Spatio-temporal Data Model Research Articles

Combining residual convolutional LSTM with attention mechanisms for spatiotemporal forest cover prediction

Understanding spatiotemporal variations in forest cover is crucial for effective forest resource management. However, existing models often lack accuracy in simultaneously capturing temporal continuity and spatial correlation. To address this challenge, we developed ResConvLSTM-Att, a novel hybrid model integrating residual neural networks, Convolutional Long Short-Term Memory (ConvLSTM) networks, and attention mechanisms. We evaluated ResConvLSTM-Att against four deep learning models: LSTM, combined convolutional neural network and LSTM (CNN-LSTM), ConvLSTM, and ResConvLSTM for spatiotemporal prediction of forest cover in Tasmania, Australia. ResConvLSTM-Att achieved outstanding prediction performance, with an average root mean square error (RMSE) of 6.9% coverage and an impressive average coefficient of determination of 0.965. Compared with LSTM, CNN-LSTM, ConvLSTM, and ResConvLSTM, ResConvLSTM-Att achieved RMSE reductions of 31.2%, 43.0%, 10.1%, and 6.5%, respectively. Additionally, we quantified the impacts of explanatory variables on forest cover dynamics. Our work demonstrated the effectiveness of ResConvLSTM-Att in spatiotemporal data modelling and prediction.

A Study on a Spatiotemporal Entity-Based Event Data Model

An event is an important medium for recording, expressing, and understanding the real world. Additionally, a data model can provide a digital and structured description method for the real world. Therefore, studying event data models is highly important for describing the real world. By analyzing the representational categories of the existing event data models, the representation of existing event models was found to have different emphases and not be sufficiently balanced, and the universality and comprehensiveness need to be improved. Therefore, based on the advantages of the ontological event model in expressing semantic information and the advantages of the object-event-based spatiotemporal data model in expressing entity multidimensional characteristics and dynamic processes, a spatiotemporal entity-based event data model and the modeling method were designed to provide model support for event organization and processing. Additionally, the Long March and its important battles were selected as case studies to validate the proposed model. The validation shows that the proposed model performs well in terms of event dynamics, hierarchical structure, and complex interrelationships.

The Impact of Educational Informatics on School Management Decision-Making in the Context of Big Data

In the domain of private education, particularly vocational education, school management encounters a complex and variable environment with diverse demands. As the advancement of educational informatics progresses, schools have accumulated a substantial amount of data, including student learning behavior, teaching data, and classroom utilization statistics. However, the efficient utilization of these data for scientific management decisions to enhance the quality of education and resource efficiency presents an urgent challenge. The study of the impacts of educational informatics on school management decision-making is of significant importance. It aids administrators in comprehensively understanding and analyzing the allocation and usage of educational resources, thereby enhancing management efficiency and teaching quality and further promoting the development of educational informatics. Despite some progress in data analysis and decision-making methods within educational informatics, deficiencies remain. Traditional methods often overlook comprehensive considerations of spatiotemporal data, failing to accurately reflect the dynamic changes in educational resources. Existing decision-making methods, predominantly based on single-agent models, lack studies on multi-agent collaborative decision-making, resulting in suboptimal decision outcomes. This study comprises three main components: first, the data modeling of educational informatics based on a spatiotemporal data model; second, an intelligent decision-making framework for school management under a reinforcement learning mechanism; and third, the implementation of an intelligent school management decision-making method based on multi-agent reinforcement learning. Through these investigations, the scientific nature and efficiency of school management are enhanced, providing new ideas and methods for management decision-making in other educational domains.

Dynamic Gaussian process regression for spatio-temporal data based on local clustering

This paper introduces techniques in Gaussian process regression model for spatio-temporal data collected from complex systems. This study focuses on extracting local structures and then constructing surrogate models based on Gaussian process assumptions. The proposed Dynamic Gaussian Process Regression (DGPR) consists of a sequence of local surrogate models related to each other. In DGPR, the time-based spatial clustering is carried out to divide the systems into sub-spatio-temporal parts whose interior has similar variation patterns, where the temporal information is used as the prior information for training the spatial-surrogate model. The DGPR is robust and especially suitable for the loosely coupled model structure, also allowing for parallel computation. The numerical results of the test function show the effectiveness of DGPR. Furthermore, the shock tube problem is successfully approximated under different phenomenon complexity.

Modeling Spatiotemporal Heterogeneity of Customer Preferences With Small-Scale Aggregated Data: A Spatial Panel Modeling Approach

Abstract Customer preferences are found to evolve over time and correlate with geographical locations. Studying the spatiotemporal heterogeneity of customer preferences is crucial to engineering design as it provides a dynamic perspective for understanding the trend of customer preferences. However, existing choice models for demand modeling do not take the spatiotemporal heterogeneity of customer preferences into consideration. Learning-based spatiotemporal data modeling methods usually require large-scale datasets for model training, which are not applicable to small aggregated data, such as the sale records of a product in several regions and years. To fill this research gap, we propose a spatial panel modeling approach to investigate the spatiotemporal heterogeneity of customer preferences. Product and regional attributes varying in time are included as model inputs to support demand forecasting in engineering design. With case studies using the dataset of small SUVs and compact sedans in China's automotive market, we demonstrate that the spatial panel modeling approach outperforms other statistical spatiotemporal data models and non-parametric regression methods in goodness of fit and prediction accuracy. We also illustrate a potential design application of the proposed approach in a portfolio optimization of two vehicles from the same producer. While the spatial panel modeling approach exists in econometrics, applying this approach to support engineering decisions by considering spatiotemporal heterogeneity and introducing engineering attributes in demand forecasting is the contribution of this work. Our paper is focused on presenting the approach rather than the results per se.

A Review of Bayesian Spatiotemporal Models in Spatial Epidemiology

Spatial epidemiology investigates the patterns and determinants of health outcomes over both space and time. Within this field, Bayesian spatiotemporal models have gained popularity due to their capacity to incorporate spatial and temporal dependencies, uncertainties, and intricate interactions. However, the complexity of modelling and computations associated with Bayesian spatiotemporal models vary across different diseases. Presently, there is a limited comprehensive overview of Bayesian spatiotemporal models and their applications in epidemiology. This article aims to address this gap through a thorough review. The review commences by delving into the historical development of Bayesian spatiotemporal models concerning disease mapping, prediction, and regression analysis. Subsequently, the article compares these models in terms of spatiotemporal data distribution, general spatiotemporal data models, environmental covariates, parameter estimation methods, and model fitting standards. Following this, essential preparatory processes are outlined, encompassing data acquisition, data preprocessing, and available statistical software. The article further categorizes and summarizes the application of Bayesian spatiotemporal models in spatial epidemiology. Lastly, a critical examination of the advantages and disadvantages of these models, along with considerations for their application, is provided. This comprehensive review aims to enhance comprehension of the dynamic spatiotemporal distribution and prediction of epidemics. By facilitating effective disease scrutiny, especially in the context of the global COVID-19 pandemic, the review holds significant academic merit and practical value. It also aims to contribute to the development of improved ecological and epidemiological prevention and control strategies.

A zero-inflated model for spatiotemporal count data with extra zeros: application to 1950–2015 tornado data in Kansas

A zero-inflated model for spatiotemporal count data with extra zeros: application to 1950–2015 tornado data in Kansas

AugGKG: a grid-augmented geographic knowledge graph representation and spatio-temporal query model

ABSTRACTAs an emerging knowledge representation model in the domain of knowledge graphs, geographic knowledge graph can take full advantage of semantic, spatial and temporal information to facilitate answering spatio-temporal questions and completing relations. However, the representation of geographic knowledge graphs still has issues such as the difficulty of unified heterogeneous spatio-temporal data modelling, weak ability to answer spatio-temporal queries for dynamic multiobjective problems, and low efficiency of graph querying. This paper presents a grid-augmented geographic knowledge graph (AugGKG) based on the GeoSOT global subdivision grid model and time slice subgraph architecture. AugGKG discretely normalizes the spatio-temporal data of the graph, which involves five types of nodes and two types of relations. By using the geo-hidden layer of the graph and geocoding algebraic operations, the AugGKG can quickly answer complex multiobjective spatio-temporal queries and complete implicit spatio-temporal relations. Compared with existing geographic knowledge graphs (YAGO, GeoKG and GEKG), the comparative experiments verified the obvious advantages of AugGKG in terms of uniformity of accuracy, completeness, and efficiency. Hence, AugGKG is expected to be regarded as an innovative and robust geographic knowledge graph that can perform fast computation and relation completion for complex spatio-temporal queries in future geospatial question answering applications.

Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysis.

Devising and analysing learning models for spatiotemporal network data is of importance for tasks including forecasting, anomaly detection, and multi-agent coordination, among others. Graph Convolutional Neural Networks (GCNNs) are an established approach to learn from time-invariant network data. The graph convolution operation offers a principled approach to aggregate multi-resolution information in each layer and offers some degree of mathematical analysis by exploring tools from graph signal processing. This analysis provides insights on the equivariance properties of GCNNs; spectral behaviour of the learned filters; and the stability to perturbations in the graph topology, which arises because of support perturbations or uncertainties. However, extending the convolution-principled learning and respective analysis to the spatiotemporal domain is challenging because spatiotemporal data have more intrinsic dependencies. Hence, a higher flexibility to capture jointly the spatial and the temporal dependencies is required to learn meaningful higher-order representations. Here, we leverage product graphs to represent the spatiotemporal dependencies in the data and introduce Graph-Time Convolutional Neural Networks (GTCNNs) as a principled architecture to aid learning. The proposed approach can work with any type of product graph and we also introduce a parametric product graph to learn also the spatiotemporal coupling. The convolution principle further allows a similar mathematical tractability as for GCNNs. In particular, the stability result shows GTCNNs are stable to spatial perturbations but there is an implicit trade-off between discriminability and robustness; i.e., the more complex the model, the less stable. Extensive numerical results on benchmark datasets corroborate our findings and show the GTCNN compares favourably with state-of-the-art solutions. We anticipate the GTCNN to be a starting point for more sophisticated models that achieve good performance but are also fundamentally grounded.

Estimation and variable selection for high-dimensional spatial dynamic panel data models

Spatiotemporal modeling of networks is of great practical importance, with modern applications in epidemiology and social network analysis. Despite rapid methodological advances, how to effectively and efficiently estimate the parameters of spatial dynamic panel models remains a challenging problem. To tackle this problem, we construct consistent complex least-squares estimators by the eigendecomposition of a spatial weight matrix method originally proposed for undirected networks. We no longer require all eigenvalues and eigenvectors to be real, which is a remarkable achievement as it implies that the proposed method is now applicable to spatiotemporal data modeling of directed networks. Under mild, interpretable conditions, we show that the proposed parameter estimators are consistent and asymptotically normally distributed. We also present a complex orthogonal greedy algorithm for variable selection and rigorously investigate its convergence properties. Moreover, we incorporate fixed effects into the spatial dynamic panel models and provide a model transformation so that the proposed method can also be applied to the transformed model. Extensive simulation studies and data examples demonstrate the effectiveness of the proposed method.

Review of Sujit Sahu’s “Bayesian modeling of spatio-temporal data with R”

Review of Sujit Sahu’s “Bayesian modeling of spatio-temporal data with R”

Graph Regression Model for Spatial and Temporal Environmental Data-Case of Carbon Dioxide Emissions in the United States.

We develop a new model for spatio-temporal data. More specifically, a graph penalty function is incorporated in the cost function in order to estimate the unknown parameters of a spatio-temporal mixed-effect model based on a generalized linear model. This model allows for more flexible and general regression relationships than classical linear ones through the use of generalized linear models (GLMs) and also captures the inherent structural dependencies or relationships of the data through this regularization based on the graph Laplacian. We use a publicly available dataset from the National Centers for Environmental Information (NCEI) in the United States of America and perform statistical inferences of future CO2 emissions in 59 counties. We empirically show how the proposed method outperforms widely used methods, such as the ordinary least squares (OLS) and ridge regression for this challenging problem.

Dynamic ICAR Spatiotemporal Factor Models

We propose a novel class of dynamic factor models for spatiotemporal areal data. This novel class of models assumes that the spatiotemporal process may be represented by some few latent factors that evolve through time according to dynamic linear models. As the dimension of the vector of latent factors is typically much smaller than the number of subregions, our proposed class of models may achieve substantial dimension reduction. At each time point, the vector of observations is linearly related to the vector of latent factors through a matrix of factor loadings. Each column of this matrix may be seen as a vectorized map of factor loadings relating one latent factor to the vector of observations. Thus, to account for spatial dependence, we assume that each column of the matrix of factor loadings follows an intrinsic conditional autoregressive (ICAR) process. Hence, we call our class of models the Dynamic ICAR Spatiotemporal Factor Models (DIFM). We develop a Gibbs sampler for exploration of the posterior distribution. In addition, we develop model selection through a Laplace-Metropolis estimator of the predictive density. We present two case studies. The first case study, which is for simulated data, demonstrates that our DIFMs are identifiable and that our proposed inferential procedure works well at recovering the underlying data generating process. Finally, the second case study demonstrates the utility and flexibility of our DIFM framework with an application to the drug overdose epidemic in the United States from 2015 to 2021.

Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach

Traffic speed is central to characterizing the fluidity of the road network. Many transportation applications rely on it, such as real-time navigation, dynamic route planning, and congestion management. Rapid advances in sensing and communication techniques make traffic speed detection easier than ever. However, due to sparse deployment of static sensors or low penetration of mobile sensors, speeds detected are incomplete and far from network-wide use. In addition, sensors are prone to error or missing data due to various kinds of reasons, speeds from these sensors can become highly noisy. These drawbacks call for effective techniques to recover credible estimates from the incomplete data. In this work, we first identify the issue as a spatiotemporal kriging problem and propose a Laplacian enhanced low-rank tensor completion (LETC) framework featuring both low-rankness and multi-dimensional correlations for large-scale traffic speed kriging under limited observations. To be specific, three types of speed correlation including temporal continuity, temporal periodicity, and spatial proximity are carefully chosen and simultaneously modeled by three different forms of graph Laplacian, named temporal graph Fourier transform, generalized temporal consistency regularization, and diffusion graph regularization. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging. By performing experiments on two public million-level traffic speed datasets, we finally draw the conclusion and find our proposed LETC achieves the state-of-the-art kriging performance even under low observation rates, while at the same time saving more than half computing time compared with baseline methods. Some insights into spatiotemporal traffic data modeling and kriging at the network level are provided as well.

GIScience can facilitate the development of solar cities for energy transition

The energy transition is increasingly being discussed and implemented to cope with the growing environmental crisis. However, great challenges remain for effectively harvesting and utilizing solar energy in cities related to time and location-dependant supply and demand, which needs more accurate forecasting- and an in-depth understanding of the electricity production and dynamic balancing of the flexible energy supplies concerning the electricity market. To tackle this problem, this article discusses the development of solar cities over the past few decades and proposes a refined and enriched concept of a sustainable solar city with six integrated modules, namely, land surface solar irradiation, three-dimensional (3D) urban surfaces, spatiotemporal solar distribution on 3D urban surfaces, solar photovoltaic (PV) planning, solar PV penetration into different urban systems, and the consequent socio-economic and environmental impacts. In this context, Geographical Information Science (GIScience) demonstrates its potent capability in building the conceptualized solar city with a dynamic balance between power supply and demand over time and space, which includes the production of multi-sourced spatiotemporal big data, the development of spatiotemporal data modelling, analysing and optimization, and geo-visualization. To facilitate the development of such a solar city, this article from the GIScience perspective discusses the achievements and challenges of (i) the development of spatiotemporal big data used for solar farming, (ii) the estimation of solar PV potential on 3D urban surfaces, (iii) the penetration of distributed PV systems in digital cities that contains the effects of urban morphology on solar accessibility, optimization of PV systems for dynamic balancing between supply and demand, and PV penetration represented by the solar charging of urban mobility, and (iv) the interaction between PV systems and urban thermal environment. We suggest that GIScience is the foundation, while further development of GIS models is required to achieve the proposed sustainable solar city.

Diffusion equations with Markovian switching: Well-posedness, numerical generation and parameter inference

Complex systems in real world often experience abrupt changes or jumps that cannot be accurately captured by traditional partial differential equation modeling methods. However, the Markov switching model can effectively describe these abrupt system changes. To address this issue, it is essential to consider adopting the Markov switching model. In this paper, we propose a novel diffusion equation model with Markovian switching to represent the state jump phenomena of complex systems. We then establish the well-posedness property of this model and provide a numerical method with non-uniform grids to accurately simulate the solution of this mixture model with time-varying parameters. Moreover, a discrete sparse Bayesian learning algorithm are presented to estimate the diffusion equation’s parameters from spatiotemporal data with noise. Finally, we conduct several numerical simulation experiments to validate the effectiveness and precision of the proposed method. The results demonstrate that the Markov switching model is more adaptable than the traditional models for spatiotemporal data and can more accurately simulate the state jump phenomena of real-world systems.

Exploring Daily Activity Pattern Using Spatio-Temporal Statistics with R for Predicting Trip Production

Spatio-temporal data modelling is one of the methods in data analysis that uses space (spatial) and time (temporal) approaches. This study used Spatio-temporal statistical modelling to observe the daily activity patterns of people. Spatio-temporal modelling selected for support activity-based transportation demand. This research identifies community mobility patterns that will provide trip production data for transportation demand prediction. Using Spatio-temporal statistical modelling benefit this study because statistical this model can make model components in a physical system appearing to be random. Even if they are not, the models are helpful as they have accurate and precise predictions. In this study, descriptive analysis was used. Incorporating statistical distributions into the model is a natural way to solve the problem. This research collects daily activity data from 400 respondents recorded every 15 minutes. From this data, a pattern of respondents’ daily activities was formed, which was analyzed using R. Software R also visualizes data on daily activities of the community in Spatio-temporal modelling. This research aims to depict the daily activity patterns to predict trip production. This research found three clusters of trip production patterns with specific groups member and specific patterns between workdays and holidays.

On Semiparametrically Dynamic Functional-Coefficient Autoregressive Spatio-Temporal Models with Irregular Location Wide Nonstationarity

Nonlinear dynamic modeling of spatio-temporal data is often a challenge, especially due to irregularly observed locations and location-wide nonstationarity. In this article we propose a semiparametric family of Dynamic Functional-coefficient Autoregressive Spatio-Temporal (DyFAST) models to address the difficulties. We specify the autoregressive smoothing coefficients depending dynamically on both a concerned regime and location so that the models can characterize not only the dynamic regime-switching nature but also the location-wide nonstationarity in real data. Different smoothing schemes are then proposed to model the dynamic neighboring-time interaction effects with irregular locations incorporated by (spatial) weight matrices. The first scheme popular in econometrics supposes that the weight matrix is pre-specified. We show that locally optimal bandwidths by a greedy idea popular in machine learning should be cautiously applied. Moreover, many weight matrices can be generated differently by data location features. Model selection is popular, but may suffer from loss of different candidate features. Our second scheme is thus to suggest a weight matrix fusion to let data combine or select the candidates with estimation done simultaneously. Both theoretical properties and Monte Carlo simulations are investigated. The empirical application to an EU energy market dataset further demonstrates the usefulness of our DyFAST models. Supplementary materials for this article are available online.

Spatio-Temporal Semantic Data Model for Precision Agriculture IoT Networks

In crop and livestock management within the framework of precision agriculture, scenarios full of sensors and devices are deployed, involving the generation of a large volume of data. Some solutions require rapid data exchange for action or anomaly detection. However, the administration of this large amount of data, which in turn evolves over time, is highly complicated. Management systems add long-time delays to the spatio-temporal data injection and gathering. This paper proposes a novel spatio-temporal semantic data model for agriculture. To validate the model, data from real livestock and crop scenarios, retrieved from the AFarCloud smart farming platform, are modeled according to the proposal. Time-series Database (TSDB) engine InfluxDB is used to evaluate the model against data management. In addition, an architecture for the management of spatio-temporal semantic agricultural data in real-time is proposed. This architecture results in the DAM&DQ system responsible for data management as semantic middleware on the AFarCloud platform. The approach of this proposal is in line with the EU data-driven strategy.

Spatiotemporal Database Schema for Data Driven Applications in Smart Agriculture

Background: Data driven sustainable agriculture involves the collection, storage, processing, and analysis of enormous spatiotemporal data related to crop production processes, systems, infrastructure, and environment. Literature survey on smart agriculture research projects indicates that there is a need for improving handling of spatiotemporal data. There are gaps in handling spatial and temporal variability of parameters, division of crop field into management zones to reduce the variability for optimizing application of inputs such as fertilizers, water or pesticides. These gaps are to be addressed at design level of spatiotemporal database for smart agriculture. Objective: To engineer a spatiotemporal database schema that can be used for data driven sustainable agriculture. Methods: The methodology involves spatiotemporal data representation and modeling, Object oriented analysis and design of the database and Verification of the database using life cycle model and algorithmic steps. Findings: The resulting database is capable to store spatial and temporal variability of soil, plant and water parameters as well as handle spatial split, spatial merge, geometry and location changes of spatiotemporal objects. Novelty: Novel Use cases in smart agriculture along with spatiotemporal attributes are identified so that efficient applications can be realized. Adaption of the spatiotemporal database schema for Smart Irrigation System and its implementation methodology are presented. Keywords: Spatiotemporal Database Design; Data-Driven Agriculture; Agriculture Informatics; Database Verification; Spatiotemporal Data Analysis