• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于时空机器学习的2000 - 2022年全球草原类别和范围的年度30米地图。

Annual 30-m maps of global grassland class and extent (2000-2022) based on spatiotemporal Machine Learning.

作者信息

Parente Leandro, Sloat Lindsey, Mesquita Vinicius, Consoli Davide, Stanimirova Radost, Hengl Tomislav, Bonannella Carmelo, Teles Nathália, Wheeler Ichsani, Hunter Maria, Ehrmann Steffen, Ferreira Laerte, Mattos Ana Paula, Oliveira Bernard, Meyer Carsten, Şahin Murat, Witjes Martijn, Fritz Steffen, Malek Ziga, Stolle Fred

机构信息

OpenGeoHub Foundation, Doorwerth, The Netherlands.

Land & Carbon Lab, World Resources Institute, Washington, DC, USA.

出版信息

Sci Data. 2024 Dec 11;11(1):1303. doi: 10.1038/s41597-024-04139-6.

DOI:10.1038/s41597-024-04139-6
PMID:39663386
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11634896/
Abstract

The paper describes the production and evaluation of global grassland extent mapped annually for 2000-2022 at 30 m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity covariates, spatiotemporal machine learning (per-class Random Forest) and over 2.3 M reference samples (visually interpreted in Very High Resolution imagery). Custom probability thresholds (based on five-fold spatial cross-validation) were used to derive dominant class maps with balanced user's and producer's accuracy, resulting in f1 score of 0.64 and 0.75 for cultivated and natural/semi-natural grassland, respectively. The produced maps (about 4 TB in size) are available under an open data license as Cloud-Optimized GeoTIFFs and as Google Earth Engine assets. The suggested uses of data include (1) integration with other compatible land cover products and (2) tracking the intensity and drivers of conversion of land to cultivated grasslands and from natural / semi-natural grasslands into other land use systems.

摘要

本文描述了2000 - 2022年每年以30米空间分辨率绘制的全球草地范围的制作与评估。利用GLAD Landsat ARD - 2图像存档，结合气候、地形和邻近协变量、时空机器学习（逐类随机森林）以及超过230万个参考样本（在超高分辨率图像中进行目视解译），生成了显示耕地和天然/半天然草地类别的时空分布的数据集。使用自定义概率阈值（基于五折空间交叉验证）来推导具有平衡用户精度和生产者精度的优势类别地图，耕地和天然/半天然草地的F1分数分别为0.64和0.75。生成的地图（大小约4TB）可根据开放数据许可作为云优化地理TIFF文件和谷歌地球引擎资产获取。数据的建议用途包括：（1）与其他兼容的土地覆盖产品集成；（2）跟踪土地转变为人工草地以及从天然/半天然草地转变为其他土地利用系统的强度和驱动因素。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/ba5f0f4db891/41597_2024_4139_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/0615acff9b5a/41597_2024_4139_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/c7dde25849f3/41597_2024_4139_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/9ff5e15943b9/41597_2024_4139_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/30b78fab30d7/41597_2024_4139_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/266bee3f8798/41597_2024_4139_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/6615b0e89500/41597_2024_4139_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/a725c46c3b69/41597_2024_4139_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/9c6a63416db3/41597_2024_4139_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/c350d81e0bbb/41597_2024_4139_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/15856cb60b93/41597_2024_4139_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/ba5f0f4db891/41597_2024_4139_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/0615acff9b5a/41597_2024_4139_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/c7dde25849f3/41597_2024_4139_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/9ff5e15943b9/41597_2024_4139_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/30b78fab30d7/41597_2024_4139_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/266bee3f8798/41597_2024_4139_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/6615b0e89500/41597_2024_4139_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/a725c46c3b69/41597_2024_4139_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/9c6a63416db3/41597_2024_4139_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/c350d81e0bbb/41597_2024_4139_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/15856cb60b93/41597_2024_4139_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2d41/11634896/ba5f0f4db891/41597_2024_4139_Fig11_HTML.jpg

相似文献

1
Annual 30-m maps of global grassland class and extent (2000-2022) based on spatiotemporal Machine Learning.基于时空机器学习的2000 - 2022年全球草原类别和范围的年度30米地图。
Sci Data. 2024 Dec 11;11(1):1303. doi: 10.1038/s41597-024-04139-6.
2
A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000-2019) based on LUCAS, CORINE and GLAD Landsat.基于 LUCAS、CORINE 和 GLAD Landsat 数据，为欧洲（2000-2019 年）生成土地利用/土地覆盖时间序列地图的时空集成机器学习框架
PeerJ. 2022 Jul 21;10:e13573. doi: 10.7717/peerj.13573. eCollection 2022.
3
A computational framework for processing time-series of earth observation data based on discrete convolution: global-scale historical Landsat cloud-free aggregates at 30 m spatial resolution.一种基于离散卷积处理地球观测数据时间序列的计算框架：30米空间分辨率的全球尺度历史陆地卫星无云聚合数据。
PeerJ. 2024 Dec 4;12:e18585. doi: 10.7717/peerj.18585. eCollection 2024.
4
Automated mapping of land cover in Google Earth Engine platform using multispectral Sentinel-2 and MODIS image products.利用多光谱哨兵 -2 号和中分辨率成像光谱仪（MODIS）影像产品在谷歌地球引擎平台上自动绘制土地覆盖图。
PLoS One. 2025 Apr 7;20(4):e0312585. doi: 10.1371/journal.pone.0312585. eCollection 2025.
5
Thematic accuracy assessment of the 2011 National Land Cover Database (NLCD).2011年国家土地覆盖数据库（NLCD）的专题精度评估。
Remote Sens Environ. 2017;191:328-341. doi: 10.1016/j.rse.2016.12.026.
6
Land use/land cover changes in the central part of the Chitwan Annapurna Landscape, Nepal.尼泊尔奇特万-安纳普尔纳景观中部的土地利用/土地覆被变化。
PeerJ. 2022 May 20;10:e13435. doi: 10.7717/peerj.13435. eCollection 2022.
7
Ecodatacube.eu: analysis-ready open environmental data cube for Europe.Ecodatacube.eu：适用于欧洲的分析就绪开放式环境数据立方体。
PeerJ. 2023 Jun 6;11:e15478. doi: 10.7717/peerj.15478. eCollection 2023.
8
The first generation of a regional-scale 1-m forest canopy cover dataset using machine learning and google earth engine cloud computing platform: A case study of Arkansas, USA.利用机器学习和谷歌地球引擎云计算平台生成的第一代区域尺度1米森林冠层覆盖数据集：以美国阿肯色州为例
Data Brief. 2023 Dec 30;52:109986. doi: 10.1016/j.dib.2023.109986. eCollection 2024 Feb.
9
Mapping management intensity types in grasslands with synergistic use of Sentinel-1 and Sentinel-2 satellite images.利用哨兵-1和哨兵-2卫星图像协同绘制草原管理强度类型图。
Sci Rep. 2024 Dec 30;14(1):32066. doi: 10.1038/s41598-024-83699-4.
10
Integrating low-altitude drone based-imagery and OBIA for mapping and manage semi natural grassland habitats.将基于低空无人机的图像与 OBIA 集成，用于绘制和管理半自然草地生境地图。
J Environ Manage. 2022 Nov 1;321:115723. doi: 10.1016/j.jenvman.2022.115723. Epub 2022 Aug 19.

引用本文的文献

1
Global 30-m annual median vegetation height maps (2000-2022) based on ICESat-2 data and Machine Learning.基于ICESat-2数据和机器学习的全球30米年度植被高度中位数地图（2000 - 2022年）
Sci Data. 2025 Aug 23;12(1):1470. doi: 10.1038/s41597-025-05739-6.
2
Light use efficiency (LUE) based bimonthly gross primary productivity (GPP) for global grasslands at 30 m spatial resolution (2000-2022).基于光能利用效率（LUE）的全球草原双月总初级生产力（GPP），空间分辨率为30米（2000 - 2022年）。
PeerJ. 2025 Aug 12;13:e19774. doi: 10.7717/peerj.19774. eCollection 2025.
3
Addressing critiques refines global estimates of reforestation potential for climate change mitigation.

本文引用的文献

1
A computational framework for processing time-series of earth observation data based on discrete convolution: global-scale historical Landsat cloud-free aggregates at 30 m spatial resolution.一种基于离散卷积处理地球观测数据时间序列的计算框架：30米空间分辨率的全球尺度历史陆地卫星无云聚合数据。
PeerJ. 2024 Dec 4;12:e18585. doi: 10.7717/peerj.18585. eCollection 2024.
2
A global land cover training dataset from 1984 to 2020.一个全球土地覆盖训练数据集，时间跨度为 1984 年至 2020 年。
Sci Data. 2023 Dec 7;10(1):879. doi: 10.1038/s41597-023-02798-5.
3
EuroCrops: The Largest Harmonized Open Crop Dataset Across the European Union.
回应批评意见有助于完善对用于缓解气候变化的造林潜力的全球评估。
Nat Commun. 2025 Jun 11;16(1):4572. doi: 10.1038/s41467-025-59799-8.
欧麦斯：欧盟最大的作物数据集
Sci Data. 2023 Sep 11;10(1):612. doi: 10.1038/s41597-023-02517-0.
4
Global maps of cropland extent and change show accelerated cropland expansion in the twenty-first century.全球耕地范围和变化图表明，二十一世纪耕地扩张速度加快。
Nat Food. 2022 Jan;3(1):19-28. doi: 10.1038/s43016-021-00429-z. Epub 2021 Dec 23.
5
A new approach to characterising and predicting crop rotations using national-scale annual crop maps.利用全国尺度的年度作物图对作物轮作进行特征描述和预测的新方法。
Sci Total Environ. 2023 Feb 20;860:160471. doi: 10.1016/j.scitotenv.2022.160471. Epub 2022 Nov 23.
6
Forest tree species distribution for Europe 2000-2020: mapping potential and realized distributions using spatiotemporal machine learning.2000-2020 年欧洲森林树种分布：利用时空机器学习绘制潜在和实现分布的地图。
PeerJ. 2022 Jul 25;10:e13728. doi: 10.7717/peerj.13728. eCollection 2022.
7
A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000-2019) based on LUCAS, CORINE and GLAD Landsat.基于 LUCAS、CORINE 和 GLAD Landsat 数据，为欧洲（2000-2019 年）生成土地利用/土地覆盖时间序列地图的时空集成机器学习框架
PeerJ. 2022 Jul 21;10:e13573. doi: 10.7717/peerj.13573. eCollection 2022.
8
Global land use changes are four times greater than previously estimated.全球土地利用变化比之前估计的高出四倍。
Nat Commun. 2021 May 11;12(1):2501. doi: 10.1038/s41467-021-22702-2.
9
Rapid expansion of human impact on natural land in South America since 1985.自1985年以来，人类对南美洲自然土地的影响迅速扩大。
Sci Adv. 2021 Apr 2;7(14). doi: 10.1126/sciadv.abg1620. Print 2021 Apr.
10
Climate warming from managed grasslands cancels the cooling effect of carbon sinks in sparsely grazed and natural grasslands.从管理的草原释放出的温室气体抵消了稀疏放牧和自然草原碳汇的冷却效应。
Nat Commun. 2021 Jan 5;12(1):118. doi: 10.1038/s41467-020-20406-7.