Forest Type Classification Based On Multi-temporal SAR And SPOT Remote Sensing Data In Pangu Forest Farm

Forests are major natural resources in the ecosystem and play an important role in global carbon and hydrological cycle. With increasing demand for forest resources forest type information extraction is of great significance. With the development of remote sensing to monitor the forest has become the inevitable trend of development. In recent years, remote sensing has become multi-source information. Compared with the single remote sensing information source, different remote sensing fusion can obtain more accurate number generator of stand type recognition results.Information extraction of forest type is difficult in remote sensing image classification. Daxing’an Mountains is an important forestry area in China mainly distributed by natural forests, rich with a wide range of plants resources which makes it difficult to accurately identify the forest types in this region. In order to compare and improve the accuracy of classification result, combining with the main and passive remote sensing and using the spectrum and polarization characteristics and multi-temporal in different forest type classification in high accuracy.In this study taking Pangu Forest Farm in Daxing’an Mountains as the study area, we proposed three methods to classify forest types by using the maximum likelihood and support vector machine (SVM) method combining with SPOT-5 and two different temporal RADARSAT-2 fully polarimetric SAR remote sensing data. Three schemes were designed to classify the forest types and the accuracy was compared. In the three schemes (1) SPOT image was only used to distinguish forest types. (2)Some descriptive parameters extracted from SAR polarimetry (POLSAR) images and the SPOT data were used for classification. (3)The integration of parameters extracted from multi-temporal of full polarimetric SAR (PolSAR) images with SPOT data was used for classification. The results indicated that the most effective method to identify white birches, larch, Pinus sylvestris and spruce among the three proposed schemes was the third using multi-temporal SAR and SPOT remote sensing image. The classification accuracy and the Kappa coefficient is 84.64% and 0.79. However, the accuracy of forest type classification by using only SPOT data is the lowest of 76.66%, and the Kappa coefficient is 0.70.The third scheme by using support vector machine has the higher accuracy is 85.89%, and the Kappa coefficient is 0.79.