清华大学全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022）

​

全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022）基于30 米分辨率的NASADEM 卫星影像、联合国政府间海洋学委员会的450 m分辨率GEBCO_2021 公开数据和部分区域高分辨率海洋地形数据，采用深度残差预训练神经网络和迁移学习（Transfer Learning）相结合技术，构建了适用于全球区域的DEM-SRNet模型生产完成。前言 – 人工智能教程

全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022）是清华大学黄小猛教授团队基于30米分辨率的NASADEM卫星影像、联合国政府间海洋学委员会的450米分辨率GEBCO_2021公开数据和部分区域高分辨率海洋地形数据，采用深度残差预训练神经网络和迁移学习相结合技术，构建的适用于全球区域的DEM超分模型，制作的全球90米分辨率的海陆DEM产品。

GDEM_2022产品具有以下特点：

• 高分辨率：90米的空间分辨率，可用于监测地形变化、土地利用变化、灾害风险评估等。
• 高精度：平均精度约为1米，可满足多种应用需求。
• 全球覆盖：涵盖全球陆地和海洋地区，可用于全球尺度的环境研究和监测。

GDEM_2022产品是宝贵的遥感数据资源，可用于多种应用，包括：

• 地形变化监测：可用于监测山体滑坡、泥石流、地震等自然灾害引起的地形变化。
• 土地利用变化监测：可用于监测城市扩张、森林砍伐、农田变更等土地利用变化。
• 灾害风险评估：可用于评估地震、洪水、台风等自然灾害对地形和土地利用的影响。
• 其他应用：可用于地图制作、3D建模、城市规划等。

数据集ID:

THU/GDEM_2022

时间范围: 2022年-2022年

范围: 全球

来源: 清华大学

复制代码段: ​

var images = pie.ImageCollection("THU/GDEM_2022")

代码：

/**
* @File   :   全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022）
* @Time   :   2023/02/06
* @Author  :   piesat
* @Version :   1.0
* @Contact :   400-890-0662
* @License :   (C)Copyright 航天宏图信息技术股份有限公司
* @Desc   :   加载全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022）
*/
//矢量范围
/*color:#f8f8ff*/
var geometry0 = pie.Geometry.Polygon([
    [
        [
            65.93833802280002,
            58.177979827588246
        ],
        [
            173.65551741218366,
            58.177979827588246
        ],
        [
            173.65551741218366,
            -17.351364110676386
        ],
        [
            65.93833802280002,
            -17.351364110676386
        ],
        [
            65.93833802280002,
            58.177979827588246
        ]
    ]
], null);
//引用全球90米分辨率海洋和陆地DEM数据产品（GDEM_2022），通过矢量范围进行过滤，并选择波段进行均值合成
var imgs = pie.ImageCollection("THU/GDEM_2022")
              .filterBounds(geometry0)
              .select("B1")
              .mean()
//在地图上加载并显示数据
Map.addLayer(imgs, {
      min:-9348, max:8832, 
      "palette": [
        "#002275","#002476","#00287F","#003090","#0039A3","#0042B1","#004FC8","#0057D8","#0066ED","#0075FE","#1887F9","#389CF8","#53AFF8","#74C2FD","#8AD0FC","#A4DFFE","#ACDFFD","#BEEAFB",
        "#659135","#A1CA7A","#D3E6A2","#F0EAB5","#E5D1A4", "#E3BD8A","#D9AB51","#B59E13","#A59006","#867513","#755D03","#5B4B01","#553F0B","#6E571A","#C08262","#CBA292","#D2B3A9","#D6BCB3",
      ]})
//加载显示图例
var data = {
    title: "高程（m）",
    colors: [
        "#002275","#002476","#00287F","#003090","#0039A3","#0042B1","#004FC8","#0057D8","#0066ED","#0075FE","#1887F9","#389CF8","#53AFF8","#74C2FD","#8AD0FC","#A4DFFE","#ACDFFD","#BEEAFB",
        "#659135","#A1CA7A","#D3E6A2","#F0EAB5","#E5D1A4", "#E3BD8A","#D9AB51","#B59E13","#A59006","#867513","#755D03","#5B4B01","#553F0B","#6E571A","#C08262","#CBA292","#D2B3A9","#D6BCB3","#D5BEB5"
    ],
    labels: ["-9348","8832"],
};
var style = {
        right: "150px",
        bottom: "80px",
        height: "70px",
        width: "350px"
    };

var legend = ui.Legend(data, style);
Map.addUI(legend);

 文章引用：
1.Sonogashira M, M Shonai, and M.J.P.o. Iiyama. High-resolution bathymetry by deep-learning-based image superresolution. Plos one 2020;15: e0235487.
2. Chen B, Xu B, Zhu Z, et al. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Sci. Bull 2019; 64:370-373.
3. Bashir S M A, Wang Y, Khan M, et al. A Comprehensive Review of Deep Learning-based Single Image Super-resolution. PeerJ Comput 2021;7: e621.
4. Molnar, P. Continental tectonics in the aftermath of plate tectonics. Nature 1988; 335: 131–137.
5. JPL N. NASADEM Merged DEM Global 1 arc second V001. 2020; Distributed by OpenTopography.
6. Group G.C. GEBCO 2021 Grid. 2021; G.C. Group, Editor.
7. German Aerospace Center (DLR) (2018): TanDEM-X - Digital Elevation Model (DEM) - Global, 90m.
8. Canadian Hydrographic Service. Non-navigational (NONNA-100) bathymetric data. 2019, from https://open.canada.ca/data/en/dataset/d3881c4c-650d-4070-bf9b-1e00aabf0a1d.
9. John, Morgan D., Campbell, Kerry J., and Christine A. Devine. BOEM's 3DX-Based Regional Bathymetric Data Set, Deepwater Gulf of Mexico: Automated Seafloor Characterization, Geohazards Assessment, and Engineering Planning. Offshore Technology Conference, Houston, Texas, USA, 2018.
10. British Antarctic Survey. South Georgia Geographic Information System (SGGIS), 2017.
11. Zhong ming, Zhu, and Liu Wei. The data behind the search for MH370: Phase Two data released, 2018.
12. Parums, R., Spinoccia, M. 50m Multibeam Dataset of Australia 2018. Geoscience Australia, Canberra, 2019.
13. Beaman, R.J. High-resolution depth model for the Great Barrier Reef - 30 m. Geoscience Australia, Canberra, 2017.
14. Chen L and Zeng Y. Deep Learning and Practice with MindSpore ser. Springer. Tsinghua University Press, 2021.
15. Demiray B Z, Sit M and Demir I. D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks. SN Comput 2021; 2: 48.

​