Potential and realized distribution at 30m for Aleppo pine (Pinus halepensis) in Europe for 2000 - 2020

Probability and uncertainty maps showing the potential and realized distribution for the Aleppo pine (Pinus halepensis, Mill.) for Europe from the dataset prepared by Bonannella et al. (2022) and predicted using Ensemble Machine Learning (EML). Potential distribution map cover the period 2018 - 2020; realized distribution cover the period 2000 - 2020, split in the following time periods:

2000 - 2002,

2002 - 2006,

2006 - 2010,

2010 - 2014,

2014 - 2018,

2018 - 2020.

Files are named according to the following naming convention, e.g:

veg_pinus.halepensis_anv.eml_md_30m_0..0cm_2000..2002_eumap_epsg3035_v0.3

with the following fields:

theme: e.g. veg,

species code: e.g. pinus.halepensis,

species distribution type: e.g. anv (= actual natural vegetation),

species estimation method: e.g. eml,

species estimation type: e.g. md ( = model deviation),

resolution in meters e.g. 30m,

reference depths (vertical dimension): e.g. 0..0cm,

reference period begin end: e.g. 2000..2002,

reference area: e.g. eumap,

coordinate system: e.g. epsg3035,

data set version: e.g. v0.3.

For each species is then easy to identify probability and uncertainty distribution maps:

veg_pinus.halepensis_anv.eml_md: model uncertainty for realized distribution

veg_pinus.halepensis_anv.eml_p: probability for realized distribution

veg_pinus.halepensis_pnv.eml_md: model uncertainty for potential distribution

veg_pinus.halepensis_pnv.eml_p: probability for potential distribution

Files are provided as Cloud Optimized GeoTIFFs and projected in the Coordinate Reference System ETRS89 / LAEA Europe (= EPSG code 3035). Styling files are provided in both SLD and QML format.

If you would like to know more about the creation of the maps and the modeling:

watch the talk at Open Data Science Workshop 2021 (TIB AV-PORTAL)

access the repository with our R/Python scripts and follow the instructions (GitLab)

access the repository with the training dataset (Zenodo)

read the tutorial with executable code on our GitBook

A publication describing, in detail, all processing steps, accuracy assessment and general analysis of species distribution maps is available on PeerJ. To suggest any improvement/fix use https://gitlab.com/geoharmonizer_inea/spatial-layers/-/issues.

本数据集包含由Bonannella等人（2022）构建、使用集成机器学习（Ensemble Machine Learning, EML）预测得到的欧洲区域阿勒颇松（*Pinus halepensis* Mill.）潜在分布与实际分布的概率及不确定性地图。其中，潜在分布地图的时间范围为2018-2020年；实际分布地图的时间范围为2000-2020年，并拆分为以下时段：

2000 - 2002，
2002 - 2006，
2006 - 2010，
2010 - 2014，
2014 - 2018，
2018 - 2020。

文件遵循以下命名规范，示例如下：

veg_pinus.halepensis_anv.eml_md_30m_0..0cm_2000..2002_eumap_epsg3035_v0.3

各字段含义如下：
- 字段`theme`（主题）：示例为`veg`
- 字段`species code`（物种代码）：示例为`pinus.halepensis`
- 字段`species distribution type`（物种分布类型）：示例为`anv`（即`actual natural vegetation`，实际天然植被）
- 字段`species estimation method`（物种估算方法）：示例为`eml`
- 字段`species estimation type`（物种估算类型）：示例为`md`（即`model deviation`，模型偏差）
- 字段`resolution in meters`（空间分辨率，单位：米）：示例为`30m`
- 字段`reference depths (vertical dimension)`（参考深度，即垂直维度）：示例为`0..0cm`
- 字段`reference period begin end`（参考时段起止）：示例为`2000..2002`
- 字段`reference area`（参考区域）：示例为`eumap`
- 字段`coordinate system`（坐标系）：示例为`epsg3035`
- 字段`data set version`（数据集版本）：示例为`v0.3`

针对任一物种，均可通过文件名快速识别其概率分布与不确定性分布地图：
- veg_pinus.halepensis_anv.eml_md：实际分布的模型不确定性地图
- veg_pinus.halepensis_anv.eml_p：实际分布的概率地图
- veg_pinus.halepensis_pnv.eml_md：潜在分布的模型不确定性地图
- veg_pinus.halepensis_pnv.eml_p：潜在分布的概率地图

所有文件均采用云优化GeoTIFF（Cloud Optimized GeoTIFF）格式，投影坐标系为ETRS89 / LAEA Europe（即EPSG代码3035）。同时提供SLD与QML格式的样式文件。

若需了解地图制作与建模的详细信息，可通过以下途径获取：
1. 观看2021年开放数据科学研讨会（Open Data Science Workshop 2021）的主题报告（TIB AV-PORTAL平台）
2. 访问包含R/Python脚本的代码仓库并按照指引完成操作（GitLab）
3. 访问训练数据集的存储仓库（Zenodo）
4. 在GitBook平台阅读包含可执行代码的教程文档

一篇详细阐述物种分布地图全流程处理、精度评估与综合分析的研究论文已发表于PeerJ期刊。若需提出改进建议或提交问题修复请求，请访问https://gitlab.com/geoharmonizer_inea/spatial-layers/-/issues。