A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques
Road networks are the main source of mortality for many species. Amphibians, which are in global decline, are the most road-killed fauna group, due to their activity patterns and preferred habitats. Many different methodologies have been applied in modeling the relationship between environment and r...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/5/343 |
| _version_ | 1797533686968614912 |
|---|---|
| author | Diana Sousa-Guedes Marc Franch Neftalí Sillero |
| author_facet | Diana Sousa-Guedes Marc Franch Neftalí Sillero |
| author_sort | Diana Sousa-Guedes |
| collection | DOAJ |
| description | Road networks are the main source of mortality for many species. Amphibians, which are in global decline, are the most road-killed fauna group, due to their activity patterns and preferred habitats. Many different methodologies have been applied in modeling the relationship between environment and road-kills events, such as logistic regression. Here, we compared the performance of five regression techniques to relate amphibians’ road-kill frequency to environmental variables. For this, we surveyed three country roads in northern Portugal in search of road-killed amphibians. To explain the presence of road-kills, we selected a set of environmental variables important for the presence of amphibians and the occurrence of road-kills. We compared the performances of five modeling techniques: (i) generalized linear models, (ii) generalized additive models, (iii) random forest, (iv) boosted regression trees, and (v) geographically weighted regression. The boosted regression trees and geographically weighted regression techniques performed the best, with a percentage of deviance explained between 61.8% and 76.6% and between 55.3% and 66.7%, respectively. Moreover, the geographically weighted regression showed a great advantage over the other techniques, as it allows mapping local parameter coefficients as well as local model performance (pseudo-R<sup>2</sup>). The results suggest that geographically weighted regression is a useful tool for road-kill modeling, as well as to better visualize and map the spatial variability of the models. |
| first_indexed | 2024-03-10T11:19:11Z |
| format | Article |
| id | doaj.art-81f7e3d6012e43c481ef666fd4034bcb |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T11:19:11Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-81f7e3d6012e43c481ef666fd4034bcb2023-11-21T20:11:47ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-05-0110534310.3390/ijgi10050343A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression TechniquesDiana Sousa-Guedes0Marc Franch1Neftalí Sillero2Centro de Investigação em Ciências Geo-Espaciais (CICGE), Faculdade de Ciências da Universidade do Porto, Alameda do Monte da Virgem, 4430-146 Vila Nova de Gaia, PortugalCentro de Investigação em Ciências Geo-Espaciais (CICGE), Faculdade de Ciências da Universidade do Porto, Alameda do Monte da Virgem, 4430-146 Vila Nova de Gaia, PortugalCentro de Investigação em Ciências Geo-Espaciais (CICGE), Faculdade de Ciências da Universidade do Porto, Alameda do Monte da Virgem, 4430-146 Vila Nova de Gaia, PortugalRoad networks are the main source of mortality for many species. Amphibians, which are in global decline, are the most road-killed fauna group, due to their activity patterns and preferred habitats. Many different methodologies have been applied in modeling the relationship between environment and road-kills events, such as logistic regression. Here, we compared the performance of five regression techniques to relate amphibians’ road-kill frequency to environmental variables. For this, we surveyed three country roads in northern Portugal in search of road-killed amphibians. To explain the presence of road-kills, we selected a set of environmental variables important for the presence of amphibians and the occurrence of road-kills. We compared the performances of five modeling techniques: (i) generalized linear models, (ii) generalized additive models, (iii) random forest, (iv) boosted regression trees, and (v) geographically weighted regression. The boosted regression trees and geographically weighted regression techniques performed the best, with a percentage of deviance explained between 61.8% and 76.6% and between 55.3% and 66.7%, respectively. Moreover, the geographically weighted regression showed a great advantage over the other techniques, as it allows mapping local parameter coefficients as well as local model performance (pseudo-R<sup>2</sup>). The results suggest that geographically weighted regression is a useful tool for road-kill modeling, as well as to better visualize and map the spatial variability of the models.https://www.mdpi.com/2220-9964/10/5/343ecological niche modelinggeographically weighted regressionlogistic regressionroad ecologyspatial regressionwildlife-vehicle collision |
| spellingShingle | Diana Sousa-Guedes Marc Franch Neftalí Sillero A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques ISPRS International Journal of Geo-Information ecological niche modeling geographically weighted regression logistic regression road ecology spatial regression wildlife-vehicle collision |
| title | A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques |
| title_full | A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques |
| title_fullStr | A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques |
| title_full_unstemmed | A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques |
| title_short | A Spatial Approach for Modeling Amphibian Road-Kills: Comparison of Regression Techniques |
| title_sort | spatial approach for modeling amphibian road kills comparison of regression techniques |
| topic | ecological niche modeling geographically weighted regression logistic regression road ecology spatial regression wildlife-vehicle collision |
| url | https://www.mdpi.com/2220-9964/10/5/343 |
| work_keys_str_mv | AT dianasousaguedes aspatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques AT marcfranch aspatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques AT neftalisillero aspatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques AT dianasousaguedes spatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques AT marcfranch spatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques AT neftalisillero spatialapproachformodelingamphibianroadkillscomparisonofregressiontechniques |