Search for: All records

The theory of microbial stoichiometry can predict the proportional coupling of microbial assimilation of carbon (C), nitrogen (N), and phosphorus (P). The proportional coupling is quantified by the homeostasis value (H). Covariation of H values for C, N, and P indicates that microbial C, N, and P assimilation are coupled. Here, we used a global dataset to investigate the spatiotemporal dynamics of H values of microbial C, N, and P across biomes. We found that land use and management led to the decoupling of P from C and N metabolism over time and across space. Results from structural equation modeling revealed that edaphic factors dominate the microbial homeostasis of P, while soil elemental concentrations dominate the homeostasis of C and N. This result was further confirmed using the contrasting factors on microbial P vs. microbial C and N derived from a machine-learning algorithm. Overall, our study highlights the impacts of management on shifting microbial roles in nutrient cycling.

 

Recent advances in deep generative models have led to immense progress in 3D shape synthesis. While existing models are able to synthesize shapes represented as voxels, point-clouds, or implicit functions, these methods only indirectly enforce the plausibility of the final 3D shape surface. Here we present a 3D shape synthesis framework (SurfGen) that directly applies adversarial training to the object surface. Our approach uses a differentiable spherical projection layer to capture and represent the explicit zero isosurface of an implicit 3D generator as functions defined on the unit sphere. By processing the spherical representation of 3D object surfaces with a spherical CNN in an adversarial setting, our generator can better learn the statistics of natural shape surfaces. We evaluate our model on large-scale shape datasets, and demonstrate that the end-to-end trained model is capable of generating high fidelity 3D shapes with diverse topology. 

Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks and pores in the testing images. In addition to the application of static image analysis, defect detection is also successfully applied on a video which mimics the AM process control images. The trained Detectron2 model can identify almost all the pores and cracks that exist in the original video. This study lays a foundation for future in situ process monitoring of the 3D printing process.