Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Comprehensive evaluation and spatial-temporal evolution characteristics of urban resilience in Chengdu-Chongqing Economic Circle

To clarify the connotations and extensions of urban resilience,this study focuses on the Chengdu-Chongqing Economic Circle with 16 cities as research subjects.A comprehensive evaluation index system was constructed to measure the resilience of each city from 2003 to 2020.The spatial-temporal evolution characteristics were analyzed using Kernel density estimation,standard deviation ellipse,and spatial Markov chain analysis,and the spatial Tobit model was introduced to discover the influencing factors.The results indicate the following:①Urban resilience in the Chengdu-Chongqing Economic Circle displays an upward trend,with the center of gravity moving to the southwest,and the polarization phenomenon intensifying.②The urban resilience level in a region has certain spatial and geographical dependence,while the probability of urban resilience transfer differs in adjacent cities with different resilience levels.③Urban centrality,economic scale,openness level,and financial development promote urban resilience,whereas government scale significantly inhibits it.Finally,this paper proposes countermeasures and suggestions to improve the urban resilience of the Chengdu-Chongqing Economic Circle.

Spatial-temporal distribution and geochemistry of highly evolved Mesozoic granites in Great Xing’an Range,NE China:Discriminant criteria and geological significance

Highly evolved granite is an important sign of the mature continent crust and closely associated with deposits of rare metals.In this work,the authors undertake systematically zircon U-Pb ages and whole rock elemental data for highly evolved granitic intrusions from the Great Xing’an Range(GXR),NE China,to elucidate their discriminant criteria,spatial-temporal distribution,differentiation and geodynamic mecha-nism.Geochemical data of these highly evolved granites suggest that high w(SiO_(2))(>70%)and differentiation index(DI>88)could be quantified indicators,while strong Eu depletion,high TE_(1,3),lowΣREE and low Zr/Hf,Nb/Ta,K/Rb could only be qualitative indicators.Zircon U-Pb ages suggest that the highly evolved gran-ites in the GXR were mainly formed in Late Mesozoic,which can be divided into two major stages:Late Ju-rassic-early Early Cretaceous(162-136 Ma,peak at 138 Ma),and late Early Cretaceous(136-106 Ma,peak at 126 Ma).The highly evolved granites are mainly distributed in the central-southern GXR,and display a weakly trend of getting younger from northwest to southeast,meanwhile indicating the metallogenic potential of rare metals within the central GXR.The spatial-temporal distribution,combined with regional geological data,indicates the highly evolved Mesozoic granites in the GXR were emplaced in an extensional environ-ment,of which the Late Jurassic-early Early Cretaceous extension was related to the closure of the Mongol-Okhotsk Ocean and roll-back of the Paleo-Pacific Plate,while the late Early Cretaceous extension was mainly related to the roll-back of the Paleo-Pacific Plate.

Spatial-temporal Variation Characteristics of Water Quality in the Lower Reaches of the Nenjiang River

As an important river in the western part of Jilin Province,the lower reach of the Nenjiang River is an important wetland water source conservation area in Jilin Province.Within the watershed,it governs the Momoge Wetland,the Xianghai Wetland,and the Danjiang Wetland in Jilin Province.The main problem in the lower reaches of the Nenjiang River is the uneven distribution of water resources in time and space,and the intensification of land salinization.Zhenlai County and Da an City in the Nenjiang River Basin have sufficient surface water resources,with surface water as the drinking water source.Baicheng City and Tongyu County have scarce surface water resources,and both use groundwater as their domestic water source.The main polluted section in the basin is the Xianghai Reservoir,and the annual water quality evaluation is Class V.However,the water quality of the Tao er River,the main stream of the Nenjiang River,is significantly better than that of the Xianghai Reservoir.In order to better study the water environmental pollution situation in the Nenjiang River basin,monitoring data from five sections of non seasonal rivers in the basin from 2012 to 2021 were selected for studying water quality.This in-depth exploration of the water pollution status and river water quality change trends in the Nenjiang River basin is of great significance for future rural development,agricultural pattern transformation,and the promotion of water ecological civilization construction.

Spatial-temporal difference between nitrate in groundwater and nitrogen in soil based on geostatistical analysis

The study of temporal and spatial variations of nitrate in groundwater under different soil nitrogen environments is helpful to the security of groundwater resources in agricultural areas.In this paper,based on 320 groups of soil and groundwater samples collected at the same time,geostatistical analysis and multiple regression analysis were comprehensively used to conduct the evaluation of nitrogen contents in both groundwater and soil.From May to August,as the nitrification of groundwater is dominant,the average concentration of nitrate nitrogen is 34.80 mg/L;The variation of soil ammonia nitrogen and nitrate nitrogen is moderate from May to July,and the variation coefficient decreased sharply and then increased in August.There is a high correlation between the nitrate nitrogen in groundwater and soil in July,and there is a high correlation between the nitrate nitrogen in groundwater and ammonium nitrogen in soil in August and nitrate nitrogen in soil in July.From May to August,the area of low groundwater nitrate nitrogen in 0-5 mg/L and 5-10 mg/L decreased from 10.97%to 0,and the proportion of high-value area(greater than 70 mg/L)increased from 21.19%to 27.29%.Nitrate nitrogen is the main factor affecting the quality of groundwater.The correlation analysis of nitrate nitrogen in groundwater,nitrate nitrogen in soil and ammonium nitrogen shows that they have a certain period of delay.The areas with high concentration of nitrate in groundwater are mainly concentrated in the western part of the study area,which has a high consistency with the high value areas of soil nitrate distribution from July to August,and a high difference with the spatial position of soil ammonia nitrogen distribution in August.

Wave Energy Resource Availability Assessment in the Philippines Based on 30-Year Hindcast Data

With the goal of evaluating the wave and wave energy conditions in the Philippines,the simulated wave nearshore(SWAN)model was used to estimate the wavefield using 30 years of cross-calibrated multi-platform(CCMP)wind field data(1987-2016).The spatiotemporal patterns of annual and monthly averaged significant wave heights and wave energy in the Philippines were analyzed based on the simulated data.Results showed that they had similar values;in particular,significant wave heights and wave energy were smaller in the south and southwest and higher in the north and northeast.A total of 12 representative points along the Philippine coast were selected to draw wave and wave energy roses.A directional analysis showed that the dominant wave was in the north north-east(NNE),northeast(NE),and east north-east(ENE)directions.Wave energy was mainly distributed in regions with an energy period between 1 and 10 s and significant wave heights between 0 and 4 m.To better utilize wave energy data in the Philippines,this paper studied the available and rich area of wave energy and analyzed the annual and monthly variability index of wave energy in the country.Moreover,the available significant wave heights of wave energy conversion devices(WECs)were set as 0.5-4 m,and the maximum annual average available wave energy occurred in the eastern Philippine Sea area,reaching 13 kW m^(-1).For the safety of WECs,extreme typhoon-induced wave conditions must be considered.Furthermore,the results showed that the maximum significant wave height and mean period over the 50-year return period reached 18 m and 15 s,respectively.

STGSA:A Novel Spatial-Temporal Graph Synchronous Aggregation Model for Traffic Prediction

The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most existing frameworks typically utilize separate modules for spatial and temporal correlations modeling.However,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some steps.Furthermore,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between nodes.To overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies simultaneously.Specifically,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution process.In each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting operation.Meanwhile,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven manner.Then,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global information.It projects the embedding input repeatedly with multiple different channels.Finally,the predicted values are generated by stacking several multi-stream modules.Extensive experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA model significantly outperforms the benchmarks.

Dense Spatial-Temporal Graph Convolutional Network Based on Lightweight OpenPose for Detecting Falls

Fall behavior is closely related to high mortality in the elderly,so fall detection becomes an important and urgent research area.However,the existing fall detection methods are difficult to be applied in daily life due to a large amount of calculation and poor detection accuracy.To solve the above problems,this paper proposes a dense spatial-temporal graph convolutional network based on lightweight OpenPose.Lightweight OpenPose uses MobileNet as a feature extraction network,and the prediction layer uses bottleneck-asymmetric structure,thus reducing the amount of the network.The bottleneck-asymmetrical structure compresses the number of input channels of feature maps by 1×1 convolution and replaces the 7×7 convolution structure with the asymmetric structure of 1×7 convolution,7×1 convolution,and 7×7 convolution in parallel.The spatial-temporal graph convolutional network divides the multi-layer convolution into dense blocks,and the convolutional layers in each dense block are connected,thus improving the feature transitivity,enhancing the network’s ability to extract features,thus improving the detection accuracy.Two representative datasets,Multiple Cameras Fall dataset(MCF),and Nanyang Technological University Red Green Blue+Depth Action Recognition dataset(NTU RGB+D),are selected for our experiments,among which NTU RGB+D has two evaluation benchmarks.The results show that the proposed model is superior to the current fall detection models.The accuracy of this network on the MCF dataset is 96.3%,and the accuracies on the two evaluation benchmarks of the NTU RGB+D dataset are 85.6%and 93.5%,respectively.

Availability of Antimalarial Medicines in Community Pharmacies of Lusaka District, Zambia: Implications on Compliance to Malaria Treatment Guidelines

Background: Malaria remains a major cause of morbidity and mortality in Zambia, affecting all levels of society, with children under the age of five and pregnant women being most at risk of serious illness. The availability of antimalarial medicines is one of the key interventions of malaria management. This study assessed the availability of antimalarial medicines in community pharmacies in Lusaka district, Zambia. Materials and Methods: This was a cross-sectional study that was conducted among 210 community pharmacies from September to November 2022 using a well-structured checklist in selected areas of Lusaka district. The availability was verified by a physical check of the product. The checklist contained the medicines listed both in the guidelines for diagnosis and treatment of malaria in Zambia as well as in the World Health Organization (WHO) malaria treatment guidelines. Results: This study found that all antimalarials listed in the local treatment guidelines for malaria were available in community pharmacies, though with the varying distribution. Of the 210 community pharmacies, 209 (99.5%) had artemether/lumefantrine in stock. The lowest available antimalarial was quinine/clindamycin, which was only available in 3 (1.4%) of the outlets. Conversely, 3 out of 16 (18.8%) antimalarials that were available in community pharmacies were not listed in the local treatment guidelines of malaria in Zambia, despite being listed in the WHO malaria treatment guidelines. This translated into a compliance level of 81.2% based on the local malaria treatment guidelines. Conclusion: This study concluded that antimalarials were available for all categories of malaria management in community pharmacies, though with a varying distribution. The presence of antimalarials not listed in the Zambian treatment guidelines is of public health concern which may have an impact on antimicrobial resistance in the future.

Diverse functions of GmNLA1 members in controlling phosphorus homeostasis highlight coordinate response of soybean to nitrogen and phosphorus availability

Nitrogen(N) and phosphorus(P) are two essential mineral nutrients for plant growth,which are required in relative high amount in plants.Plants have evolved a series of strategies for coordinately acquiring and utilizing N and P.However,physiological and molecular mechanisms underlying of N and P interactions remain largely unclear in soybean(Glycine max).In this study,interactions of N and P were demonstrated in soybean as reflected by significant increases of phosphate(Pi) concentration in both leaves and roots by N deficiency under Pi sufficient conditions.A total of four nitrogen limitation adaptation(NLA),encoding RING-type E3 ubiquitin ligase were subsequently identified in soybean genome.Among them,transcription of Gm NLA1-1 and Gm NLA1-3 was decreased in soybean by N starvation under Pi sufficient conditions,not for Gm NLA1-2.Suppression of all three Gm NLA1 members was able to increase Pi concentration regardless of the P and N availability in the growth medium,but decrease fresh weight under normal conditions in soybean hairy roots.However,comparted to changes in control lines at two N levels,N deficiency only resulted in a relatively higher increase of Pi concentration in Gm NLA1-1 or Gm NLA1-3 suppression lines,strongly indicating that Gm NLA1-1 and Gm NLA1-3 might regulate P homeostasis in soybean response to N starvation.Taken together,our result suggest that redundant and diverse functions present in Gm NLA1 members for soybean coordinate responses to P and N availability,which mediate P homeostasis.

Health Data Availability Protection:Delta-XOR-Relay Data Update in Erasure-Coded Cloud Storage Systems

To achieve the high availability of health data in erasure-coded cloud storage systems,the data update performance in erasure coding should be continuously optimized.However,the data update performance is often bottlenecked by the constrained cross-rack bandwidth.Various techniques have been proposed in the literature to improve network bandwidth efficiency,including delta transmission,relay,and batch update.These techniques were largely proposed individually previously,and in this work,we seek to use them jointly.To mitigate the cross-rack update traffic,we propose DXR-DU which builds on four valuable techniques:(i)delta transmission,(ii)XOR-based data update,(iii)relay,and(iv)batch update.Meanwhile,we offer two selective update approaches:1)data-deltabased update,and 2)parity-delta-based update.The proposed DXR-DU is evaluated via trace-driven local testbed experiments.Comprehensive experiments show that DXR-DU can significantly improve data update throughput while mitigating the cross-rack update traffic.

Study of Optimal Frequency to the Repairable System Due to Failure Finding Interval to Maximize Availability System

This research article is based on a study of optimal frequency to the repairable system due to the failure finding interval to maximize as well as minimize the availability of some components devices. We studied together maintenance and corrective actions that carried out item of failure and periodic failure finding designed to check whether a system is still working. The model is proved as well as useful application in detecting the problem related to finding failure tasks of different scheme devices by maximization. The model formulated and the numerical application to the relevant mathematical model have been discussed to demonstrate the article quality. Therefore based on probability analytic development, the optimal maintenance policy is then obtained as solution of an optimization problem in which the maintenance cost rate is the objective function and the risk of corrective maintenance is the constraint function. Finally, the solution to the optimal device in the considered development model has been well adjusted due to derivation to the experimental observation rather than theory which will be taken into consideration in the next applied practical design research related and the system device provided that, the proactive device agreed with using the exponential distribution to the survive distribution function which can not be considered as valid.

Spatial-temporal variations and driving factors of soil organic carbon in forest ecosystems of Northeast China

Forest soil carbon is a major carbon pool of terrestrial ecosystems,and accurate estimation of soil organic carbon(SOC)stocks in forest ecosystems is rather challenging.This study compared the prediction performance of three empirical model approaches namely,regression kriging(RK),multiple stepwise regression(MSR),random forest(RF),and boosted regression trees(BRT)to predict SOC stocks in Northeast China for 1990 and 2015.Furthermore,the spatial variation of SOC stocks and the main controlling environmental factors during the past 25 years were identified.A total of 82(in 1990)and 157(in 2015)topsoil(0–20 cm)samples with 12 environmental factors(soil property,climate,topography and biology)were selected for model construction.Randomly selected80%of the soil sample data were used to train the models and the other 20%data for model verification using mean absolute error,root mean square error,coefficient of determination and Lin's consistency correlation coefficient indices.We found BRT model as the best prediction model and it could explain 67%and 60%spatial variation of SOC stocks,in 1990,and 2015,respectively.Predicted maps of all models in both periods showed similar spatial distribution characteristics,with the lower SOC in northeast and higher SOC in southwest.Mean annual temperature and elevation were the key environmental factors influencing the spatial variation of SOC stock in both periods.SOC stocks were mainly stored under Cambosols,Gleyosols and Isohumosols,accounting for 95.6%(1990)and 95.9%(2015).Overall,SOC stocks increased by 471 Tg C during the past 25 years.Our study found that the BRT model employing common environmental factors was the most robust method for forest topsoil SOC stocks inventories.The spatial resolution of BRT model enabled us to pinpoint in which areas of Northeast China that new forest tree planting would be most effective for enhancing forest C stocks.Overall,our approach is likely to be useful in forestry management and ecological restoration at and beyond the regional scale.

Research and Practice on High Availability Scheme of Unified Identity Authentication System Based on CAS in Colleges and Universities

Unified identity authentication has become the basic information service provided by colleges and universities for teachers and students. Security, stability, high concurrency and easy maintenance are our requirements for a unified identity authentication system. Based on the practical work experience of China University of Geosciences (Beijing), this paper proposes a high availability scheme of unified identity authentication system based on CAS, which is composed of multiple CAS Servers, Nginx for load balancing, and Redis as a cache database. The scheme has been practiced in China University of Geosciences (Beijing), and the application effect is good, which has practical reference significance for other universities.

Heavy metal availability and impact on activity of soil microorganisms along a Cu/Zn contamination gradient

All the regulations that define a maximum concentration of metals in the receiving soil are based on total soil metal concentration. However, the potential toxicity of a heavy metal in the soil depends on its speciation and availability. We studied the effects of heavy metal speciation and availability on soil microorganism activities along a Cu/Zn contamination gradient. Microbial biomass and enzyme activity of soil contaminated with both Cu and Zn were investigated. The results showed that microbial biomass was negatively affected by the elevated metal levels. The microbial biomass-C （Cmic）/organic C （Corg） ratio was closely correlated to heavy metal stress. There were negative correlations between soil microbial biomass, phosphatase activity and NH4NO3 extractable heavy metals. The soil microorganism activity could be predicted using empirical models with the availability of Cu and Zn. We observed that 72% of the variation in phosphatase activity could be explained by the NH4NO3-extractable and total heavy metal concentration. By considering different monitoring approaches and different viewpoints, this set of methods applied in this study seemed sensitive to site differences and contributed to a better understanding of the effects of heavy metals on the size and activity of microorganisms in soils. The data presented demonstrate the relationship between heavy metals availability and heavy metal toxicity to soil microorganism along a contamination gradient.

Spatial-temporal Patterns and Driving Forces of Water Retention Service in China

Overwhelming water-deficiency conditions and an unbalanced water supply and demand have been major concerns of both the Chinese government and the general public during recent decades. Studying the spatial-temporal patterns and impact factors that influence water retention in China is important to enhance the management of water resources in China and other similar countries. We employed a revised Integrated Valuation of Ecosystem Services and Tradeoffs(InVEST) model and regression analyses to investigate the water retention service in China. The results showed that the southeastern China generally performed much better than Northwest China in terms of the spatial distribution of water retention. In general, the efficacy of the water retention service in China increased from 2000 to 2014; although some areas still had a downward trend. Water retention service increased significantly(P < 0.05) in aggregate in the Qinghai-Tibet Plateau, and the Da Hinggan Mountains and Xiao Hinggan Mountains. However, the service in southwestern China showed a decreasing trend(P < 0.05), which would have significant negative impact on the downstream population. This study also showed that in China the changes in water retention service were primarily due to climate change(which could explain 83.49% of the total variance), with anthropogenic impact as a secondary influence(likewise the ecological programs and socioeconomic development could explain 9.47% and 1.06%, respectively). Moreover, the identification of water retention importance indicated that important areas conservation and selection based on downstream beneficiaries is vital for optimization protection of ecosystem services, and has practical significance for natural resources and ecosystem management.

THE AVAILABILITY OF DISSOLVED ORGANIC PHOSPHORUS COMPOUNDS TO MARINE PHYTOPLANKTON

The availability of three dissolved organic phosphorus （DOP） compounds as nutrient sources for experimentalcultare of three algae was studied. Results indicated that these compounds could be utilized byalgae, and that dissolved inorganic phosphorus （DIP） was first to be uptaken when various forms ofphosphorus （DIP and DOP） co-existed. Dicrateria zhanjiangensis’ uptake of sodium glycerophosphatewas faster than that of D-ribose-5-phosphate. The increase of sodium glycerphosphate had little effecton the maximum uptake rate(Vmax) of Chlorella sp., but increased the semisaturation constant（Ks） remarkably;the photosynthesis rates（PR） of Dicrateria zhanjiangensis and Chlorella sp. were rarely affected byusing various forms of phosphorus in the culture experiments. The possible DOP pathways utilizedby algae are discussed.

Phenotypic plasticity in response to soil moisture availability in the clonal plant Eremosparton songoricum (Litv.) Vass.

Eremosparton songoricum （Litv.） Vass is a dwarf clonal shrubby legume developed on the windward slopes of mobile or semi-fixed sand dunes of Central Asia. It is assumed that E. songoricum must possess a high degree of phenotypic plasticity for such a heterogeneous habitat. The variations of E. songoricum plants growing in two typical microhabitats （the upper slope and the lower slope of semi-mobile dune） were investigated. The morphological characteristics and the biomass allocation patterns were measured and compared at the clonal fragment level. Compared with the clonal fragment on the lower slope of dune, the clonal fragment on the upper slope of the dune （a） declined in total biomass and ramet height, （b） increased the length of rhizomes and the number of roots, （c） increased the degree of asym- metry, and （d） heightened allocation to the belowground biomass. Our results confirmed the hypothesis of high phenotypic adjustment capacity of E. songoricum to habitat moisture availability. Phenotypic plasticity of E. songoricum contributed to reduce the damage risk, led to an environmentally induced specialization in function of resources exploitation, resulted in its persistence in heterogeneous environments and was adaptive in sand dune environment.

Research on Spatial-Temporal Characteristics and Driving Factor of Agricultural Carbon Emissions in China

Macroscopic grasp of agricultural carbon emissions status, spatial-temporal characteristics as well as driving factors are the basic premise in further research on China’s agricultural carbon emissions. Based on 23 kinds of major carbon emission sources including agricultural materials inputs, paddy ifeld, soil and livestock breeding, this paper ifrstly calculated agricultural carbon emissions from 1995 to 2010, as well as 31 provinces and cities in 2010 in China. We then made a decomposed analysis to the driving factors of carbon emissions with logarithmic mean Divisia index （LMDI） model. The results show：（1） The amount of agricultural carbon emissions is 291.1691 million t in 2010. Compared with 249.5239 million t in 1995, it increased by 16.69%, in which, agricultural materials inputs, paddy ifeld, soil, enteric fermentation, and manure management accounted for 33.59, 22.03, 7.46, 17.53 and 19.39%of total agricultural carbon emissions, respectively. Although the amount exist ups and downs, it shows an overall trend of cyclical rise; （2） There is an obvious difference among regions：the amount of agricultural carbon emissions from top ten zones account for 56.68%, while 9.84%from last 10 zones. The traditional agricultural provinces, especially the major crop production areas are the main source regions. Based on the differences of carbon emission rations, 31 provinces and cities are divided into ifve types, namely agricultural materials dominant type, paddy ifeld dominant type, enteric fermentation dominant type, composite factors dominant type and balanced type. The agricultural carbon emissions intensity in west of China is the highest, followed by the central region, and the east zone is the lowest; （3） Compared with 1995, efifciency, labor and structure factors cut down carbon emissions by 65.78, 27.51 and 3.19%, respectively;while economy factor increase carbon emissions by 113.16%.

Rhizosphere soil bacterial community composition in soybean genotypes and feedback to soil P availability

Soil with low phosphorus (P) availability and organic matter contents exists in large area of southwest of China, but some soybean genotypes still show well adaptations to this low yield farmland. However, to date, the underlying mechanisms of how soybean regulates soil P availability still remains unclear, like microbe-induced changes. The objective of the present study was to compare the differences of rhizosphere bacterial community composition between E311 and E109 in P-sufficiency (10.2 mg kg^-1) and P-insufficiency (5.5 mg kg^-1), respectively, which then feedback to soil P availability. In P-sufficiency, significant differences of the bacterial community composition were observed, with fast-growth bacterial phylum Proteobacteria, genus Dechloromonas, Pseudomonas, Massilia, and Propionibacterium that showed greater relative abundances in E311 compared to E109, while in P-insufficiency were not. A similar result was obtained that E311 and E109 were clustered together in P-insufficiency rather than in P-sufficiency by using principal component analysis and hierarchical clustering analysis. The quadratic relationships between bacterial diversity and soil P availability in rhizosphere were analyzed, confirming that bacterial diversity enhanced the soil P availability. Moreover, the high abundance of Pseudomonas and Massilia in the rhizosphere of E311 might increased the P availability. In the present study, the soybean E311 showed capability of shaping rhizosphere bacterial diversity, and subsequently, increasing soil P availability. This study provided a strategy for rhizosphere management through soybean genotype selection and breeding to increase P use efficiency, or upgrade middle or low yield farmland.