Mikania micrantha is a fast-growing global invasive weed species that causes severe damage to natural ecosystems and very large economic losses of forest and crop production.  It has advantages in photosynthesis, including a similar net photosynthetic rate as C₄ plants and a higher carbon fixation capacity.  We used a combination of genomics and transcriptomics approaches to study the evolutionary mechanisms and circadian expression patterns of M. micrantha.  In M. micrantha, 16 positive selection genes focused on photoreaction and utilization of photoassimilates.  In different tissues, 98.1% of the genes associated with photoresponse had high expression in stems, and more than half of the genes of the C₄ cycle had higher expression in stems than in leaves.  In stomatal opening and closing, 2 genes of carbonic anhydrase (CAs) had higher expression at 18:00 than at 8:00, and the slow anion channel 1 (SLAC1) and high-leaf-temperature 1 kinase (HT1) genes were expressed at low levels at 18:00.  In addition, genes associated with photosynthesis had higher expression levels at 7:00 and 17:00.  We hypothesized that M. micrantha may undergo photosynthesis in the stem and flower organs and that some stomata of the leaves were opening at night by CO₂ signals.  In addition, its evolution may attenuate photoinhibition at high light intensities, and enhance more efficient of photosynthesis during low light intensity.  And the tissue-specific photosynthetic types and different diurnal pattern of photosynthetic-related genes may contribute to its rapid colonization of new habitats of M. micrantha.

Online automated identification of farmland pests is an important auxiliary means of pest control.  In practical applications, the online insect identification system is often unable to locate and identify the target pest accurately due to factors such as small target size, high similarity between species and complex backgrounds.  To facilitate the identification of insect larvae, a two-stage segmentation method, MRUNet was proposed in this study.  Structurally, MRUNet borrows  the practice of object detection before semantic segmentation from Mask R-CNN and then uses an improved lightweight UNet to perform the semantic segmentation.  To reliably evaluate the segmentation results of the models, statistical methods were introduced to measure the stability of the performance of the models among samples in addition to the evaluation indicators commonly used for semantic segmentation.  The experimental results showed that this two-stage image segmentation strategy is effective in dealing with small targets in complex backgrounds.  Compared with existing state-of-the-art semantic segmentation methods, MRUNet shows better stability and detail processing ability under the same conditions.  This study provides a reliable reference for the automated identification of insect larvae.