Ginkgo biloba Sex Identification Methods Using Hyperspectral Imaging and Machine Learning.

Ginkgo biloba L. is a rare dioecious species that is valued for its diverse applications and is cultivated globally. This study aimed to develop a rapid and effective method for determining the sex of a Ginkgo biloba. Green and yellow leaves representing annual growth stages were scanned with a hyperspectral imager, and classification models for RGB images, spectral features, and a fusion of spectral and image features were established. Initially, a ResNet101 model classified the RGB dataset using the proportional scaling-background expansion preprocessing method, achieving an accuracy of 90.27%. Further, machine learning algorithms like support vector machine (SVM), linear discriminant analysis (LDA), and subspace discriminant analysis (SDA) were applied. Optimal results were achieved with SVM and SDA in the green leaf stage and LDA in the yellow leaf stage, with prediction accuracies of 87.35% and 98.85%, respectively. To fully utilize the optimal model, a two-stage Period-Predetermined (PP) method was proposed, and a fusion dataset was built using the spectral and image features. The overall accuracy for the prediction set was as high as 96.30%. This is the first study to establish a standard technique framework for Ginkgo sex classification using hyperspectral imaging, offering an efficient tool for industrial and ecological applications and the potential for classifying other dioecious plants.

Improving grain yield prediction through fusion of multi-temporal spectral features and agronomic trait parameters derived from UAV imagery.

Rapid and accurate prediction of crop yield is particularly important for ensuring national and regional food security and guiding the formulation of agricultural and rural development plans. Due to unmanned aerial vehicles' ultra-high spatial resolution, low cost, and flexibility, they are widely used in field-scale crop yield prediction. Most current studies used the spectral features of crops, especially vegetation or color indices, to predict crop yield. Agronomic trait parameters have gradually attracted the attention of researchers for use in the yield prediction in recent years. In this study, the advantages of multispectral and RGB images were comprehensively used and combined with crop spectral features and agronomic trait parameters (i.e., canopy height, coverage, and volume) to predict the crop yield, and the effects of agronomic trait parameters on yield prediction were investigated. The results showed that compared with the yield prediction using spectral features, the addition of agronomic trait parameters effectively improved the yield prediction accuracy. The best feature combination was the canopy height (CH), fractional vegetation cover (FVC), normalized difference red-edge index (NDVI_RE), and enhanced vegetation index (EVI). The yield prediction error was 8.34%, with an R2 of 0.95. The prediction accuracies were notably greater in the stages of jointing, booting, heading, and early grain-filling compared to later stages of growth, with the heading stage displaying the highest accuracy in yield prediction. The prediction results based on the features of multiple growth stages were better than those based on a single stage. The yield prediction across different cultivars was weaker than that of the same cultivar. Nevertheless, the combination of agronomic trait parameters and spectral indices improved the prediction among cultivars to some extent.

How Antioxidants, Osmoregulation, Genes and Metabolites Regulate the Late Seeding Tolerance of Rapeseeds (Brassica napus L.) during Wintering.

Rapeseed seeding dates are largely delayed under the rice-rape rotation system, but how rapeseeds adapt to the delayed environment remains unclear. Here, five seeding dates (20 October, 30 October, 10 November, 20 November and 30 November, T1 to T5) were set and the dynamic differences between two late-seeding-tolerant (LST) and two late-seeding-sensitive (LSS) rapeseed cultivars were investigated in a field experiment. The growth was significantly repressed and the foldchange (LST/LSS) of yield increased from 1.50-T1 to 2.64-T5 with the delay in seeding. Both LST cultivars showed higher plant coverage than the LSS cultivars according to visible/hyperspectral imaging and the vegetation index acquired from an unmanned aerial vehicle. Fluorescence imaging, DAB and NBT staining showed that the LSS cultivars suffered more stress damage than the LST cultivars. Antioxidant enzymes (SOD, POD, CAT, APX) and osmoregulation substances (proline, soluble sugar, soluble protein) were decreased with the delay in seeding, while the LST cultivar levels were higher than those of the LSS cultivars. A comparative analysis of transcriptomes and metabolomes showed that 55 pathways involving 123 differentially expressed genes (DEGs) and 107 differentially accumulated metabolites (DAMs) participated in late seeding tolerance regulation, while 39 pathways involving 60 DEGs and 68 DAMs were related to sensitivity. Levanbiose, α-isopropylmalate, s-ribosyl-L-homocysteine, lauroyl-CoA and argino-succinate were differentially accumulated in both cultivars, while genes including isocitrate dehydrogenase, pyruvate kinase, phosphoenolpyruvate carboxykinase and newgene_7532 were also largely regulated. This study revealed the dynamic regulation mechanisms of rapeseeds on late seeding conditions, which showed considerable potential for the genetic improvement of rapeseed.

A hybrid attention and dilated convolution framework for entity and relation extraction and mining.

Mining entity and relation from unstructured text is important for knowledge graph construction and expansion. Recent approaches have achieved promising performance while still suffering from inherent limitations, such as the computation efficiency and redundancy of relation prediction. In this paper, we propose a novel hybrid attention and dilated convolution network (HADNet), an end-to-end solution for entity and relation extraction and mining. HADNet designs a novel encoder architecture integrated with an attention mechanism, dilated convolutions, and gated unit to further improve computation efficiency, which achieves an effective global receptive field while considering local context. For the decoder, we decompose the task into three phases, relation prediction, entity recognition and relation determination. We evaluate our proposed model using two public real-world datasets that the experimental results demonstrate the effectiveness of the proposed model.

Predicting isoscapes based on an environmental similarity model for the geographical origin of Chinese rice.

The authentication of geographical origin of food is important using stable isotope analysis. However, the isotopic databank is still short of comprehensive. The isoscapes model based on environmental similarity is used for the first time to predict the geospatial distribution of δ13C, δ2H and δ18O in Chinese rice in 2017 and 2018. 794 rice samples in 2017 were used to build isoscapes model. Independent verification shows that the predicted isotope distribution from this new approach is of high accuracy, with a root mean square error (RMSE) of 0.51 ‰, 7.09 ‰ and 2.06 ‰ for δ13C, δ2H and δ18O values for 2017, respectively. Our results indicate that it is possible to predict the spatial distribution of stable isotopes in rice using an isoscapes model based on environmental similarity. This novel strategy can enrich and complement a stable isotope reference database for rice origin identification at regional scale.

Photosynthetic rate and chlorophyll fluorescence of barley exposed to simulated acid rain.

Acid rain is considered one of the most serious plant abiotic stresses. Photosynthesis is the basis of crop growth and development. The effect of acid rain on barley photosynthesis remains unclear. A glasshouse experiment was conducted, and the photosynthetic rate, chlorophyll (Chl) fluorescence, and pigment content of barley were measured in simulated acid rain (SAR) under pH 6.5, 5.5, 4.5, and 3.5. The results showed that net photosynthetic rate, maximal photosynthetic rate, and light saturation point decreased and the light compensation point, and dark respiration rate increased with increasing acidity. The results suggested that photosynthesis in barley plants was inhibited by SAR stress. The Chl content and stomatal conductance declined in parallel with the reduced net photosynthetic rate when barley plants were under SAR stress conditions. This indicated that non-stomatal factors may contribute to reduced photosynthesis under acid rain stress. Acid rain had greater effects on the photosynthesis of the acid rain-sensitive plant Zhepi 33 than on non-sensitive Kunlun 12. A significant difference in parameters such as the maximal fluorescence, variable fluorescence, and active PSII reaction centers was found among the SAR treatments and may be used to evaluate the sensitivity of plants to acid rain stress. The visualization model showed that the photosynthetic reaction centers were inactivated in acid rain stressed barley plants. These findings are valuable for the evaluation of the plant sensitivity to acid rain stress and may be used for the detection and monitoring of acid rain effects on plants in the future.