Large-Scale Sub-Canopy Topography Estimation From Tandem-X InSAR and ICESat-2 Data Using Machine Learning Method

Huacan Hu; Zhu Jianjun; Fu Haiqiang; Lopez-Sanchez Juan M.; Gómez Cristina; Zhang Tao; Liu Kui

doi:10.11834/jrs.20233152

Views : 0 下载量: 130 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

Large-Scale Sub-Canopy Topography Estimation From Tandem-X InSAR and ICESat-2 Data Using Machine Learning Method
Pages: 1-14(2023)
Published Online： 24 October 2023 ，
DOI： 10.11834/jrs.20233152

扫描看全文

胡华参，朱建军，付海强，Juan M. Lopez-Sanchez，Cristina Gómez，张涛，刘奎.XXXX.基于机器学习联合TanDEM-X InSAR和ICESat-2数据估计大范围林下地形.遥感学报，XX（XX）： 1-14

Huacan Hu，Zhu Jianjun，Fu Haiqiang，Lopez-Sanchez Juan M.，Gómez Cristina，Zhang Tao，Liu Kui. XXXX. Large-Scale Sub-Canopy Topography Estimation From Tandem-X InSAR and ICESat-2 Data Using Machine Learning Method. National Remote Sensing Bulletin， XX（XX）：1-14
胡华参，朱建军，付海强，Juan M. Lopez-Sanchez，Cristina Gómez，张涛，刘奎.XXXX.基于机器学习联合TanDEM-X InSAR和ICESat-2数据估计大范围林下地形.遥感学报，XX（XX）： 1-14 DOI： 10.11834/jrs.20233152.

Huacan Hu，Zhu Jianjun，Fu Haiqiang，Lopez-Sanchez Juan M.，Gómez Cristina，Zhang Tao，Liu Kui. XXXX. Large-Scale Sub-Canopy Topography Estimation From Tandem-X InSAR and ICESat-2 Data Using Machine Learning Method. National Remote Sensing Bulletin， XX（XX）：1-14 DOI： 10.11834/jrs.20233152.

摘要

双站TanDEM-X InSAR系统已成功应用于生产全球数字高程模型。然而，受X波段SAR信号的穿透能力限制和森林体积散射的影响，在森林地区提取的DEM包含严重森林信号。因此，利用TanDEM-X InSAR数据估计林下地形的关键在于如何降低森林体散射对InSAR测高的影响。鉴于此，本文提出了一种基于机器学习联合TanDEM-X InSAR、ICESat-2和Landsat 8数据估计林下地形的方法。为验证所提方法的有效性，选用了两个具有不同地形条件和森林类型特征的试验区进行了测试，并利用高精度机载LiDAR DTM进行精度评定。在加蓬热带雨林试验区，估计的林下地形RMSE为5.45 m和5.91 m，与InSAR DEM （14.70 m和18.58 m）相比提高了60%以上；在西班牙北方森林试验区，林下地形的RMSE也从6.05~9.10 m降低到了3.06~4.42 m。

Abstract

Digital elevation models (DEMs) are indispensable data source for natural resource investigation

climate change analysis

disaster monitoring and assessment. TanDEM-X

as the first twin-satellite synthetic aperture radar interferometric (InSAR) system

has been successfully obtained a high-precision global DEM with 12 m resolution. However

the penetrability of short-wave signals is limited

and the DEMs obtained in dense forest areas are typical of low precision

contaminated by the forest canopy signal. The phase center height (PCH) height caused due to the forest volume scattering needs to be removed from InSAR-derived DEM to obtain sub-canopy topography. Unfortunately

the TanDEM-X global standard mode acquires single-baseline

single-polarization data

which is difficult to satisfy the existing model calculations

and external data needs to be introduced. In this paper

we propose a machine learning-based method to estimate sub-canopy topography by combining TanDEM-X InSAR data

ICESat-2 data

and Landsat 8 OLI data. The effectiveness of the proposed method is tested and validated in two test sites with different topography properties and forest types. In the Estuaire rainforest test site

compared with the airborne LiDAR digital terrain model (DTM)

the root-mean-square errors (RMSEs) of the InSAR DEMs corresponding to two locations are 14.70 m and 18.58 m. After removing the PCH

the accuracy is improved to 5.54 m and 5.86 m

which represents an improvement of over 60%. In the Spanish northern forest test site with complex terrain

the RMSE of sub-canopy topography also increased from 6.05~9.10 m to 3.06~4.42 m. In addition

we investigated the necessity of the proposed method to use InSAR observations and the impact of the accuracy of the ICESat-2 control points used on the sub-canopy topography estimation. These satisfactory results demonstrate the potential of the proposed method to estimate sub-canopy topography for future spaceborne InSAR missions (e.g. TanDEM-L and LT-1)

when only single polarization and baseline data are available. Additionally

combining the high resolution of the TanDEM-X with the strong penetrability of the BIOMASS

the sub-canopy topography with higher accuracy and resolution will be estimated in the future.

关键词

林下地形合成孔径雷达干涉测量相位中心高度机器学习TanDEM-XICESat-2

Keywords

sub-canopy topographyInSARphase center height (PCH)machine learningTanDEM-XICESat-2

references

Abrams M, Crippen R, Fujisada H, 2020. ASTER Global Digital Elevation Model (GDEM) and ASTER Global Water Body Dataset (ASTWBD). Remote Sensing, 12(7): 1156. [DOI:10.3390/rs12071156http://dx.doi.org/10.3390/rs12071156]

Arozarena A, 2006. The Spanish National Territory Observation Program: current states and next steps. (in Spanish) Mapping Inter, 2006: 16-22.

Ben Jabeur S, Gharib C, Mefteh-Wali S, Ben Arfi W, 2021. CatBoost model and artificial intelligence techniques for corporate failure prediction. Technological Forecasting and Social Change, 166: 120658. [DOI:10.1016/j.techfore.2021.120658http://dx.doi.org/10.1016/j.techfore.2021.120658]

Cloude S R, Papathanassiou K P, 1998. Polarimetric SAR interferometry. IEEE Transactions on Geoscience and Remote Sensing, 36(5): 1551-1565. [DOI:10.1109/36.718859http://dx.doi.org/10.1109/36.718859]

DALL J. 2007. InSAR Elevation Bias Caused by Penetration Into Uniform Volumes. IEEE Transactions on Geoscience and Remote Sensing, 45(7): 2319-2324. [https://doi.org/10.1109/TGRS.2007.896613https://doi.org/10.1109/TGRS.2007.896613]

Dias De Paiva R C, Buarque D C, Collischonn W, Bonnet M P, Frappart F, Calmant S, Bulhoes Mendes C A, 2013. Large-scale hydrologic and hydrodynamic modeling of the Amazon River basin. Water Resources Research, 49(3): 1226-1243. [DOI:10.1002/wrcr.20067http://dx.doi.org/10.1002/wrcr.20067]

Dong Jiachen, Ni Wenjian, Zhang Zhiyu, Sun Guoqing, 2021. Evaluation of the effect of ICESat-2 vegetation canopy height and surface elevation data products for forest height extraction. Journal of Remote Sensing, 25(6): 1294-1307.

董佳臣, 倪文俭, 张志玉, 孙国清, 2021. ICESat-2植被冠层高度和地表高程数据产品用于森林高度提取的效果评价. 遥感学报, 25(6): 1294-1307.

Fatoyinbo T, Armston J, Simard M, Saatchi S, Denbina M, Lavalle M, Hofton M, Tang H, Marselis S, Pinto N, Hancock S, Hawkins B, Duncanson L, Blair B, Hansen C, Lou Y, Dubayah R, Hensley S, Silva C, Poulsen J R, Labriere N, Barbier N, Jeffery K, Kenfack D, Herve M, Bissiengou P, Alonso A, Moussavou G, White L T J, Lewis S, Hibbard K, 2021. The NASA AfriSAR campaign: Airborne SAR and lidar measurements of tropical forest structure and biomass in support of current and future space missions. Remote Sensing of Environment, 264: 112533. [DOI:10.1016/j.rse.2021.112533http://dx.doi.org/10.1016/j.rse.2021.112533]

Fu H, Wang C, Zhu J, Xie Q, Zhang B, 2016. Estimation of Pine Forest Height and Underlying DEM Using Multi-Baseline P-Band PolInSAR Data. Remote Sensing, 8(10): 820. [DOI:10.3390/rs8100820http://dx.doi.org/10.3390/rs8100820]

Fu H, Zhu J, Wang C, Wang H, Zhao R, 2017. Underlying Topography Estimation over Forest Areas Using High-Resolution P-Band Single-Baseline PolInSAR Data. Remote Sensing, 9(4): 363. [DOI:10.3390/rs9040363http://dx.doi.org/10.3390/rs9040363]

Garestier F, Dubois-Fernandez P C, Champion I, 2008. Forest Height Inversion Using High-Resolution P-Band Pol-InSAR Data[J/OL]. Ieee Transactions on Geoscience and Remote Sensing, 46(11): 3544-3559. [DOI:10.1109/TGRS.2008.922032http://dx.doi.org/10.1109/TGRS.2008.922032]

Gruber A, Wessel B, Huber M, Roth A, 2012. Operational TanDEM-X DEM calibration and first validation results. Isprs Journal of Photogrammetry and Remote Sensing, 73: 39-49. [DOI:10.1016/j.isprsjprs.2012.06.002http://dx.doi.org/10.1016/j.isprsjprs.2012.06.002]

Hansen M C, Roy D P, Lindquist E, Adusei B, Justice C O, Altstatt A, 2008. A method for integrating MODIS and Landsat data for systematic monitoring of forest cover and change in the Congo Basin. Remote Sensing of Environment, 112(5): 2495-2513. [DOI:10.1016/j.rse.2007.11.012http://dx.doi.org/10.1016/j.rse.2007.11.012]

Hawker L, Uhe P, Paulo L, Sosa J, Savage J, Sampson C, Neal J, 2022. A 30 m global map of elevation with forests and buildings removed. Environmental Research Letters, 17(2): 024016. [DOI:10.1088/1748-9326/ac4d4fhttp://dx.doi.org/10.1088/1748-9326/ac4d4f]

Kulp S A, Strauss B H, 2018. CoastalDEM: A global coastal digital elevation model improved from SRTM using a neural network. Remote Sensing of Environment, 206: 231-239. [DOI:10.1016/j.rse.2017.12.026http://dx.doi.org/10.1016/j.rse.2017.12.026]

Lei Y, Treuhaft R, Goncalves F, 2021. Automated estimation of forest height and underlying topography over a Brazilian tropical forest with single-baseline single-polarization TanDEM-X SAR interferometry. Remote Sensing of Environment, 252: 112132. [DOI:10.1016/j.rse.2020.112132http://dx.doi.org/10.1016/j.rse.2020.112132]

Lopez-Sanchez J M, Vicente-Guijalba F, Erten E, Campos-Taberner M, Javier Garcia-Haro F, 2017. Retrieval of vegetation height in rice fields using polarimetric SAR interferometry with TanDEM-X data. Remote Sensing of Environment, 192: 30-44. [DOI:10.1016/j.rse.2017.02.004http://dx.doi.org/10.1016/j.rse.2017.02.004]

Magruder L, Neuenschwander A, Klotz B, 2021. Digital terrain model elevation corrections using space-based imagery and ICESat-2 laser altimetry. Remote Sensing of Environment, 264: 112621. [DOI:10.1016/j.rse.2021.112621http://dx.doi.org/10.1016/j.rse.2021.112621]

Martone M, Brautigam B, Krieger G, 2015. Quantization Effects in TanDEM-X Data. IEEE Transactions on Geoscience and Remote Sensing, 53(2): 583-597. [DOI:10.1109/TGRS.2014.2325976http://dx.doi.org/10.1109/TGRS.2014.2325976]

Neuenschwander A L, Magruder L A, 2019. Canopy and Terrain Height Retrievals with ICESat-2: A First Look. Remote Sensing, 11(14): 1721. [DOI:10.3390/rs11141721http://dx.doi.org/10.3390/rs11141721]

Neuenschwander A, Guenther E, White J C, Duncanson L, Montesano P, 2020. Validation of ICESat-2 terrain and canopy heights in boreal forests. Remote Sensing of Environment, 251: 112110. [DOI:10.1016/j.rse.2020.112110http://dx.doi.org/10.1016/j.rse.2020.112110]

O’Loughlin F E, Paiva R C D, Durand M, Alsdorf D E, Bates P D, 2016. A multi-sensor approach towards a global vegetation corrected SRTM DEM product. Remote Sensing of Environment, 182: 49-59. [DOI:10.1016/j.rse.2016.04.018http://dx.doi.org/10.1016/j.rse.2016.04.018]

Papathanassiou K P, Cloude S R, 2001. Single-baseline polarimetric SAR interferometry. Ieee Transactions on Geoscience and Remote Sensing, 39(11): 2352-2363. [DOI:10.1109/36.964971http://dx.doi.org/10.1109/36.964971]

Prăvălie R, Sîrodoev I, Nita I A, Patriche C, Dumitraşcu M, Roşca B, Tişcovschi A, Bandoc G, Săvulescu I, Mănoiu V, Birsan M V, 2022. NDVI-based ecological dynamics of forest vegetation and its relationship to climate change in Romania during 1987–2018. Ecological Indicators, 136: 108629. [DOI:10.1016/j.ecolind.2022.108629http://dx.doi.org/10.1016/j.ecolind.2022.108629]

Rahman M M, Csaplovics E, Koch B, 2005. An efficient regression strategy for extracting forest biomass information from satellite sensor data. International Journal of Remote Sensing, 26(7): 1511-1519. [DOI:10.1080/01431160500044705http://dx.doi.org/10.1080/01431160500044705]

Rizzoli P, Martone M, Gonzalez C, Wecklich C, Tridon D B, Braeutigam B, Bachmann M, Schulze D, Fritz T, Huber M, Wessel B, Krieger G, Zink M, Moreira A, 2017. Generation and performance assessment of the global TanDEM-X digital elevation model. Isprs Journal of Photogrammetry and Remote Sensing, 132: 119-139. [DOI:10.1016/j.isprsjprs.2017.08.008http://dx.doi.org/10.1016/j.isprsjprs.2017.08.008]

Son N T, Chen C F, Chen C R, Minh V Q, Trung N H, 2014. A comparative analysis of multitemporal MODIS EVI and NDVI data for large-scale rice yield estimation. Agricultural and Forest Meteorology, 197: 52-64. [DOI:10.1016/j.agrformet.2014.06.007http://dx.doi.org/10.1016/j.agrformet.2014.06.007]

Su Y, Guo Q, Ma Q, Li W, 2015. SRTM DEM Correction in Vegetated Mountain Areas through the Integration of Spaceborne LiDAR, Airborne LiDAR, and Optical Imagery. Remote Sensing, 7(9): 11202-11225. [DOI:10.3390/rs70911202http://dx.doi.org/10.3390/rs70911202]

Treuhaft R N, Madsen S N, Moghaddam M, Zyl J J Van, 1996. Vegetation characteristics and underlying topography from interferometric radar. Radio Science, 31(6): 1449-1485. [DOI:10.1029/96RS01763http://dx.doi.org/10.1029/96RS01763]

Wang H, Fu H, Zhu J, Liu Z, Zhang B, Wang C, Li Z, Hu J, Yu Y, 2021. Estimation of subcanopy topography based on single-baseline TanDEM-X InSAR data. Journal of Geodesy, 95(7): 84. [DOI:10.1007/s00190-021-01519-3http://dx.doi.org/10.1007/s00190-021-01519-3]

Xu Jialu, 2022. Discussion on key technologies for obtaining high-precision DEM based on airborne LiDAR data. Geospatial Information, 20(11): 5-8.

许家录, 2022. 基于机载LiDAR数据获取高精度DEM的关键技术探讨. 地理空间信息, 20(11): 5-8.

Zhang Tao, Zhu Jianjun, Fu Haiqiang, Wang Changcheng, 2022. Single baseline TanDEM-X InSAR coherence inversion of forest height. Journal of Surveying and Mapping, 51(09): 1931-1941.

张涛, 朱建军, 付海强, 汪长城, 2022. 单基线TanDEM-X InSAR相干性反演森林高度. 测绘学报, 51(09): 1931-1941.

Zhu Jianjun, Fu Haiqiang, Wang Changcheng, 2018. InSAR understory topographic surveying and mapping methods and research progress. Journal of Wuhan University (Information Science), 43(12): 2030-2038. [DOI:10.13203/j.whugis20180266http://dx.doi.org/10.13203/j.whugis20180266]

朱建军, 付海强, 汪长城, 2018. InSAR林下地形测绘方法与研究进展. 武汉大学学报(信息科学版), 43(12): 2030-2038. [DOI:10.13203/j.whugis20180266http://dx.doi.org/10.13203/j.whugis20180266]

Alert me when the article has been cited

提交

Sub-canopy topography extraction via TanDEM-X DEM combined Sentinel-2 multispectral data

Glacier mass balance changes in Malan Mountain based on InSAR and LiDAR altimetry

Improving the quality of remotely sensed precipitation product from GPM satellites by using a spatial random forest

Development of deep learning-based hyperspectral remote sensing image unmixing