Scene classification is one of the areas of remote sensing image processing that is gaining much attention. Aiming to solve the problem of the limited precision of optical scene classification caused by complex spatial patterns, a high similarity between classes, and a high diversity of classes, a feature cross-layer interaction hybrid algorithm for optical remote sensing scene classification is proposed in this paper. Firstly, a number of features are extracted from two branches, a vision transformer branch and a Res2Net branch, to strengthen the feature extraction capability of the strategy. A novel interactive attention technique is proposed, with the goal of focusing on the strong correlation between the two-branch features, to fully use the complementing advantages of the feature information. The retrieved feature data are further refined and merged. The combined characteristics are then employed for classification. The experiments were conducted by using three open-source remote sensing datasets to validate the feasibility of the proposed method, which performed better in scene classification tasks than other methods.

Semantic segmentation stands as a prominent domain within remote sensing that is currently garnering significant attention. This paper introduces a pioneering semantic segmentation model based on TransUNet architecture with improved coordinate attention for remote-sensing imagery. It is composed of an encoding stage and a decoding stage. Notably, an enhanced and improved coordinate attention module is employed by integrating two pooling methods to generate weights. Subsequently, the feature map undergoes reweighting to accentuate foreground information and suppress background information. To address the issue of time complexity, this paper introduces an improvement to the transformer model by sparsifying the attention matrix. This reduces the computing expense of calculating attention, making the model more efficient. Additionally, the paper uses a combined loss function that is designed to enhance the training performance of the model. The experimental results conducted on three public datasets manifest the efficiency of the proposed method. The results indicate that it excels in delivering outstanding performance for semantic segmentation tasks pertaining to remote-sensing images.

Leaf angle is a crucial morphological trait for improving crop architecture and facilitating high-density planting. This study aims to explore the mechanism underlying leaf angle formation in sorghum. We used the el1 mutant, generated through ethyl methane sulfonate mutagenesis in our laboratory, to conduct a comprehensive analysis, including phenotypic, cytological, and integrated transcriptomic and metabolomic studies. At the S3 stage, el1 leaves exhibited shrinkage, and their leaf angles were significantly smaller compared to those of the wild type (WT). Cytological analyses revealed that at the S1 stage, the auricles of el1 had larger cell sizes and fewer cells than those of the WT. Metabolomic analysis based on the Kyoto Encyclopedia of Genes and Genomes (KEGG) identified 19 significantly differentiated metabolites, with 10 upregulated and 9 downregulated. Transcriptomics KEGG analysis revealed 858 upregulated and 533 downregulated differentially expressed genes (DEGs). Integrated analysis highlighted that 12 DEGs were associated with trans-5-O-(p-coumaroyl)shikimate in phenylpropanoid biosynthesis, with 11 positively correlated and one negatively correlated DEG. Additionally, 43 DEGs were linked to coniferyl alcohol, with 35 positively correlated and 8 negatively correlated in el1 compared to WT. This study establishes a theoretical foundation for understanding the molecular mechanisms by which phenylpropanoid biosynthesis influences leaf angle formation in sorghum and offers a basis for optimizing plant architecture to enable high-density planting.

In this study, a novel cambered snow removal device is designed to achieve automatic snow removal in large curved areas, such as the south roof of a Chinese solar greenhouse. The theory of structural parameters and shear force is ambiguous. People are not based on the greenhouse structure parameters for the selection of snow removal devices. Therefore, the quantitative relationship between the structure of the greenhouse span and the number of scissor arm-length knots is analysed, and the relationship between the material strength and application distance is determined. This study’s objectives are (1) to establish a theoretical model of scissor arm motion and (2) to analyse the force distribution of the scissor arm using multi-body dynamics. The results show that the scissor arm of a round-arch greenhouse has fewer sections but a larger arm length, whereas the scissor arm of a traditional solar greenhouse has more sections but a smaller arm length. Based on the shear force of the scissor structure, the optimised wall thickness reduces the force of the node by 17%.

Sorghum is an important raw material for China’s baijiu (liquor) brewing industry, and the tannin content in its grains directly affects the quality and nutritional value of the liquor. Grain color is closely associated with tannin content, yet the genetic mechanism underlying grain color formation remains incompletely understood. In this study, we systematically observed grain development in the yellow-grained sorghum line GW605. The results showed that from 1 to 16 days after flowering (DAF), the grains underwent a rapid growth phase, after which the expansion rate slowed. On 25 DAF, the green color of the grains gradually faded, shifting from white to yellow and continuously deepening, ultimately turning dark yellow. A segregating population was subsequently constructed using GW605 (yellow grain) and 6E16 (white grain) as parents. Bulked segregant analysis (BSA) localized the gene controlling the yellow grain to chromosome 1. Through fine mapping based on recombinant individuals, the gene was narrowed to a 108 kb physical interval containing seven candidate genes. Sequencing and functional annotation of the candidate genes suggested that Yellow Seed 2 (Sobic.001G397900) is the candidate gene associated with yellow grain color difference between the two parental lines. Haplotype analysis of Yellow Seed 2 using resequencing data from 698 sorghum germplasm accessions detected a total of 11 SNP loci, forming four haplotypes, among which Hap1 was the predominant haplotype. Further analysis revealed that the haplotype diversity of Yellow Seed 2 increased considerably during the domestication process from Chinese landraces to Chinese cultivars, suggesting that this gene may have incorporated genetic lineages from foreign germplasm during domestication.

Leaf morphology influences photosynthesis, transpiration, and, ultimately, crop yield. To elucidate the molecular regulatory mechanisms underlying narrow leaves in Sorghum bicolor, we identified key DEGs (differentially expressed genes) influencing leaf morphology. The nal6 (the narrow-leaf mutant6) was obtained through 0.1% EMS (ethyl methane sulfonate) chemical mutagenesis of the WT (BTX623). Compared with the WT leaves, there were significant differences in leaf width and length at the flowering stage. A total of 1520 DEGs between the nal6 and WT were screened at the flowering stage based on the transcriptome analysis of sword leaves. KEGG and GO enrichment analyses revealed that DEGs were significantly enriched in pathways such as plant signal transduction, cytokinin biosynthesis, photosynthetic antenna proteins, and secondary metabolite biosynthesis. Further analysis indicated that four DEGs are involved in regulating auxin signaling transduction, thirteen DEGs are involved in regulating zeatin signal transduction, and two DEGs are involved in regulating zeatin biosynthesis. These genes are differentially expressed in nal6, directly affecting the signaling of auxin and zeatin and the biosynthesis of zeatin. Our findings provide a theoretical foundation for understanding the molecular regulation of narrow leaves and breeding ideal plant types in Sorghum bicolor.