Temporal dynamics of genetic architecture governing leaf development in Populus

Leaf development is a multifaceted and dynamic process orchestrated by a myriad of genes to shape the proper size and morphology. The dynamic genetic network underlying leaf development remains largely unknown. Utilizing a synergistic genetic approach encompassing dynamic genome-wide association study (GWAS), time-ordered gene co-expression network (TO-GCN) analyses and gene manipulation, we explored the temporal genetic architecture and regulatory network governing leaf development in Populus. We identified 42 time-specific and 18 consecutive genes that displayed different patterns of expression at various time points. We then constructed eight TO-GCNs that covered the cell proliferation, transition, and cell expansion stages of leaf development. Integrating GWAS and TO-GCN, we postulated the functions of 27 causative genes for GWAS and identified PtoGRF9 as a key player in leaf development. Genetic manipulation via overexpression and suppression of PtoGRF9 revealed its primary influence on leaf development by modulating cell proliferation. Furthermore, we elucidated that PtoGRF9 governs leaf development by activating PtoHB21 during the cell proliferation stage and attenuating PtoLD during the transition stage. Our study provides insights into the dynamic genetic underpinnings of leaf development and understanding the regulatory mechanism of PtoGRF9 in this dynamic process.

ResNet incorporating the fusion data of RGB & hyperspectral images improves classification accuracy of vegetable soybean freshness

The freshness of vegetable soybean (VS) is an important indicator for quality evaluation. Currently, deep learning-based image recognition technology provides a fast, efficient, and low-cost method for analyzing the freshness of food. The RGB (red, green, and blue) image recognition technology is widely used in the study of food appearance evaluation. In addition, the hyperspectral image has outstanding performance in predicting the nutrient content of samples. However, there are few reports on the research of classification models based on the fusion data of these two sources of images. We collected RGB and hyperspectral images at four different storage times of VS. The ENVI software was adopted to extract the hyperspectral information, and the RGB images were reconstructed based on the downsampling technology. Then, the one-dimensional hyperspectral data was transformed into a two-dimensional space, which allows it to be overlaid and concatenated with the RGB image data in the channel direction, thereby generating fused data. Compared with four commonly used machine learning models, the deep learning model ResNet18 has higher classification accuracy and computational efficiency. Based on the above results, a novel classification model named ResNet-R &H, which is based on the residual networks (ResNet) structure and incorporates the fusion data of RGB and hyperspectral images, was proposed. The ResNet-R &H can achieve a testing accuracy of 97.6%, which demonstrates a significant enhancement of 4.0% and 7.2% compared to the distinct utilization of hyperspectral data and RGB data, respectively. Overall, this research is significant in providing a unique, efficient, and more accurate classification approach in evaluating the freshness of vegetable soybean. The method proposed in this study can provide a theoretical reference for classifying the freshness of fruits and vegetables to improve classification accuracy and reduce human error and variability.

Application of the Improved Rapidly Exploring Random Tree Algorithm to an Insect-like Mobile Robot in a Narrow Environment

When intelligent mobile robots perform global path planning in complex and narrow environments, several issues often arise, including low search efficiency, node redundancy, non-smooth paths, and high costs. This paper proposes an improved path planning algorithm based on the rapidly exploring random tree (RRT) approach. Firstly, the target bias sampling method is employed to screen and eliminate redundant sampling points. Secondly, the adaptive step size strategy is introduced to address the limitations of the traditional RRT algorithm. The mobile robot is then modeled and analyzed to ensure that the path adheres to angle and collision constraints during movement. Finally, the initial path is pruned, and the path is smoothed using a cubic B-spline curve, resulting in a smoother path with reduced costs. The evaluation metrics employed include search time, path length, and the number of sampling nodes. To evaluate the effectiveness of the proposed algorithm, simulations of the RRT algorithm, RRT-connect algorithm, RRT* algorithm, and the improved RRT algorithm are conducted in various environments. The results demonstrate that the improved RRT algorithm reduces the generated path length by 25.32% compared to the RRT algorithm, 26.42% compared to the RRT-connect algorithm, and 4.99% compared to the RRT* algorithm. Moreover, the improved RRT algorithm significantly improves the demand for reducing path costs. The planning time of the improved RRT algorithm is reduced by 64.96% compared to that of the RRT algorithm, 40.83% compared to that of the RRT-connect algorithm, and 27.34% compared to that of the RRT* algorithm, leading to improved speed. These findings indicate that the proposed method exhibits a notable improvement in the three crucial evaluation metrics: sampling time, number of nodes, and path length. Additionally, the algorithm performed well after undergoing physical verification with an insect-like mobile robot in a real environment featuring narrow elevator entrances.

A CNN-LSTM-att hybrid model for classification and evaluation of growth status under drought and heat stress in chinese fir (Cunninghamia lanceolata)

BACKGROUND

Cunninghamia lanceolata (Chinese fir), is one of the most important timber trees in China. With the global warming, to develop new resistant varieties to drought or heat stress has become an essential task for breeders of Chinese fir. However, classification and evaluation of growth status of Chinese fir under drought or heat stress are still labor-intensive and time-consuming.

RESULTS

In this study, we proposed a CNN-LSTM-att hybrid model for classification of growth status of Chinese fir seedlings under drought and heat stress, respectively. Two RGB image datasets of Chinese fir seedling under drought and heat stress were generated for the first time, and utilized in this study. By comparing four base CNN models with LSTM, the Resnet50-LSTM was identified as the best model in classification of growth status, and LSTM would dramatically improve the classification performance. Moreover, attention mechanism further enhanced performance of Resnet50-LSTM, which was verified by Grad-CAM. By applying the established Resnet50-LSTM-att model, the accuracy rate and recall rate of classification was up to 96.91% and 96.79% for dataset of heat stress, and 96.05% and 95.88% for dataset of drought, respectively. Accordingly, the R² value and RMSE value for evaluation on growth status under heat stress were 0.957 and 0.067, respectively. And, the R² value and RMSE value for evaluation on growth status under drought were 0.944 and 0.076, respectively.

CONCLUSION

In summary, our proposed model provides an important tool for stress phenotyping in Chinese fir, which will be a great help for selection and breeding new resistant varieties in future.