不同长径比的具有固定宽度金纳米棒的合成

金纳米棒在光学、电学、信息学和生物医学等领域具有广泛的应用。然而,一些具有特殊要求的金纳米棒还不能通过常规的方法制备。在本研究中,我们创新地将十二醇(LA)分子引入到传统种子生长方法中,成功实现了具有固定宽度的不同长径比(AR)金纳米棒(FW-Au NR)的按需制备。此外,通过合理地选择相应的反应条件(如氯金酸和硝酸银的浓度),可以在130–38.4,109–26.4和16–46 nm范围之间分别调节FW^(23)-Au NRs,FW^(14)-Au NRs和FW^(6.5)-Au NRs (右上角的标注数字表示金纳米棒的宽度)的长度。即,可在一个较大的长度范围内调节具有固定宽度的金纳米棒的长径比。并且,在合适浓度的十二醇,0.24–0.30 mmol·L^(-1)范围内调节硝酸银浓度,可以使这些金纳米棒的宽度固定在6.5–23 nm之间。另外,实现FW-Au NRs制备的关键是银离子和十二醇分子对分布在金种子晶面上的CTA-Br-Ag^(+)化合物的密度的协同影响。

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning method.We demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model structure.However,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial obstacle.This issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data security.To address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

Four-dimensional flow magnetic resonance imaging for noninvasive diagnosis of clinically significant portal hypertension and high-risk gastroesophageal varices in patients with cirrhosis

Introduction:Noninvasive diagnoses of clinically significant portal hypertension(CSPH)and high-risk gastroesophageal varices are clinically relevant but challenging.Four-dimensional(4D)flow magnetic resonance imaging(MRI)provides comprehensive flow information and is a promising alternative.This study evaluated the efficacy of 4D flow MRI as a noninvasive method for diagnosing CSPH and high-risk varices in patients with liver cirrhosis.Methods:This prospective study enrolled consecutive patients diagnosed with liver cirrhosis at a tertiary referral center between October 2020 and March 2021.Each participant underwent abdominal 4D flow MRI.Hemodynamic parameters within the portal vein,including the average and peak flow velocities,normalized flow volume(Q_(normal)),and regurgitant fraction(R%),were extracted and compared between healthy individuals and patients with CSPH and between participants with high-and low-risk varices.Subsequently,these parameters were incorporated into a logistic regression(LR)model refined using L1 regularization and validated using five-fold cross-validation.The diagnostic efficacy was evaluated using receiver operating characteristic(ROC)curves.Results:Eighty-two participants were enrolled(71 patients diagnosed with liver cirrhosis and 11 healthy individuals serving as controls).Among hemodynamic parameters,patients with CSPH exhibited a notable increase in Q_(normal)of 0.66±0.19 ml*m^(2)/[cycle*kg](P=0.001)and an R%of 1.98(2.05)(P=0.002).Similarly,patients with high-risk varices showed a higher Q_(normal)of 0.61±0.15 ml*m^(2)/[cycle*kg](P<0.001)and R%of 1.88(2.81)(P=0.006).ROC analysis revealed an area under the curve(AUC)for Q_(normal)of 0.93 and 0.91 for R%for diagnosing CSPH,while the LR model showcased a superior AUC of 0.95.For high-risk varices,Q_(normal)and R%showed AUC values of 0.75 and 0.70,respectively,whereas the LR model showed a higher AUC of 0.84.Conclusion:As a noninvasive imaging modality,4D flow MRI exhibits considerable potential for the diagnosis of CSPH and high-risk gastroesophageal varices;thus,it may minimize the reliance on invasive procedures in patients with cirrhosis.

Targeted doping induces interfacial orientation for constructing surface-functionalized Schottky junctions to coordinate redox reactions in water electrolysis

Tuning the surface properties of catalysts is an effective method for accelerating water electrolysis.Herein,we propose a directional doping and interfacial coupling strategy to design two surface-functionalized Schottky junction catalysts for coordinating the hydrogen evolution reaction(HER)and oxygen evolution reaction(OER).Directional doping with B/S atoms endows amphiphilic g-C_(3)N_(4)with significant n-/p-type semiconductor properties.Further coupling with Fe_(3)C modulates the energy band levels of B-C_(3)N_(4)and S-C_(3)N_(4),thus resulting in functionalized Schottky junction catalysts with specific surface-adsorption properties.The space-charge region generated by the dual modulation induces a local“OH-and Ht-enriched”environment,thus selectively promoting the kinetic behavior of the OER/HER.Impressively,the designed B-C_(3)N_(4)@Fe_(3)C||S-C_(3)N_(4)@Fe_(3)C pair requires only a low voltage of 1.52 V to achieve efficient water electrolysis at 10 mA cm^(-2).This work highlights the potential of functionalized Schottky junction catalysts for coordinating redox reactions in water electrolysis,thereby resolving the trade-off between catalytic activity and stability.

金融科技对商业银行成长性的影响研究

本文以2011-2020年38家上市商业银行作为研究样本,分析金融科技对商业银行成长性的影响效应及其路径。研究表明,金融科技显著推动了商业银行的成长。在此基础上,本文分析了银行负债结构的中介效应,发现金融科技可以通过改变银行负债结构促进商业银行成长性。进一步的异质性分析表明,中小型商业银行的成长性受金融科技的影响更为明显。据此,本文在金融科技与商业银行融合发展、商业银行转型升级以及金融科技监管的角度提出相应的政策建议。

毛细管微流控芯片器件研究进展

毛细管微流控芯片是微流控芯片领域中重要的一部分,因其具有制备难度低、材料成本低、化学性能优良以及设计灵活的独特优势而得到了广泛的应用与研究。文中对毛细管微流控芯片的基本工作原理与制作方法进行了详细叙述,重点综述了近年来毛细管微流控芯片在液滴生成、纤维纺丝等领域中的研究进展与应用,最后对目前面临的问题进行了探讨,并展望了该技术未来在标准化、高通量及灵活性等方面应用的发展方向。

TiO_2 nanocrystals/graphene hybrids with enhanced Li-ion storage performance

TiO2 nanocrystals/graphene hybrids（TiO2-G） with ultrafine TiO2 nanocrystals（7 nm in size） conformally coated on ultrathin graphene nanosheets（ 2 layers thick） were successfully prepared via a facile one-pot solvothermal route under mediated conditions.With the feature of large surface area,abundant mesopores and high thermal stability,the TiOi-G nanohybrids exhibited large reversible Li-ion storage capacity with excellent cycling stability（629 mAh·g-1 after 400 cycles at a current of 60 mA·g-1） and good rate capability（184 mAh·g-1 at a current density of 3 A·g-1） due to the synergetic effects and strong interactions between the components,showing great promise in applications for advanced energy storage devices.

Synergistic impact of cocatalysts and hole scavenger for promoted photocatalytic H2 evolution in mesoporous TiO2–NiSx hybrid

Photocatalytic solar energy conversion to hydrogen is sustainable and attractive for addressing the global energy and environmental issue. Herein, a novel photocatalytic system (NiS/Ni3S4 cocatalysts modified mesoporous TiO2) with superior photocatalytic hydrogen evolution capability through the synergistic impact of NiS/Ni3S4 (NiSx) cocatalyst and efficient hole scavenger has been demonstrated. The photocatalytic hydrogen evolution of TiO2-NiSx hybrids with the different content of NiSx and upon different organic hole scavengers was both investigated. The hybrid of TiO2 decorated with 3%(mole ratio of Ni^2+) NiSx cocatalyst in methanol solution showed the optimal photocatalytic hydrogen evolution rate of 981.59 μmol h^-1 g^-1 which was about 20 times higher than that of bare mesoporous TiO2. Our results suggested that the boosted hydrogen production performance is attributed to both the improved photoinduced electrons migration between NiS and Ni3S4 in cocatalyst and the high hole captured efficiency by hole scavengers of methanol.

The mechanism of slope instability due to rainfall-induced structural decay of earthquake-damaged loess

Natural loess slopes are characterized by a strong geological structure,which is an important factor in maintaining slope stability.The magnitude and duration of the earthquake may disturb the soil structure at different levels degrees,locally changing the arrangement between soil particles.The process of rainfall humidification weakens the cementation between soil particles,and the disturbance and humidification change the structural state of the soil,which in turn causes sliding of the slope along with the decay of soil mechanical properties.As slope instability is often the result of a series of post-earthquake ripple effects,it is of great scientific significance to study the mechanism of slope instability due to the structural decay of earthquake-damaged loess exacerbated by rainfall.In this paper,the impact of structural decay of loess on slope stability is simulated by GEOSTUDIO software under three conditions:pre-earthquake rainfall,post-earthquake rainfall and earthquake,taking the landslide in Buzi Village,Min County,Gansu Province as an example.The comparative analysis of the calculation results shows that the structural properties of the slope without earthquake disturbance are influenced by infil-tration amount.When it is fully saturated,the structural properties are similar to those of saturated soil,and the safety factor is reduced by 12.9%.In addition,the earthquake intensity and duration have different degrees of structural damage to the soil.When the structure is fully damaged,it is similar to that of remodelled soil,and the safety factor is reduced by 45.84%.Notably,the process of the earthquake and the following humidification generates the most serious damage to the loess structure,with a reduction in the safety factor of up to 56.15%.The quantitative analysis above obviously illustrates that the post-earthquake rainfall causes the most severe damage to structural loess slopes,and the resulting landslide hazard should not be underestimated.

Landscape of cell heterogeneity and evolutionary trajectory in ulcerative colitis-associated colon cancer revealed by single-cell RNA sequencing

Objective:The goal of this study was to get preliminary insight on the intra-tumor heterogeneity in colitisassociated cancer(CAC)and to reveal a potential evolutionary trajectory from ulcerative colitis(UC)to CAC at the single-cell level.Methods:Fresh samples of tumor tissues and adjacent UC tissues from a CAC patient with pT3N1M0 stage cancer were examined by single-cell RNA sequencing(scRNA-seq).Data from The Cancer Genome Atlas(TCGA)and The Human Protein Atlas were used to confirm the different expression levels in normal and tumor tissues and to determine their relationships with patient prognosis.Results:Ultimately,4,777 single-cell transcriptomes(1,220 genes per cell)were examined,of which 2,250(47%)and 2,527(53%)originated from tumor and adjacent UC tissues,respectively.We defined the composition of cancer-associated stromal cells and identified six cell clusters,including myeloid,T and B cells,fibroblasts,endothelial and epithelial cells.Notable pathways and transcription factors involved in these cell clusters were analyzed and described.Moreover,the precise cellular composition and developmental trajectory from UC to UCassociated colon cancer were graphed,and it was predicted that CD74,CLCA1,and DPEP1 played a potential role in disease progression.Conclusions:scRNA-seq technology revealed intra-tumor cell heterogeneity in UC-associated colon cancer,and might provide a promising direction to identify novel potential therapeutic targets in the evolution from UC to CAC.

Effects of pituitary-specific overexpression of FSHα/β on reproductive traits in transgenic boars

Background： Follicle-stimulating hormone（FSH） is a gonadotropin synthesized and secreted by the pituitary gland.FSH stimulates follicle development and maturation in females. It also plays an important role in spermatogenesis in males, including humans and mice. However, the effects of FSH on male pigs are largely unknown. In this study,we generated transgenic pigs to investigate the effects of FSHα/β overexpression on reproductive traits in boars.Results： After five transgenic F0 founders were crossed with wide-type pigs, 193 F_1 animals were obtained. Of these,96 were confirmed as transgenic. FSHα and FSHβ m RNAs were detected only in pituitary tissue. Transgenic boars exhibited significantly higher levels of FSHα and FSHβ m RNA, serum FSH, and serum testosterone, compared to ful-sib non-transgenic boars. Significant increases in testis weight, vas deferens diameter, seminiferous tubule diameter,and the number of Leydig cel s were observed, suggesting that the exogenous FSHα/β affects reproductive traits. Final y,transgenic and non-transgenic boars had similar growth performance and biochemical profiles.Conclusions： Pituitary-specific overexpression of FSHα/β genes is likely to impact reproductive traits positively, as indicated by enhancements in serum testosterone level, testis weight, the development of vas deferens, seminiferous tubules, and Leydig cells in transgenic boars. A high level of serum FSH induces secretion of serum testosterone,possibly by boosting the number of Leydig cells, which presumably increases the libido and the frequency of sexual activity in transgenic boars. Our study provides a preliminary foundation for the genetic improvement of reproductive traits in male pigs.

Effects of arbuscular mycorrhizal fungi and plant growth-promoting rhizobacteria on growth and reactive oxygen metabolism of tomato fruits under low saline conditions

Land salinization is a major form of land degradation,which is not conducive to the growth and quality of fruits and vegetables.Plant salt tolerance can be enhanced by arbuscular mycorrhizal fungi(AMF)or plant growth-promoting rhizobacteria(PGPR).This study examined the effects of inoculation with PGPR singly or in combination with AMF,on the growth and quality of tomato fruits under low saline conditions.Tomatoes were cultivated in a greenhouse with sterilized soil,inoculated with PGPR,AMF,or co-inoculated with PGPR and AMF,and NaCl solution(1%)was added to the soil.The results indicated that AMF+PGPR decreased the roots and shoot biomass accumulation,and increased the number and fresh biomass in tomato fruits to a certain extent compared with non-inoculated plants.PGPR and AMF mediated the level of reactive oxygen and lipid peroxidation,the accumulation of antioxidants,and the activity of antioxidant enzymes,including proanthocyanidins,flavonoids,ascorbic acid,superoxide dismutase,peroxidase,and total antioxidant capacity.Furthermore,PGPR,AMF,and PGPR+AMF improved the overall osmotic adjustments and accumulation of soluble sugars and soluble proteins.Therefore,the AMF-Funneliformis mosseae and PGPR-Bacillus subtilis can potentially alleviate the adverse effects of salt stress and be applied as a biofertilizer in agricultural practice.

Sub-Regional Infrared-Visible Image Fusion Using Multi-Scale Transformation

Infrared-visible image fusion plays an important role in multi-source data fusion,which has the advantage of integrating useful information from multi-source sensors.However,there are still challenges in target enhancement and visual improvement.To deal with these problems,a sub-regional infrared-visible image fusion method(SRF)is proposed.First,morphology and threshold segmentation is applied to extract targets interested in infrared images.Second,the infrared back-ground is reconstructed based on extracted targets and the visible image.Finally,target and back-ground regions are fused using a multi-scale transform.Experimental results are obtained using public data for comparison and evaluation,which demonstrate that the proposed SRF has poten-tial benefits over other methods.

Metabolic diversity and seasonal variation of soil microbial communities in natural forested wetlands

This study explores the effects of vegetation and season on soil microorganisms and enzymatic activity of different wetlands in a temperate climate.Microbial carbon metabolism diversity was assessed using community-level physiological profiles(CLPP)with 31 different carbon substrates.CLPP indicated that significant interactions occur during carbon substrate metabolism of the microorganisms.Furthermore,the different types of vegetation present in the wetland ecosystem combined with the seasonal effects to influence microbial carbon metabolism and enzymatic activity.The most significant differences occurred to carbohydrates,carboxylic acids,and amino acids.The Mantel test confirmed positive correlations between soil enzymatic activities and microbial carbon metabolism.Soil microorganisms in Betula ovalifolia and Carex schmidtii wetlands used carbon substrates more efficiently in summer than those in other forested wetlands during other periods.Enzymatic activities also showed a similar trend as microbial carbon metabolism.The results demonstrate that microbial carbon metabolism patterns can be used as biological indicators in wetland ecological alterations due to vegetation type or to seasonal factors.

Season-dependence of soil extracellular enzyme activities in a Pinus koraiensis forest on Changbai Mountain

Changbai Mountain,central in the distribution of Pinus koraiensis,supports a virgin Korean pine forest with vertical gradient distribution.Soil extracellular enzyme activity(EEA) and enzyme stoichiometry(ES) are reliable indicators of the energy and nutrients utilized by microbial communities and of soil nutrient changes.We measured four representative soil EEAs(sucrase,cellulase,urease,acid phosphatase) at two soil layers(A:0-5 cm and B:5-10 cm)beneath Korean pine forest at five elevations on Changbai Mountain during growing season.The vertical and seasonal variations of EEAs were analyzed by soil enzyme stoichiometry to quantify the role of soil microorganism in the nutrient cycling process.The activities of four soil extracellular enzymes and the ratios of enzyme activity to soil microbial biomass carbon(EA/SMBC) did not vary with elevation.The first partition point of multiple regression trees was in September,and the second branch was split by elevation.Seasonal change had more influence on soil enzyme activity(A layer:75.6%;B layer:71.3%) than did change in elevation(A layer:7.8%;B layer:7.5%).Over one entire growing season,both vector length and vector angle were unchanged by elevation,but varied significantly by month.Among the soil physicochemical factors,available phosphorus and pH were the main factors affecting the four soil EE As.The ratio of basal area of the coniferous tree to broad-leaved tree species(S_(con)/S_(br)),soil microbial biomass carbon(MBC) and nitrogen(MBN) influenced the four soil EE As.The results of vector analysis revealed that C and N sources were generally sufficient,but P was limiting(vector angle> 45°).The vector angle for September was significantly higher than for other months.This result verified that phosphorus was the limiting factor affecting soil microorganism function in nutrient metabolism and cycling.Soil enzyme stoichiometry proved to be an efficient index for quantifying soil microorganismmediated nutrient cycling in the Korean pine ecosystem.

Arsenic removal from acidic industrial wastewater by ultrasonic activated phosphorus pentasulfide

Arsenic is one of the main harmful elements in industrial wastewater.How to remove arsenic has always been one of the research hotspots in academic circles.In the process of arsenic removal by traditional sulfuration,the use of traditional sulfurizing agent will introduce new metal cations,which will affect the recycling of acid.In this study,phosphorus pentasulfide (P_(2)S_(5)) was used as sulfurizing agent,which hydrolyzed to produce H_(3)PO_(4) and H_(2)S without introducing new metal cations.The effect of ultrasound on arsenic removal by P_(2)S_(5) was studied.Under the action of ultrasound,the utilization of P_(2)S_(5) was improved and the reaction time was shortened.The effects of S/As molar ratio and reaction time on arsenic removal rate were investigated under ultrasonic conditions.Ultrasonic enhanced heat and mass transfer so that the arsenic removal rate of 94.5%could be achieved under the conditions of S/As molar ratio of 2.1:1 and reaction time of 20 min.In the first 60 min,under the same S/As molar ratio and reaction time,the ultrasonic hydrolysis efficiency of P_(2)S_(5) was higher.This is because P_(2)S_(5) forms ([(P_(2)S_(4))])^(2+)under the ultrasonic action,and the structure is damaged,which is easier to be hydrolyzed.In addition,the precipitation after arsenic removal was characterized and analyzed by X-ray diffraction,scanning electron microscope-energy dispersive spectrometer,X-ray fluorescence spectrometer and X-ray photoelectron spectroscopy.Our research avoids the introduction of metal cations in the arsenic removal process,and shortens the reaction time.

Topology and Semantic Information Fusion Classification Network Based on Hyperspectral Images of Chinese Herbs

Most methods for classifying hyperspectral data only consider the local spatial relation-ship among samples,ignoring the important non-local topological relationship.However,the non-local topological relationship is better at representing the structure of hyperspectral data.This paper proposes a deep learning model called Topology and semantic information fusion classification network(TSFnet)that incorporates a topology structure and semantic information transmis-sion network to accurately classify traditional Chinese medicine in hyperspectral images.TSFnet uses a convolutional neural network(CNN)to extract features and a graph convolution network(GCN)to capture potential topological relationships among different types of Chinese herbal medicines.The results show that TSFnet outperforms other state-of-the-art deep learning classification algorithms in two different scenarios of herbal medicine datasets.Additionally,the proposed TSFnet model is lightweight and can be easily deployed for mobile herbal medicine classification.

Transcriptomic and metabolomic analysis of the effects of Zhenwu decoction on kidney yang deficiency pattern in chronic kidney disease

Objective:To explore the kidney yang deficiency pattern(KYDP)in a chronic kidney disease(CKD)rat model and the mechanisms underlying the effects of Zhenwu decoction(ZWD)by conducting tran-scriptomic and metabolomic analyses.Methods:Adriamycin(ADR)combined with hydrocortisone(HC)was used to induce CKD with KYDP in rats.ADR was injected into the tail vein twice.HC was injected intramuscularly for 8 weeks.ZWD was administered by gavage for 8 weeks.The general condition was observed,24-h urine protein was detected,serum corticosterone,triiodothyronine,thyroxine,TSH,testosterone,cAMP,and cGMP levels were determined,and pathological analysis was conducted.Transcriptomic and metabolomic analyses were conducted to screen differentially expressed genes(DEGs),differentially expressed metabolites(DEMs),and differentially expressed pathways(DEPs).The core DEMs and DEGs were input to Metab-oanalyst 5.0 to identify the pathways affected by ZWD.Results:In the HC group,KYDP symptoms were observed.Compared with control group,the levels of 24-h urine protein,TSH,and cGMP significantly increased(all P<0.01),and corticosterone,triiodothyronine,thyroxine,and cAMP significantly decreased(all P<0.01)in the HC group.After ZWD intervention,the levels of above-mentioned indicators could be reversed to some extent.Pathological analysis in the HC group revealed kidney lesions.DEGs in the ZWD group were mainly associated with pathways such as nucleotide synthesis and endocrine pathways.In the ZWD group,differences in biosynthesis of unsat-urated fatty acids and butanoate metabolism were observed.The following pathways were significantly affected by ZWD:arachidonic acid metabolism,valine,leucine,and isoleucine biosynthesis,linoleic acid metabolism,and alpha-linolenic acid metabolism.Conclusion:ZWD can be used to treat KYDP in CKD through regulating arachidonic acid metabolism,valine,leucine,and isoleucine biosynthesis,linoleic acid metabolism,and alpha-linolenic acid metabolism.

Genotype Screening of Recipient Resources with High Regeneration and Transformation Efficiency in Chrysanthemum

Genetic transformation is one of the key steps in the molecular breeding of chrysanthemum,which relies on an optimal regeneration and transformation system.However,the regeneration system of different chrysanthemum cultivars varies,and the regeneration time of most cultivars is long.To screen cultivars with highly efficient regeneration,leaves and shoot tip thin cell layers(tTCL)from eight chrysanthemum cultivars with different flower colors and flower types were cultured on Murashige and Skoog media(MS)supplemented with 1.0-5.0 mg L^(−1)6-benzylaminopurine(6-BA)and 0.1-1.0 mg L^(−1)α-naphthaleneacetic(NAA).The results showed that the most efficient regeneration media were MS+6-BA 1.0 mg L^(−1)+NAA 0.5 mg L^(−1)for leaf explants and MS+6-BA 5.0 mg L^(−1)+NAA 0.1 mg L^(−1)for tTCL explants.Subsequently,another 13 chrysanthemum cultivars were screened by using the media,and finally,three cultivars with high regeneration efficiency were obtained from 21 cultivars.Among these,C1 had the highest regeneration efficiency:the regeneration rate of leaf explants reached 80.0%after 42 days of culture,and the regeneration rate of tTCL explants reached 100%after 31 days of culture.Furthermore,we also established the transformation system for C1 as follows:preculturing for one day,infecting with Agrobacterium suspension(OD_(600)=0.6)for 10 min,and cultivating in the regeneration medium with 350 mg L^(−1)carbenicillin and 10 mg L^(−1)kanamycin,thus ultimately achieving a transformation rate of 4.0%.In this study,a new chrysanthemum cultivar with an efficient regeneration and transformation system was screened,which is beneficial to enrich the flower color of chrysanthemum transgenic plant recipients and to the functional research of flower color or type-related genes.

Nitrogen Content Inversion of Corn Leaf Data Based on Deep Neural Network Model

To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention mechanism was applied to make the network pay more attention to effective features,thereby improving the operating efficiency.By introducing an improved activation function,the data correlation was reduced based on increasing the operation rate,and the problem of over-fitting was alleviated.By introducing simulated annealing,the network chose the optimal learning rate by itself,which avoided falling into the local optimum to the greatest extent.To evaluate the performance of the SA-DNN,the coefficient of determination(R^(2)),root mean square error(RMSE),and other metrics were used to evaluate the model.The results show that the performance of the SA-DNN is significantly better than other traditional methods.