此外,在对比实验中,我们的方法超越了最先进的深度学习网络,凸显了我们提出的方法的有效性。与现有产品的比较分析,包括 2020 年 30 mGlobeLand30(Junetal.,2014 年)、2020 年 10 m Esri土地覆被图(Karra et al.,2021 年)、2020年10 m ESA 世界覆被图(Zanagaetal.,2021 年)、1 m 国家尺度土地覆被图(SinoLC- 1m)(Lietal、 2023)、2m城市树木覆盖数据集(UTC-2m)(Heetal)。
[1] He D, Shi Q, Liu X, Zhong Y, Zhang L. 2022. Generating 2m fine-scale urban tree cover product over 34 metropolises in China based on deep context-aware sub-pixel mapping network. International Journal of Applied Earth Observation and Geoinformation; 106:1 02667.
[2] Jun C, Ban Y, Li S. 2014. Open access to Earth land-cover map. Nature; 514: 434-434.
[3] Karra K, Kontgis C, Statman-Weil Z, Mazzariello JC, Mathis M, Brumby SP. 2021. Global land use / land cover with Sentinel 2 and deep learning. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: 4704 -4707.
[4] Li Z, He W, Cheng M, Hu J, Yang G, Zhang H. 2023. SinoLC- 1: the first 1-meter resolution national-scale land-cover map of China created with the deep learning framework and open-access data. Earth Syst. Sci. Data Discuss.; 2023: 1 -38.
[5] Shi Q, Liu M, MarinoniA, Liu X. 2023. UGS- 1m: fine-grained urban green space mapping of 31 major cities in China based on the deep learning framework. Earth Syst. Sci. Data; 15: 555 - 577.
[6] Xu Z, Zhao S. UBGG-3m: Fine-grained urban blue-green-gray landscape dataset for 36 Chinese cities based on deep learning network, Zenodo, 2023 .
[7] ZanagaD, Van De Kerchove R, De Keersmaecker W, SouverijnsN, Brockmann C, Quast R, et al. ESA WorldCover 10 m 2020 v100, Zenodo, 2021 .