标题: An Intelligent Learning Reconfiguration Model Based on Optimized Transformer and Multisource Features (TMSFs) for High-Precision InSAR DEM Void Filling

作者: Zhang, TF (Zhang, Tengfei); Chen, YM (Chen, Yumin); Zhu, R (Zhu, Rui); Wilson, JP (Wilson, John P.); Song, J (Song, Jun); Chen, RX (Chen, Ruoxuan); Liu, LC (Liu, Licheng); Bao, LH (Bao, Lanhua)

来源出版物: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 卷: 63 文献号: 5203418 DOI: 10.1109/TGRS.2025.3535546 Published Date: 2025

摘要: The synthetic aperture radar (SAR) systems can provide submeter terrain mapping and accurate point elevation information quickly and efficiently. The interferometric SAR (InSAR) technology has proven to be a powerful method for producing digital elevation models (DEMs). However, DEM generation using InSAR technology is limited by mountain shadow overlap, atmospheric noise, low backscatter coefficient, and spatiotemporal incoherence, leading to the problem of voids. This article proposes an intelligent learning reconfiguration model based on optimized transformer and multisource features (TMSFs). First, the intelligent learning reconfiguration model based on the transformer and convolutional neural network (CNN) was constructed, and the multisource feature connection module was used for feature supervision and loss function optimization. Then, the relationship of nonvoid areas between the low-resolution (LR) DEM and the high-resolution (HR) InSAR DEM was found, and the voids were intelligently filled. The experiments used 19 TerraSAR-X images in San Diego (SD), USA, and 18 PAZ images in Yan'an (YA), China, to generate high-precision InSAR void DEMs and intelligently fill the voids. Compared with traditional interpolation or deep learning models, modeling accuracy improved by 11.31%-45.74% and 2.32%-8.78% in the SD and YA areas, respectively. Using the photogrammetric DEM to evaluate the accuracy of the filled DEM, the new method showed improvements of 15.64%-25.91% and 5.60%-28.26%, respectively. In addition, 122 Ice, Cloud, and land Elevation Satellite (ICESat)/Geosciences Laser Altimeter System (GLAS) points collected in the YA area were further validated, with an improvement of 4.40%-22.28%. The generated DEM has considerable advantages for terrain feature preservation and river network extraction, and the new method can provide technical support for DEM void filling.

作者关键词: Accuracy; Atmospheric modeling; Noise; Training; Transformers; Deformation; Synthetic aperture radar; Data integration; Convolutional neural networks; Spatiotemporal phenomena; Digital elevation models (DEMs); interferometric synthetic aperture radar (InSAR); learning reconfiguration; multisource features; transformer; void filling

地址: [Zhang, Tengfei; Chen, Yumin; Chen, Ruoxuan; Liu, Licheng; Bao, Lanhua] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Zhu, Rui] ASTAR, Inst High Performance Comp IHPC, Singapore 138632, Singapore.

[Wilson, John P.] Univ Southern Calif, Spatial Sci Inst, Los Angeles, CA 90089 USA.

[Song, Jun] Hong Kong Baptist Univ, Dept Geog, Hong Kong, Peoples R China.

通讯作者地址: Chen, YM (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

电子邮件地址: tengfeizhang@whu.edu.cn; ymchen@whu.edu.cn; zhur@ihpc.a-star.edu.sg; jpwilson@usc.edu; junsong@hkbu.edu.hk; 2023202050017@whu.edu.cn; 2020302051126@whu.edu.cn; lanhuabao@whu.edu.cn

影响因子：7.5