cross-validation matters in species distribution models: a case study with goatfish species

DataONE2024-09-05 更新2025-08-23 收录

下载链接：

https://search.dataone.org/view/sha256:aba24de7f433a2075846fc88c0dc912ceca253b811ec231fc5455a5eb8f94f64

下载链接

链接失效反馈

官方服务：

资源简介：

In an era of ongoing biodiversity, it is critical to map biodiversity patterns in space and time for better-informing conservation and management. Species distribution models (SDMs) are widely applied in various types of such biodiversity assessments. Cross-validation represents a prevalent approach to assess the discrimination capacity of a target SDM algorithm and determine its optimal parameters. Several alternative cross-validation methods exist; however, the influence of choosing a specific cross-validation method on SDM performance and predictions remains unresolved. Here, we tested the performance of random versus spatial cross-validation methods for SDM using goatfishes (Actinopteri: Syngnathiformes: Mullidae) as a case study, which are recognized as indicator species for coastal waters. Our results showed that the random versus spatial cross-validation methods resulted in different optimal model parameterizations in 57 out of 60 modeled species. Significant difference existed i..., According to the best-practice standards (AraÃºjoÂ et al.,Â 2019; Feng et al.,Â 2019), when constructing an SDM, we should pay due attention to hyperparameter optimization of modeling algorithms in order to maximize model predictive performance. Cross-validation represents a key approach toÂ comparing the predictive performance of competing models with different hyperparameters, hence helping to determine the optimal configuration of parameters (AraÃºjo & Guisan,Â 2006; Hijmans,Â 2012; GuisanÂ et al.,Â 2017). Taking the widely-used five-fold cross-validation approach as an example, 80% of the data is used for model training and the withholding 20% for model validation, and this step is repeated five times while the validation fold is changed. To date, most SDM studies have adopted this random cross-validation strategy for model evaluation during hyperparameter optimization (GuisanÂ et al.,Â 2017; Roberts et al.,Â 2017). Recently, however, researchers argued that the random cross-validation appro..., , # Data from:Â cross-validation matters in species distribution models: a case study with goatfish species R scripts were used to explore random and spatial cross-validation methods with goatfish species \################################ ## R scripts used to generate background data for Maxent \################################ R1_maxent_background_1000km.R R1_maxent_background_2000km.R \################################ ## R scripts of random and spatial cross-validation methods used to tune maxent parameters \################################ R2.1_SDM_CV_random_1000km.R R2.1_SDM_CV_random_2000km.R R2.2_SDM_CV_spatial_1000km_5x5.R R2.2_SDM_CV_spatial_2000km_5x5.R R2.2_SDM_CV_spatial_1000km_10x10.R R2.2_SDM_CV_spatial_2000km_10x10.R \################################ ## R scripts of random and spatial cross-validation methods used to predict species distribution \################################ R3.1_SDM_prediction_random_1000km.R R3.1_SDM_prediction_random_2000km.R R3.2_SDM_predict...

在全球生物多样性持续演变的时代，绘制时空尺度下的生物多样性分布格局，可为保护与管理决策提供科学依据，这一点至关重要。物种分布模型（Species Distribution Models，SDMs）被广泛应用于各类此类生物多样性评估工作中。交叉验证（Cross-Validation）是评估目标物种分布模型算法判别能力、确定其最优参数的主流方法。目前存在多种可选的交叉验证方法，但选取特定交叉验证方法对物种分布模型性能与预测结果的影响仍未明确。本研究以羊鱼（辐鳍鱼纲：海龙鱼目：羊鱼科）作为案例类群——该类群被公认为近海水域的指示物种，对比检验了随机交叉验证与空间交叉验证方法在物种分布模型中的应用性能。本研究结果显示，在60个模拟物种中，有57个物种的最优模型参数化方案在随机交叉验证与空间交叉验证下存在显著差异。... 根据行业最佳实践标准（Araújo等，2019；Feng等，2019），构建物种分布模型时，需充分关注建模算法的超参数优化，以最大化模型的预测性能。交叉验证是对比不同超参数的竞争模型预测性能的核心方法，因此可辅助确定参数的最优配置（Araújo & Guisan，2006；Hijmans，2012；Guisan等，2017）。以广泛使用的五折交叉验证为例，将80%的数据用于模型训练，剩余20%用于模型验证，该步骤需重复五次，每次更换验证折数据集。截至目前，多数物种分布模型研究在超参数优化阶段均采用该随机交叉验证策略进行模型评估（Guisan等，2017；Roberts等，2017）。然而近期有研究者指出，随机交叉验证方法存在... # 数据来源：《交叉验证在物种分布模型中的重要性：以羊鱼物种为例》本研究使用R脚本对羊鱼类群的随机与空间交叉验证方法开展探究 ################################ ## 用于生成Maxent背景数据的R脚本 ################################ R1_maxent_background_1000km.R R1_maxent_background_2000km.R ################################ ## 用于调优Maxent参数的随机与空间交叉验证方法R脚本 ################################ R2.1_SDM_CV_random_1000km.R R2.1_SDM_CV_random_2000km.R R2.2_SDM_CV_spatial_1000km_5x5.R R2.2_SDM_CV_spatial_2000km_5x5.R R2.2_SDM_CV_spatial_1000km_10x10.R R2.2_SDM_CV_spatial_2000km_10x10.R ################################ ## 用于预测物种分布的随机与空间交叉验证方法R脚本 ################################ R3.1_SDM_prediction_random_1000km.R R3.1_SDM_prediction_random_2000km.R R3.2_SDM_predict...

创建时间：

2025-08-04