3D-M2C-ResNet: A Multi-Scale feature enhancement and fusion model for Fine-Scale tree species classification in urban forests

• We develop a novel 3D-M²C-ResNet model for fine tree species classification, achieving 98.08% accuracy. • Expanding the model’s receptive field reduces salt-and-pepper noise. • Making full use of shallow features can improve the accuracy of forest margin classification. • Phenological parameters improve classification of spectrally similar species. Forests play a crucial role in global carbon sequestration, and the varying carbon storage capacities of tree species underscore the need for accurate vegetation classification. This study introduces 3D-M 2 C-ResNet, a deep learning model for high-resolution, fine-scale tree species classification. The model leverages fused remote sensing inputs, combining Zhuhai-1 hyperspectral imagery with phenological parameters derived from Sentinel-2 time-series data. A Multi-Scale Cascaded Dilated Convolution (MCDC) module was developed to expand the receptive field through a three-branch architecture, enabling comprehensive spectral–spatial feature extraction. Additionally, a Multi-level Feature Enhancement Strategy (MFES) adaptively refines shallow and deep features, enhancing semantic–spatial integration across layers. The model was evaluated against support vector machine (SVM), VGG16, and ResNet50 on a test set of 22,380 pixels. 3D-M 2 C-ResNet achieved an overall accuracy of 98.08% and a Kappa coefficient of 97.88%, outperforming baseline methods. Ablation experiments confirmed the effectiveness of the MCDC and MFES modules. Notably, incorporating phenological information substantially improved classification performance, particularly for spectrally similar tree species. This approach provides a robust and scalable solution for detailed urban forest mapping, supporting ecological monitoring, carbon accounting, and sustainable forest management. Data and code are publicly available at: https://github.com/qinjs123/3D-M2C-ResNet .