flexsdm : An r package for supporting a comprehensive and flexible species distribution modelling workflow
flexsdm : An r package for supporting a comprehensive and flexible species distribution modelling workflow
复制标题
flexsdm ：一个 R 包，用于支持全面且灵活的物种分布建模工作流程
DOI：
10.1111/2041-210x.13874
复制
发表时间：
2022
影响因子：
6.6
通讯作者：
Franklin, Janet
中科院分区：
文献类型：
--
作者：
Velazco, Santiago José;Rose, Miranda Brooke;de Andrade, André Felipe;Minoli, Ignacio;Franklin, Janet
物种分布模型(SDM)因其数据要求简单、应用广泛而被广泛应用于不同的研究领域。然而，SDM的结果对数据输入和方法选择很敏感。这种敏感性和多样化的应用意味着需要灵活地为给定的数据和模型的使用创建具有定制协议的SDMS。我们引入了用于支持灵活物种分布建模工作流程的热封装FlexsDM。主要特点是建模灵活性、与其他建模工具的集成、返回对象的简单性和函数速度。作为说明，我们使用flesdm为加州红杉定义了一个完整的工作流程。这个程序包通过结合结构为三个步骤的综合工具来提供建模灵活性：(A)准备输入的建模前功能，例如，采样偏差校正、采样假缺席和背景点、数据分割，以及减少预测器中的共线性。(B)建模功能允许对不同的建模方法进行拟合和评价，包括单独的算法、调整后的模型、小模型的集合和集合模型。(C)建模后功能包括与模型预测、内插和过度预测校正有关的工具。由于FlexsDM包括从离群值检测到过度预测校正的SDM过程的很大一部分，因此FlexsDM用户可以根据组合功能来描述部分或完整的工作流程，以满足特定的建模需求。
Species distribution models (SDM) are widely used in diverse research areas because of their simple data requirements and application versatility. However, SDM outcomes are sensitive to data input and methodological choices. Such sensitivity and diverse applications mean that flexibility is necessary to create SDMs with tailored protocols for a given set of data and model use.We introduce therpackageflexsdmfor supporting flexible species distribution modelling workflows.flexsdmfunctions and their arguments serve as building blocks to construct a specific modelling protocol for user's needs. The mainflexsdmfeatures are modelling flexibility, integration with other modelling tools, simplicity of the objects returned and function speed. As an illustration, we usedflexsdmto define a complete workflow for California red firAbies magnifica.This package provides modelling flexibility by incorporating comprehensive tools structured in three steps: (a) The Pre‐modelling functions that prepare input, for example, sampling bias correction, sampling pseudo‐absences and background points, data partitioning, and reducing collinearity in predictors. (b) The Modelling functions allow fitting and evaluating different modelling approaches, including individual algorithms, tuned models, ensembles of small models and ensemble models. (c) The Post‐modelling functions include tools related to models' predictions, interpolation and overprediction correction.Becauseflexsdmcomprises a large part of the SDM process, from outlier detection to overprediction correction,flexsdmusers can delineate partial or complete workflows based on the combination functions to meet specific modelling needs.