Temporal Attributes Research Articles

Optimization study of pruning strategy based on KNN trajectory similarity query

With the development of GPS positioning technology, a large amount of spatiotemporal trajectory data has been generated. Due to the complex structure of trajectory data, which has irregular spatial shapes and continuous temporal sequence attributes, querying massive trajectory data poses certain challenges. The pruning strategy of existing trajectory similarity query methods is not very effective. Even after pruning operations, there are still a large number of trajectories that need to undergo distance calculations to confirm whether they are similar trajectories. This paper proposes multiple local pruning optimization schemes, which maximally reduce the number of trajectories in the candidate set. Specifically, it starts with region pruning in the index space, eliminating index spaces with distances greater than the maximum similarity distance from the query trajectory. Then, it performs distance pruning between trajectories, removing trajectories that do not meet the distance conditions. Finally, it adds a termination condition: when the distance between the current index space and the query trajectory is greater than the maximum similarity distance and the number of trajectories in the result set is K, the loop is exited, and the query process ends. Tests on real datasets demonstrate that the KTSS method outperforms current algorithms of the same type.

Temporal and spatial evolution simulation and attribution analysis of vegetation photosynthesis over the past 21 years based on satellite SIF data: a case study from Asia.

Photosynthesis in vegetation is one of the key processes in maintaining regional ecological balance and climate stability, and it is of significant importance for understanding the health of regional ecosystems and addressing climate change. Based on 2001-2021 Global OCO-2 Solar-Induced Fluorescence (GOSIF) dataset, this study analyzed spatiotemporal variations in Asian vegetation photosynthesis and its response to climate and human activities. Results show the following: (1) From 2001 to 2021, the overall photosynthetic activity of vegetation in the Asian region has shown an upward trend, exhibiting a stable distribution pattern with higher values in the eastern and southern regions and lower values in the central, western, and northern regions. In specific regions such as the Turgen Plateau in northwestern Kazakhstan, Cambodia, Laos, and northeastern Syria, photosynthesis significantly declined. (2) Meteorological factors influencing photosynthesis exhibit differences based on latitude and vertical zones. In low-latitude regions, temperature is the primary driver, while in mid-latitude areas, solar radiation and precipitation are crucial. High-latitude regions are primarily influenced by temperature, and high-altitude areas depend on precipitation and solar radiation. (3) Human activities (56.44%) have a slightly greater impact on the dynamics of Asian vegetation photosynthesis compared to climate change (43.56%). This research deepens our comprehension of the mechanisms behind the fluctuations in Asian vegetation photosynthesis, offering valuable perspectives for initiatives in environmental conservation, sustainability, and climate research.

Distribution of volatile organic compounds (VOCs) in the urban atmosphere of Hangzhou, East China: Temporal variation, source attribution, and impact on the secondary formations of ozone and aerosol

Distribution of volatile organic compounds (VOCs) in the urban atmosphere of Hangzhou, East China: Temporal variation, source attribution, and impact on the secondary formations of ozone and aerosol

Does strategic coupling of TNCs affect their exit from host regions: Empirical analysis of the exit of Taiwanese enterprises from mainland China.

This study aims to investigate the temporal and spatial attributes of the exit of Taiwanese enterprises from mainland China between 2001 and 2021, by applying enterprise database data. Furthermore, the influence of strategic coupling on Taiwanese enterprises' exit from mainland China was also investigated. The following are the key findings: The spatial distribution pattern of the exit rate of Taiwanese enterprises in mainland China varied at different phases. In contrast, the inland regions of the country's central and western zones, which are characterized by comparatively less developed economies, maintained consistently high exit rates, whereas the eastern coastal region retained a low exit rate. Particularly, the relationship between Taiwanese enterprises and the invested areas changed from Captive coupling to Cooperative coupling and subsequently to Absorptive Coupling. Similarly, the coupling modes significantly influenced the exit of Taiwanese enterprises from mainland China. Moreover, the COVID-19 pandemic has contributed to the backward connection of Taiwanese corporations, which have become more reliant on the mainland China market and local suppliers than earlier. Taiwan-favoring policies and the regional innovation environment have consequently emerged as the primary locational advantages for retaining Taiwanese enterprises in the aftermath of the global financial crisis. Therefore, the aforementioned factors may help to reduce the Taiwanese enterprises' exit from mainland China and possess valuable policy implications for Taiwan investment zones in mainland China.

Study on pedestrian accessibility from urban transportation hubs to tourist destinations: A case of Shanghai Yuyuan station to Yuyuan garden

Public transportation is a crucial means for tourists to visit urban attractions. This study aims to explore pedestrian accessibility from tourist destinations to urban transportation hubs, using the renowned Yuyuan Garden in Shanghai as a case study and employing spatial syntax methodology. By investigating spatial relationships and accessibility levels from the perspectives of depth and choice. The research finds that the main transportation hubs around the Yuyuan Garden area have a limited capacity to attract visitors, and visitors have limited choices when it comes to using public transportation. Additionally, there are barriers from transportation hubs to the entrance of the tourist area, and some segments of accessibility overlap, posing challenges for the operation of the tourist area, especially during specific festivals. The study emphasizes the significance of the straightforward data acquisition method of spatial syntax for further research on transportation network accessibility, as well as the layout of commercial areas, tourist attractions, and historic districts. However, it also highlights the limitations of spatial syntax, including its abstraction, disregard for temporal attributes, and insufficient qualitative analysis. It acknowledges the subjectivity inherent in pedestrian accessibility and model creation.

Emerging Spatio-temporal Hot Spot Analysis of Beijing Subsidence Trend Detection Based on PS-InSAR

Abstract. Scholars have done a lot of research on urban settlement, but it is difficult to give consideration to the temporal and spatial attributes of settlement at the same time in its display and analysis. Most of them focused on the analysis of regional settlement, single point settlement curve and settlement rate map at a certain time, but few combined time and space for collaborative analysis. Therefore, in this paper, 32 scenes Sentinel-1B SAR data are used to obtain settlement data of Beijing via PS-InSAR method. Secondly, combined with the temporal and spatial attributes of settlement results, the subsidence law revealed by using spatio-temporal cube slicing and attribute filtering. Finally, subsidence development trend and the detection of abnormal subsidence are explored by emerging hot spots (ESH) analysis. The experimental results show that the settlement funnel center in Beijing is mainly concentrated near the junction of Chaoyang district and Tongzhou district. The settlement range tends to expand. There are several local continuous subsidence areas in the settlement oscillating area. Spatio-temporal analysis makes the development trend of urban settlement more intuitive. Emerging hotspot analysis combined with Getis-Ord Gi* statistics and Mann-Kendall trend test could more effectively analyze the settlement trend of the study area and detect new potential settlement centers, so that to provide auxiliary decision-making for urban safety early warning and city development.

Landscaping characterization of the campus at the UEMG Ituiutaba, Minas Gerais, Brazil

The purpose of this work was to characterize the landscape of the campus at the University of the Minas Gerais State (in portuguese, Universidade do Estado de Minas Gerais - UEMG), located at Ituiutaba. As for such, the local plants were identified ranging from herbaceous to shrub type, due to them being the most commonly employed to perform alterations for landscape purposes. Subsequently, some areas of the campus were photographed to create a landscape characterization of the scenery in regard to its landscape's composition and vegetation. 102 species of herbaceous, subshrub, and shrub plants were found belonging to 39 families; 38.23% being native and the other 61.77% being non-native (cultivated, naturalized, and exotic). In regard to the landscape’s composition in loco, the principles of message, equilibrium, scale, dominance, harmony, and climax were contemplated. Furthermore, in regard to the guiding principles for the selection of vegetable species, it was observed that aesthetic, functional and temporal attributes were incorporated in all the analyzed areas. In conclusion, the landscape’s composition of the campus at the UEMG Ituiutaba fulfills its aesthetic, functional and ecological roles, however it’s worth highlighting that the adequate handling can be the defining factor in assuring the continuity of these functions.

Towards the systematic reconnaissance of seismic signals from glaciers and ice sheets – Part 2: Unsupervised learning for source process characterization

Abstract. Given the high number and diversity of events in a typical cryoseismic dataset, in particular those recorded on ice sheet margins, it is desirable to use a semi-automated method of grouping similar events for reconnaissance and ongoing analysis. We present a workflow for employing semi-unsupervised cluster analysis to inform investigations of the processes occurring in glaciers and ice sheets. In this demonstration study, we make use of a seismic event catalogue previously compiled for the Whillans Ice Stream, for the 2010–2011 austral summer (outlined in Part 1, Latto et al., 2024). We address the challenges of seismic event analysis for a complex wave field by clustering similar seismic events into groups using characteristic temporal, spectral, and polarization attributes of seismic time series with the k-means++ algorithm. This provides the basis for a reconnaissance analysis of a seismic wave field that contains local events (from the ice stream) set in an ambient wave field that itself contains a diversity of signals (mostly from the Ross Ice Shelf). As one result, we find that two clusters include stick-slip events that diverge in terms of length and initiation locality (i.e., central sticky spot and/or the grounding line). We also identify a swarm of high-frequency signals on 16–17 January 2011 that are potentially associated with a surface melt event from the Ross Ice Shelf. Used together with the event detection presented in Part 1, the semi-automated workflow could readily be generalized to other locations and, as a possible benchmark procedure, could enable the monitoring of remote glaciers over time and comparisons between locations.

Revolutionary Strategy for Depicting Knowledge Graphs with Temporal Attributes

In practical applications, the temporal completeness of knowledge graphs is of great importance. However, previous studies have mostly focused on static knowledge graphs, generally neglecting the dynamic evolutionary properties of facts. Moreover, the unpredictable and limited availability of temporal knowledge graphs, together with the complex temporal dependency patterns, make current models inadequate for effectively describing facts that experience temporal transitions. To better represent the evolution of things over time, we provide a learning technique that uses quaternion rotation to describe temporal knowledge graphs. This technique describes the evolution of entities as a temporal rotation change in quaternion space. Compared to the Ermitian inner product in complex number space, the Hamiltonian product in quaternion space is better at showing how things might be connected. This leads to a learning process that is both more effective and more articulate. Experimental results demonstrate that our learning method significantly outperforms existing methods in capturing the dynamic evolution of temporal knowledge graphs, with improved accuracy and robustness across a range of benchmark datasets.

Proactive Identification of Patients with Diabetes at Risk of Uncontrolled Outcomes during a Diabetes Management Program: Conceptualization and Development Study Using Machine Learning.

The growth in the capabilities of telehealth have made it possible to identify individuals with a higher risk of uncontrolled diabetes and provide them with targeted support and resources to help them manage their condition. Thus, predictive modeling has emerged as a valuable tool for the advancement of diabetes management. This study aimed to conceptualize and develop a novel machine learning (ML) approach to proactively identify participants enrolled in a remote diabetes monitoring program (RDMP) who were at risk of uncontrolled diabetes at 12 months in the program. Registry data from the Livongo for Diabetes RDMP were used to design separate dynamic predictive ML models to predict participant outcomes at each monthly checkpoint of the participants' program journey (month-n models) from the first day of onboarding (month-0 model) up to the 11th month (month-11 model). A participant's program journey began upon onboarding into the RDMP and monitoring their own blood glucose (BG) levels through the RDMP-provided BG meter. Each participant passed through 12 predicative models through their first year enrolled in the RDMP. Four categories of participant attributes (ie, survey data, BG data, medication fills, and health signals) were used for feature construction. The models were trained using the light gradient boosting machine and underwent hyperparameter tuning. The performance of the models was evaluated using standard metrics, including precision, recall, specificity, the area under the curve, the F1-score, and accuracy. The ML models exhibited strong performance, accurately identifying observable at-risk participants, with recall ranging from 70% to 94% and precision from 40% to 88% across the 12-month program journey. Unobservable at-risk participants also showed promising performance, with recall ranging from 61% to 82% and precision from 42% to 61%. Overall, model performance improved as participants progressed through their program journey, demonstrating the importance of engagement data in predicting long-term clinical outcomes. This study explored the Livongo for Diabetes RDMP participants' temporal and static attributes, identification of diabetes management patterns and characteristics, and their relationship to predict diabetes management outcomes. Proactive targeting ML models accurately identified participants at risk of uncontrolled diabetes with a high level of precision that was generalizable through future years within the RDMP. The ability to identify participants who are at risk at various time points throughout the program journey allows for personalized interventions to improve outcomes. This approach offers significant advancements in the feasibility of large-scale implementation in remote monitoring programs and can help prevent uncontrolled glycemic levels and diabetes-related complications. Future research should include the impact of significant changes that can affect a participant's diabetes management.

XWaveNet: Enabling uncertainty quantification in short-term ocean wave height forecasts and extreme event prediction

To aid accurate short-term forecast of wave heights and extreme events prediction from buoy data, a deep learning approach is proposed. Wave heights are forecasted up to 72 h in advance from multivariate meteorological and oceanographic data, followed by quantification of uncertainty in the forecasted values, and estimation of exceedance probabilities for extreme event conditions. Using Monte Carlo dropout technique, network regularization and forecast uncertainty assessment were performed. To forecast wave heights, a stacked long short-term memory (LSTM) model was trained on historical buoy data augmented with positionally encoded features. Per comparative evaluation of different models, across the 72 h forecast horizon, positionally encoded temporal attributes resulted in a mean prediction error and forecast uncertainty of only 3 % and 13.5 %, respectively. Contrarily, without temporal feature augmentation mean error was 5 % and uncertainty, 15 %. Therefore, the former model was ensembled with a Random Forest model for exceedance probability estimation. The hybrid model yielded a 21.4 % better separability between the extreme and normal observations in the test data from a nearby buoy in the northern Gulf of Mexico than individual models. All the four extreme events in the test set were correctly predicted with 97 % mean accuracy. Further evaluation of the deep ensemble model on 5 other spatially diverse buoy datasets from the Gulf of Mexico, Atlantic and Pacific coasts, suggested excellent generalizability for short-term wave forecasts and extreme event prediction, with an average maximum error of just 5.2 % across all the 6 buoy test datasets and the entire forecast horizon.

IFC-GNN: Combining interactions of functional connectivity with multimodal graph neural networks for ASD brain disorder analysis

Many studies now indicate that brain disorders are associated with functional connectivity between brain regions, but the impact of interactions among functional connections on diseases remains to be explored. Moreover, existing models for analyzing the temporal and spatial attributes of fMRI data exhibit limitations in their efficacy. Currently, there is an absence of a comprehensive model capable of simultaneously capturing disease-related interactions within functional connectivity, fully leveraging the temporal and spatial characteristics of fMRI, and achieving superior diagnostic accuracy. To address these gaps, we propose a model to classify brain disorders that employs a novel algorithm and multimodal graph convolutional networks to process the temporal and spatial features of fMRI data separately, along with the demographic information. In the proposed model, a deep feature selection algorithm is employed to discover disease-related biomarkers and evaluate their impact on brain disorders. Remarkably, this approach has led to a classification accuracy of 80.66%, which surpasses the performance of graph neural networks by approximately 10%. Notably, our investigations have uncovered novel biomarkers linked to autism, with our findings corroborated by relevant literature. These achievements underscore the model's potential in revealing critical insights pertinent to autism, thereby facilitating groundbreaking experimental research in the field.

MeMalDet: A memory analysis-based malware detection framework using deep autoencoders and stacked ensemble under temporal evaluations

Malware attacks continue to evolve, making detection challenging for traditional static and dynamic analysis techniques. On the other hand, memory analysis provides valuable behavioral insights, but prior research lacks temporal evaluations which are critical for robust detection of new malware variants over time. This paper presents MeMalDet, a novel memory analysis-based malware detection technique using deep autoencoders and stacked ensemble learning. We introduce an improved dataset with temporal attributes enabling more realistic evaluations of memory-based malware detection techniques under concept drift (temporal data split). MeMalDet extracts optimal features from memory dumps using deep autoencoders in an unsupervised manner, avoiding manual feature engineering. A stacked ensemble of supervised classifiers then performs highly accurate malware detection. Extensive experiments on our improved large-scale public dataset demonstrate MeMalDet’s ability to maintain high performance when detecting obfuscated malware under temporal splits. We achieve up to 98.82% accuracy and 98.72% F1-score in detecting previously unseen advanced obfuscated malware, significantly improving upon state-of-the-art memory analysis-based malware detection techniques. The improved dataset enables temporally robust evaluations, which is a novel contribution. MeMalDet combines the benefits of representation learning and supervised machine learning ensemble classification for effective malware detection over time using memory analysis. This research provides a new capability for identifying evasive modern malware and combating evolving real-world threats.

When grey model meets deep learning: A new hazard classification model

The classification of hazard is critical in industrial informatics, as it enhances early safety alerts, supports decision-making, and facilitates policy assessment. However, previous studies have generally neglected the temporal attributes of hazards, thereby constraining the effectiveness of models. This paper introduces a new model for hazard classification termed DLGM. DLGM represents a deep learning framework, with the structural parameters of grey models to encapsulate the hazard temporal attributes. To better accommodate the fluctuations of hazard series, a new grey model termed FSGM(1,1) equipped with Fourier series is proposed. Moreover, DLGM leverages a novel hierarchical feature fusion neural network (HFFNN) to optimize feature processing. Extensive experiments across three hazard themes involving 18 large-scale industrial processes have demonstrated the competitiveness of DLGM (e.g., it surpasses benchmark models such as Random Forest and BERT by approximately 2% in both accuracy and F1), the suitability of FSGM(1,1) (e.g., its mean absolute percentage error is less than 10% and mean squared error is below 0.02) and the effectiveness of HFFNN (e.g., it enhances the accuracy and F1 of DLGM by about 1%).

S2O: A smart objects orchestrator framework based on the web of things

The Web of Things (WoT) is a new paradigm in which everyday objects are connected to the Internet using popular Web technologies. The smart things are abstracted into RESTful Web services to facilitate their manipulation. The composition of these objects within the same business process creates an automated, time-synchronized routine that can perform even the most complex tasks. BPEL is an orchestration language that defines the process responsible for coordinating the Web services involved. However, this language presents some limitations in this context. BPEL 2.0 does not support RESTful Web services; its specification is incompatible with this architectural style of services. Moreover, its temporal expressivity is insufficient to cover all the constraints that may arise when composing services. This work aims to adapt BPEL to the requirements of the WoT environment, enabling it to create processes that invoke the smart things in precise time intervals. The solution is to exploit one of BPEL's strengths: its extensibility. The BPEL specification is enriched with four activities that reflect the REST uniform interface. They include the necessary attributes to send the request to the target object and receive the response in convened format representation. Also, temporal attributes are added to BPEL elements to schedule their start, end, and duration of execution. The manual addition of these temporal values requires a verification of their accuracy. The BPEL process must be reviewed to ensure its validity before its execution. A temporal Petri Net is proposed to detect any conflicts or inconsistencies between BPEL activities. As a result, associating the formal model with the extension allows BPEL to orchestrate smart things represented by RESTful Web services according to a well-defined temporal scenario. They respect the REST constraints and provide the BPEL activities with temporal attributes for efficient time management. The approach can be applied in all application areas to create temporal scenarios.

Blending Indigenous and western science: Quantifying cultural burning impacts in Karuk Aboriginal Territory.

The combined effects of Indigenous fire stewardship and lightning ignitions shaped historical fire regimes, landscape patterns, and available resources in many ecosystems globally. The resulting fire regimes created complex fire-vegetation dynamics that were further influenced by biophysical setting, disturbance history, and climate. While there is increasing recognition of Indigenous fire stewardship among western scientists and managers, the extent and purpose of cultural burning is generally absent from the landscape-fire modeling literature and our understanding of ecosystem processes and development. In collaboration with the Karuk Tribe Department of Natural Resources, we developed a transdisciplinary Monte Carlo simulation model of cultural ignition location, frequency, and timing to simulate spatially explicit cultural ignitions across a 264,399-ha landscape within Karuk Aboriginal Territory in northern California. Estimates of cultural ignition parameters were developed with Tribal members and knowledge holders using existing interviews, historical maps, ethnographies, recent ecological studies, contemporary maps, and generational knowledge. Spatial and temporal attributes of cultural burning were explicitly tied to the ecology of specific cultural resources, fuel receptivity, seasonal movement patterns, and spiritual practices. Prior to colonization, cultural burning practices were extensive across the study landscape with an estimated 6972 annual ignitions, averaging approximately 6.5 ignitions per Indigenous fire steward per year. The ignition characteristics we document align closely with data on historical fire regimes and vegetation but differ substantially from the location and timing of contemporary ignitions. This work demonstrates the importance of cultural burning for developing and maintaining the ecosystems present at the time of colonization and underscores the need to work collaboratively with Indigenous communities to restore ecocultural processes in these systems.

Cellular traffic forecasting based on inverted transformer for mobile perception dual-level base station sleep control

Due to the extensive implementation of the fifth generation wireless communication networks (5 G), numerous base stations are being strategically deployed in densely inhabited areas to address the escalating need for network traffic. Within wireless cellular networks, over 80% of energy consumption is primarily concentrated on the side of the base station. In comparison to 4 G base stations, the 5 G base stations exhibit notable enhancements in terms of bandwidth, peak rate, and transmission power. Nonetheless, they suffer from limited signal coverage and extensive resource consumption. To address this challenge effectively, the present study introduces a Mobile Perception Dual-Level (MPDL) base station sleep control strategy based on cellular traffic forecasting. The strategy aims to satisfy the demands for reduced power consumption and enhanced service quality by monitoring both the current network traffic of the base station and the user's mobility, consequently placing the base station into two different sleep states. Specifically, we first designed an inverted Transformer (iTransformer) model to accurately forecast cellular traffic. The model is capable of effectively capturing both the spatial and temporal attributes of cellular traffic. It also takes into account the impact of geographical features, such as Points of Interest (POIs) and the quantity of Base Stations (BSs), on the forecasting outcomes. Consequently, it attains precise predictions of the cellular traffic. Based on the forecasting outcomes of cellular traffic, this study presents a mobility perception dual-level sleep strategy. This strategy proposal differentiates sleep into deep sleep and light sleep, while also taking into account the mobility attributes of users. It incorporates considerations for Quality of Service (QoS) and energy consumption. We assess the performance and application impacts of cellular traffic forecasting and base station sleep strategy in real-world datasets. Several experiments and validations have confirmed that the MPDL, as proposed in this paper, effectively decreases power consumption by a range of 22% to 41% when compared to baselines.

Integration of temporal & spatial properties of dynamic functional connectivity based on two-directional two-dimensional principal component analysis for disease analysis.

Dynamic functional connectivity, derived from resting-state functional magnetic resonance imaging (rs-fMRI), has emerged as a crucial instrument for investigating and supporting the diagnosis of neurological disorders. However, prevalent features of dynamic functional connectivity predominantly capture either temporal or spatial properties, such as mean and global efficiency, neglecting the significant information embedded in the fusion of spatial and temporal attributes. In addition, dynamic functional connectivity suffers from the problem of temporal mismatch, i.e., the functional connectivity of different subjects at the same time point cannot be matched. To address these problems, this article introduces a novel feature extraction framework grounded in two-directional two-dimensional principal component analysis. This framework is designed to extract features that integrate both spatial and temporal properties of dynamic functional connectivity. Additionally, we propose to use Fourier transform to extract temporal-invariance properties contained in dynamic functional connectivity. Experimental findings underscore the superior performance of features extracted by this framework in classification experiments compared to features capturing individual properties.

Enhanced multimodal emotion recognition in healthcare analytics: A deep learning based model-level fusion approach

Deep learning techniques have drawn considerable interest in emotion recognition due to recent technological developments in healthcare analytics. Automatic patient emotion recognition can assist healthcare analytics by providing feedback to the stakeholders of competent healthcare about the conditions of the patients and their satisfaction levels. In this paper, we propose a novel model-level fusion technique based on deep learning for enhanced emotion recognition from multimodal signals to monitor patients in connected healthcare. The representative visual features from the video signals are extracted through the Depthwise Separable Convolution Neural Network, and the optimized temporal attributes are derived from the multiple physiological data utilizing Bi-directional Long Short-Term Memory. A soft attention method fused the high multimodal features obtained from the two data modalities to retrieve the most significant features by focusing on emotionally salient parts of the features. We exploited two face detection methods, Histogram of Oriented Gradients and Convolutional Neural Network-based face detector (ResNet-34), to observe the effects of facial features on emotion recognition. Lastly, extensive experimental evaluations have been conducted using the widely used Bio Vid Emo DB multimodal dataset to verify the performance of the proposed architecture. Experimental results show that the developed fusion architecture improved the accuracy of emotion recognition from multimodal signals and outperformed the performance of both state-of-the-art techniques and baseline methods.

Spatiotemporal knowledge graph completion via diachronic and transregional word embedding

Knowledge Graph Completion (KGC) is an essential application in the field of knowledge graphs (KGs) that attempts to fill in the missing information in the process of KG modelling. With the popularity of temporal knowledge graphs (TKGs), a wide range of techniques based on temporal knowledge graph completion (TKGC) have appeared, solving the issue of real-world knowledge with temporal properties. However, there is little study on KGC with spatiotemporal attributes, some real-world data include both spatial and temporal attributes. Effectively handling the completion of missing entities or predicates in spatiotemporal knowledge graphs (STKGs) is an important challenge. Our study fills the gap in knowledge completion techniques in the field of STKG. We present a model for completion based on the well-known tensor factorization canonical polyadic (CP) decomposition. It introduces temporal and spatial attributes into the decomposition vector to achieve entity and link predictions. We name it diachronic and transregional word embedding (DT-WE), which includes two different modules: the embedding framework and the scoring module. Firstly, send the vectors to the embedding framework to get the new vector representation, then, we send it to the scoring module to compute, and finally, the resulting values are added together to compute the prediction probability. We conducted extensive experiments on three real-world STKGs: YAGO10K, Wikidata40K and Opensky. The results indicate that the newly introduced spatiotemporal attributes not only improve accuracy in predicting entities and predicates compared to temporal models but also achieve state-of-the-art performance with lower spatial complexity.