Multispectral LiDAR (Light Detection and Ranging) point clouds, as a new kind of data, can be characterized by high consistency and integrity of spectral information geometric data. which makes it beneficial for land use classification. However, the direct classification of multispectral LiDAR data remains challenging, since the data are irregular and unordered. By describing the point cloud in the form of graph data, utilizing graph convolution to naturally model local geometric structures representation, higher processing accuracy and efficiency can be achieved. Notably, however, due to the complexity of graph data, employing only a single graph convolution to learn the data features may limit the capacity of the architecture; in addition selecting appropriate graph convolutions requires human expertise and massive numbers of trials. In this paper, we propose a network that combines several outstanding graph convolutions by adapting neural architecture search (NAS) for point cloud segmentation, an approach referred to as GCNAS, which can adaptively achieve different levels of semantic expression. In the search module, we use the Monte Carlo tree search (MCTS) method to select the layer-wise graph convolution kernels. Experiments on the Titan multispectral LiDAR dataset have verified the effectiveness of GCNAS.

The hyperspectral image (HSI) distinguishes itself in material identification through its exceptional spectral resolution. However, its spatial resolution is constrained by hardware limitations, prompting the evolution of HSI super-resolution (SR) techniques. Single HSI SR endeavors to reconstruct high-spatial-resolution HSI from low-spatial-resolution inputs, and recent progress in deep learning-based algorithms has significantly advanced the quality of reconstructed images. However, convolutional methods struggle to extract comprehensive spatial and spectral features. Transformer-based models have yet to harness long-range dependencies across both dimensions fully, thus inadequately integrating spatial and spectral data. To solve the above problem, in this paper, we propose a new HSI SR method, SSAformer, which merges the strengths of CNNs and Transformers. It introduces specially designed attention mechanisms for HSI, including spatial and spectral attention modules, and overcomes the previous challenges in extracting and amalgamating spatial and spectral information. Evaluations on benchmark datasets show that SSAformer surpasses contemporary methods in enhancing spatial details and preserving spectral accuracy, underscoring its potential to expand HSI’s utility in various domains, such as environmental monitoring and remote sensing.

The varved sediments of Kusai Lake on the northern Tibetan Plateau are rhythmically laminated with the interaction of dark and light layers formed during winter and summer within a year. This provides opportunities to explore the seasonal fluxes of varves and, thus, assess the potential for annual-resolution climate reconstruction. Here, we define a season index (SI) based on the difference in thickness between the light and dark layers, to evaluate the factors influencing the seasonal flux of varved Kusai Lake sediments. A positive SI represents more summer flux, and a negative SI indicates more winter flux. The results showed that the summer flux was higher than the winter flux in most of the last 2280 years. The summer flux had periodicities of approximately 2.3–2.9, 27, and 99 years at the 99% confidence level and approximately 15–16, 36 and 285 years at the 95% confidence level, indicating that summer flux is affected mainly by solar activity (Gleissberg and 350 unnamed cycle) at centennial scales, by the Pacific Decadal Oscillation (Pacific Decadal Oscillation with a period of 15–25 years) at decadal scales, and by the Quasi-biennial Oscillation (Quasi-biennial Oscillation with a period of 2–3 years) at interannual scales. Noticeable increasing spikes of high winter flux corresponded well to lower solar activity and stronger Siberian high pressure (SH). The periods of high and low winter flux are generally related to the negative and positive phases of the North Atlantic Oscillation and Atlantic Multidecadal Oscillation respectively, during the last 1000 years.

The 3-D point cloud semantic segmentation extends the development of computer vision. Accurate point cloud semantic segmentation is a fundamental problem in point cloud applications. However, effective point cloud semantic segmentation is still a competitive problem due to the disorder and irregularity of point clouds. Witnessing the success of the transformer structure in natural language processing and 2-D computer vision, researchers have introduced the transformer into point cloud semantic segmentation and conducted many helpful explorations. The transformer is characterized by global modeling, and it is worth exploring how to obtain the local spatial inductive bias. In this article, we design an asymmetric network that simultaneously extracts local and global features. The network structure consists of two branches: a pointwise convolutional network with a feedback mechanism and a transformer structure based on multiscale pooling. The cascaded asymmetric network structures are used for point cloud semantic segmentation. We validate the effectiveness of the proposed network on a multispectral light detection and ranging point cloud dataset. In addition, we also conduct a series of experiments to explore the effectiveness of different structures. The proposed method achieves state-of-the-art performance compared with previously designed point cloud semantic segmentation networks.