Automatic segmentation of stem and leaf components and individual maize plants in field terrestrial LiDAR data using convolutional neural networks

High-throughput maize phenotyping at both organ and plant levels plays a key role in molecular breeding for increasing crop yields. Although the rapid development of light detection and ranging(Li DAR) provides a new way to characterize three-dimensional(3 D) plant structure, there is a need to develop robust algorithms for extracting 3 D phenotypic traits from Li DAR data to assist in gene identification and selection. Accurate 3 D phenotyping in field environments remains challenging, owing to difficulties in segmentation of organs and individual plants in field terrestrial Li DAR data. We describe a two-stage method that combines both convolutional neural networks(CNNs) and morphological characteristics to segment stems and leaves of individual maize plants in field environments. It initially extracts stem points using the Point CNN model and obtains stem instances by fitting 3 D cylinders to the points. It then segments the field Li DAR point cloud into individual plants using local point densities and 3 D morphological structures of maize plants. The method was tested using 40 samples from field observations and showed high accuracy in the segmentation of both organs(F-score =0.8207) and plants(Fscore =0.9909). The effectiveness of terrestrial Li DAR for phenotyping at organ(including leaf area and stem position) and individual plant(including individual height and crown width) levels in field environments was evaluated. The accuracies of derived stem position(position error =0.0141 m), plant height(R^(2)>0.99), crown width(R^(2)>0.90), and leaf area(R^(2)>0.85) allow investigating plant structural and functional phenotypes in a high-throughput way. This CNN-based solution overcomes the major challenges in organ-level phenotypic trait extraction associated with the organ segmentation, and potentially contributes to studies of plant phenomics and precision agriculture.

A novel ground surface subsidence prediction model for sub-critical mining in the geological condition of a thick alluvium layer

A substantial number of the coal mines in China are in the geological condition of thick alluvium layer. Under these circumstances, it does not make sense to predict ground surface subsidence and other deformations by using conventional prediction models. This paper presents a novel ground surface subsidence prediction model for sub-critical mining in the geological condition of thick alluvium layer. The geological composition and mechanical properties of thick alluvium is regarded as a random medium, as are the uniformly distributed loads on rock mass; however, the overburden of the rock mass in the bending zone is looked upon as a hard stratum controlling the ground surface subsidence. The different subsidence and displacement mechanisms for the rock mass and the thick alluvium layer are respectively considered and described in this model, which indicates satisfactory performances in a practical prediction case.