Search

As one of the important lakes in the "One Lake and Two Seas" of the Inner Mongolia Autonomous Region, the monitoring of water quality in Lake Daihai has attracted increasing attention, and the concentration of chlorophyll-a directly affects the water quality, making the monitoring of chlorophyll-a concentration in Lake Daihai particularly crucial. Traditional methods of monitoring chlorophyll-a concentration are not only inefficient but also require significant human and material resources. Remote sensing technology has the advantages of wide coverage and short update cycles. For lakes such as Daihai with a high salinity content, salinity is considered a key factor when inverting the concentration of chlorophyll-a. In this study, machine learning models, including model stacking from ensemble learning, a ridge regression model, and a random forest model, were constructed. After comparing the training accuracy of the three models on Zhuhai-1 satellite data, the random forest model, which had the highest accuracy, was selected as the final training model. By comparing the accuracy changes before and after adding salinity factors to the random forest model, a high-precision model for inverting chlorophyll-a concentration in hypersaline lakes was obtained. The research results show that, without considering the salinity factor, the root mean square error (RMSE) of the model was 0.056, and the coefficient of determination (R2) was 0.64, indicating moderate model performance. After adding the salinity factor, the model accuracy significantly improved: the RMSE decreased to 0.047, and the R2 increased to 0.92. This study provides a solid basis for the application of remote sensing technology in hypersaline aquatic environments, confirming the importance of considering salinity when estimating chlorophyll-a concentration in hypersaline waters. This research helps us gain a deeper understanding of the water quality and ecosystem evolution in Daihai Lake. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of vehicle trajectories and ensure driving safety, and considering the differences in driver behavior and the impact of these differences on vehicle trajectories, a vehicle trajectory-prediction method (DBC-Informer) based on the categorization of driver behavior is proposed: firstly, the characteristic driver feature data are extracted through data preprocessing; secondly, descriptive statistical data are obtained through the classification of the driver's behavior into categories; finally, based on the Informer model, a two-layer driver category trajectory-prediction network architecture is established, which inputs the vehicle trajectories of different driving types into independent prediction sub-networks, respectively, to realize the accurate prediction of vehicle trajectories. The experimental results show that the MAE and MSE values of trajectory prediction of the DBC-Informer model in different time domains are much smaller than those of other comparative models, and the improvement of accuracy is more obvious in the long-term domain trajectory-prediction task scenario, and the increase in prediction error of the DBC-Informer model is significantly reduced after the prediction time exceeds 1 s. The on-line behavioral categorization is achieved by comparing different categorization models; it reaches 98% in classification accuracy and, according to the results of ablation experiments, the addition of the driver behavior-classification method to the prediction model improves the accuracy of prediction in longitudinal and lateral motion by 56% and 61%, respectively, which verifies the effectiveness of the driver behavior-classification method. It can be seen that the DBC-Informer model can more accurately portray the effects of different driving behaviors on vehicle trajectories and improve the accuracy of vehicle trajectory prediction, which provides important data support for vehicle warning systems. [ABSTRACT FROM AUTHOR]

Stevioside is a secondary metabolite of diterpenoid glycoside production in plants. It has been used as a natural sweetener in various foods because of its high sweetness and low-calorie content. In this study, we constructed a Saccharomyces cerevisiae strain for the complete synthesis of stevioside using a metabolic engineering strategy. Firstly, the synthesis pathway of steviol was modularly constructed in S. cerevisiae BY4742, and the precursor pathway was strengthened. The yield of steviol was used as an indicator to investigate the expression effect of different sources of diterpene synthases under different combinations, and the strains with further improved steviol yield were screened. Secondly, glycosyltransferases were heterologously expressed in this strain to produce stevioside, the sequence of glycosyltransferase expression was optimized, and the uridine diphosphate-glucose (UDP-Glc) supply was enhanced. Finally, the results showed that the strain SST-302III-ST2 produced 164.89 mg/L of stevioside in a shake flask experiment, and the yield of stevioside reached 1104.49 mg/L in an experiment employing a 10 L bioreactor with batch feeding, which was the highest yield reported. We constructed strains with a high production of stevioside, thus laying the foundation for the production of other classes of steviol glycosides and holding good prospects for application and promotion. [ABSTRACT FROM AUTHOR]

Background: Vitamin B12 (VB12) has a wide range of applications and high economic value. In this study, a new strain with high VB12 production potential, Ensifer adhaerens S305, was identified in sewage. Because E. adhaerens strains have become the main strains for VB12 production via fermentation in recent years, the directional modification of the S305 strain to obtain a strain suitable for the industrial production of VB12 has great potential and commercial value. Results: 16S rRNA and genome-wide phylogenetic tree analysis combined with average nucleotide identity (ANI) analysis showed that the high-yielding VB12 strain was a E. adhaerens strain and that its VB12 synthesis pathway genes were highly similar to related genes of strains of this and other species, including E. adhaerens Casida A, Pseudomonas denitrificans SC 510, and E. adhaerens Corn53. High-pressure liquid chromatography (HPLC) results indicated that the VB12 yields of the S305 strain were more than double those of the Casida A strain under different medium components. Multiple genes with significantly upregulated and downregulated transcription were identified by comparing the transcription intensity of different genes through transcriptome sequencing. KEGG enrichment analysis of the porphyrin metabolism pathway identified 9 significantly upregulated and downregulated differentially expressed genes (DEGs) in the VB12 synthesis pathway, including 7 transcriptionally upregulated genes (cobA, cobT, hemA, cobJ, cobN, cobR, and cobP) that were episomally overexpressed in the Casida A strain. The results showed that the VB12 yield of the overexpressed strain was higher than that of the wild-type strain. Notably, the strains overexpressing the cobA and cobT genes exhibited the most significant increases in VB12 yield, i.e., 31.4% and 24.8%, respectively. The VB12 yield of the S305 strain in shake-flask culture was improved from 176.6 ± 8.21 mg/L to 245.6 ± 4.36 mg/L by integrating the cobA and cobT genes into the strain. Conclusion: Phylogenetic tree and ANI analysis showed that the Ensifer and Sinorhizobium strains were quite different at the genome level; the overexpression and integrated expression of significantly upregulated genes in the VB12 synthesis pathway could increase the yield of VB12, further improving the VB12 yield of the E. adhaerens S305 strain. [ABSTRACT FROM AUTHOR]

To block and weaken the bacterial branched VB12 synthetic metabolic pathway, homologous recombination technology was used to knock out the sirohaem synthase gene cysG located in the chromosome and the endogenous A plasmid of the Ensifer adhaerens Casida A strain, and the expression of the uroporphyrinogen III decarboxylase gene hemE was weakened by weak promoter substitution. The growth of the engineered strains and the production of VB12 and haem were analysed and measured in the engineered strains, aiming to provide a new strategy for enhancement of VB12 biosynthesis. The results showed that the chromosomal cysG gene knockout strain ΔcysG, endogenous A plasmid cysG gene knockout strain ΔpAcysG and cysG gene double knockout strain ΔcysGΔpAcysG grew normally, with VB12 yield increases of 19.9%, 11.2%, and 27.4% compared to the starting strain, respectively. In the background of the cysG gene knockout strain, the expression of the hemE gene was weakened, resulting in the generation of the strain ΔcysGΔpAcysG-E-pdnaD, and the VB12 yield of ΔcysGΔpA cysG-E-pdnaD reached 114.17 ± 5.77 mg L−1, an increase of 45.1% compared to the yield of the original strain. The above results indicate that the strategy of increasing VB12 production by knocking out the haem synthesis pathway and weakening the haem synthesis pathway is effective. [ABSTRACT FROM AUTHOR]