Neural Network-Based Fusion of InSAR and Optical Digital Elevation Models with Consideration of Local Terrain Features

被引:0
|
作者
Gui, Rong [1 ,2 ]
Qin, Yuanjun [1 ]
Hu, Zhi [1 ]
Dong, Jiazhen [1 ]
Sun, Qian [3 ,4 ]
Hu, Jun [1 ,2 ]
Yuan, Yibo [1 ]
Mo, Zhiwei [1 ]
机构
[1] Cent South Univ, Sch Geosci & Infophys, Changsha 410083, Peoples R China
[2] Early Warning & Emergency Rescue Engn Technol Res, Hunan Geol Disaster Monitoring, Changsha 410004, Peoples R China
[3] Hunan Normal Univ, Coll Geog Sci, Changsha 410081, Peoples R China
[4] Key Lab Geospatial Big Data Min & Applicat, Changsha 410081, Peoples R China
基金
中国国家自然科学基金;
关键词
local terrain; DEM fusion; neural network; InSAR and optical DEMs; TANDEM-X;
D O I
10.3390/rs16193567
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
InSAR and optical techniques represent two principal approaches for the generation of large-scale Digital Elevation Models (DEMs). Due to the inherent limitations of each technology, a single data source is insufficient to produce high-quality DEM products. The increasing deployment of satellites has generated vast amounts of InSAR and optical DEM data, thereby providing opportunities to enhance the quality of final DEM products through the more effective utilization of the existing data. Previous research has established that complete DEMs generated by InSAR technology can be combined with optical DEMs to produce a fused DEM with enhanced accuracy and reduced noise. Traditional DEM fusion methods typically employ weighted averaging to compute the fusion results. Theoretically, if the weights are appropriately selected, the fusion outcome can be optimized. However, in practical scenarios, DEMs frequently lack prior information on weights, particularly precise weight data. To address this issue, this study adopts a fully connected artificial neural network for elevation fusion prediction. This approach represents an advancement over existing neural network models by integrating local elevation and terrain as input features and incorporating curvature as an additional terrain characteristic to enhance the representation of terrain features. We also investigate the impact of terrain factors and local terrain feature as training features on the fused elevation outputs. Finally, three representative study areas located in Oregon, USA, and Macao, China, were selected for empirical validation. The terrain data comprise InSAR DEM, AW3D30 DEM, and Lidar DEM. The results indicate that compared to traditional neural network methods, the proposed approach improves the Root-Mean-Squared Error (RMSE) ranges, from 5.0% to 12.3%, and the Normalized Median Absolute Deviation (NMAD) ranges, from 10.3% to 26.6%, in the test areas, thereby validating the effectiveness of the proposed method.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Correction of global digital elevation models in forested areas using an artificial neural network-based method with the consideration of spatial autocorrelation
    Li, Yanyan
    Li, Linye
    Chen, Chuanfa
    Liu, Yan
    INTERNATIONAL JOURNAL OF DIGITAL EARTH, 2023, 16 (01) : 1568 - 1588
  • [2] Multimodal Registration of Optical Images and Digital Elevation Models Using Terrain Features
    Zhao, Jiayang
    Li, Hui
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [3] A Neural Network-Based Fusion Approach for Improvement of SAR Interferometry-Based Digital Elevation Models in Plain and Hilly Regions of India
    Girohi, Priti
    Bhardwaj, Ashutosh
    AI, 2022, 3 (04) : 820 - 843
  • [4] AUTOMATED CLASSIFICATION OF GENERIC TERRAIN FEATURES IN DIGITAL ELEVATION MODELS
    GRAFF, LH
    USERY, EL
    PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 1993, 59 (09): : 1409 - 1417
  • [5] Reconstruction of Terrain based on corrected Digital Elevation Models
    Korotin, A. S.
    Popov, E., V
    MECHANICAL SCIENCE AND TECHNOLOGY UPDATE (MSTU 2019), 2019, 1260
  • [6] Comparison and fusion of LIDAR and InSAR digital elevation models over urban areas
    Gamba, P
    Dell'Acqua, F
    Houshmand, B
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (22) : 4289 - 4300
  • [7] Capsule graph neural network based on global and local features fusion
    Qian, Rong
    Zhang, Ru
    Zhang, Ke-Jun
    Jin, Xin
    Ge, Shi-Liang
    Jiang, Sheng
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2021, 51 (03): : 1048 - 1054
  • [8] Multiside graph neural network-based attention for local co-occurrence features fusion in lung nodule classification
    Saihood, Ahmed Ali
    Hasan, Mustafa Asaad
    Shnawa, Shafaa mahmood
    Fadhel, Mohammed A.
    Alzubaid, Laith
    Gupta, Ashish
    Gu, Yuantong
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 252
  • [9] Segmentation and Fusion of Building Features Based on InSAR and Optical Data
    Thiele, A.
    Wegner, J. D.
    Cadario, E.
    Schulz, K.
    Soergel, U.
    REMOTE SENSING FOR ENVIRONMENTAL MONITORING, GIS APPLICATIONS, AND GEOLOGY IX, 2009, 7478
  • [10] Design of a neural network-based digital multiplier
    Biederman, DC
    Ososanya, ET
    PROCEEDINGS OF THE TWENTY-NINTH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY, 1997, : 320 - 326