In order to explore the advantages and complementarity of optical data and synthetic aperture radar (SAR) data in forest type classification, this study focused on the overlapping area of Landsat8 data and ALOS2 data from one scene SAR image in Simao District, Puer City, Yunnan Province, China, and used hierarchical classification technology for forest type classification research. Three feature sets were constructed: optical feature set (spectral + vegetation + texture + terrain features), SAR feature set (backscattering + polarization decomposition features), and optical-SAR fusion feature set (spectral + vegetation + texture + terrain + backscattering + polarization decomposition features). Recursive Feature Elimination (RFE) was employed to perform stratified feature selection on the three feature sets, and random forest (RF) and support vector machine (SVM) were used for forest type classification. The SVM classification with the fusion of optical images and SAR data achieved the best results. The results showed, 1) In the first layer (vegetation/non-vegetation) classification, the overall accuracy was 98.57%, the Kappa coefficient was 0.971. 2) In the second layer (forest/non-forest) classification, the overall accuracy was 92.14%, the Kappa coefficient was 0.826. 3) In the third layer (coniferous/broad-leaved/mixed forest) classification, the overall accuracy was 83.47%, and the Kappa coefficient was 0.743. The fusion data showed an improvement of 6.74% in accuracy compared to optical data feature set classification and 29.24% compared to SAR classification. 4) In the classification of the third layer using fusion data, the influence of different window sizes (3×3, 5×5, 7×7, 9×9) of texture features in optical images was compared, and the highest accuracy was achieved with a 7×7 texture window. Results shows that, the accuracy of forest type classification using multi-source data is higher than that using a single data source.
TIANJ, XINGY Q, YAOS T,et al.Comparison of Landsat-TM image forest type classification based on cellular automata and BP neural network algorithm[J].Scientia Silvae Sinicae,2017,53(2):26-34.
WUZ S, LINH, SUNH,et al.Classification of forest types by tree decision based on MODIS images[J].Journal of Central South University of Forestry & Technology,2017,37(9):80-85.
DONGL B, LIANGK F, ZHANGY F,et al.Classification of forest types in Cuigang forest farm based on time series data of Landsat 8[J].Chinese Journal of Applied Ecology,2022,33(9):2339-2346.
[12]
LEHMANNA E, CACCETTAP, ZHOUZ,et al.Joint processing of Landsat and ALOS-PALSAR data for forest mapping and monitoring[J].IEEE Transactions on Geoscience and Remote Sensing,2011,50(1):55-67.
[13]
WANGJ Z, QUJ J, ZHANGW M,et al.Classification of full polarization ALOS-PALSAR imagery using SVM in arid area of Dunhuang[J].Sciences in Cold and Arid Regions,2016,8(3):263-267.
JIAS C, XUED J, LIC R.Application of polarization characteristic combination in ALOS PALSAR data classification[J].Bulletin of Surveying and Mapping,2018(7):29-33,47.
[16]
ERINJERYJ J, SINGHM, KENTR.Mapping and assessment of vegetation types in the tropical rainforests of the Western Ghats using multispectral Sentinel-2 and SAR Sentinel-1 satellite imagery[J].Remote Sensing of Environment,2018,216:345-354.
MAOX G, ZHUL, LIUY T,et al.Object-oriented classification for tree species based on high spatial resolution images and spaceborne polarimetric SAR cooperation with feature[J].Scientia Silvae Sinicae,2019,55(9):92-102.
LIANGX W, ZHAOY H, ZHENZ,et al.Forest vegetation classification of Landsat-8 based on rotation forest[J].Journal of Northeast Forestry University,2017,45(8):39-48.
JIAM M, RENC Y, LIUD W,et al.Object-oriented forest classification based on combination of HJ-1 CCD and MODIS-NDVI data[J].Acta Ecologica Sinica,2014,34(24):7167-7174.
ZHOUX C, ZHENGL, HUANGH Y.Classification of forest stand based on multi-feature optimization of UAV visible light remote sensing[J].Scientia Silvae Sinicae,2021,57(6):24-36.
WUY S, ZHANGX L.Object-oriented tree species classification with multi-scale texture features based on airborne hyperspectral images[J].Journal of Beijing Forestry University,2020,42(6):91-101.
JIAK, LIUY Y, FANW Y.Constructing a multivariate estimation forest above-ground biomass model using full-polarization SAR data[J].Journal of Northeast Forestry University,2024,52(1):61-66,102.
LIN C, HUC B, WANGW,et al.Polarimetric SAR target decomposition method based on independent polarization orientation angle integration[J].Acta Geodaetica et Cartographica Sinica,2023,52(12):2141-2153.
WANGX S, CHENGS W.Polarimetric synthetic aperture radar interpretation and recognition:advances and perspectives[J].Journal of Radars,2020,9(2):259-276.
ZHANGB H, ZHANGY L, GUC J,et al.Land cover classification based on random forest and feature optimism in the southeast Qinghai-Tibet Plateau[J].Scientia Geographica Sinica,2023,43(3):388-397.
JIAX F, ZHUH C, LINGF,et al.Study on forest cover change in Han River Basin based on Landsat multispectral and PALSAR/PALSAR-2 data[J].Resources and Environment in the Yangtze Basin,2021,30(2):321-329.
ZHANGC F, RENG B, WUP Q,et al.Mangrove species classification in the Hainan Bamen Bay based on GF optics and fully polarimetric SAR[J].Journal of Tropical Oceanography,2023,42(2):153-168.
WANGY H, FANW Y, LIUC Y.An object-based fusion of Quickbird data and RADARSAT SAR data for classification analysis[J].Journal of Northeast Forestry University,2016,44(9):44-49.
ZHANGL M, DUANB L, ZOUB.Research development on target decomposition method of polarimetric SAR image[J].Journal of Electronics & Information Technology,2016,38(12):3289-3297.
HOUJ Y, ZHANGY C, CHENGW Y.Supervised classification of polarimetric SAR images with interference features-stand type identification of Jiangle forest farm[J].Journal of Northeast Forestry University,2020,48(11):33-38.
LIA Q, YANGL, CAIY Y,et al.Digital mapping of soil fertility attributes in croplands in Jiangsu,Zhejiang and Shanghai based on recursive feature elimination-random forest model[J].Scientia Geographica Sinica,2024,44(1):168-178.
XIEY, WANGJ N, LIUY.Research on winter wheat planting area identification method based on sentinel-1/2 data feature optimization[J].Transactions of the Chinese Society for Agricultural Machinery,2024,55(2):231-241.
WANGJ, LIH K, LONGB P,et al.Tree species identification in southern hilly areas using Sentinel series images with multi-temporal features[J].Journal of Northeast Forestry University,2024,52(3):60-68.
NINGL L, ZHANGX L.A Preliminary study on vegetation classification based on texture information of Landsat-8 images[J].Journal of Central South University of Forestry & Technology,2014,34(9):60-64.
XUH, PANP, YANGW,et al.Classification and accuracy evaluation of forest resources based on multi-source remote sensing images[J].Acta Agriculturae Universitatis Jiangxiensis,2019,41(4):751-760.
[59]
KASAPOGLUN G, ANFINSENS N, ELTOFTT.Fusion of optical and multifrequency polsar data for forest classification[C].2012 IEEE International Geoscience and Remote Sensing Symposium,Munich,Germany,2012,3355-3358.
[60]
SANOE E, FERREIRAL G, HUETEA R.Synthetic aperture radar(L band) and optical vegetation indices for discriminating the Brazilian savanna physiognomies:A comparative analysis[J].Earth Interactions,2005,9(15):1-15.
[61]
YUY, LIM, FUY.Forest type identification by random forest classification combined with SPOT and multitemporal SAR data[J].Journal of Forestry Research,2018,29(5):1407-1414.
[62]
KURVONENL, HALLIKAINENM T.Textural information of multitemporal ERS-1 and JERS-1 SAR images with applications to land and forest type classification in Boreal zone[C].IEEE Transactions on Geoscience and Remote Sensing,1999,37:680–689.
[63]
LEEJ S, GRUNESM R, AINSWORTHT,et al.Forest classification based on L-band polarimetric and inteferometric SAR data[C].In POLINSAR 2005(ESA SP-586),January 17-21,Frascati,Italy.
[64]
TOUZIR, LANDRYR, CHARBONNEAUF J.Forest type discrimination using calibrated C-band polarimetric SAR data[J].Canadian Journal of Remote Sensing,2004,30(3):543–551.
[65]
YATABES M, LECKIED C.Clearcut and forest-type discrimination in satellite SAR imagery[J].Canadian Journal of Remote Sensing,1996,21(4):455–467.
[66]
BAIY, SUNG, LIY,et al.Comprehensively analyzing optical and polarimetric SAR features for land-use/land-cover classification and urban vegetation extraction in highly-dense urban area[J].International Journal of Applied Earth Observation and Geoinformation,2021,103:102496.