基于深度学习的方法由于其优于传统技术的优势而在冰川提取中引起了极大的关注。本研究验证了LandsNet架构在冰川提取中的可行性和有效性，我们应用改进的LandsNet（M-LandsNet）提取了三江源头地区的冰川轮廓。采用波段比法、U-Net、U-Net++、GlacierNet、SaU-Net、U-Net+cSE和LandsNet两种场景进行比较。对两个场景的分析表明，M-LandsNet在1986种方法中具有最好的性能和泛化能力。
", "ds_source": "获得可靠的冰川清单是训练深度学习网络的第一步。在这项研究中，SCGI被用作真实的冰川轮廓，并被视为地面真相。
", "ds_process_way": "我们利用M-LandsNet和人工调整，在共40个时期进一步提取了三江源头地区的冰川轮廓。
", "ds_quality": "数据质量良好
", "ds_acq_start_time": "1986-01-01 00:00:00", "ds_acq_end_time": "2021-12-31 00:00:00", "ds_acq_place": "三江源头地区", "ds_acq_lon_east": 89.4, "ds_acq_lat_south": 31.5, "ds_acq_lon_west": 102.45, "ds_acq_lat_north": 37.11666666666667, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "open-access", "ds_total_size": 8011385, "ds_files_count": 2, "ds_format": ".shp", "ds_space_res": null, "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "WGS84", "ds_thumbnail": "791599d6-8d0b-4dd7-8bb0-a9b35e031a45.gif", "ds_thumb_from": 2, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "0a4269e1-65f4-45f1-aeba-88ea3068eebf", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 3, "publish_time": "2023-08-29 09:57:49", "last_updated": "2025-06-30 16:17:38", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.ZENODO.DB3941.2023", "i18n": { "en": { "title": "Long time-series glacier profile dataset for the Sanjiangyuan area (1986-2021)", "ds_format": ".shp", "ds_source": "&Emsp; Obtaining a reliable glacier inventory is the first step in training a deep learning network. In this study, SCGI is used as a real glacier profile and is considered as ground truth.
", "ds_quality": "&Emsp;Good quality of data
", "ds_ref_way": "", "ds_abstract": "&Emsp Deep learning-based methods have attracted great attention in glacier extraction due to their advantages over traditional techniques. In this study, we verified the feasibility and effectiveness of LandsNet architecture in glacier extraction, and we applied the improved LandsNet (M-LandsNet) to extract the glacier contours in the headwaters of the Three Rivers. Two scenarios were compared using the band ratio method, U-Net, U-Net++, GlacierNet, SaU-Net, U-Net+cSE and LandsNet. The analysis of the two scenarios shows that M-LandsNet has the best performance and generalization ability among the 1986 methods.
", "ds_time_res": "", "ds_acq_place": "Sanjiangyuan headwaters region", "ds_space_res": "", "ds_projection": "WGS84", "ds_process_way": "&Emsp;We further extracted the glacier outlines in the Three Rivers headwaters region in a total of 40 periods using M-LandsNet and manual adjustment.
", "ds_ref_instruction": "" } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "CC BY 4.0", "doi_reg_from": "reg_outside", "cstr_reg_from": "reg_outside", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "冰川轮廓", "冰川面积", "时空冰川变化" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "三江源头地区" ], "ds_time_tags": [ 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021 ], "ds_contributors": [ { "true_name": "张万昌", "email": "zhangwc@radi.ac.cn", "work_for": "中国科学院空天信息创新研究院", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "张万昌", "email": "zhangwc@radi.ac.cn", "work_for": "中国科学院空天信息创新研究院", "country": "中国" } ], "ds_managers": [ { "true_name": "张万昌", "email": "zhangwc@radi.ac.cn", "work_for": "中国科学院空天信息创新研究院", "country": "中国" } ], "category": "冰川" }