The best of two worlds: using stacked generalisation for integrating expert range maps in species distribution models

Aim Species distribution models (SDMs) are powerful tools for assessing suitable habitats across large areas and at fine spatial resolution. Yet, the usefulness of SDMs for mapping species' realised distributions is often limited since data biases or missing information on dispersal barriers or biotic interactions hinder them from accurately delineating species' range limits. One way to overcome this limitation is to integrate SDMs with expert range maps, which provide coarse-scale information on the extent of species' ranges and thereby range limits that are complementary to information offered by SDMs. Innovation Here, we propose a new approach for integrating expert range maps in SDMs based on an ensemble method called stacked generalisation. Specifically, our approach relies on training a meta-learner regression model using predictions from one or more SDM algorithms alongside the distance of training points to expert-defined ranges as predictor variables. We demonstrate our app..., , , # The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models [https://doi.org/10.5061/dryad.6q573n65m](https://doi.org/10.5061/dryad.6q573n65m) This repository contains Supporting Information for the article \"The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models\" ([https://doi.org/10.1111/geb.13911](https://doi.org/10.1111/geb.13911)). It contains three files: 1. \"model_df.csv\": CSV table containing modeling data frame with occurrence information (presence/background) for 49 bat species alongside values of predictors used for building SDMs 2. \"predictor_stack_agg.tif\": GeoTIFF containing raster stack of predictor variables used in SDMs, re-sampled to a reduced spatial resolution of 10km for demonstration purposes 3. \"iucn_dists.tif\": GeoTIFF containing raster stack of distance layers describing the distance of raster cells to the boundary of IUCN ranges for 49 ...研究目标 物种分布模型（Species Distribution Models，SDMs）是在大尺度范围内以精细空间分辨率评估物种适宜栖息地的有力工具。然而，其在绘制物种实际分布范围方面的实用性往往受限：数据偏差、扩散障碍或生物交互作用信息的缺失，会阻碍模型精准划定物种的分布边界。克服该局限的一种可行方案是将物种分布模型与专家分布范围图相结合——专家分布范围图可提供物种分布范围乃至分布边界的粗尺度信息，以此弥补物种分布模型所提供信息的不足。 研究创新 本研究提出一种全新方法，基于堆叠泛化（Stacked Generalisation）这一集成学习方法，将专家分布范围图整合至物种分布模型中。具体而言，该方法以一个或多个物种分布模型算法的预测结果，以及训练样本点到专家划定分布范围的距离作为预测变量，训练元学习回归模型。本研究展示了所提方法的应用效果……# 两全其美：利用堆叠泛化整合专家分布范围图与物种分布模型 [https://doi.org/10.5061/dryad.6q573n65m](https://doi.org/10.5061/dryad.6q573n65m) 本数据集仓库包含论文《两全其美：利用堆叠泛化整合专家分布范围图与物种分布模型》（DOI: 10.1111/geb.13911）的补充材料。 仓库内含3个文件： 1. "model_df.csv"：该CSV表格包含建模数据集框架，涵盖49种蝙蝠的出现记录信息（存在点/背景点），以及构建物种分布模型所用的预测变量取值。 2. "predictor_stack_agg.tif"：该GeoTIFF文件包含物种分布模型所用预测变量的栅格堆叠数据集，为便于演示已重采样至10km的降低空间分辨率。 3. "iucn_dists.tif"：该GeoTIFF文件包含距离图层的栅格堆叠数据集，用于描述栅格像元到49个国际自然保护联盟（International Union for Conservation of Nature，IUCN）分布范围边界的距离……