标题: Local Climate Zone Mapping by Coupling Multilevel Features With Prior Knowledge Based on Remote Sensing Images
作者: Zhong, XR (Zhong, Xinrun); Li, HF (Li, Huifang); Shen, HF (Shen, Huanfeng); Gao, ML (Gao, Meiling); Wang, ZH (Wang, Zhihua); He, JQ (He, Jinqiang)
来源出版物: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 卷: 62 文献号: 4403014 DOI: 10.1109/TGRS.2024.3360522 Published Date: 2024
摘要: Local climate zone (LCZ) mapping can explore the variability of the impact of urban form on the thermal environment in different urban contexts, and large-scale LCZ mapping can help us to better understand the spatial and temporal dynamics of the climate in urban areas around the world. Studies have indicated that deep learning-based methods can effectively perform the LCZ classification. However, the accuracy of LCZ classification on large-scale datasets is still unsatisfactory, mainly due to the fact that the traditional convolutional neural networks are not good at mining contextual information, which is crucial for fully understanding remote sensing (RS) scenes. In this article, to solve this problem, we propose an LCZ mapping method based on RS images by coupling multilevel features mined from global and local ranges with prior knowledge, named LCZ-MFKNet. The global and local features are extracted through Swin Transformer and space-maintained ResNet (SM-ResNet) model branches, respectively, and then fused through an improved squeeze-and-excitation (iSE) module. The prior knowledge studied from the theoretical definition and experimental tests is that two typical sets of LCZ categories are easily confounded in multiclass classification but separable in two-class classification. Experiments are conducted on the large publicly available So2Sat LCZ42 dataset, where the proposed LCZ-MFKNet method achieved the highest LCZ mapping accuracy. Moreover, six megacities were selected globally for LCZ mapping, and the results verified the accuracy and the general applicability of the proposed LCZ-MFKNet method in large-scale LCZ mapping.
作者关键词: Feature extraction; Biological system modeling; Urban areas; Remote sensing; Transformers; Meteorology; Data models; Local climate zone; local-global feature fusion; multilevel features; prior knowledge; transformer
地址: [Zhong, Xinrun; Li, Huifang; Shen, Huanfeng] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.
[Shen, Huanfeng] Wuhan Univ, Collaborat Innovat Ctr Geospatial Technol, Wuhan 430079, Peoples R China.
[Gao, Meiling] Changan Univ, Coll Geol Engn & Geomat, Xian 710054, Peoples R China.
[Wang, Zhihua] Arizona State Univ, Sch Sustainable Engn & Built Environm, Tempe, AZ 85287 USA.
[He, Jinqiang] China Univ Min & Technol, Sch Environm & Spatial Informat, Xuzhou, Peoples R China.
通讯作者地址: Li, HF (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.
电子邮件地址: 2021202050019@whu.edu.cn; huifangli@whu.edu.cn; shenhf@whu.edu.cn; gaomeiling@chd.edu.cn; zhwang@asu.edu; 08205101@cumt.edu.cn
影响因子：8.2
