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
  • [41] Performance Analysis of Recurrent Neural Network-based Digital Pre-Distortion for Optical Coherent Transmission
    Bajaj, Vinod
    Aref, Vahid
    Wahls, Sander
    2022 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC), 2022,
  • [42] Convolutional neural network-based models for diagnosis of breast cancer
    Masud, Mehedi
    Rashed, Amr E. Eldin
    Hossain, M. Shamim
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (14): : 11383 - 11394
  • [43] Research on extraction of stream network based on digital elevation models
    State Key Laboratory of Environmental Geochemistry, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang 550002, China
    不详
    Liaoning Gongcheng Jishu Daxue Xuebao (Ziran Kexue Ban), 2006, SUPPL. (313-315):
  • [44] Digital Watermarking Based on Neural Network and Image Features
    Huang, Song
    Zhang, Wei
    ICIC 2009: SECOND INTERNATIONAL CONFERENCE ON INFORMATION AND COMPUTING SCIENCE, VOL 2, PROCEEDINGS: IMAGE ANALYSIS, INFORMATION AND SIGNAL PROCESSING, 2009, : 238 - +
  • [45] Transfer learning of recurrent neural network-based plasticity models
    Heidenreich, Julian N.
    Bonatti, Colin
    Mohr, Dirk
    INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 2024, 125 (01)
  • [46] Estimation of Prediction Intervals in Neural Network-based Regression Models
    Miok, Kristian
    2018 20TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2018), 2019, : 463 - 468
  • [47] Accelerated Algorithm for Generating Measurements of Terrain Following Radar Based on Digital Elevation Models
    Hong, Kyungwoo
    Kim, Sungjoong
    Bang, Hyochoong
    Seo, Kwansik
    Jeon, Jiyeon
    JOURNAL OF THE KOREAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, 2023, 51 (06) : 399 - 406
  • [48] Progressive Neural Network-based Knowledge Transfer in Acoustic Models
    Moriya, Takafumi
    Masumura, Ryo
    Asami, Taichi
    Shinohara, Yusuke
    Delcroix, Marc
    Yamaguchi, Yoshikazu
    Aono, Yushi
    2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 998 - 1002
  • [49] A Deep Neural Network-Based Feature Fusion for Bearing Fault Diagnosis
    Hoang, Duy Tang
    Tran, Xuan Toa
    Van, Mien
    Kang, Hee Jun
    SENSORS, 2021, 21 (01) : 1 - 13
  • [50] Classifying Slope Unit by Combining Terrain Feature Lines Based on Digital Elevation Models
    Wang, Hao
    Hu, Guanghui
    Ma, Junfei
    Wei, Hong
    Li, Sijin
    Tang, Guoan
    Xiong, Liyang
    LAND, 2023, 12 (01)