In order to explore the potential of L-band full-polarization SAR data to estimate forest aboveground biomass (AGB), five polarimetric scattering ratio parameters (R1, R2, R3, R4, R5) were constructed based on the canopy-ground scattering component of Unmmaned Aero Vehicle Synthetic Aperture Radar (UAVSAR) data of the AfricaSAR project. Calculating the Radar Vegetation Index (RVI), and 21 polarimetric decomposition parameters were extracted by four model-based decompositions, including six-component and seven-component decomposition. Finally, all features were merged and the random forest feature importance was used to screen out the optimal feature combination, and random forest (RF), support vector machine regression (SVR), K-nearest neighbor regression (KNN) were used to estimate forest AGB of Lope, The Gaboneses Repbulic, Africa, with different feature combinations. The results showed that the polarimetric scattering ratio parameters, bulk scattering (Vol) and RVI had high sensitivity to forest AGB, and the correlation between R2 and AGB was 0.823, and the optimal feature combination was Vol, polarimetric scattering ratio parameters and RVI. Machine learning models with different feature combinations had shown good performance, the coefficient of determination (R2) of the machine learning model based on the polarimetric decomposition parameters was bigger than 0.800, and the root mean square error (RMSE) was less than 88.000 Mg/hm2, and the best effect was the RF model based on the optimal feature combination, which increased R2 by 0.144 and decreased RMSE by 30.327 Mg/hm2 compared with the polarimetric decomposition parameters alone. The polarimetric scattering ratio parameter had certain potential in the estimation of forest AGB, the introduction of RVI improved the accuracy of the model, the model-based decomposition was suitable for forest AGB estimation, and the machine learning model based on feature screening can better invert forest AGB, and there was no obvious saturation point when the AGB reached 400 Mg/hm2.
本研究获取试验区机载L波段全极化UAVSAR影像和LiDAR网格化AGB数据来估测Lope森林AGB。数据源自美国国家航空航天局(National Aeronautics and Space Administration,NASA)、欧洲航天局(European Space Agency,ESA)和加蓬航天局合作开展的非洲合成孔径雷达(Afri-SAR)项目中的机载合成孔径雷达(UAVSAR)、陆地植被和冰(Land Vegetation and Ice Sensor,LVIS)激光雷达传感器[28]。
GILLT, JOHANSENK, PHINNS,et al.A method for mapping Australian woody vegetation cover by linking continental-scale field data and long-term Landsat time series[J].International Journal of Remote Sensing,2017,38(3/4):679-705.
[2]
WATSONR T, ZINYOWERAM C, MOSSR H.The regional impacts of climate change:an assessment of vulnerability[M].Cambridge,UK:Cambridge University Press,1998.
[3]
DAVIDR M, ROSSERN J, DONOGHUED N M.Remote sensing for monitoring tropical dryland forests: A review of current research,knowledge gaps and future directions for Southern Africa[J].Environmental Research Communications,2022,4(4):042001.
[4]
SANNIERC, MCROBERTSR E, FICHETL V,et al.Using the regression estimator with Landsat data to estimate proportion forest cover and net proportion deforestation in Gabon[J].Remote Sensing of Environment: An Interdisciplinary Journal,2014,151:138-148.
[5]
MEDJIBEV P, PUTZF E, ROMEROC.Certified and uncertified logging concessions compared in Gabon: changes in stand structure,tree species,and biomass[J].Environmental Management,2013,51(3):524-540.
[6]
NÆSSETE, MCROBERTSR E, PEKKARINENA,et al.Use of local and global maps of forest canopy height and aboveground biomass to enhance local estimates of biomass in miombo woodlands in Tanzania[J].International Journal of Applied Earth Observation and Geoinformation,2020,89:102109.
XUZ Y, LIY C, LIM Y,et al.Forest biomass retrieval based on Sentinel-1A and Landsat 8 image[J].Journal of Central South University of Forestry & Technology,2020,40(11):147-155.
[9]
陈尔学.合成孔径雷达森林生物量估测研究进展[J].世界林业研究,1999,12(6):18-23.
[10]
CHENE X.Development of forest biomass estimation using SAR data[J].World Forestry Research,1999,12(6):18-23.
[11]
HOUGHTONR A, HALLF, GOETZS J.Importance of biomass in the global carbon cycle[J].Journal of Geophysical Research Biogeosciences,2009,114(G2):G00E03.
[12]
YUEJ B, YANGG J, TIANQ J,et al.Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices[J].ISPRS Journal of Photogrammetry and Remote Sensing,2019,150:226-244.
[13]
HYDEP, DUBAYAHR, WALKERW,et al.Mapping forest structure for wildlife habitat analysis using multi-sensor (LiDAR,SAR/InSAR,ETM+,Quickbird) synergy[J].Remote Sensing of Environment,2006,102(1/2):63-73.
[14]
ZHAOP P, LUD S, WANGG X,et al.Examining spectral reflectance saturation in landsat imagery and corresponding solutions to improve forest aboveground biomass estimation[J].Remote Sensing,2016,8(6):469.
[15]
MCELHINNYC, GIBBONSP, BRACKC,et al.Forest and woodland stand structural complexity: Its definition and measurement[J].Forest Ecology and Management,2005,218(1/3):1-24.
[16]
BAGHDADIN, LE MAIREG, BAILLYJ S,et al.Evaluation of ALOS/PALSAR L-band data for the estimation of Eucalyptus plantations aboveground biomass in Brazil[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(8):3802-3811.
[17]
CLOUDES R, POTTIERE.A review of target decomposition theorems in radar polarimetry[J].IEEE Transactions on Geoscience and Remote Sensing,1996,34(2):498-518.
[18]
SANDBERGG, ULANDERL M H, FRANSSONJ E S,et al.L- and P-band backscatter intensity for biomass retrieval in hemiboreal forest[J].Remote Sensing of Environment,2011,115(11):2874-2886.
MAX X.Research on building extraction method based on PolSAR incoherent decomposition[D].Beijing:University of Chinese Academy of Sciences (Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences),2018.
[23]
CHOWDHURYT, THIELC, SCHMULLIUSC,et al.Polarimetric parameters for growing stock volume estimation using ALOS PALSAR L-band data over Siberian forests[J].Remote Sensing,2013,5(11):5725-5756.
[24]
SINGHG, MALIKR, MOHANTYS,et al.Seven-component scattering power decomposition of POLSAR coherency matrix[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(11):8371-8382.
[25]
LUOM, WANGY F, XIEY H,et al.Combination of feature selection and CatBoost for prediction: the first application to the estimation of aboveground biomass[J].Forests,2021,12(2):216.
[26]
LIB, XUX M, ZHANGL,et al.Above-ground biomass estimation and yield prediction in potato by using UAV-based RGB and hyperspectral imaging[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,162:161-172.
[27]
FATOYINBOT, ARMSTONJ, SIMARDM,et al.The NASA AfriSAR campaign: Airborne SAR and lidar measurements of tropical forest structure and biomass in support of current and future space missions[J].Remote Sensing of Environment,2021,264:112533.
[28]
FREEMANA.Fitting a two-component scattering model to polarimetric SAR data from forests[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(8):2583-2592.
[29]
FREEMANA, DURDENS L.Three-component scattering model to describe polarimetric SAR data[C]//SPIE Proceedings,Radar Polarimetry.San Diego,CA,USA.SPIE,1993:213-224.
[30]
YAMAGUCHIY, MORIYAMAT, ISHIDOM,et al.Four-component scattering model for polarimetric SAR image decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(8):1699-1706.
[31]
ANW T, XIEC H, YUANX Z,et al.Four-component decomposition of polarimetric SAR images with deorientation[J].IEEE Geoscience and Remote Sensing Letters,2011,8(6): 1090-1094.
[32]
YAMAGUCHIY, YAJIMAY, YAMADAH.A four-component decomposition of POLSAR images based on the coherency matrix[J].IEEE Geoscience and Remote Sensing Letters,2006,3(3):292-296
[33]
YAMAGUCHIY, SATOA, BOERNERW M,et al.Four-component scattering power decomposition with rotation of coherency matrix[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(6):2251-2258.
[34]
SINGHG, YAMAGUCHIY.Model-based six-component scattering matrix power decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(10):5687-5704.
[35]
MAY, ZHANGL J,IM J,et al.Novel features of canopy height distribution for aboveground biomass estimation using machine learning: a case study in natural secondary forests[J].Remote Sensing,2023,15(18):4364.
[36]
LIUZ H, MICHELO O, WUG M,et al.The potential of fully polarized ALOS-2 data for estimating forest above-ground biomass[J].Remote Sensing,2022,14(3):669.
[37]
ZENGP, ZHANGW F, LIY,et al.Forest total and component above-ground biomass (AGB) estimation through C- and L-band polarimetric SAR data[J].Forests,2022,13(3):442.