Tree species classification is important for the management and sustainable development of forest resources. Traditional object-oriented tree species classification methods, such as support vector machines, require manual feature selection and generally low accuracy, whereas deep learning technology can automatically extract image features to achieve end-to-end classification. Therefore, a tree classification method based on deep learning is proposed in this study. This method combines the semantic segmentation network U-Net and the feature extraction network ResNet into an improved Res-UNet network, where the convolutional layer of the U-Net network is represented by the residual unit of ResNet, and linear interpolation is used instead of deconvolution in each upsampling layer. At the output of the network, conditional random fields are used for post-processing. This network model is used to perform classification experiments on airborne orthophotos of Nanning Gaofeng Forest Farm in Guangxi, China. The results are then compared with those of U-Net and ResNet networks. The proposed method exhibits higher classification accuracy with an overall classification accuracy of 87%. Thus, the proposed model can effectively implement forest tree species classification and provide new opportunities for tree species classification in southern China.

No abstract

No abstract

No abstract

Controllable regulation of stem cell differentiation is a critical concern in stem cell-based regenerative medicine. In particular, there are still great challenges in controlling the directional differentiation of neural stem cells (NSCs) into neurons. Herein, we developed a novel linear-branched poly(β-amino esters) (S4-TMPTA-BDA-DT, STBD) through a two-step reaction. The synthesized STBD linear branched polymers possess multiple positively charged amine terminus and degradable intermolecular ester bonds, thus endowing them with excellent properties such as high gene load, efficient gene delivery, and effective gene release and transcription in cells. In the mCherry transfection test, a high transfection efficiency of approximately 70% was achieved in primary NSCs after a single transfection. Moreover, STBD also showed high biocompatibility to NSCs without disturbing their viability and neural differentiation. With the high gene delivery property, STBD is capable of delivering siRNA (shSOX9) expression plasmid into NSCs to significantly interfere with the expression of SOX9, thus enhancing the neuronal differentiation and maturation of NSCs. The STBD/DNA nano-polyplex represents a powerful non-viral approach of gene delivery for manipulating the differentiation of stem cells, showing broad application prospects in NSC-based regenerative therapy for treating neurodegenerative diseases.