Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases

The proliferation of open repositories offering georeferenced occurrences on biodiversity has boosted the use of species distribution models (SDMs). However, the need of presence-only records from these repositories yields a substantial limitation due to sampling biases, which can introduce uncertai...

Full description

Saved in:
Bibliographic Details
Main Authors: Claudio A. Bracho-Estévanez, Salvador Arenas-Castro, Juan P. González-Varo, Pablo González-Moreno
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954124004588
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249791241453568
author Claudio A. Bracho-Estévanez
Salvador Arenas-Castro
Juan P. González-Varo
Pablo González-Moreno
author_facet Claudio A. Bracho-Estévanez
Salvador Arenas-Castro
Juan P. González-Varo
Pablo González-Moreno
author_sort Claudio A. Bracho-Estévanez
collection DOAJ
description The proliferation of open repositories offering georeferenced occurrences on biodiversity has boosted the use of species distribution models (SDMs). However, the need of presence-only records from these repositories yields a substantial limitation due to sampling biases, which can introduce uncertainty and skew SDM predictions. Furthermore, most predictions rely only on non-spatial metrics such as the AUC and the TSS to evaluate model performance. These metrics may not adequately account for spatially biased predictions, whereas the use of spatially explicit metrics could be more informative. Here, the effectiveness of both non-spatial and spatially explicit metrics is evaluated in response to predictions affected by sampling biases. Using SDMs, the distribution of 31 fleshy-fruited plants was predicted as a case study with contrasting settings to generate pseudo-absences and sampling bias corrections. Then, the performance of predictions was assessed with two non-spatial and three alternative, spatially explicit metrics. Predictions were affected by substantial sampling biases, particularly from West to East. Significant discrepancies were found between non-spatial and spatially explicit metrics. The non-spatial metrics failed to detect predictions affected by sampling biases, often yielding higher scores for less reliable predictions. In contrast, spatially explicit metrics benefited the implementation of bias corrections. Moreover, the method to generate pseudo-absences was more influential in determining spatial differences between predictions than either the bias correction or the geographical characteristics of input occurrences. Overall, our findings reveal the utility of spatially explicit metrics as a complementary tool to evaluate SDMs affected by sampling biases.
format Article
id doaj-art-dbf458094359446d9fcb8865562d7f42
institution OA Journals
issn 1574-9541
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-dbf458094359446d9fcb8865562d7f422025-08-20T01:58:24ZengElsevierEcological Informatics1574-95412024-12-018410291610.1016/j.ecoinf.2024.102916Spatially explicit metrics improve the evaluation of species distribution models facing sampling biasesClaudio A. Bracho-Estévanez0Salvador Arenas-Castro1Juan P. González-Varo2Pablo González-Moreno3Department of Biology, Instituto Universitario de Investigación Marina (INMAR), Universidad de Cádiz, Campus Río San Pedro, Puerto Real, Cádiz, Spain; Corresponding author.Area of Ecology, Department of Botany, Ecology and Plant Physiology, Faculty of Sciences, Universidad de Córdoba, Córdoba, SpainDepartment of Biology, Instituto Universitario de Investigación Marina (INMAR), Universidad de Cádiz, Campus Río San Pedro, Puerto Real, Cádiz, SpainDepartment of Forest Engineering, Universidad de Córdoba, Córdoba, SpainThe proliferation of open repositories offering georeferenced occurrences on biodiversity has boosted the use of species distribution models (SDMs). However, the need of presence-only records from these repositories yields a substantial limitation due to sampling biases, which can introduce uncertainty and skew SDM predictions. Furthermore, most predictions rely only on non-spatial metrics such as the AUC and the TSS to evaluate model performance. These metrics may not adequately account for spatially biased predictions, whereas the use of spatially explicit metrics could be more informative. Here, the effectiveness of both non-spatial and spatially explicit metrics is evaluated in response to predictions affected by sampling biases. Using SDMs, the distribution of 31 fleshy-fruited plants was predicted as a case study with contrasting settings to generate pseudo-absences and sampling bias corrections. Then, the performance of predictions was assessed with two non-spatial and three alternative, spatially explicit metrics. Predictions were affected by substantial sampling biases, particularly from West to East. Significant discrepancies were found between non-spatial and spatially explicit metrics. The non-spatial metrics failed to detect predictions affected by sampling biases, often yielding higher scores for less reliable predictions. In contrast, spatially explicit metrics benefited the implementation of bias corrections. Moreover, the method to generate pseudo-absences was more influential in determining spatial differences between predictions than either the bias correction or the geographical characteristics of input occurrences. Overall, our findings reveal the utility of spatially explicit metrics as a complementary tool to evaluate SDMs affected by sampling biases.http://www.sciencedirect.com/science/article/pii/S1574954124004588Plant distributionPerformance metricsSampling biasBias correction
spellingShingle Claudio A. Bracho-Estévanez
Salvador Arenas-Castro
Juan P. González-Varo
Pablo González-Moreno
Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
Ecological Informatics
Plant distribution
Performance metrics
Sampling bias
Bias correction
title Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
title_full Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
title_fullStr Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
title_full_unstemmed Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
title_short Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
title_sort spatially explicit metrics improve the evaluation of species distribution models facing sampling biases
topic Plant distribution
Performance metrics
Sampling bias
Bias correction
url http://www.sciencedirect.com/science/article/pii/S1574954124004588
work_keys_str_mv AT claudioabrachoestevanez spatiallyexplicitmetricsimprovetheevaluationofspeciesdistributionmodelsfacingsamplingbiases
AT salvadorarenascastro spatiallyexplicitmetricsimprovetheevaluationofspeciesdistributionmodelsfacingsamplingbiases
AT juanpgonzalezvaro spatiallyexplicitmetricsimprovetheevaluationofspeciesdistributionmodelsfacingsamplingbiases
AT pablogonzalezmoreno spatiallyexplicitmetricsimprovetheevaluationofspeciesdistributionmodelsfacingsamplingbiases