Image detection model construction of Apolygus lucorum and Empoasca spp. based on improved YOLOv5.

BACKGROUND: The polyphagous mirid bug Apolygus lucorum (Meyer-Dür) and the green leafhopper Empoasca spp. Walsh are small pests that are widely distributed and important pests of many economically important crops, especially kiwis. Conventional monitoring methods are expensive, laborious and error-prone. Currently, deep learning methods are ineffective at recognizing them. This study proposes a new deep-learning-based YOLOv5s_HSSE model to automatically detect and count them on sticky card traps. RESULTS: Based on a database of 1502 images, all images were collected from kiwi orchards at multiple locations and times. We trained the YOLOv5s model to detect and count them and then changed the activation function to Hard swish in YOLOv5s, introduced the SIoU Loss function, and added the squeeze-and-excitation attention mechanism to form a new YOLOv5s_HSSE model. Mean average precision of this model in the test dataset was 95.9%, the recall rate was 93.9% and the frames per second was 155, which are higher than those of other single-stage deep-learning models, such as SSD, YOLOv3 and YOLOv4. CONCLUSION: The proposed YOLOv5s_HSSE model can be used to identify and count A. lucorum and Empoasca spp., and it is a new, efficient and accurate monitoring method. Pest detection will benefit from the broader applications of deep learning. © 2024 Society of Chemical Industry.

Response of thermal conductivity of loess after high temperature in northern Shaanxi burnt rock area, China.

Spontaneous combustion of coal seams can produce a high temperature of about 800 ℃, which greatly changes the thermal conductivity of the overlying loess layer. The thermal conductivity of loess plays an important role in ecological restoration design and the calculation of roadbed and slope stability. In this study, loess in northern Shaanxi, China was taken as the research object to measure the mass-loss rate and heat conduction parameters of loess specimens after high temperature. The test results show that, between 23 and 900 °C, with temperature increasing, the mass-loss rate is reduced. And the heat conduction coefficient (λ), specific heat capacity (c), and thermal diffusion coefficient (α) decreased by 48.9%, 23.1%, and 35.6%. This is due to the air thermal resistance effect caused by the increase of pores and cracks in loess specimens after high temperature.

Effect of heat treatment on the emission rate of radon from red sandstone.

High temperature and pore structure are important factors affecting the emission rate of radon in rocks. This study mainly focused on the correlation between radon emission rate and temperature in red sandstone. The results showed that in the temperature range of 25-400 °C, as the temperature increased, the connectivity of the internal pores of the sample became better, resulting in a significantly increased radon emission rate. The radon emission rate at 400 °C was 2.86 times the original. To explain the changes that occurred in the internal structure of the samples, the porosity characteristics of the samples after heat treatment were studied by nuclear magnetic resonance (NMR). It was found that the pore structure was also an important factor affecting the rate of radon emission. The smaller pore size of the micropores (r < 0.1 µm) inhibited the emission of radon in the sandstone. These results helped in understanding the mechanism of radon emission rate and provide an important basis for predicting rock fragmentation and coal fire.

Comparative analysis of the complete chloroplast genome sequences in psammophytic Haloxylon species (Amaranthaceae).

The Haloxylon genus belongs to the Amaranthaceae (formerly Chenopodiaceae) family. The small trees or shrubs in this genus are referred to as the King of psammophytic plants, and perform important functions in environmental protection, including wind control and sand fixation in deserts. To better understand these beneficial plants, we sequenced the chloroplast (cp) genomes of Haloxylon ammodendron (HA) and Haloxylon persicum (HP) and conducted comparative genomic analyses on these and two other representative Amaranthaceae species. Similar to other higher plants, we found that the Haloxylon cp genome is a quadripartite, double-stranded, circular DNA molecule of 151,570 bp in HA and 151,586 bp in HP. It contains a pair of inverted repeats (24,171 bp in HA and 24,177 bp in HP) that separate the genome into a large single copy region of 84,214 bp in HA and 84,217 bp in HP, and a small single copy region of 19,014 bp in HA and 19,015 bp in HP. Each Haloxylon cp genome contains 112 genes, including 78 coding, 30 tRNA, and four ribosomal RNA genes. We detected 59 different simple sequence repeat loci, including 44 mono-nucleotide, three di-nucleotide, one tri-nucleotide, and 11 tetra-nucleotide repeats. Comparative analysis revealed only 67 mutations between the two species, including 44 substitutions, 23 insertions/deletions, and two micro-inversions. The two inversions, with lengths of 14 and 3 bp, occur in the petA-psbJ intergenic region and rpl16 intron, respectively, and are predicted to form hairpin structures with repeat sequences of 27 and 19 bp, respectively, at the two ends. The ratio of transitions to transversions was 0.76. These results are valuable for future studies on Haloxylon genetic diversity and will enhance our understanding of the phylogenetic evolution of Amaranthaceae.