Spatial-temporal Data Research Articles

Where, When, What, and Which? Using Characteristics of Migratory Species to Inform Conservation Policy Questions

Although many migratory species are of conservation concern, traditional conservation policies and economic analysis rarely address the unique characteristics of migratory species, limiting their impact. After a brief description of key attributes of migratory species, this paper explores how those features alter approaches to answering critical conservation policy questions: where, when, with what tools, and which migratory species to conserve? Because migratory species make movement decisions across space and time, migratory species conservation also considers the joint question of when and where to conserve. Policy analysis that considers the spatial–temporal actions of migratory species throughout their annual habitat and incorporates the use of near real-time information is of particular importance for migratory species conservation. Regression analysis of increasingly available spatial–temporal data about species movements could generate important insights about species responses to human-managed landscapes and provide inputs that simplify and empirically ground spatial–dynamic conservation policy analysis.

Spatial–Temporal Tensor Graph Convolutional Network for Traffic Speed Prediction

Accurate traffic speed prediction is crucial for the guidance and management of urban traffic, which at the same time requires a model with a satisfactory computational burden and memory space in applications. In this paper, we propose a factorized Spatial-Temporal Tensor Graph Convolutional Network for traffic speed prediction. Traffic networks are modeled and unified into a graph tensor that integrates spatial and temporal information simultaneously. We extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data. We further introduce Tucker decomposition and derive a factorized tensor convolution to reduce the computational burden, which performs separate filtering in small-scale space, time, and feature modes. Besides, we can benefit from noise suppression of traffic data when discarding those trivial components in the process of tensor decomposition. Extensive experiments on the three real-world datasets demonstrate that our method is more effective than traditional prediction methods, and achieves state-of-the-art performance.

Learning a Local-Global Alignment Network for Satellite Video Super-Resolution

Satellite video is a novel data source for earth observation, which can be applied in multiple fields for dynamic monitoring. It is always equipped with high temporal resolution at the cost of low spatial resolution of tiny moving objects. Video super-resolution (VSR) is utilized to improve the spatial resolution of satellite video and obtain high spatial-temporal resolution data. However, most existing VSR methods mainly focus on the local inter-frame information during feature alignment, which lack the ability to model long-distance correspondence. In this article, a novel two-branch alignment network with an efficient fusion module is proposed for satellite VSR. Both deformable convolution and transformer-like attention are employed to fully explore the local and global information between frames. Further, a fusion module is proposed to model the residuals between fusion features and compensate them for better fusion. Experiments on Jilin-1 satellite videos demonstrate that the proposed network can achieve comparable results to current state-of-the-art VSR methods with tiny parameters.

A Novel Nonconvex Low-Rank Tensor Completion Approach for Traffic Sensor Data Recovery From Incomplete Measurements

Complete traffic sensor data is considered to be one of the critical ingredients for intelligent transportation systems (ITS). However, the traffic measurements prevalently suffer from the inevitable and ubiquitous missing values. Current missing data completion algorithms are difficult to leverage the global low-rank property and the fine-grained spatial-temporal structure simultaneously. To circumvent this problem, this work presents a novel collaborative nonconvex low-rank spatial-temporal data tensor completion model that can take full advantage of the inherent spatial-temporal characteristics of traffic measurement data. First, the tensor Schatten p-norm, as an effective nonconvex surrogate of rank function, is used to exploit the global multi-dimensional correlation of traffic data. Then, we present an elastic net self-representation method and utilize an autoregression model in order to simultaneously capture the self-similarity and the temporal continuity of traffic data acquired in the same sensor network. By integrating the above elements in a unified nonconvex learning model, our method can explore the inherent structure of traffic data from the viewpoints of both global multi-dimensional correlation and fine-grained spatial and temporal dependency. Then, in the view of the general framework of the alternating directions method of multipliers (ADMM), an efficient iterative algorithm is designed to solve our model. Besides, to optimize the parameter combination of the model, a Bayesian optimization-based parameter selection algorithm is developed, which avoids manual parameter adjustment. Extensive experiments and analyses on two real-world traffic datasets are carried out. The results demonstrate the advantages of our model under diverse missing patterns and missing ratios.

Applicability Analysis of GF-2PMS and PLANETSCOPE Data for Ground Object Recognition in Karst Region

Remote sensing image with high spatial and temporal resolution is very important for rational planning and scientific management of land resources. However, due to the influence of satellite resolution, revisit period, and cloud pollution, it is difficult to obtain high spatial and temporal resolution images. In order to effectively solve the “space–time contradiction” problem in remote sensing application, based on GF-2PMS (GF-2) and PlanetSope (PS) data, this paper compares and analyzes the applicability of FSDAF (flexible spatiotemporal data fusion), STDFA (the spatial temporal data fusion approach), and Fit_FC (regression model fitting, spatial filtering, and residual compensation) in different terrain conditions in karst area. The results show the following. (1) For the boundary area of water and land, the FSDAF model has the best fusion effect in land boundary recognition, and provides rich ground object information. The Fit_FC model is less effective, and the image is blurry. (2) For areas such as mountains, with large changes in vegetation coverage, the spatial resolution of the images fused by the three models is significantly improved. Among them, the STDFA model has the clearest and richest spatial structure information. The fused image of the Fit_FC model has the highest similarity with the verification image, which can better restore the coverage changes of crops and other vegetation, but the actual spatial resolution of the fused image is relatively poor, the image quality is fuzzy, and the land boundary area cannot be clearly identified. (3) For areas with dense buildings, such as cities, the fusion image of the FSDAF and STDFA models is clearer and the Fit_FC model can better reflect the changes in land use. In summary, compared with the Fit_FC model, the FSDAF model and the STDFA model have higher image prediction accuracy, especially in the recognition of building contours and other surface features, but they are not suitable for the dynamic monitoring of vegetation such as crops. At the same time, the image resolution of the Fit_FC model after fusion is slightly lower than that of the other two models. In particular, in the water–land boundary area, the fusion accuracy is poor, but the model of Fit_FC has unique advantages in vegetation dynamic monitoring. In this paper, three spatiotemporal fusion models are used to fuse GF-2 and PS images, which improves the recognition accuracy of surface objects and provides a new idea for fine classification of land use in karst areas.

A reduced latency regional gap-filling method for SMAP using random forest regression

The soil moisture active/passive (SMAP) mission represents a significant advance in measuring soil moisture from satellites. However, its large spatial-temporal data gaps limit the use of its values in near-real-time (NRT) applications. Considering this, the study uses NRT operational metadata (precipitation and skin temperature),together with some surface parameterization information, to feed into a random forest model to retrieve the missing values of the SMAP L3 soil moisture product. This practice was tested in filling the missing points for both SMAP descending (6:00 AM) and ascending orbits (6:00 PM) in a crop-dominated area from 2015 to 2019. The trained models with optimized hyper-parameters show the goodness of fit (R2 ≥ 0.86), and their resulting gap-filled estimates were compared against a range of competing products with in situ and triple collocation validation. This gap-filling scheme driven by low-latency data sources is first attempted to enhance NRT spatiotemporal support for SMAP L3 soil moisture.

Characterization of liquid film distribution and sub-flow regimes of annular flow in helically coiled tubes using ring island array sensor

The distribution of liquid film thickness in helically coiled tubes (HCTs) directly affects the heat transfer performance of the annular flow region. However, due to the limitation of measurement technology, accurate measurement data of liquid film thickness in HCTs is very rare. In this paper, a non-invasive contact liquid film thickness sensor (ring island array sensor) is successfully developed to obtain the refined three-dimensional spatial-temporal distribution data of liquid film thickness in HCTs. According to the results, four typical liquid film flow regimes are defined based on the circumferential position of the thicker liquid film appearing in the tube wall, i.e., the bottom distribution (BD) dominated by liquid phase gravity force, the outside distribution (OD) dominated by liquid phase centrifugal force, the inside distribution (ID) dominated by gas centrifugal force and the inside-outside distribution (IOD) dominated by the secondary flow. These circumferential distributions of liquid film thickness are mainly affected by the HCT structure (e.g., coil diameter and coil pitch) and superficial gas-liquid velocities. Based on the modified Dean number De* and the modified Lockhart-Martinelli parameter X*, which consider the influence of HCT structures, fluid properties and operating parameters, a general sub-flow regime map of annular flow is proposed. The prediction models of transition boundaries of different liquid film flow regimes are also established and verified with present and available data in the literature.

The Spatial-Temporal Transition and Influencing Factors of Green and Low-Carbon Utilization Efficiency of Urban Land in China under the Goal of Carbon Neutralization

Urban-land development and utilization is one of the main sources of carbon emissions. Improving the green and low-carbon utilization efficiency of urban land (GLUEUL) under the goal of carbon neutrality is crucial to the low-carbon transition and green development of China's economy. Combining the concept of green and low-carbon development in urban land use, carbon emissions and industrial-pollution emissions are incorporated into the unexpected outputs of the GLUEUL evaluation system. The super-efficient slacks-based measure (SBM) model, Exploratory Spatial-Temporal Data Analysis (ESTDA) method and Geographically and Temporally Weighted Regression (GTWR) model were used to analyze the spatial-temporal transition and the influencing factors of GLUEUL in 282 cities in China from 2005 to 2020. The result shows that: (1) From 2005 to 2020, the green and low-carbon land-utilization efficiency of Chinese cities shows an increasing temporal-evolution trend, but the gap between cities is gradually widening. (2) From the spatial-temporal dynamic characteristics of Local Indicators of Spatial Association (LISA), regions with the highest GLUEUL have strong dynamics and instability, while cities at the lowest level have a relatively stable spatial structure. On the whole, the local-spatial-transfer direction of GLUEUL of each city is stable, with certain path-dependent characteristics. (3) There are differences in the degree of influence and direction of action of different factors on GLUEUL. The economic development level, industrial-structure upgrading, financial support, wealth level, and green-technology-innovation ability have positive effects on overall GLUEUL, with industrial-structure upgrading promoting GLUEUL the most, while urban population size, foreign-investment scale, and financial-development level play a negative role. This study can provide some empirical and theoretical references for the improvement of GLUEUL.

Combining random forest and graph wavenet for spatial-temporal data prediction

The prosperity of deep learning has revolutionized many machine learning tasks (such as image recognition, natural language processing, etc.). With the widespread use of autonomous sensor networks, the Internet of Things, and crowd sourcing to monitor real-world processes, the volume, diversity, and veracity of spatial-temporal data are expanding rapidly. However, traditional methods have their limitation in coping with spatial-temporal dependencies, which either incorporate too much data from weakly connected locations or ignore the relationships between those interrelated but geographically separated regions. In this paper, a novel deep learning model (termed RF-GWN) is proposed by combining Random Forest (RF) and Graph WaveNet (GWN). In RF-GWN, a new adaptive weight matrix is formulated by combining Variable Importance Measure (VIM) of RF with the long time series feature extraction ability of GWN in order to capture potential spatial dependencies and extract long-term dependencies from the input data. Furthermore, two experiments are conducted on two real-world datasets with the purpose of predicting traffic flow and groundwater level. Baseline models are implemented by Diffusion Convolutional Recurrent Neural Network (DCRNN), Spatial-Temporal GCN (ST-GCN), and GWN to verify the effectiveness of the RF-GWN. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) are selected as performance criteria. The results show that the proposed model can better capture the spatial-temporal relationships, the prediction performance on the METR-LA dataset is slightly improved, and the index of the prediction task on the PEMS-BAY dataset is significantly improved. These improvements are extended to the groundwater dataset, which can effectively improve the prediction accuracy. Thus, the applicability and effectiveness of the proposed model RF-GWN in both traffic flow and groundwater level prediction are demonstrated.

Weighted Vest Loads Do Not Elicit Changes in Spatial-Temporal Gait Parameters in Children and Adolescents With Autism.

Weighted vests have been used primarily as behavioral interventions for children and adolescents with autism. Contemporary research has begun to examine weighted vest effects on movement. Previous research in children with neurotypical development revealed 15% body mass loads modified spatial-temporal gait characteristics; however, a value applicable to children and adolescents with autism has not been established. The purpose of this study was to establish an appropriate mass value by examining spatial-temporal gait parameters in children and adolescents with autism with various loads in a weighted vest. Nine children and adolescents with autism, aged 8-17, walked without a weighted vest, with 5%, 10%, 15%, and 20% body mass while spatial-temporal data were captured. Repeated-measures analysis of variance (α = .05) were conducted among conditions for each variable, with a Holm-Bonferroni method correction. Analysis revealed significant decreases in right step length, but no differences in stride width, left step length, double-limb support time, or stride velocity were observed. Due to insignificant findings, an appropriate mass value could not be determined for weighted vests for children with autism. However, unchanged spatial-temporal gait parameters with increasing loads could be clinically relevant as weighted vest loads of 10% are typically used for behavioral interventions.

Robust Traffic Prediction From Spatial-Temporal Data Based on Conditional Distribution Learning.

Traffic prediction based on massive speed data collected from traffic sensors plays an important role in traffic management. However, it is still challenging to obtain satisfactory performance due to the complex and dynamic spatial-temporal correlations among the data. Recently, many research works have demonstrated the effectiveness of graph neural networks (GNNs) for spatial-temporal modeling. However, such models are restricted by conditional distribution during training, and may not perform well when the target is outside the primary region of interest in the distribution. In this article, we address this problem with a stagewise learning mechanism, in which we redefine speed prediction as a conditional distribution learning followed by speed regression. We first perform a conditional distribution learning for each observed speed class, and then obtain speed prediction by optimizing regression learning, based on the learned conditional distribution. To effectively learn the conditional distribution, we introduce a mean-residue loss, consisting of two parts: 1) a mean loss, which penalizes the differences between the mean of the estimated conditional distribution and the ground truth and 2) a residue loss, which penalizes residue errors of the long tails in the distribution. To optimize the subsequent regression based on distribution information, we combine the mean absolute error (MAE) as another part of the loss function. We also incorporate a GNN-based architecture with our proposed learning mechanism. Mean-residue loss is employed to supervise the hidden speed representation in the network at each time interval, followed by a shared layer to recalibrate the hidden temporal dependencies in the conditional distribution. The experimental results based on three public traffic datasets have demonstrated that the effectiveness of the proposed method outperforms state-of-the-art methods.

Alleviating Data Sparsity Problems in Estimated Time of Arrival via Auxiliary Metric Learning

With millions of people using ride-hailing platforms for daily travel, estimated time of arrival (ETA) has become a significant problem in intelligent transportation systems and attracted considerable attention recently. Deep learning-based ETA methods have achieved promising results using massive spatial-temporal data. However, we find that the prediction accuracy is not satisfactory in practical applications due to the prevalent data sparsity problems. Instead of focusing on the average prediction performance as many other methods, this study aims to alleviate the data sparsity problems in ETA to enhance user experience. In general, the data sparsity problems arise from two aspects. The first is the road network, where many links are only traversed by few floating cars. The second aspect is drivers, where many drivers’ trajectories are too scarce (e.g., with only 3 trip records). To alleviate the sparsity in road network, we propose a Road Network Metric Learning framework for ETA (RNML-ETA), where an auxiliary metric learning task is used to improve the link-embedding, especially for links with insufficient data. A novel triangle loss is proposed to improve metric learning effectiveness for links. Experiments on massive real-world data show that RNML-ETA outperforms competing methods by promoting the cold links with limited data. Furthermore, we propose a novel unified framework to Alleviate Data Sparsity problems in ETA (ADS-ETA) by extending RNML-ETA with an additional auxiliary task for driver ID embedding. Results with extensive experiments demonstrate that ADS-ETA can effectively alleviate the data sparsity problems caused by road network and driver sparsity.

Building a Unified Spatio-Temporal Data Model for Grid Resources Based on Microservice Architecture

Under the background of accelerating the process of power grid construction, the unified spatial-temporal data model of power grid resources has become a necessary means to describe the relationship between spatial objects and power grid data. Affected by the defect of the information island, some unified spatiotemporal data models of power grid resources have poor updating performance. Therefore, a unified spatiotemporal data model of power grid resources based on microservice architecture is designed. The architecture can obtain the spatial structure elements of the power grid area, identify the spatial correlation characteristics of the modeling object through the distribution of power energy supply lines, eliminate the dimension of meteorological data variables, design a unified resource scheduling scheme based on the microservice architecture, calculate the space-time weight matrix, and build a space-time data model. Test results are that under the two update task scenarios, the average update performance of the unified spatiotemporal data model of power grid resources based on the Internet of things is 11363 times/second. The average update performance of the unified spatiotemporal data model of power grid resources based on the Internet of things is 9958 times/second). And the average update performance of the unified spatiotemporal data model of power grid resources based on the genetic algorithm is 9771 times/second. It shows that the designed unified spatiotemporal data model of power grid resources is perfect after combining the microservice architecture.

Multi-scale convolutional networks for traffic forecasting with spatial-temporal attention

• Capturing complex spatial-temporal correlations for both short and long term traffic prediction. • Applying soft thresholding fusion to eliminate unimportant spatial-temporal features. • Designing a trainable module to automatically determine the spatial and temporal thresholds. • Constructing multiple convolutions networks and forming groups of units to extract multi-scale features. Traffic forecasting is a classical spatial-temporal data prediction problem with extensive applications, such as dynamic traffic management, route planning and traffic congestion alleviation. However, accurate traffic forecasting is challenging due to complex correlations of traffic data. Few approaches are satisfied with both long-term and short-term prediction tasks. In this paper, we propose a novel Multi-Scale Convolutional Networks (MSCN), an end-to-end solution to solve traffic forecasting problem. MSCN first employs an encoder with spatial-temporal attention mechanism to model both spatial and temporal correlations. Then, the decoder utilizes multiple convolutions and form groups of units to to extract spatial-temporal features for different resolutions. In particular, we propose a soft thresholding fusion mechanism to adaptively adjust the conditions of spatial and temporal correlations. Experiments on two real traffic datasets demonstrate that the proposed MSCN obtains improvements over the state-of-the-art baselines.

Parkinson’s Disease Diagnosis beyond Clinical Features: A Bio-marker using Topological Machine Learning of Resting-state Functional Magnetic Resonance Imaging

Parkinson’s disease (PD) is one of the leading causes of neurological disability, and its prevalence is expected to increase rapidly in the following few decades. PD diagnosis heavily depends on clinical features using the patient’s symptoms. Therefore, an accurate, robust, and non-invasive bio-marker is of critical clinical importance for PD. This study proposes to develop a new bio-marker for PD diagnosis using resting-state functional Magnetic Resonance Imaging (rs-fMRI). Unlike most existing rs-fMRI data analytics using correlational analysis, a Topological Machine Learning approach is proposed to construct the bio-marker. The default functional network is identified first using rs-fMRI. Next, rs-fMRI’s high dimensional spatial–temporal data structure is mapped on a Riemann Manifold using topological dimensional reduction. Following the topological dimensional reduction, machine learning is used for classification and sensitivity analysis. The proposed methodology is applied to three open fMRI databases for demonstration and validation. The PD diagnosis accuracy can reach 96.4% when the proposed methodology is used. Thus, rs-fMRI and topological machine learning provide a quantifiable and verifiable bio-marker for future PD early detection and treatment evaluation.

Multiresolution convolutional autoencoders

We propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.

A Dynamic Heterogeneous Graph Convolution Network For Traffic Flow Prediction

Abstract Traffic prediction has attracted a lot of attention in recent years. However, it is challenging due to the dynamic and heterogeneous spatial–temporal correlations. Most of the existing methods adopt the attention mechanism to capture the dynamic spatial features, but it is difficult for the attention mechanism to learn the real-time change of spatial dependencies, which restrict accurate spatial dependencies learning. Furthermore, most methods are out at elbows when solving heterogeneous spatial–temporal data. To overcome these problems, we propose a novel traffic prediction model called Dynamic spatial–temporal Heterogeneous Graph Convolution Network. Different from the existing methods, we have designed a dynamic localized graph and a corresponding adaptive localized graph convolution network, which are capable of simultaneously capturing dynamic and heterogeneous spatial correlations. We propose a gated adaptive temporal convolution network to capture the temporal heterogeneity of traffic data and enjoy global receptive fields. Finally, a global correlations fusion network is provided to incorporate the global spatial–temporal correlations. Compared with 11 baselines, our proposed model achieves state-of-the-art performance in the accuracy of prediction.

Ship carbon dioxide emission estimation in coastal domestic emission control areas using high spatial-temporal resolution data: A China case

It is necessary to accurately calculate ship carbon emissions for shipping suitability. The state-of-the-art approaches could arguably not be able to estimate ship carbon emissions accurately due to the uncertainties of Ship Technical Specification Database (STSD) and the geographical and temporal breakpoints in Automatic Identification System (AIS) data, hence requiring a new methodology to be developed to address such defects and further improve the accuracy of emission estimation. Firstly, a novel STSD iterative repair model is proposed based on the random forest algorithm by the incorporation of13 ship technical parameters. The repair model is scalable and can substantially improve the quality of STSD. Secondly, a new ship AIS trajectory segmentation algorithm based on ST-DBSCAN is developed, which effectively eliminates the impact of geographical and temporal AIS breakpoints on emission estimation. It can accurately identify the ships' berthing and anchoring trajectories and reasonably segment the trajectories. Finally, based on this proposed framework, the ship carbon dioxide emissions within the scope of domestic emission control areas (DECA) along the coast of China are estimated. The experiment results indicate that the proposed STSD repair model is highly credible due to the significant connections between ship technical parameters. In addition, the emission analysis shows that, within the scope of China's DECA, the berthing period of ships is longer owing to the joint effects of coastal operation features and the strict quarantine measures under the COVID-19 pandemic, which highlights the emissions produced by ship auxiliary engines and boilers. The carbon intensity of most coastal provinces in China is relatively high, reflecting the urgent demand for the transformation and updates of the economic development models. Based on the theoretical models and results, this study recommends a five-stage decarbonization scheme for China's DECA to advance its decarbonization process.

Use of Data Mining to Predict the Influx of Patients to Primary Healthcare Centres and Construction of an Expert System

In any productive sector, predictive tools are crucial for optimal management and decision-making. In the health sector, it is especially important to have information available in advance, as this not only means optimizing resources, but also improving patient care. This work focuses on the management of healthcare resources in primary care centres. The main objective of this work is to develop a model capable of predicting the number of patients who will demand health care in a primary care centre on a daily basis. This model is integrated into a decision support system that is accessible and easy to use by the manager through a web application. In this case, data from a primary care centre in the city of Jaén, Spain, were used. The model was estimated using spatial-temporal training data, the daily health demand data in that centre for five years, and a series of meteorological data. Different regression algorithms have been employed. The workflow requires selecting the parameters that influence the health demand prediction and discarding those that distort the model. The main contribution of this research is the daily prediction of the number of patients attending the health centre with absolute errors better than 3%, which is crucial for decision-making on the sizing of health resources in a primary care health centre.

Spatial clustering of property abandonment in shrinking cities: a case study of targeted demolition in Buffalo, NY’s African American neighborhoods

ABSTRACT Many low-income and minority-concentrated neighborhoods have been struggling for decades with the acute problem of endemic abandonment in shrinking cities. Using high-resolution spatial–temporal data, this study attempts to extend our understanding of the influence of abandonment on future abandonment and the impact of interventions such as demolition by identifying spatial patterns of housing abandonment and demolition in Buffalo, New York when the city invested heavily in an aggressive 5-in-5 demolition plan targeting predominantly African American neighborhoods with high rates of abandonment. Our results confirmed that the clustering of abandoned properties has been consistently confined to the city's majority African American east side neighborhood. We found a higher level of duress housing sales on the east side after the 5-in-5 plan's implementation. In essence, 5-in-5 was a demolition and slum clearance policy akin to mid-twentieth-century urban renewal programs focusing on removing blighted properties without a concomitant revitalization component.