Xian-Ge Hu

Betula luminifera, an indigenous hardwood tree in South China, possesses significant economic and ecological value. In view of the current severe drought situation, it is urgent to enhance this tree’s drought tolerance. However, traditional artificial methods fall short of meeting the demands of breeding efforts due to their inefficiency. To monitor drought situations in a high-throughput and automatic approach, a deep learning model based on phenotype characteristics was proposed to identify and classify drought stress in B. luminifera seedlings. Firstly, visible-light images were obtained from a drought stress experiment conducted on B. luminifera shoots. Considering the images’ characteristics, we proposed an SAM-CNN architecture by incorporating spatial attention modules into classical CNN models. Among the four classical CNNs compared, ResNet50 exhibited superior performance and was, thus, selected for the construction of the SAM-CNN. Subsequently, we analyzed the classification performance of the SAM-ResNet50 model in terms of transfer learning, training from scratch, model robustness, and visualization. The results revealed that SAM-ResNet50 achieved an accuracy of 1.48% higher than that of ResNet50, at 99.6%. Furthermore, there was a remarkable improvement of 18.98% in accuracy, reaching 82.31% for the spatial transform images generated from the test set images by applying movement and rotation for robustness testing. In conclusion, the SAM-ResNet50 model achieved outstanding performance, with 99.6% accuracy and realized high-throughput automatic monitoring based on phenotype, providing a new perspective for drought stress classification and technical support for B. luminifera-related breeding work.

The spatial shifts and vulnerability assessments of ecological niches for trees will offer fresh perspectives for sustainable development and preservation of forests, particularly within the framework of rapid climate change. Betula luminifera is a fast-growing native timber plantation species in China, but the natural resources have been severely damaged. Here, a comprehensive habitat suitability model (including ten niche-based GIS modeling algorithms) was developed that integrates three types of environmental factors, namely, climatic, soil, and ultraviolet variables, to assess the species contemporary and future distribution of suitable habitats across China. Our results suggest that the habitats of B. luminifera generally occur in subtropical areas (about 1.52 × 10⁶ km²). However, the growth of B. luminifera is profoundly shaped by the nuances of its local environment, the most reasonable niche spaces are only 1.15 × 10⁶ km² when limiting ecological factors (soil and ultraviolet) are considered, generally considered as the core production region. Furthermore, it is anticipated that species-suitable habitats will decrease by 10 and 8% with climate change in the 2050s and 2070s, respectively. Our study provided a clear understanding of species-suitable habitat distribution and identified the reasons why other niche spaces are unsuitable in the future, which can warn against artificial cultivation and conservation planning.