Evaluation of the ecological status of shallow-water coral reefs in China using a novel method and identification of environmental factors for coral decline.

Coral reefs worldwide have faced extensive damage due to natural catastrophes and anthropogenic disturbances.The decline can cause their widespread collapse and an inability to recover from natural disturbances, highlighting the urgent need for their protection. This study conducted an extensive ecological condition assessment of seven coral reef regions in China's offshore. Our findings revealed the presence of 204 species of scleractinian corals belonging to 16 families. Massive corals were the predominant reef-building corals in all regions. The degradation of coral reef ecosystems was apparent in the present compared to historical reef conditions. The ecosystem suffered varying degrees of damage in surveyed regions according to a novel assessment approach, impling more effective measures should be taken to mitigate the local pressures. Our research establishes a baseline for understanding the status of coral reefs that can be used in future and provides a crucial foundation to designate protective zones for their conservation.

Biogas production prediction model of food waste anaerobic digestion for energy optimization using mixup data augmentation-based global attention mechanism.

Achieving rapid, efficient, and cost-effective anaerobic digestion (AD) of food waste is a key means to improve the efficiency of food waste treatment. However, in view of the shortage of historical anaerobic digestion data, the limitation of general neural networks in predicting biogas production, and its sensitivity to abnormal variation points, achieving accurate prediction of biogas production is not easy. This paper proposes a novel biogas production prediction model of food waste AD for energy optimization based on the mixup data augmentation integrating an improved global attention mechanism long short-term memory (LSTM). Taking the AD data of the actual factory as samples, the mixup data augmentation is introduced to generate virtual samples with the similar distribution as original samples. Then original samples and generated virtual samples are used as the input of the global attention mechanism LSTM to establish the food waste AD biogas production prediction model. Finally, the proposed method is applied in the biogas production prediction of actual food waste treatment plants. Compared with other industrial modeling models, the experimental results show that the proposed method has the highest prediction accuracy of 0.988, which performs well in predicting biogas production and can effectively guide and timely adjust feed configuration of AD plants.

Comparative transcriptome analysis and flavonoid profiling of floral mutants reveals CmMYB11 regulating flavonoid biosynthesis in chrysanthemum.

Flavonoids, of which the major groups are flavones, flavonols, and anthocyanins, confer a variety of colors on plants. Bud sports with variation of floral colors occur occasionally during chrysanthemum cultivation. Although it has been reported that methylation at the promoter of CmMYB6 was related to anthocyanin contents, the regulatory networks of flavonoid biosynthesis still remain largely unknown in mutation of chrysanthemum. We compared phenotypes, pigment composition and transcriptomes in two chrysanthemum cultivars, 'Anastasia Dark Green' and 'Anastasia Pink', and regenerated bud sports of these cultivars with altered floral colors. Increased anthocyanins turned the 'Anastasia Dark Green' mutant red, while decreased anthocyanins turned the 'Anastasia Pink' mutant white. Moreover, total flavonoids were reduced in both mutants. Multiple flavonoid biosynthetic genes and regulatory genes encoding MYBs and bHLHs transcription factors were differentially expressed in pairwise comparisons of transcriptomes in 'Anastasia Dark Green' or 'Anastasia Pink' and their mutants at different flowering stages. Among these regulatory genes, the expression patterns of CmMYB6 and CmbHLH2 correlated to changes of anthocyanin contents, and down-regulation of CmMYB11 correlated to decreased total flavonoid contents in two mutants. CmMYB11 was shown to directly activate the promoter activities of CmCHS2, CmCHI, CmDFR, CmANS, CmFNS, and CmFLS. Furthermore, overexpression of CmMYB11 increased both flavonols and anthocyanins in tobacco petals. Our work provides new insights into regulatory networks involved in flavonoid biosynthesis and coloration in chrysanthemum.

Novel risk assessment model of food quality and safety considering physical-chemical and pollutant indexes based on coefficient of variance integrating entropy weight.

Food safety is important for sustainable social and economic development and people's health. The traditional single risk assessment model is one-sided to the weight distribution of food safety factors including physical-chemical and pollutant indexes, which cannot comprehensively assess food safety risks. Therefore, a novel food safety risk assessment model combining the coefficient of variation (CV) integrating the entropy weight (EWM) (CV-EWM) is proposed in this paper. The CV and the EWM are used to calculate the objective weight of each index with physical-chemical and pollutant indexes effecting food safety, respectively. Then, the weights determined by the EWM and the CV are coupled by the Lagrange multiplier method. The ratio of the square root of the product of two weights and the weighted sum of the square root of the product are regarded as the combined weight. Thus, the CV-EWM risk assessment model is constructed to comprehensively assess the food safety risk. Moreover, the Spearman rank correlation coefficient method is used to test the compatibility of the risk assessment model. Finally, the proposed risk assessment model is applied to evaluate the quality and safety risk of sterilized milk. By analyzing the attribute weight and comprehensive risk value of physical-chemical and pollutant indexes effecting the sterilized milk quality, the results show that this proposed model can scientifically obtain the weight of physical-chemical and pollutant indexes to objectively and reasonably evaluate the overall risk of food, which has certain practical value for discovering the influencing factors of risk occurrence to risk prevention and control of food quality and safety.

Novel economy and carbon emissions prediction model of different countries or regions in the world for energy optimization using improved residual neural network.

Nowadays, the world has achieved tremendous economic development at the expense of the long-term habitability of the planet. With the rapid economic development, the global greenhouse effect caused by excessive carbon dioxide (CO2) emissions is also accumulating, which generates the negative impact of global warming on nature and human beings. Meanwhile, economy and CO2 emissions prediction methods based on traditional neural networks lead to gradient disappearance or gradient explosion, making the economy and CO2 emissions prediction inaccurate. Therefore, this paper proposes a novel economy and CO2 emissions prediction model based on a residual neural network (RESNET) to optimize and analyze energy structures of different countries or regions in the world. The skip links are used in the inner residual block of the RESNET to alleviate vanishing gradients due to increasing depth in deep neural networks. Consequently, the proposed RESNET can optimize this problem and protect the integrity of information by directly bypassing the input information to the output, which can increase the precision of the prediction model. The needs for natural gas, hydroelectricity, oil, coal, nuclear energy, and renewable energy in 24 different countries or regions from 2009 to 2020 are used as inputs, the CO2 emissions and the gross domestic product (GDP) per capita are respectively used as the undesired output and the desired output of the RESNET to build an economy and CO2 emissions prediction model. The experimental results show that the RESNET has higher correctness and functionality than the traditional convolutional neural network (CNN), the radial basis function (RBF), the extreme learning machine (ELM) and the back propagation (BP). Furthermore, the proposed model provides guidance and development plans for countries or regions with low energy efficiency, which can improve energy efficiency, economic development and reasonably control CO2 emissions.

Whole-transcriptome profiles of Chrysanthemum seticuspe improve genome annotation and shed new light on mRNA-miRNA-lncRNA networks in ray florets and disc florets.

BACKGROUND: Chrysanthemum seticuspe has emerged as a model plant species of cultivated chrysanthemums, especially for studies involving diploid and self-compatible pure lines (Gojo-0). Its genome was sequenced and assembled into chromosomes. However, the genome annotation of C. seticuspe still needs to be improved to elucidate the complex regulatory networks in this species. RESULTS: In addition to the 74,259 mRNAs annotated in the C. seticuspe genome, we identified 18,265 novel mRNAs, 51,425 novel lncRNAs, 501 novel miRNAs and 22,065 novel siRNAs. Two C-class genes and YABBY family genes were highly expressed in disc florets, while B-class genes were highly expressed in ray florets. A WGCNA was performed to identify the hub lncRNAs and mRNAs in ray floret- and disc floret-specific modules, and CDM19, BBX22, HTH, HSP70 and several lncRNAs were identified. ceRNA and lncNAT networks related to flower development were also constructed, and we found a latent functional lncNAT-mRNA combination, LXLOC_026470 and MIF2. CONCLUSIONS: The annotations of mRNAs, lncRNAs and small RNAs in the C. seticuspe genome have been improved. The expression profiles of flower development-related genes, ceRNA networks and lncNAT networks were identified, laying a foundation for elucidating the regulatory mechanisms underlying disc floret and ray floret formation.

Short-Time Wavelet Entropy Integrating Improved LSTM for Fault Diagnosis of Modular Multilevel Converter.

The modular multilevel converter (MMC) is the main part of MMC-based high-voltage direct current (HVDC) system. The MMC bridge arm inductance fault and the submodule IGBT fault have the greatest influence on the transmission quality of transmission systems. Therefore, this article proposes a novel fault diagnosis method based on short-time wavelet entropy integrating the long short-term memory network (LSTM) and the support vector machine (SVM). The proposed short-time wavelet entropy calculation method is used to extract the fault information. First, the optimal short-term wavelet packet calculation period is determined. Moreover, the improved LSTM topology can process the wavelet entropy fault information in the time dimension. Then, the output of the LSTM is set as the input of the SVM to obtain the fault diagnosis result based on the adaptive classification. Finally, through the MMC fault diagnosis experiment of the double-ended MMC-HVDC transmission system, the effectiveness of the proposed method is verified. Compared with the traditional fault diagnosis method, the proposed method has better robustness, adaptability, and accuracy, which can greatly reduce the number of electrical signal samples and realize the fault diagnosis of multiple fault types by collecting a single signal.

An intelligent moving window sparse principal component analysis-based case based reasoning for fault diagnosis: Case of the drilling process.

The drilling process is an important step in petrochemical industries, but the drilling process is risky and costly. In order to improve the safety and cost the impact of faults in the drilling process, this paper proposes intelligent moving window based sparse principal component analysis (MWSPCA) integrating case-based reasoning (CBR) (MWSPCA-CBR) in the fault diagnosis of the drilling process in the petrochemical industry. Through introducing sparsity into the PCA model, the Lasso constraint function of the MWSPCA method is used to optimize the sparse principals. The corresponding T2 and Q statistics calculated by the selected sparse principals decide whether the faults have occurred, and the occurrence time of the anomaly is quickly located based on the MWSPCA method. Then the CBR method is used to analyze the anomaly data to identify the possible fault types, and provide the relational handling methods for real-time monitoring experts. Finally, the MWSPCA method is verified based on the intelligent diagnosis of the Tennessee Eastman (TE) process, reducing false negatives and false positives and improving the accuracy rate and the diagnosis speed. Furthermore, the proposed method is applied to analyze the data of the drilling process. The experimental results demonstrate that the proposed method can effectively diagnosis faults in the drilling process and reduce risks and costs in the petrochemical industry.

Novel variation mode decomposition integrated adaptive sparse principal component analysis and it application in fault diagnosis.

The sparse principal component analysis (SPCA) is widely used in the fault detection for nonlinear complex chemical processes in recent years. However, insufficient data processing, fixed models and fault type single classification cannot be used in the time-varying process. Therefore, a novel adaptive sparse principal component analysis (ASPCA) algorithm fused with improved variation mode decomposition (IVMD) (ASPCA-IVMD) is proposed for fault detection in chemical processes. The bat algorithm is innovatively integrated to optimize the parameters of the variable modulus decomposition. Then the optimized parameters are used for data preprocessing to suppress noise. In addition, based on the traditional SPCA, the threshold calculation is fused to realize the adaptive selection of principal components. After the principal components are determined, T2 and Q statistics are used for fault detection. Finally, the proposed method is verified by the Tennessee Eastman process case. The results demonstrate that the proposed method can select the principal components adaptively according to the data for having the real-time property of chemical process. Meanwhile, compared with traditional methods (principal component analysis, sparse principal component analysis, deep belief network integrating dropout, adaptive unscented Kalman filter integrating radial basis function and sparse deep belief network), the detection rate of the ASPCA-IVMD method is more than 99%, which shows superiority.

CmMYB9a activates floral coloration by positively regulating anthocyanin biosynthesis in chrysanthemum.

KEY MESSAGE: An R2R3-MYB transcription factor, CmMYB9a, activates floral coloration in chrysanthemum by positively regulating CmCHS, CmDFR and CmFNS, but inhibiting the expression of CmFLS. Chrysanthemum is one of the most popular ornamental plants worldwide. Flavonoids, such as anthocyanins, flavones, and flavonols, are important secondary metabolites for coloration and are involved in many biological processes in plants, like petunia, snapdragon, Gerbera hybrida, as well as chrysanthemum. However, the metabolic regulation of flavonoids contributing to chrysanthemum floral coloration remains largely unexplored. Here, an R2R3-MYB transcription factor, CmMYB9a, was found to be involved in flavonoid biosynthesis. Phylogenetic analysis and amino acid sequence analysis suggested that CmMYB9a belonged to subgroup 7. Transient overexpression of CmMYB9a in flowers of chrysanthemum cultivar 'Anastasia Pink' upregulated the anthocyanin-related and flavone-related genes and downregulated CmFLS, which led to the accumulation of anthocyanins and flavones. We further demonstrated that CmMYB9a independently activates the expression of CmCHS, CmDFR and CmFNS, but inhibits the expression of CmFLS. Overexpression of CmMYB9a in tobacco resulted in increased anthocyanins and decreased flavonols in the petals by upregulating NtDFR and downregulating NtFLS. These results suggest that CmMYB9a facilitates metabolic flux into anthocyanin and flavone biosynthesis. Taken together, this study functionally characterizes the role of CmMYB9a in regulating the branched pathways of flavonoids in chrysanthemum flowers.

A novel transcription factor CmMYB012 inhibits flavone and anthocyanin biosynthesis in response to high temperatures in chrysanthemum.

Flavones are among the major colorless pigments synthesized through branches of the flavonoid pathway in plants. However, due to the absence of a gene encoding flavone synthase (FNS) in the model plant Arabidopsis thaliana species, the regulatory mechanism of FNS-catalyzed flavone biosynthesis has rarely been studied in plants. Here, it was found that flavones play a predominant role in the elimination of excess reactive oxygen species (ROS) at high temperatures in colorless plant organs. A novel atypical subgroup 7 (SG7) R2R3-MYB transcription factor, CmMYB012, was found to be induced in response to prolonged high temperatures and to inhibit flavone biosynthesis by directly regulating CmFNS. Moreover, CmMYB012 was also found to inhibit anthocyanin biosynthesis by suppressing the expression of CmCHS, CmDFR, CmANS, and CmUFGT. CmMYB012 overexpression exerted a negative influence on plant fitness and pink flower color formation, while CmMYB012 suppression had the opposite effect in response to high temperatures. Our findings provide new insights into the mechanisms by which high temperatures regulate the metabolism of flavones and anthocyanins to affect plant fitness and flower color formation.

Functional identification of a flavone synthase and a flavonol synthase genes affecting flower color formation in Chrysanthemum morifolium.

Flavonoids confer a wide color range to plants, thus influencing the flower quality and commercial value of various ornamental plants. Flavones and flavonols are colorless pigments that are distinct from the colored anthocyanins. Flavones and flavonols are transformed from flavanones and dihydrokaempferol, which are catalyzed by flavone synthase (FNS) and flavonol synthase (FLS), respectively, and play important roles in regulating plant growth and development, and resistance to various stresses, in addition to coloration. However, few studies have been conducted on CmFNS and CmFLS genes in chrysanthemums. In this study, we isolated and identified CmFNS and CmFLS from Chrysanthemum morifolium. CmFNS and CmFLS were constitutively expressed at different levels in various C. morifolium organs, and in vitro catalytic activity of CmFNS and CmFLS was verified. CmFNS- and CmFLS-overexpressing tobacco plants exhibited phenotypes that accumulated more flavones and flavonols, respectively, but less anthocyanins. Moreover, the transcripts of CmFNS were negatively correlated with flower color, whereas CmFLS presented an opposite trend compared to CmFNS in five flower color cultivars with different anthocyanin levels. These findings suggest that CmFNS and CmFLS act as important regulators of flavone and flavonol biosynthesis, respectively, and dicate flower coloration in chrysanthemums.

Economy and carbon emissions optimization of different countries or areas in the world using an improved Attention mechanism based long short term memory neural network.

The combustion of fossil fuels produces a large amount of carbon dioxide (CO2), which leads to global warming in the world. How to rationally consume fossil energy and control CO2 emissions has become an unavoidable problem for human beings while vigorously developing economy. This paper proposes a novel economy and CO2 emissions prediction model using an improved Attention mechanism based long short term memory (LSTM) neural network (Attention-LSTM) to analyze and optimize the energy consumption structures in different countries or areas. The Attention mechanism can add the weight of different inputs in the previous information or related factors to realize the indirect correlation between output and related inputs of the LSTM. Therefore, the Attention-LSTM can allocate more computing resources to the parts with a higher relevance of correlation in the case of limited computing power. Through inputs with the consumption of oil, natural gas, coal, hydroelectricity and renewable energy, the desirable output with the per capita gross domestic product (GDP) and the undesirable output with CO2 emissions prediction model of different countries and areas is established based on the Attention-LSTM. The experimental results show that compared with the normal LSTM, the back propagation (BP), the radial basis function (RBF) and the extreme learning machine (ELM) neural networks, the Attention-LSTM is more accurate and practical. Meanwhile, the proposed model provides guidance for optimizing energy structures to develop economy and reasonably control CO2 emissions.

Economy and carbon dioxide emissions effects of energy structures in the world: Evidence based on SBM-DEA model.

Nowadays, the increasing global warming phenomenon caused by large carbon dioxide (CO2) emissions has a huge impact on the economic and social sustainable development in the world. And CO2 emissions come mainly from the burning of fossil energy, such as oil, natural gas and coal. Therefore, a novel economy and CO2 emissions evaluation model based on the slacks-based measure integrating the data envelopment analysis (SBM-DEA) is proposed to analyze and optimize energy structures of some countries and regions in the world. The consumption of oil, natural gas and coal are inputs of the proposed method. In addition, per capita gross domestic product (GDP) value is the desirable output and CO2 emission is the undesirable output. Then the economy and CO2 emissions evaluation model of some countries and regions in the world is built. The results show that the overall efficiency of developed countries and regions is higher than that of developing countries. Moreover, due to the optimal configuration of slack variables of inputs and the undesirable output, the efficiency values of some inefficient countries and regions can be improved greatly. Furthermore, whether in 2017 or 2018, the average efficiency values of Europe and Oceania are both relatively high, and these two years average efficiency values of Asia are all the lowest among the five continents.

Carbon emission analysis and evaluation of industrial departments in China: An improved environmental DEA cross model based on information entropy.

Environmental protection and carbon emission reduction play a crucial role in the sustainable development procedure. However, the environmental efficiency analysis and evaluation based on the traditional data envelopment analysis (DEA) cross model is subjective and inaccurate, because all elements in a column or a row of the cross evaluation matrix (CEM) in the traditional DEA cross model are given the same weight. Therefore, this paper proposes an improved environmental DEA cross model based on the information entropy to analyze and evaluate the carbon emission of industrial departments in China. The information entropy is applied to build the entropy distance based on the turbulence of the whole system, and calculate the weights in the CEM of the environmental DEA cross model in a dynamic way. The theoretical results show that the new weight constructed based on the information entropy is unique and optimal globally by using the Monte Carlo simulation. Finally, compared with the traditional environmental DEA and DEA cross model, the improved environmental DEA cross model has a better efficiency discrimination ability based on the data of industrial departments in China. Moreover, the proposed model can obtain the potential of carbon emission reduction of industrial departments to improve the energy efficiency.

Hybrid robust model based on an improved functional link neural network integrating with partial least square (IFLNN-PLS) and its application to predicting key process variables.

In this paper, a hybrid robust model based on an improved functional link neural network integrating with partial least square (IFLNN-PLS) is proposed. Firstly, an improved functional link neural network with small norm of expanded weights and high input-output correlation (SNEWHIOC-FLNN) was proposed for enhancing the generalization performance of FLNN. Unlike the traditional FLNN, the expanded variables of the original inputs are not directly used as the inputs in the proposed SNEWHIOC-FLNN model. The original inputs are attached to some small norm of expanded weights. As a result, the correlation coefficient between some of the expanded variables and the outputs is enhanced. The larger the correlation coefficient is, the more relevant the expanded variables tend to be. In the end, the expanded variables with larger correlation coefficient are selected as the inputs to improve the performance of the traditional FLNN. In order to test the proposed SNEWHIOC-FLNN model, three UCI (University of California, Irvine) regression datasets named Housing, Concrete Compressive Strength (CCS), and Yacht Hydro Dynamics (YHD) are selected. Then a hybrid model based on the improved FLNN integrating with partial least square (IFLNN-PLS) was built. In IFLNN-PLS model, the connection weights are calculated using the partial least square method but not the error back propagation algorithm. Lastly, IFLNN-PLS was developed as an intelligent measurement model for accurately predicting the key variables in the Purified Terephthalic Acid (PTA) process and the High Density Polyethylene (HDPE) process. Simulation results illustrated that the IFLNN-PLS could significant improve the prediction performance.

A robust hybrid model integrating enhanced inputs based extreme learning machine with PLSR (PLSR-EIELM) and its application to intelligent measurement.

In this paper, a robust hybrid model integrating an enhanced inputs based extreme learning machine with the partial least square regression (PLSR-EIELM) was proposed. The proposed PLSR-EIELM model can overcome two main flaws in the extreme learning machine (ELM), i.e. the intractable problem in determining the optimal number of the hidden layer neurons and the over-fitting phenomenon. First, a traditional extreme learning machine (ELM) is selected. Second, a method of randomly assigning is applied to the weights between the input layer and the hidden layer, and then the nonlinear transformation for independent variables can be obtained from the output of the hidden layer neurons. Especially, the original input variables are regarded as enhanced inputs; then the enhanced inputs and the nonlinear transformed variables are tied together as the whole independent variables. In this way, the PLSR can be carried out to identify the PLS components not only from the nonlinear transformed variables but also from the original input variables, which can remove the correlation among the whole independent variables and the expected outputs. Finally, the optimal relationship model of the whole independent variables with the expected outputs can be achieved by using PLSR. Thus, the PLSR-EIELM model is developed. Then the PLSR-EIELM model served as an intelligent measurement tool for the key variables of the Purified Terephthalic Acid (PTA) process and the High Density Polyethylene (HDPE) process. The experimental results show that the predictive accuracy of PLSR-EIELM is stable, which indicate that PLSR-EIELM has good robust character. Moreover, compared with ELM, PLSR, hierarchical ELM (HELM), and PLSR-ELM, PLSR-EIELM can achieve much smaller predicted relative errors in these two applications.