Construction of crown profile prediction model of Pinus yunnanensis based on CNN-LSTM-Attention method

Longfeng Deng¹Jianming Wang^1*Jiting Yin²Yuling Chen³Baoguo Wu⁴

• ¹Dali University, Dali, China
• ²Dali Forestry and Grassland Science Research Institute, Dali, China
• ³Peking University, Beijing, Beijing Municipality, China
• ⁴Beijing Forestry University, Beijing, Beijing, China

Pinus yunnanensis is a significant tree species in southwest China, crucial for the ecological environment and forest resources. Accurate modeling of its crown profile is essential for forest management and ecological analysis. However, existing modeling approaches face limitations in capturing the crown's spatial heterogeneity and vertical structure. This study developed CNN-LSTM-Attention models to predict both non-directional and directional (East, South, West, North) crown profiles of Pinus yunnanensis, based on data from 629 trees across five age-differentiated temporary plots on Cangshan Mountain, Dali, Yunnan Province. To better represent inter-tree competition across vertical layers and enhance model accuracy, a Crown Profile Competition Index (CPCI) was proposed, incorporating vertical structure and directional differences through a specialized allocation formula. Experimental results showed that the hybrid CNN-LSTM and CNN-LSTM-Attention models significantly outperformed the Vanilla LSTM model. In particular, the CNN-LSTM-Attention model achieved the best performance (MSE=0.00755 m 2 , RMSE=0.08691 m, MAE=0.05198 m, R² =0.98161), with absolute R² improvements of 0.16 and 0.17 over the Vanilla LSTM model by the CNN-LSTM and CNN-LSTM-Attention models, respectively. Additionally, the CNN-LSTM-Attention model demonstrated superior stability and performance in handling directional crown profile datasets. Incorporating CPCI improved prediction accuracy across all models, especially benefiting the Vanilla LSTM model. In conclusion, the proposed hybrid deep learning framework significantly enhances crown profile prediction for Pinus yunnanensis, and the introduction of CPCI provides a more precise representation of vertical and directional crown competition.