Machine learning identification of microhabitat features associated with occupancy of artificial nestboxes by hazel dormice (Muscardinus avellanarius) in a UK woodland site

Hazel dormice (Muscardinus avellanarius) have severely declined since 2000 leading to increased legislative protection in the UK and Europe. Artificial nestboxes are widely used for its conservation and monitoring. Previous research has focused on how to identify suitable areas for nestboxes, but where to place individual boxes to promote occupancy is less well understood. Here, we demonstrate the use of machine learning Random Forest regression to predict nestbox occupancy from a wide range of microhabitat variables using a UK woodland as a case study. Random forest models are powerful predictive tools that allow simultaneous testing of many predictors with relatively few observations. Field data included observed nestbox occupancy (2017-2021) and measurements of 76 microhabitat variables collected in the summer of 2021 from 45 occupied and unused nestboxes located in a deciduous woodland in Berkshire, UK. We applied Random Forest regression to identify important variables and predict ..., Study area and dormice surveys The study area was within the grounds of Basildon Park House (BPH), a National Trust property with extensive woodland, located in Berkshire, UK (see paper for further details). In 2013, 144 nestboxes were erected at two different woodland areas within BPH: 78 were located in clusters within the northern site, and 66 were positioned along three distinct lines in the southern site. Within the northern site, mature beech (Fagus sylvatica), ash (Fraxinus excelsior) and oak (Quercus spp.) are the most frequent tree species with sweet chestnut (Castanea sativa) and field elm (Ulmus minor) occasional. Hawthorn and coppiced hazel are dominant in the understorey layer, with holly (Ilex aquifoliaceae) and young sycamore (Acer pseudoplatanus) frequent, and other species such as field maple (Acer campestre), whitebeam (Sorbus aria) and rowan (Sorbus aucuparia) occasional. Bramble (Rubus fruticosus agg.) and honeysuckle are abundant in both the understorey and field ..., , # Data from: Machine learning identification of microhabitat features associated with occupancy of artificial nestboxes by hazel dormice (*Muscardinus avellanarius*) in a UK woodland site [https://doi.org/10.5061/dryad.1c59zw43q](https://doi.org/10.5061/dryad.1c59zw43q) ## Description of the data and file structure Two datasets in csv format describing hazel dormice occupancy and microhabitat features for 45 artificial nestboxes in a UK woodland, and one R script (Rmd format) providing all code necessary to recreate the analyses and graphs presented in the published paper. ###### **Dataset 1 \"MalyanetalDataPub1.csv\" main dataset describing nestbox occupancy and microhabitat variable data collected in May 2021.** The dataset contains 46 rows (1 header with variable names and 45 observations, 1 per studied nestbox) and 75 columns (variables). Variables are described in the table below. Missing data is indicated by NA. | **Variable Name** | **Description** ...榛睡鼠（Hazel dormouse，*Muscardinus avellanarius*）自2000年以来种群数量急剧下降，促使英国与欧洲多国强化了针对该物种的立法保护措施。人工巢箱已被广泛应用于榛睡鼠的保护与监测工作。过往研究多聚焦于如何筛选适宜安置巢箱的区域，但针对如何精准布设单个巢箱以提升其被睡鼠占用的概率，相关认知仍较为匮乏。本研究以英国某片落叶林为案例，运用机器学习中的随机森林回归（Random Forest regression）模型，基于多类微生境变量预测巢箱占用情况。随机森林模型作为高效的预测工具，可在观测样本量相对有限的前提下，同时对众多预测因子开展检验。 实地数据涵盖2017至2021年的巢箱占用观测记录，以及2021年夏季于英国伯克郡一片落叶林内采集的76项微生境变量数据，采样对象为45个被占用及未被使用的人工巢箱。本研究采用随机森林回归模型识别关键影响变量并开展预测…… # 研究区域与睡鼠调查 研究区域位于英国伯克郡的巴兹尔登庄园（Basildon Park House，BPH）园区内，该地块隶属于国民信托（National Trust）所有，拥有大面积林地，详细信息参见原文。 2013年，研究团队于巴兹尔登庄园内的两片林地共布设144个人工巢箱：其中78个集群布置于北部样地，剩余66个沿三条独立线路布置于南部样地。北部样地的优势乔木树种为欧洲山毛榉（Fagus sylvatica）、白蜡树（Fraxinus excelsior）与栎属（Quercus spp.），甜栗（Castanea sativa）与欧洲小叶榆（Ulmus minor）为偶见树种；林下植被层以山楂与萌生榛树为主，常见物种包括冬青（Ilex aquifoliaceae）与幼龄挪威槭（Acer pseudoplatanus），另有茶条槭（Acer campestre）、白面子树（Sorbus aria）与花楸（Sorbus aucuparia）等偶见物种。悬钩子属（Rubus fruticosus agg.）与金银花在林下与田间区域均广泛分布…… 数据来源：《Machine learning identification of microhabitat features associated with occupancy of artificial nestboxes by hazel dormice (*Muscardinus avellanarius*) in a UK woodland site》，DOI链接：https://doi.org/10.5061/dryad.1c59zw43q ## 数据与文件结构说明 本数据集包含两份CSV格式文件，用于记录英国某林地内45个人工巢箱的榛睡鼠占用情况与微生境特征数据，以及一份R Markdown（Rmd）格式的R脚本，可复现已发表论文中所有分析与图表的生成代码。 ###### 数据集1"MalyanetalDataPub1.csv"为核心数据集，收录了2021年5月采集的巢箱占用情况与微生境变量数据。该数据集包含46行（含1行变量名表头与45条对应每个研究巢箱的观测记录）与75列（变量）。变量详情如下表所示。缺失数据以NA标注。 | 变量名 | 变量描述 ...