Spatial filtering to reduce sampling bias can improve the performance of ecological niche models

By Robert A. Boria, L. Olson, S. Goodman, R. P. Anderson. 2014

1,338 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Genetics

View Paper: https://www.semanticscholar.org/paper/21ee3e6fc4ae9819c56d1483060ffb16547ed13d

How researchers see this paper

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

In Ecological Modeling

1. A. Townsend Peterson
2. Jorge Soberón
3. R. P. Anderson
4. Monica Papes
5. Dan L. Warren
6. J. Secondi
7. Yoan Fourcade
8. D. Rödder

In Ecology

1. A. Townsend Peterson
2. Jorge Soberón
3. R. P. Anderson
4. Monica Papes
5. Dan L. Warren
6. J. Secondi
7. Yoan Fourcade
8. Yiwen Zeng

In Genetics

1. Monica Papes
2. A. Townsend Peterson
3. Jorge Soberón
4. Dan L. Warren
5. D. Rödder
6. Janet Franklin
7. D. Yeo
8. J. Engler

Citations in the corpus

• Comparing sample bias correction methods for species distribution modeling using virtual species (2021, background): “…based on nearest neighbor distances, such as removing observations that are within a certain distance of one another (e.g., Kramer-Schadt et al. 2013, Boria et al. 2014), while others use spatial grids to filter observations from cells with high sample densities (e.g., Vandergast et al. 2013).”
• Fusarium Wilt of Bananas: A Review of Agro-Environmental Factors in the Venezuelan Production System Affecting Its Development (2021, methodology): “To reduce spatial autocorrelation, presence records were submitted to spatial filtering, delimiting a minimum distance of 1 km between each locality data [86] using the spThin package in R and repeated four times.”
• Environmental filtering improves ecological niche models across multiple scales (2019, methodology): “For the threshold- independent measures, we used the commonly reported AUC and the difference in training AUC and testing AUC (AUCdiff; Boria et al., 2014).”
• SDMtoolbox: a python‐based GIS toolkit for landscape genetic, biogeographic and species distribution model analyses (2014, background): “When spatial clusters of localities exist, often models are over-fit towards environmental biases (reducing the model’s ability to predict spatially independent data) and model performance values are inflated (Veloz 2009; Hijmans 2012; Boria et al. 2014).”
• SDMtoolbox 2.0: the next generation Python-based GIS toolkit for landscape genetic, biogeographic and species distribution model analyses (2017, neutral): “1D; Veloz 169 2009; Hijimans et al. 2012; Boria et al. 2014).”
• Predictor complexity and feature selection affect Maxent model transferability: Evidence from global freshwater invasive species (2020, methodology): “To reduce the effect of sampling bias, spatial filtering (Boria et al., 2014; Fourcade et al., 2014) was carried out on the occurrences datasets.”