[{"data":1,"prerenderedAt":143},["ShallowReactive",2],{"content-query-nw0edTU97C":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"date":10,"cover":11,"type":12,"body":13,"_type":137,"_id":138,"_source":139,"_file":140,"_stem":141,"_extension":142},"/news/en/2743","en",false,"","MindSpore and Tsinghua University Release a 3-Arcsecond Global Digital Elevation Model Dataset","Recently, MindSpore, Ascend AI4Sci Lab, and Professor Huang Xiaomeng's team from the Department of Earth System Science, Tsinghua University jointly launched a super-resolution 3-arcsecond (90-meter) global digital elevation model (DEM) and the related data product. The related article has been published in Science Bulletin.","2023-02-06","https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2023/09/13/da075669d489471ba0a0925f72bd4f68.png","news",{"type":14,"children":15,"toc":134},"root",[16,24,38,43,48,53,58,66,71,76,81,86,93,98,103,108,115,124,129],{"type":17,"tag":18,"props":19,"children":21},"element","h1",{"id":20},"mindspore-and-tsinghua-university-release-a-3-arcsecond-global-digital-elevation-model-dataset",[22],{"type":23,"value":8},"text",{"type":17,"tag":25,"props":26,"children":27},"p",{},[28,30,36],{"type":23,"value":29},"Recently, MindSpore, Ascend AI4Sci Lab, and Professor Huang Xiaomeng's team from the Department of Earth System Science, Tsinghua University jointly launched a super-resolution 3-arcsecond (90-meter) global digital elevation model (DEM) and the related data product. The related article has been published in ",{"type":17,"tag":31,"props":32,"children":33},"em",{},[34],{"type":23,"value":35},"Science Bulletin",{"type":23,"value":37},".",{"type":17,"tag":25,"props":39,"children":40},{},[41],{"type":23,"value":42},"The model is based on the Ascend AI Software and Hardware Platform and outperforms popular super-resolution models in terms of RMSE, resolution, and details. The new model is now open-sourced in the MindSpore community.",{"type":17,"tag":25,"props":44,"children":45},{},[46],{"type":23,"value":47},"High-resolution DEMs can provide accurate basic geographical data and play a vital role in research on global climate change, ocean tidal movement, and earth sphere material exchange. High-resolution global ocean DEMs, as a frontier branch of marine geology and marine surveying and mapping, provide a direct basis for understanding the tectonic movement and evolution of the seabed. However, technical limitations and surveying and mapping costs have made it expensive to obtain high-resolution global ocean DEMs.",{"type":17,"tag":25,"props":49,"children":50},{},[51],{"type":23,"value":52},"Based on 30-meter resolution NASADEM satellite images, the 450-meter resolution GEBCO_2021 public data of the United Nations Intergovernmental Oceanographic Commission, and the high-resolution ocean topographic data of some regions, a global DEM-SRNet model has been built, and a global 3-arcsecond (90-meter) resolution global DEM product GDEM_2022 has been developed in this study by adopting the technology combining a deep residual pre-training neural network and transfer learning.",{"type":17,"tag":25,"props":54,"children":55},{},[56],{"type":23,"value":57},"DEM-SRNet model architecture",{"type":17,"tag":25,"props":59,"children":60},{},[61],{"type":17,"tag":62,"props":63,"children":65},"img",{"alt":7,"src":64},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2023/09/13/a2044464dd4b452292849dcc4f04c9ca.png",[],{"type":17,"tag":25,"props":67,"children":68},{},[69],{"type":23,"value":70},"Based on MindSpore, this model reconstructs a global DEM dataset with a resolution of 90 meters (3 arcseconds). The elevation values of about 93.3 billion pixels were calculated. The team cooperates with Pengcheng Lab to conduct experiments based on MindSpore, Ascend 910 AI processor, and Huawei Cloud ModelArts.",{"type":17,"tag":25,"props":72,"children":73},{},[74],{"type":23,"value":75},"The DEM outperforms the widely used methods based on interpolation or deep learning. An average improvement in RMSE of 23.75% can be found in the GDEM_2022 product over the traditional interpolation methods. When GDEM_2022 and GEBCO_2021 are compared, it is found that GDEM_2022 has better visual and detail outputs.",{"type":17,"tag":25,"props":77,"children":78},{},[79],{"type":23,"value":80},"The super-resolution model can greatly reduce the number of sea areas or points that need to be measured, and complement the fine mapping of the seabed and the construction of global high-resolution DEM topographic maps.",{"type":17,"tag":25,"props":82,"children":83},{},[84],{"type":23,"value":85},"The 3-arcsecond (90-meter) global DEM dataset GDEM_2022",{"type":17,"tag":25,"props":87,"children":88},{},[89],{"type":17,"tag":62,"props":90,"children":92},{"alt":7,"src":91},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2023/09/13/050f9fb5e9564ed58fa632f6f88f02dd.png",[],{"type":17,"tag":25,"props":94,"children":95},{},[96],{"type":23,"value":97},"This achievement is the first global DEM dataset with a resolution of less than 100 meters. It meets the needs of ocean sounding data in different fields and at different levels and provides important support for research on the relationship between the global land-sea gravity field and topography with different terrain complexity, exploration of the equilibrium mechanism of different land-sea tectonic units, and research on the influence of land-sea topography on ocean tidal current movement.",{"type":17,"tag":25,"props":99,"children":100},{},[101],{"type":23,"value":102},"In the future, the joint team will continue to release innovative models for marine weather forecasting, and will work with more academic and scientific research partners to jointly explore and make progress in the ocean and atmosphere fields.",{"type":17,"tag":25,"props":104,"children":105},{},[106],{"type":23,"value":107},"You can scan the following QR code to obtain the dataset for free:",{"type":17,"tag":25,"props":109,"children":110},{},[111],{"type":17,"tag":62,"props":112,"children":114},{"alt":7,"src":113},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2023/09/13/9bc700a3eac0443482894ef724509118.png",[],{"type":17,"tag":25,"props":116,"children":117},{},[118],{"type":17,"tag":119,"props":120,"children":121},"strong",{},[122],{"type":23,"value":123},"References",{"type":17,"tag":25,"props":125,"children":126},{},[127],{"type":23,"value":128},"1. Chen L. Deep Learning and Practice with MindSpore[M]. Springer Nature, 2021.",{"type":17,"tag":25,"props":130,"children":131},{},[132],{"type":23,"value":133},"2. Zhang, Bo, Wei Xiong, Muyuan Ma, Mingqing Wang, Dong Wang, Xing Huang, Le Yu et al. Super-resolution reconstruction of a 3 arcsecond global DEM dataset[J]. Science Bulletin, 2022.",{"title":7,"searchDepth":135,"depth":135,"links":136},4,[],"markdown","content:news:en:2743.md","content","news/en/2743.md","news/en/2743","md",1776506045635]