The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models
Abstract How to effectively obtain species‐related low‐dimensional data from massive environmental variables has become an urgent problem for species distribution models (SDMs). In this study, we will explore whether dimensionality reduction on environmental variables can improve the predictive perf...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ece3.10747 |
| _version_ | 1797448627210158080 |
|---|---|
| author | Hao‐Tian Zhang Wen‐Yong Guo Wen‐Ting Wang |
| author_facet | Hao‐Tian Zhang Wen‐Yong Guo Wen‐Ting Wang |
| author_sort | Hao‐Tian Zhang |
| collection | DOAJ |
| description | Abstract How to effectively obtain species‐related low‐dimensional data from massive environmental variables has become an urgent problem for species distribution models (SDMs). In this study, we will explore whether dimensionality reduction on environmental variables can improve the predictive performance of SDMs. We first used two linear (i.e., principal component analysis (PCA) and independent components analysis) and two nonlinear (i.e., kernel principal component analysis (KPCA) and uniform manifold approximation and projection) dimensionality reduction techniques (DRTs) to reduce the dimensionality of high‐dimensional environmental data. Then, we established five SDMs based on the environmental variables of dimensionality reduction for 23 real plant species and nine virtual species, and compared the predictive performance of those with the SDMs based on the selected environmental variables through Pearson's correlation coefficient (PCC). In addition, we studied the effects of DRTs, model complexity, and sample size on the predictive performance of SDMs. The predictive performance of SDMs under DRTs other than KPCA is better than using PCC. And the predictive performance of SDMs using linear DRTs is better than using nonlinear DRTs. In addition, using DRTs to deal with environmental variables has no less impact on the predictive performance of SDMs than model complexity and sample size. When the model complexity is at the complex level, PCA can improve the predictive performance of SDMs the most by 2.55% compared with PCC. At the middle level of sample size, the PCA improved the predictive performance of SDMs by 2.68% compared with the PCC. Our study demonstrates that DRTs have a significant effect on the predictive performance of SDMs. Specifically, linear DRTs, especially PCA, are more effective at improving model predictive performance under relatively complex model complexity or large sample sizes. |
| first_indexed | 2024-03-09T14:14:09Z |
| format | Article |
| id | doaj.art-d466a2cb75fc4c18a8a55fef8b083794 |
| institution | Directory Open Access Journal |
| issn | 2045-7758 |
| language | English |
| last_indexed | 2024-03-09T14:14:09Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecology and Evolution |
| spelling | doaj.art-d466a2cb75fc4c18a8a55fef8b0837942023-11-29T05:44:08ZengWileyEcology and Evolution2045-77582023-11-011311n/an/a10.1002/ece3.10747The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution modelsHao‐Tian Zhang0Wen‐Yong Guo1Wen‐Ting Wang2School of Mathematics and Computer Science Northwest Minzu University Lanzhou ChinaResearch Center for Global Change and Complex Ecosystems, School of Ecological and Environmental Sciences East China Normal University Shanghai ChinaSchool of Mathematics and Computer Science Northwest Minzu University Lanzhou ChinaAbstract How to effectively obtain species‐related low‐dimensional data from massive environmental variables has become an urgent problem for species distribution models (SDMs). In this study, we will explore whether dimensionality reduction on environmental variables can improve the predictive performance of SDMs. We first used two linear (i.e., principal component analysis (PCA) and independent components analysis) and two nonlinear (i.e., kernel principal component analysis (KPCA) and uniform manifold approximation and projection) dimensionality reduction techniques (DRTs) to reduce the dimensionality of high‐dimensional environmental data. Then, we established five SDMs based on the environmental variables of dimensionality reduction for 23 real plant species and nine virtual species, and compared the predictive performance of those with the SDMs based on the selected environmental variables through Pearson's correlation coefficient (PCC). In addition, we studied the effects of DRTs, model complexity, and sample size on the predictive performance of SDMs. The predictive performance of SDMs under DRTs other than KPCA is better than using PCC. And the predictive performance of SDMs using linear DRTs is better than using nonlinear DRTs. In addition, using DRTs to deal with environmental variables has no less impact on the predictive performance of SDMs than model complexity and sample size. When the model complexity is at the complex level, PCA can improve the predictive performance of SDMs the most by 2.55% compared with PCC. At the middle level of sample size, the PCA improved the predictive performance of SDMs by 2.68% compared with the PCC. Our study demonstrates that DRTs have a significant effect on the predictive performance of SDMs. Specifically, linear DRTs, especially PCA, are more effective at improving model predictive performance under relatively complex model complexity or large sample sizes.https://doi.org/10.1002/ece3.10747dimensionality reduction techniquesenvironmental variablesmodel complexitypredictive performancesample sizesspecies distribution models |
| spellingShingle | Hao‐Tian Zhang Wen‐Yong Guo Wen‐Ting Wang The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models Ecology and Evolution dimensionality reduction techniques environmental variables model complexity predictive performance sample sizes species distribution models |
| title | The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| title_full | The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| title_fullStr | The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| title_full_unstemmed | The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| title_short | The dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| title_sort | dimensionality reductions of environmental variables have a significant effect on the performance of species distribution models |
| topic | dimensionality reduction techniques environmental variables model complexity predictive performance sample sizes species distribution models |
| url | https://doi.org/10.1002/ece3.10747 |
| work_keys_str_mv | AT haotianzhang thedimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels AT wenyongguo thedimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels AT wentingwang thedimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels AT haotianzhang dimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels AT wenyongguo dimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels AT wentingwang dimensionalityreductionsofenvironmentalvariableshaveasignificanteffectontheperformanceofspeciesdistributionmodels |