Optimizing Spatial Relationships in GCN to Improve the Classification Accuracy of Remote Sensing Images

Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods for interpreting remote-sensing images has matured.Existing neural networks disregard the spatial relationship between two targets in remote sensing images.Semantic segmentation models that combine convolutional neural networks(CNNs)and graph convolutional neural networks(GCNs)cause a lack of feature boundaries,which leads to the unsatisfactory segmentation of various target feature boundaries.In this paper,we propose a new semantic segmentation model for remote sensing images(called DGCN hereinafter),which combines deep semantic segmentation networks(DSSN)and GCNs.In the GCN module,a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships.A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship informa-tion in the original feature information.Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images,the DGCN significantly optimizes the segmentation effect of feature boundaries,effectively reduces the noise in the segmentation results and improves the segmentation accuracy,which demonstrates the advancements of our model.

Contamination Identification of Lentinula Edodes Logs Based on Improved YOLOv5s

In order to improve the accuracy and efficiency of Lentinula edodes logs contamination identification,an improved YOLOv5s contamination identification model for Lentinula edodes logs(YOLOv5s-CGGS)is proposed in this paper.Firstly,a CA(coordinate attention)mechanism is introduced in the feature extraction network of YOLOv5s to improve the identifiability of Lentinula edodes logs contamination and the accuracy of target localiza-tion.Then,the CIoU(Complete-IOU)loss function is replaced by an SIoU(SCYLLA-IoU)loss function to improve the model’s convergence speed and inference accuracy.Finally,the GSConv and GhostConv modules are used to improve and optimize the feature fusion network to improve identification efficiency.The method in this paper achieves values of 97.83%,97.20%,and 98.20%in precision,recall,and mAP@0.5,which are 2.33%,3.0%,and 1.5%better than YOLOv5s,respectively.mAP@0.5 is better than YOLOv4,Ghost-YOLOv4,and Mobilenetv3-YOLOv4(improved by 4.61%,5.16%,and 6.04%,respectively),and the FPS increased by two to three times.

Research on Spatiotemporal Variation of Soil Temperature in China from 1948 to 2018

The change of soil temperature can affect the regional climate, so it is of great significance to research the spatial and temporal evolution characteristics of regional soil temperature over a long period of time for the research of the land-air interaction, climate change and ecological agricultural construction. We use the v2.0 and v2.1 data set combined with GLDAS and Noah models to analyze the spatiotemporal variation of temperature in soil layers of 0 - 200 cm in China during the period of 71 years from 1948 to 2018. Firstly, the Mann-Kendall test method is used to research the variation trend of soil temperature over the past 71 years in China and the spatial variation of these trends. Secondly, by calculating the spatiotemporal coefficient of variation (CV) of soil temperature, the spatial-temporal fluctuation of soil temperature in China is further studied and analyzed. Finally, the Hurst index is used to analyze the possible future trend of soil temperature in China. Based on these methods, we have drawn the following conclusions: 1) The soil temperature in most areas of northern China had an increasing trend, especially in the northeast China. The soil temperature in most of the south China had a decreasing trend. The temperature trends of the four soil layers had little difference, and it remained stable on the whole. 2) The regional difference of soil temperature in China remained stable before 1999, and decreased suddenly in 2000. After 2008, the regional difference increased. Compared with the previous period, the temperature in some areas increased or decreased abnormally. 3) The soil temperature in eastern, southeast China and Xinjiang had a relatively significant variation in the 71 years. From 0 - 10 cm soil surface to 100 - 200 cm soil bottom, the spatial difference of temperature gradually decreased, which was due to the fact that the soil temperature was more affected by the surface atmospheric temperature. 4) The soil temperature in the north and northwest of China will continue to grow, and in the southern—most will continue to decrease. The soil temperature in the north of central China will become a decreasing trend, while the temperature in the south of central China will become an increasing trend.