The Dendrolimus houi, a phytophagous pest, displays a broad range of adaptations and often inflicts localized damage to its hosts. Cupressus funebris, an indigenous timber species in China, is significantly impacted by D. houi. Investigating the suitable habitat distribution and changes in D. houi and its host plant, C. funebris, within the context of climate warming, is essential for understanding D. houi’s development and providing novel insights for managing D. houi and conserving C. funebris resources. In this study, MaxEnt was employed to simulate the distribution of D. houi and its host plant, C. funebris, in their suitable habitats, evaluating the influence of environmental factors on their distribution and determining changes under a warming scenario. MaxEnt model parameters were adjusted using the Kuenm data package based on available distribution and climatic data. The minimum temperature of the coldest month emerged as the primary environmental factor influencing the distribution of a suitable habitat for D. houi and C. funebris, with a percentage contribution of environmental factors over 60%. There was a substantial similarity in the suitable habitat distributions of D. houi and C. funebris, with varying degrees of expansion in the total habitat area under different temporal and climatic scenarios. Intersection analysis results indicated that the 2041–2060 period, especially under low (SSP1-2.6) and high (SSP5-8.5) emission scenarios, is a critical phase for D. houi control. The habitat expansion of D. houi and C. funebris due to climate change was observed, with the distribution center of D. houi shifting northeast and that of C. funebris shifting northwest.

Wood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in determining the long and short diameters of the wood, and are difficult to achieve fast measurements in complex wood stacking environments. We use a Mask R-CNN instance segmentation model to detect the contour of the wood log and employ a binocular stereo camera to measure the log diameter. A rotation search algorithm centered on the wood contour is proposed to find long and short diameters and to optimal log size according to the Chinese standard. The experiments show that the Mask R-CNN we trained obtains 0.796 average precision and 0.943 $IO{U}_{mask}$, and the recognition rate of wood log ends reaches 98.2%. The average error of the short diameter of the measurement results is 5.7 mm, the average error of the long diameter is 7.19 mm, and the average error of the diameter of the wood is 5.3 mm.

Wood recognition is necessary for work in the wood trade activities. The advantage of the one-class wood classification method is more generalization, and it only needs positive samples and does not need negative samples in the training phase, so it is suitable for rare wood species inspection. This paper proposed an improved method based on the one-class support vector machine (OCSVM) for wood species recognition. It uses cross-section images acquired with a magnifying glass, which uses a pre-trained VGG16 model for feature extraction, a normal distribution test for key features filtering, and OCSVM to determine the wood species. The results showed that the approach achieved a mean recall of 0.842 for both positive and negative samples, which indicates this method has good performance for wood recognition. In a negative public dataset, the negative recall reached as high as 0.989, which showed that this method has good generalization.

Logs require multiple verifications to ensure accurate volume and quantity measurements. Log end detection is a crucial step in measuring log volume and counting logs. Currently, this task primarily relies on the Mask R-CNN instance segmentation model. However, the Feature Pyramid Network (FPN) in Mask R-CNN may compromise accuracy due to feature redundancy during multi-scale fusion, particularly with small objects. Moreover, counting logs in a single image is challenging due to their large size and stacking. To address the above issues, we propose an improved log segmentation model based on Cascade Mask R-CNN. This method uses ResNet for multi-scale feature extraction and integrates a hierarchical Convolutional Block Attention Module (CBAM) to refine feature weights and enhance object emphasis. Then, a Region Proposal Network (RPN) is employed to generate log segmentation proposals. Finally, combined with Deep SORT, the model tracks log ends in video streams and counts the number of logs in the stack. Experiments demonstrate the effectiveness of our method, achieving an average precision ($AP$) of 82.3, $A{P}_s$ of 75.3 for small, $A{P}_m$ of 70.9 for medium, and $A{P}_l$ of 86.2 for large objects. These results represent improvements of 1.8%, 3.7%, 2.6%, and 1.4% over Mask R-CNN, respectively. The detection rate reached 98.6%, with a counting accuracy of 95%. Compared to manually measured volumes, our method shows a low error rate of 4.07%.

As part of the ecosystem, the western black-crested gibbon (Nomascus concolor) is important for ecological sustainability. Calls are an important means of communication for gibbons, so accurately recognizing and categorizing gibbon calls is important for their population monitoring and conservation. Since a large amount of sound data will be generated in the process of acoustic monitoring, it will take a lot of time to recognize the gibbon calls manually, so this paper proposes a western black-crested gibbon call recognition network based on SA_DenseNet-LSTM-Attention. First, to address the lack of datasets, this paper explores 10 different data extension methods to process all the datasets, and then converts all the sound data into Mel spectrograms for model input. After the test, it is concluded that WaveGAN audio data augmentation method obtains the highest accuracy in improving the classification accuracy of all models in the paper. Then, the method of fusion of DenseNet-extracted features and LSTM-extracted temporal features using PCA principal component analysis is proposed to address the problem of the low accuracy of call recognition, and finally, the SA_DenseNet-LSTM-Attention western black-crested gibbon call recognition network proposed in this paper is used for recognition training. In order to verify the effectiveness of the feature fusion method proposed in this paper, we classified 13 different types of sounds and compared several different networks, and finally, the accuracy of the VGG16 model improved by 2.0%, the accuracy of the Xception model improved by 1.8%, the accuracy of the MobileNet model improved by 2.5%, and the accuracy of the DenseNet network model improved by 2.3%. Compared to other classical chirp recognition networks, our proposed network obtained the highest accuracy of 98.2%, and the convergence of our model is better than all the compared models. Our experiments have demonstrated that the deep learning-based call recognition method can provide better technical support for monitoring western black-crested gibbon populations.