Species ◽

Distribution Models ◽

Distribution Modelling ◽

Manistee National Forest

Wildfire ignition distribution models are powerful tools for predicting the probability of ignitions across broad areas, and identifying their drivers. Several approaches have been used for ignition-distribution modelling, yet the performance of different model types has not been compared. This is unfortunate, given that conceptually similar species-distribution models exhibit pronounced differences among model types. Therefore, our goal was to compare the predictive performance, variable importance and the spatial patterns of predicted ignition-probabilities of three ignition-distribution model types: one parametric, statistical model (Generalised Linear Models, GLM) and two machine-learning algorithms (Random Forests and Maximum Entropy, Maxent). We parameterised the models using 16 years of ignitions data and environmental data for the Huron–Manistee National Forest in Michigan, USA. Random Forests and Maxent had slightly better prediction accuracies than did GLM, but model fit was similar for all three. Variables related to human population and development were the best predictors of wildfire ignition locations in all models (although variable rankings differed slightly), along with elevation. However, despite similar model performance and variables, the map of ignition probabilities generated by Maxent was markedly different from those of the two other models. We thus suggest that when accurate predictions are desired, the outcomes of different model types should be compared, or alternatively combined, to produce ensemble predictions.

Download Full-text

Creating individual accessible area hypotheses improves stacked species distribution model performance

Global Ecology and Biogeography ◽

10.1111/geb.12678 ◽

2017 ◽

Vol 27 (1) ◽

pp. 156-165 ◽

Cited By ~ 26

Author(s):

Jacob C. Cooper ◽

Jorge Soberón

Keyword(s):

Species Distribution ◽

Species Distribution Model ◽

Model Performance ◽

Distribution Model ◽

Accessible Area

Download Full-text

Assessing the effect of fish size on species distribution model performance in southern Chilean rivers

10.7287/peerj.preprints.26874v1 ◽

2018 ◽

Author(s):

Daniel Zamorano ◽

Fabio Labra ◽

Marcelo Villarroel ◽

Luca Mao ◽

Shaw Lucy ◽

...

Keyword(s):

Body Size ◽

Species Distribution ◽

River Flow ◽

Species Distribution Model ◽

Anthropogenic Activities ◽

Model Performance ◽

Distribution Model ◽

Distribution Models ◽

Fish Size ◽

River Fish

Despite its theoretical relationship, the effect of body size on the performance of species distribution models (SDM) has only been assessed in a few studies of terrestrial taxa. We aim to assess the effect of body size on the performance of SDM in river fish. We study seven Chilean freshwater fish, using models trained with three different sets of predictor variables: ecological (Eco), anthropogenic (Antr) and both (Eco+Antr). Our results indicate that the performance of the Eco+Antr models improves with fish size. These results highlight the importance of two novel predictive layers: the source of river flow and the overproduction of biotopes by anthropogenic activities. We compare our work with previous studies that modeled river fish, and observe a similar relationship in most cases. We discuss the current challenges of the modeling of riverine species, and how our work helps suggest possible solutions.

Download Full-text

Mammalia, Chiroptera, Phyllostomidae, Lonchophylla hesperia G. M. Allen, 1908: second record of the Western Nectar Bat in Ecuador after 70 years

Check List ◽

10.15560/7.3.315 ◽

2011 ◽

Vol 7 (3) ◽

pp. 315

Author(s):

Diego G. Tirira ◽

Santiago F. Burneo ◽

Carlos E. Boada ◽

Simón E. Lobos

Keyword(s):

Adult Male ◽

Predictive Distribution ◽

Natural Forest ◽

Distribution Model ◽

Agricultural Lands ◽

Dry Valley ◽

Corn Fields

Herein we report the second record for Lonchophylla hesperia in Ecuador, and the first one since 1939. We captured an adult male in a mountainous dry valley at Comunidad San Jacinto, Catamayo Valley, Loja Province, southwestern Ecuador. The dominant landscape consists of agricultural lands, mainly of corn fields and pastures; while the natural forest is restricted to small patches. A description of the species’ shelter and a predictive distribution model in Peru and Ecuador are presented, indicating the areas between the two countries were the habitat is climatically suitable for its presence.

Download Full-text