Sugarcane Stem Node Recognition in Field by Deep Learning Combining Data Expansion

The rapid and accurate identification of sugarcane stem nodes in the complex natural environment is essential for the development of intelligent sugarcane harvesters. However, traditional sugarcane stem node recognition has been mainly based on image processing and recognition technology, where the recognition accuracy is low in a complex natural environment. In this paper, an object detection algorithm based on deep learning was proposed for sugarcane stem node recognition in a complex natural environment, and the robustness and generalisation ability of the algorithm were improved by the dataset expansion method to simulate different illumination conditions. The impact of the data expansion and lighting condition in different time periods on the results of sugarcane stem nodes detection was discussed, and the superiority of YOLO v4, which performed best in the experiment, was verified by comparing it with four different deep learning algorithms, namely Faster R-CNN, SSD300, RetinaNet and YOLO v3. The comparison results showed that the AP (average precision) of the sugarcane stem nodes detected by YOLO v4 was 95.17%, which was higher than that of the other four algorithms (78.87%, 88.98%, 90.88% and 92.69%, respectively). Meanwhile, the detection speed of the YOLO v4 method was 69 f/s and exceeded the requirement of a real-time detection speed of 30 f/s. The research shows that it is a feasible method for real-time detection of sugarcane stem nodes in a complex natural environment. This research provides visual technical support for the development of intelligent sugarcane harvesters.

QTL for Main Stem Node Number and Its Response to Plant Densities in 144 Soybean FW-RILs

Although the main stem node number of soybean [Glycine max (L.) Merr. ] is an important yield-related trait, there have been limited studies on the effect of plant density on the identification of quantitative trait loci (QTL) for main stem node number (MSNN). To address this issue, here, 144 four-way recombinant inbred lines (FW-RILs) derived from Kenfeng 14, Kenfeng 15, Heinong 48, and Kenfeng 19 were used to identify QTL for MSNN with densities of 2.2 × 105 (D1) and 3 × 105 (D2) plants/ha in five environments by linkage and association studies. As a result, the linkage and association studies identified 40 and 28 QTL in D1 and D2, respectively, indicating the difference in QTL in various densities. Among these QTL, five were common in the two densities; 36 were singly identified for response to density; 12 were repeatedly identified by both response to density and phenotype of two densities. Thirty-one were repeatedly detected across various methods, densities, and environments in the linkage and association studies. Among the 24 common QTL in the linkage and association studies, 15 explained a phenotypic variation of more than 10%. Finally, Glyma.06G094400, Glyma.06G147600, Glyma.19G160800.1, and Glyma.19G161100 were predicted to be associated with MSNN. These findings will help to elucidate the genetic basis of MSNN and improve molecular assistant selection in high-yield soybean breeding.

Effect of Sucrose on Microtuber Induction and Inulin Accumulation in Jerusalem Artichoke (Helianthus tuberosus L.)

The effect of sucrose concentrations and photoperiod applying on microtuber induction and inulin accumulation of Jerusalem artichoke (Helianthus tuberosus L.) have conducted under in vitro condition. Numbers, lengths and weights of microtubers induced from the single node explants with 0.50 cm above stem node- and stem node- cutting was not significant difference. Concentration of sucrose (51.70, 60, 80, 100 and 108.20 g/l) containing in microtuber induction medium (MST) and photoperiod applying (10.30/13.70, 12/12, 16/8, 20/4 and 21.60/2.40 h light/dark) significant effected to numbers of microtubers (P ≤ 0.05). The optimized sucrose concentration and photoperiod applying for highest numbers of microtubers was 100 g/l and 20/4 h light/dark, respectively. The significant difference of inulin content (P ≤ 0.05) in microtuber induced from various conditions was determined. The microtubers induced on MST medium supplemented with 80 g/l sucrose under 16/8 h light/dark accumulated highest inulin content (324.84 ± 40.78 mg/ g dry weight) when compared with others. Data suggested that sucrose and light duration played role in microtuber induction and inulin accumulation of Jerusalem artichoke. Keywords: Inulin, Jerusalem artichoke, Microtuber, Photoperiod, Sucrose

Water Deficit and Recovery-Induced Changes in Growth, Photosynthetic Characteristics, Antioxidant Enzymes and Yield of Two Tartary Buckwheat Genotypes

Tartary buckwheat (Fagopyrum tataricum) is an important food crop that is widely adaptable to hostile environments. In this study the responses of two Tartary buckwheat genotypes: drought-susceptible Chuanqiao No. 1 (CQ) and drought-tolerant Jingqiao No. 2 (JQ) in terms of morphology, photosynthesis, physiology and yield to a progressive water deficit and recovery treatment (WD-R) were evaluated. Plants in the well-watered (WW) treatment were watered throughout the experiment. Compared to the WW treatment, water deficit in the WD-R treatment caused decreases in plant height, stem diameter, branch number, stem node number, biomass, seed number, soil water content (SWC), leaf relative water content (RWC), net photosynthesis rate (Pn), intercellular CO2 concentration, stomatal conductance (Gs), transpiration rate (Tr) and Fv/Fm in both CQ and JQ plants. Leaf wilting, malondialdehyde content, superoxide dismutase activity, peroxidase activity, initial fluorescence (F0) and root-to-shoot ratio were significantly increased under water stress in the WD-R treatment. Under the WD-R treatment, compared to CQ, JQ maintained higher RWC, SWC, Pn, Gs, WUE, Fv/Fm, plant height, branch number, stem node number, root biomass, stem biomass, leaf biomass, total biomass, root-to-shoot ratio, seed number per plant, and yield, but a lower Tr and F0. By correlation analysis, Gs was positively correlated with leaf RWC and SWC. These differential growth indexes, biochemical traits and physiological responses might be useful for understanding drought-tolerance genotypes that can grow under water-deficit conditions with minimum yield loss. © 2021 Friends Science Publishers

GRAIN QUALITY FORECASTING BY AMINO ACID CONCENTRATION IN THE LEAF JUICE

Field experiments with soft wheat and malting barley, conducted on sod-podzolic medium loamy soil showed that under the influence of increasing rates of nitrogen nutrition in the leaf juice in the first stem node phase, the concentration of amino acids decreases. This fact is confirmed by high correlation coefficients. There is also a close correlation between the concentration of amino acids in the leaf juice, plant productivity and grain quality indicators. Wheat showed a close negative correlation of the concentration of amino acids in the leaf juice with the weight of 1000 grains, the total content of proteins and gluten in the grain, as well as gliadin and glutenin proteins, and a close positive correlation with the content of water-soluble, non-extractable proteins in the grain and the activity of proteases. The concentration of amino acids in the malting barley leaf juice was negatively correlated with the total content of proteins in the grain, the amount of gordeins, the total activity of amylases, and positively correlated with the test value indicators, grain extractivity, and the content of water-soluble proteins in the grain. The research results indicate that the concentration of amino acids in the leaf juice in the first stem node phase provides for a fairly accurate diagnoctics of nitrogen nutrition and prediction of the quality of soft wheat and malting barley grains.