Spatial-Temporal Changes of Soil Organic Carbon During Vegetation Recovery at Ziwuling, China

To probe the processes and mechanisms of soil organic carbon (SOC) changes during forest recovery, a 150-yearchronosequence study on SOC was conducted for various vegetation succession stages at the Ziwuling area, in the centralpart of the Loess Plateau, China. Results showed that during the 150 years of local vegetation rehabilitation SOC increasedsignificantly (P < 0.05) over time in the initial period of 55-59 years, but slightly decreased afterwards. Average SOCdensities for the 0-100 cm layer of farmland, grassland, shrubland and forest were 4.46, 5.05, 9.95, and 7.49 kg C m-3,respectively. The decrease in SOC from 60 to 150 years of abandonment implied that the soil carbon pool was a sink forCO2 before the shrubland stage and became a source in the later period. This change resulted from the spatially variedcomposition and structure of the vegetation. Vegetation recovery had a maximum effect on the surface (0-20 cm) SOCpool. It. was concluded that vegetation recovery on the Loess Plateau could result in significantly increased sequestrationof atmospheric CO2 in soil and vegetation, which was ecologically important for mitigating the increase of atmosphericconcentration of CO2 and for ameliorating the local eco-environment.

Spatial-temporal Pattern and Differences of Land Use Changes in the Three Gorges Reservoir Area of China during 1975-2005

Regional land use changes are an important part of global changes.The research on land use changes in the Three Gorges Reservoir Area of China attracts a lot of attention owing to the Three Gorges Dam building.The Three Gorges Reservoir Area becomes one of the important research areas.This study analyzed the transforming processes and traits of each land use type and the regional differences of land use changes during the past 30 years,summarized the distribution of different land use types in different buffer zones and regresses the equation areas and different buffer distances based on buffer analyses and regression analyses,and then analyzed the transforming rules in different buffer distances,got the optimal influence distances.The research results indicate that,(1) cultivated land lies at the northwest of the reservoir and was decreasing,however,the construction land was increasing,especially the urban construction land,a large number of land was flooded because of the reservoir water level rise;(2) urban area was sprawling quickly in developed and neighboring areas,and a great deal of cultivated land and a considerable amount of grassland were occupied;in the earlier time,rural settlements occupied lots of cultivated land and a sum of forestry land in the later time;(3) the optimum influenced distances for cultivated land and forestry land were 10-35 km,and for urban and rural settlements were in 5-20 km.Overall,this research can reflect the spatial-temporal characteristics of land use changes during the 30 years,and it is helpful for urban planning and land use planning in the reservoir area.

Spatial-temporal changes of tidal flats in the Huanghe River Delta using Landsat TM/ETM+ images

Integrating remote sensing, geographic information system (GIS) and fractal theory, change characteristics of tidal flats and tidal creeks in the Huanghe (Yellow) River Delta over the period of 1986-2001 were discussed. The results show that evolutions of tidal flats throughout the Huanghe River Delta are influenced by various factors, and that progressive succession and regression of tidal flats concur in different coastal segments of the delta. Human activities have played an increasingly important role in the succession process of tidal flats. Due to land reclamation in coastal zones of the delta in the last 15 years, lots of tidal flats were occupied, the artificial coastline migrated seaward (the maximum change rate was 0.8 kmyr-1) and tidal creeks became sparser (the highest decreasing rate of length of tidal creeks was 14.9 kmyr-1). Except for two coastal segments from the Tiaohe Estuary to the 106 Station and from the south of the Huanghe River mouth to the north of the Xiaodao River Estuary, fractal dimension values of tidal creeks in the remaining coastal segments of the delta decreased. In addition, the time dimension, sediment fluxes into the sea, waves and tidal-currents have profound influences on the evolution process of tidal flats. Four types of tidal flats-river-dominated tidal flats, tide-dominated tidal flats, wave-dominated tidal flats and man-dominated tidal flats can be identified. Owing to the intensification of human activities in coastal zones of the delta, man-dominated tidal flats have become the main kind of tidal flats.

Spatial-temporal Changes of Vegetation Cover in Guizhou Province, Southern China

Guizhou Province is an important karst area in the world and a fragile ecological area in China. Ecological risk assessment is very necessary to be conducted in this region. This study investigates different characteristics of the spatial-temporal changes of vegetation cover in Guizhou Province of Southern China using the data set of SPOT VEGETATION(1999–2015) at spatial resolution of 1-km and temporal resolution of 10-day. The coefficient of variation, the Theil-Sen median trend analysis, and the Mann-Kendall test are used to investigate the spatial-temporal change of vegetation cover and its future trend. Results show that: 1) the spatial distribution pattern of vegetation cover in Guizhou Plateau is high in the east whereas low in the west. The average annual normalized difference vegetation index(NDVI) from west to east is higher than that from south to north. 2) Average annual NDVI improved obviously in the past 17 years. The growth rate of average annual NDVI is 0.028/10 yr, which is slower than that of vegetation in the country(0.048/10 yr) from 1998 to 2007. Average annual NDVI in karst area is lower than that in non-karst area. However, the growing rate of average annual NDVI in karst area(0.030/10 yr) is faster than that in non-karst area(0.023/10 yr), indicating that vegetation coverage increases more rapidly in karst area. 3) Vegetation coverage in the study area is stable overall, but fluctuates in the local scales. 4) Vegetation coverage presents a continuous increasing trend. The Hurst exponent of NDVI in different vegetation types has an obvious threshold in various elevations. 5) The proportion of vegetation cover with sustainable increase is higher than that of vegetation cover with sustainable decrease. The improvement in vegetation cover may expand to most parts of the study area.

Tupu methods of spatial-temporal pattern on land use change:a case study in the Yellow River Delta

Comprehensive study on land-use change of spatial pattern and temporal process is the key component in LUCC study nowadays. Based on the theories and methods of Geo-information Tupu (Carto-methodology in Geo-information, CMGI), integration of spatial pattern and temporal processes of land-use change in the Yellow River Delta (YRD) are studied in the paper, which is supported by ERDAS and ARC/INFO software. The main contents include: (1) concept models of Tupu by spatial-temporal integration on land-use change, whose Tupu unit is synthesized by "Spatial·Attribute·Process" features and composed of relatively homogeneous geographical unit and temporal unit; (2) data sources and handling process, where four stages of spatial features in 1956, 1984, 1991, and 1996 are acquired; (3) integration of series of temporal-spatial Tupu, reconstruction series of "Arising" Tupu, spatial-temporal Process Tupu and the spatial temporal Pattern Tupu on land-use change by remap tables; (4) Pattern Tupu analysis on land-use change in YRD during 1956-1996; and (5) spatial difference of the Pattern Tupu analysis by dynamic Tupu units. The various landform units and seven sub-deltas generated by the Yellow River since 1855 are different. The Tupu analysis on land-use in the paper is a promising try on the comprehensive research of "spatial pattern of dynamic process" and "temporal process of spatial pattern" in LUCC research. The Tupu methodology would be a powerful and efficient tool on integrated studies of spatial pattern and temporal process in Geo-science.

Land use change in Bohai Rim: a spatial-temporal analysis

Based on RS and GIS methods, land use information for 1985 and 1995 was acquired from TM images and analyzed. Then on both spatial and temporal aspects, this paper analyzes land use change in three provinces of Hebei, Shandong and Liaoning and two municipalities of Beijing and Tianjin in the Bohai Rim covering the period of 1985 to 1995. The extent, rate, areal difference and trend of various types of land use changes in the region, as well as spatial changes of major types of land use, their distribution characteristics and regional orientation are revealed. The regional characteristics of land use are elaborated, so as to provide effective policy support for sustainable land use in the area around the Bohai Bay.

Spatial-Temporal Pattern and Driving Forces of Land Use Changes in Xiamen

Using Landsat TM data of 1988, 1998 and 2001, the dynamic process of the spatial-temporal characteristics of land use changes during 13 years from 1988 to 2001 in the special economic zone of Xiamen, China was analyzed to improve understanding and to find the driving forces of land use change so that sustainable land utilization could be practiced. During the 13 years cropland decreased remarkably by nearly 11304.95 ha. The areas of rural-urban construction and water body increased by 10 152.24 ha and 848.94 ha, respectively. From 1988 to 2001, 52.5% of the lost cropland was converted into rural-urban industrial land. Rapid urbanization contributed to a great change in the rate of cropland land use during these years. Land-reclamation also contributed to a decrease in water body area as well as marine ecological and environmental destruction. In the study area 1) urbanization and industrialization, 2) infrastructure and agricultural intensification, 3) increased affluence of the farming community, and 4) policy factors have driven the land use changes. Possible sustainable land use measures included construction of a land management system, land planning, development of potential land resources, new technology applications, and marine ecological and environmental protection.

The spatial-temporal changes of the land use/cover in the Dongting Lake area during the last decade

The research on the land use/cover change is one of the frontiers and the hot spots in the global change research. Based on the Chinese resource and environment spatial-temporal database, and using the Landsat TM and ETM data of 1990 and 2000 respectively, we analyzed the spatial-temporal characteristics of land use/cover changes in the Dongting Lake area during the last decade. The result shows that during the last ten years there were three land-use types that had changed remarkably. The cultivated land decreased by 0.57% of the total cultivated land. The built-up land and water area expanded, with an increase of 8.97% and 0.43% respectively. The conversion between land use types mostly happened among these three land-use types, especially frequently between cultivated land and water area. The land-use change speed of land-use type is different. Three cities experienced the greatest degree of land-use change among all the administrative districts, which means that the land use in these cities changed much quickly. The following changed area was the west and south of the Dongting Lake area. The slowest changed area is the north and east area.

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.

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.

Spatial-temporal Pattern and Population Driving Force of Land Use Change in Liupan Mountains Region, Southern Ningxia, China

The Liupan Mountains is located in the southern Ningxia Hui Autonomous Region of China, which forms an important dividing line between landforms and bio-geographic regions. The populated part of the Liupan Mountains region has suffered tremendous ecological damages over time due to population pressure, excessive demand and inappropriate use of agricultural land resources. In this paper, datasets of land use between 1990 and 2000 were obtained from Landsat TM imagery, and then spatial models were used to characterize landscape conditions. Also, the relationship between the population density and land use/cover change (LUCC) was analyzed. Results indicate that cropland, forestland, and urban areas have increased by 44,186ha, 9001ha and 1550ha, respectively while the grassland area has appreciably decreased by 54,025ha in the study period. The decrease in grassland was most notable. Of the grassland lost, 49.4% was converted into cropland. The largest annual land conversion rate in the study area was less than 2%. These changes are attributed to industrial and agricultural development and population growth. To improve the eco-economic conditions in the study region, population control, urbanization and development of an ecological friendly agriculture were suggested.

The Impacts of Louisiana’s Changing Climate on Food Crop Production

While various prior studies have delved into the potential consequences of climate change on crop production in specific areas, notably in southeastern Louisiana, limited investigation has been carried out concerning some crops within the state of Louisiana. Consequently, there exists a dearth of knowledge regarding the specific hurdles and potential benefits confronting agricultural producers in this region. Therefore, the primary aim of this study was to explore and measure the impact of climate change on the yields of corn, rice, soybeans, and cotton in Louisiana, thereby addressing this informational void. The study uses data on average high temperatures and precipitation to assess the impact of climate change on these specific food crops in Louisiana. The researchers used ArcGIS and its symbology tool to create three separate maps depicting the spatial distribution of harvested cropland in Louisiana. The graduated color option was used on each map, which represented the years 2007, 2012, and 2017. Similarly, eight separate maps were created using the graduated color option to visually present the distribution patterns of Louisiana’s corn, cotton, rice, and soybean crops. These maps provided a visual representation of the state’s total crop production between 2007 and 2017. The researchers also created six bar charts to show the distribution of corn, cotton, rice, and soybean production in Louisiana over three time periods: 2007, 2012, and 2017. These charts also included information about the average high temperature and annual precipitation in each parish. The study revealed decreasing trends in Louisiana corn and cotton yields alongside consistent increases in rice and soybean yields, with projections suggesting future temperature rises may negatively impact crop yields, highlighting the need for research into climate-smart agricultural practices to mitigate these effects and safeguard global crop production. Louisiana’s response to climate change in food crop production involves implementing a comprehensive Climate-Resilient Agriculture Program, focusing on developing climate-adaptive crop varieties, sustainable water management, climate-responsive insurance, farmer education, and outreach to safeguard food security, enhance agricultural resilience, and ensure sustainable crop production.

Direct-Seeded Rice: Genetic Improvement of Game-Changing Traits for Better Adaption

The sustainability of rice production continues to be a subject of uncertainty and inquiry attributed to shifts in climatic conditions. In light of the impending climate change crisis and the high labor and water costs accompanying it, direct-seeded rice(DSR) is unquestionably one of the most practical solutions. Despite its resource and climate-friendly advantages, early maturing rice faces weed competitiveness and seedling establishment challenges. Resolving these issues is crucial for promoting its wider adoption among farmers, presenting it as a more effective sustainable rice cultivation method globally. Diverse traditional and contemporary breeding methods are employed to mitigate the limitations of the DSR approach, leveraging advanced techniques such as speed breeding and genome editing. Focusing on key traits like mesocotyl length elongation, early seedling vigor, root system architecture, and weed competitiveness holds promise for transformative improvements in DSR adaptation at a broader scale within farming communities. This review aims to summarize how these features contribute to increased crop production in DSR conditions and explore the research efforts focusing on enhancing DSR adaptation through these traits. Emphasizing the pivotal role of these game-changing traits in DSR adaptation, our analysis sheds light on their potential transformative impact and offers valuable insights for advancing DSR practices.

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 Divergence Characteristics and Driving Factors of Green Economic Efficiency in the Yangtze River Economic Belt of China

The spatial and temporal variation of green economic efficiency and its driving factors are of great significance for the construction of high-efficiency and low-consumption green development model and sustainable socio-economic development.The research focused on the Yangtze River Economic Belt(YREB)and employed the miniumum distance to strong efficient frontier DEA(MinDs)model to measure the green economic efficiency of the municipalities in the region between 2008 and 2020.Then,the spatial autocorrelation model was used to analyze the evolution characteristics of its spatial pattern.Finally,Geodetector was applied to reveal the drivers and their interactions on green economic efficiency.It is found that:1)the overall green economic efficiency of the YREB from 2008 to 2020 shows a W-shaped fluctuating upward trend,green economic efficiency is greater in the downstream and smallest in the upstream;2)the spatial distribution of green economic efficiency shows clustering characteristics,with multi-core clustering based on‘city clusters-central cities'becoming more obvious over time;the High-High agglomeration type is mainly clustered in Jiangsu and Zheji-ang,while the Low-Low agglomeration type is clustered in the western Sichuan Plateau area and southwestern Yunnan;3)from input-output factors,whether it is the YREB as a whole or the upper,middle and lower reaches regions,the economic development level,labor input,and capital investment are the leading factors in the spatial-temporal evolution of green economic efficiency,with the com-prehensive influence of economic development level and pollution index being the most important interactive driving factor;4)from so-cio-economic factors,information technology drivers such as government intervention,transportation accessibility,information infra-structure,and Internet penetration are always high impact influencers and dominant interaction factors for green economic efficiency in the YREB and the three major regions in the upper,middle and lower reaches.Accordingly,the article puts forward relevant policy re-commendations in terms of formulating differentiated green transformation strategies,strengthening network leadership and informa-tion technology construction and coordinating multi-factor integrated development,which could provide useful reference for promoting synergistic green economic efficiency in the YREB.

Biogeochemical and physical properties influencing the nutrient reservoirs of subsurface water in the changing Canada Basin

The Canada Basin is the largest basin in the Arctic Ocean.Its unique physical features have the highest concentration of nutrients being found in the subsurface layer,referred to as the subsurface nutrient maximum layer(SNM).Under climate change in the Arctic,the SNM is an essential material base for primary productivity.However,long-term trends of nutrient variations and dominant factors related to nutrient levels in the SNM are still unclear.In this study,we analyzed the SNM variations and main influencing factors of the Canada Basin based on the Global Ocean Data Analysis Project Version 2 between 1990 and 2015 and the Chinese Arctic Research Expedition between 2010 and 2016.We found that the nutrient concentrations in the SNM were relatively stable for decades[average concentrations of nitrate,phosphate,and silicate were(13.6±2.4)μmol/L,(1.8±0.2)μmol/L,and(31.5±5.7)μmol/L,respectively].Nutrient reservoirs were dominated by physical processes.Inflow and outflow water of the SNM contributed about 60.4%and-50.2%to the nutrient stocks,respectively,while particle deposition and remineralization in the Canada Basin contributed approximately one-third to the nutrient stocks.Nitrogen fixation and denitrification in the Canada Basin had no substantial impact on nutrient stocks.The overall stabilization of the SNM over the past few decades implied that the SNM would not substantially affect short term primary productivity.Understanding the long-term trends and dominant factors of reservoirs in the SNM will provide useful insights into the changing Canada Basin ecosystem.

A distributed modeling approach to water balance implications from changing land cover dynamics in permafrost environments

There is 78%permafrost and seasonal frozen soil in the Yangtze River’s Source Region(SRYR),which is situated in the middle of the Qinghai-Xizang Plateau.Three distinct scenarios were developed in the Soil and Water Assessment Tool(SWAT)to model the effects of land cover change(LCC)on various water balance components.Discharge and percolation of groundwater have decreased by mid-December.This demonstrates the seasonal contributions of subsurface water,which diminish when soil freezes.During winter,when surface water inputs are low,groundwater storage becomes even more critical to ensure water supply due to this periodic trend.An impermeable layer underneath the active layer thickness decreases GWQ and PERC in LCC+permafrost scenario.The water transport and storage phase reached a critical point in August when precipitation,permafrost thawing,and snowmelt caused LATQ to surge.To prevent waterlogging and save water for dry periods,it is necessary to control this peak flow phase.Hydrological processes,permafrost dynamics,and land cover changes in the SRYR are difficult,according to the data.These interactions enhance water circulation throughout the year,recharge of groundwater supplies,surface runoff,and lateral flow.For the region’s water resource management to be effective in sustaining ecohydrology,ensuring appropriate water storage,and alleviating freshwater scarcity,these dynamics must be considered.

Spatial-Temporal Change of Phytoplankton Biomass in the East China Sea with MODIS Data

A ten-year chlorophyll-a concentration dataset from Moderate Resolution Imaging Spectro-radiometer(MODIS) were used to analyze the variation of phytoplankton biomass and its potential relation with climate in the East China Sea. The result indicated that the phytoplankton biomass generally had a regular pattern every year, and phytoplankton bloom mainly occurred between May and July. The highest phytoplankton biomass appeared near the Yangtze River Estuary. The lowest phytoplankton biomass located near the Taiwan Strait. In general, the starting bloom time was earlier in the south than in the north, and the span time of the former was also longer. During the recent ten years, the phytoplankton biomass around the Yangtze River Estuary decreased obviously. The change of phytoplankton biomass was found to be related with the Ni?o3.4 Index. The correlation between the intensity of phytoplankton bloom with the number and square of red tide were 0.63 and 0.74, respectively.

Adaptive spatial-temporal graph attention network for traffic speed prediction

Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.