Background sampling for multi-scale ensemble habitat selection modeling: Does the number of points matter?

Hysen, Logan; Nayeri, Danial; Cushman, Samuel A.; Wan, Ho Yi

doi:10.1016/j.ecoinf.2022.101914

Cited by 11 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most presence‐only data retrieved on open‐source digital databases do not have information on species absences, which has implications for model specification. One of the solutions is to sample background or pseudo‐absence data to fit SDM (Barbet‐Massin et al, 2012; Hysen et al, 2022). Some SDMs perform well with a large number of background data sampled across the study area that can thoroughly present the background environment, such as maximum entropy (Phillips et al, 2006).…”

Section: Methodsmentioning

confidence: 99%

Using habitat suitability models for multiscale forensic geolocation analysis

Wang

Miller

Grubesic

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

Pollen is one of the most durable environmental materials that law enforcement agencies recover as trace evidence from people and objects. Although links between objects and geographic locations are essential during legal investigations, the approach of using pollen and other microbial fingerprints to build these links in an analytical framework is still underutilized. This study uses bees as objects that are mobile and collects environmental traces as a test case to determine the efficacy of predictive geolocation efforts with recovered pollen and species distribution models at both subcontinental and global scales. Results demonstrate promising performance in both the predictive capability of species distribution models and identification of possible location history of bees at both study extents. When coupling pollen with other categories of evidentiary items, this geographic attribution framework can aid law enforcement personnel in refining investigation priorities and optimizing search strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

Using habitat suitability models for multiscale forensic geolocation analysis

Wang

Miller

Grubesic

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…The most common approaches for sampling pseudo-absences involve (i) randomly surveying a large number of points across the study area (e.g. 10,000; Barbet-Massin et al, 2012;Hysen et al, 2022;Iturbide et al, 2015;Støa et al, 2019) or (ii) sampling them within or (iii) outside buffers created around presence locations (Bedia et al, 2013;VanDerWal et al, 2009). These approaches share the characteristic of deploying pseudo-absences randomly across the geographic space, which often leads to oversampling of the most common habitat conditions that are widespread in the study area (Ronquillo et al, 2020;Tessarolo et al, 2014Tessarolo et al, , 2021.…”

Section: Introductionmentioning

confidence: 99%

USE it: Uniformly sampling pseudo‐absences within the environmental space for applications in habitat suitability models

Da Re,

Tordoni,

Lenoir

et al. 2023

Methods Ecol Evol

View full text Add to dashboard Cite

Habitat suitability models infer the geographical distribution of species using occurrence data and environmental variables. While data on species presence are increasingly accessible, the difficulty of confirming real absences in the field often forces researchers to generate them in silico. To this aim, pseudo‐absences are commonly sampled randomly across the study area (i.e. the geographical space). However, this introduces sample location bias (i.e. the sampling is unbalanced towards the most frequent habitats occurring within the geographical space) and favours class overlap (i.e. overlap between environmental conditions associated with species presences and pseudo‐absences) in the training dataset. To mitigate this, we propose an alternative methodology (i.e. the uniform approach) that systematically samples pseudo‐absences within a portion of the environmental space delimited by a kernel‐based filter, which seeks to minimise the number of false absences included in the training dataset. We simulated 50 virtual species and modelled their distribution using training datasets assembled with the presence points of the virtual species and pseudo‐absences collected using the uniform approach and other approaches that randomly sample pseudo‐absences within the geographical space. We compared the predictive performance of habitat suitability models and evaluated the extent of sample location bias and class overlap associated with the different sampling strategies. Results indicated that the uniform approach: (i) effectively reduces sample location bias and class overlap; (ii) provides comparable predictive performance to sampling strategies carried out in the geographical space; and (iii) ensures gathering pseudo‐absences adequately representing the environmental conditions available across the study area. We developed a set of R functions in an accompanying R package called USE to disseminate the uniform approach.

show abstract