Spatial-temporal Relationship Research Articles

Transient cortical beta-frequency oscillations associated with contextual novelty in high density mouse EEG

Beta-frequency oscillations (20–30 Hz) are prominent in both human and rodent electroencephalogram (EEG) recordings. Discrete epochs of beta (or Beta2) oscillations are prevalent in the hippocampus and other brain areas during exploration of novel environments. However, little is known about the spatial distribution and temporal relationships of beta oscillations across the cortex in response to novel contexts. To investigate this, mice fitted with 30-channel EEG-style multi-electrode arrays underwent a single recording session in a novel environment. While changes to spectral properties of cortical oscillations were minimal, there was a profound increase in the rate of beta bursts during the initial part of the recording session, when the environment was most novel. This was true across the cortex but most notable in recording channels situated above the retrosplenial cortex. Additionally, novelty was associated with greater connectivity between retrosplenial areas and the rest of the cortex, specifically in the beta frequency range. However, it was also found that the cortex in general, is highly modulated by environmental novelty. This data further suggests the retrosplenial cortex is an important hub for distinguishing environmental context and highlights the diversity of functions for beta oscillations across the brain, which can be observed using high-density EEG.

DGMSCL: A dynamic graph mixed supervised contrastive learning approach for class imbalanced multivariate time series classification.

In the Imbalanced Multivariate Time Series Classification (ImMTSC) task, minority-class instances typically correspond to critical events, such as system faults in power grids or abnormal health occurrences in medical monitoring. Despite being rare and random, these events are highly significant. The dynamic spatial-temporal relationships between minority-class instances and other instances make them more prone to interference from neighboring instances during classification. Increasing the number of minority-class samples during training often results in overfitting to a single pattern of the minority class. Contrastive learning ensures that majority-class instances learn similar features in the representation space. However, it does not effectively aggregate features from neighboring minority-class instances, hindering its ability to properly represent these instances in the ImMTS dataset. Therefor, we propose a dynamic graph-based mixed supervised contrastive learning method (DGMSCL) that effectively fits minority-class features without increasing their number, while also separating them from other instances in the representation space. First, it reconstructs the input sequence into dynamic graphs and employs a hierarchical attention graph neural network (HAGNN) to generate a discriminative embedding representation between instances. Based on this, we introduce a novel mixed contrast loss, which includes weight-augmented inter-graph supervised contrast (WAIGC) and context-based minority class-aware contrast (MCAC). It adjusts the sample weights based on their quantity and intrinsic characteristics, placing greater emphasis on minority-class loss to produce more effective gradient gains during training. Additionally, it separates minority-class instances from adjacent transitional instances in the representation space, enhancing their representational capacity. Extensive experiments across various scenarios and datasets with differing degrees of imbalance demonstrate that DGMSCL consistently outperforms existing baseline models. Specifically, DGMSCL achieves higher overall classification accuracy, as evidenced by significantly improved average F1-score, G-mean, and kappa coefficient across multiple datasets. Moreover, classification results on a real-world power data show that DGMSCL generalizes well to real-world application.

Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling

The transient electromagnetic (TEM) method is a crucial tool for subsurface exploration, providing essential insights into the electrical resistivity structures beneath the Earth’s surface. Traditional forward modeling approaches, such as the finite-difference time-domain (FDTD) method and the finite-element method (FEM), are computationally intensive, limiting their practicality for real-time, high-resolution, or large-scale investigations. To address these challenges, we present Deep-TEMNet, an advanced deep learning framework specifically designed for two-dimensional TEM forward modeling. Deep-TEMNet integrates the U-Net architecture with a tailored two-dimensional long short-term memory (2D LSTM) module, allowing it to effectively capture complex spatial-temporal relationships in TEM data. The U-Net component enables high-resolution spatial feature extraction, while the 2D LSTM module enhances temporal modeling by processing spatial sequences in two dimensions, thereby optimizing the representation of electromagnetic field dynamics over time. Trained on high-fidelity FEM-generated datasets, Deep-TEMNet achieves exceptional accuracy in reproducing electromagnetic field distributions across diverse geological scenarios, with a mean squared error of 0.00000134 and a root mean square percentage error of 0.002373019. The framework offers over 150 times the computational speed of traditional FEMs, with an average inference time of just 3.26 s. Extensive validation across varied geological conditions highlights Deep-TEMNet’s robustness and adaptability, establishing its potential for efficient, large-scale subsurface mapping and real-time data processing. By combining U-Net’s spatial resolution capabilities with the sequential processing strength of the 2D LSTM module, Deep-TEMNet significantly advances computational efficiency and accuracy, positioning it as a valuable tool for geophysical exploration, environmental monitoring, and other applications requiring scalable, real-time TEM analyses that are easily integrated into remote sensing workflows.

РОЛЬ ПАЛЕОТЕКТОНИЧЕСКИХ МЕТОДОВ ИЗУЧЕНИЯ ОСОБЕННОСТЕЙ ГЕОЛОГИЧЕСКОГО СТРОЕНИЯ НЕФТЕГАЗОНОСНЫХ РЕГИОНОВ

The article examines the features of paleotectonic research in the context of oil and gas geology and the search for hydrocarbon (UV) deposits. Particular attention is paid to the methods of paleotectonic analysis and their role in determining the oil and gas potential of the sedimentary basin. Despite the limited range of paleotectonic analysis methods, the questions raised in such studies differ in their complexity, diversity, and breadth, necessitating the development of new approaches and methods. The relevance of the work is determined by the following aspects: 1. Research of hydrocarbon sources, their spatial and temporal location; 2. Studying collectors and fluid resistors, as well as their changes in space and time; 3. Determination of possible oil and gas accumulation zones and their spatial-temporal relationships with oil and gas production sites.

A novel spatio-temporal attention mechanism model for car-following in autonomous driving

Car following is critical for the overall safety, efficiency, and smooth operation of autonomous vehicles in traffic. However, existing car-following model primarily focuses on local feature extraction, overlooking the spatial–temporal relationships between vehicles and key information within the time series. This limitation negatively impacts prediction accuracy and generalization capabilities. To address these issues, a novel Spatio-Temporal Car-Following model based on Graph Convolution Network and Attention mechanism is proposed to enhance the safety, efficiency, and comfort of autonomous driving systems. Firstly, the spatial–temporal structure of the car-following model is constructed using the GCN network. This approach efficiently captures the topological relationships between vehicles. Secondly, we interleave spatial and temporal blocks to extract feature information from both spatial and temporal dimensions, which allows us to perceive spatial interactions and temporal motion patterns of the car. Additionally, a self-attention module assigns different attention weights to the various neighbors of a node in the car-following model, which can facilitate the capture of diverse aspects of node relationships and enhance expressive power. Finally, a Multi-Layer Perceptron (MLP) layer predicts the future behaviors of following vehicles. The proposed car-following model (CF) was trained and evaluated using five real-world datasets: HighD, SPMD, Waymo, NGSIM, and Lyft. The results indicate that our approach surpasses current models in terms of Mean Squared Error (MSE) for spacing, while also maintaining a zero collision rate across every dataset. These findings indicate that the Spatio-Temporal Attention Model (GSTAM-CF) proposed in this paper enhances safety, efficiency, and operational comfort compared to existing models.

The Impact of Urbanization-Induced Land Use Change on Land Surface Temperature

Rapid urbanization can change local climate by increasing land surface temperature (LST), particularly in metropolitan regions. This study uses two decades of remote sensing data to investigate how urbanization-induced changes in land use/land cover (LULC) affect LST in the Beijing Region, China. By focusing on the key issue of LST and its contributing variables through buffer zones, we determined how variables influence LST across buffer zones—core, transit, and suburban areas. This approach is crucial for identifying and prioritizing key variables in each zone, enabling targeted, zone-specific measures that can more effectively mitigate LST rise. The main driving variables for the Beijing Region were determined, and the spatial-temporal relationship between LST and driving variables was investigated using a geographically weighted regression (GWR) model. The results demonstrate that the Beijing Region’s LST climbed from 2002 to 2022, with increases of 0.904, 0.768, and 0.248 °C in core, transit, and suburban areas, respectively. The study found that human-induced variables contributed significantly to the increase in LST across core and transit areas. Meanwhile, natural variables in suburban areas predominated and contributed to stabilizing local climates and cooling. Over two decades and in all buffer zones, GWR models slightly outperformed ordinary least squares (OLS) models, suggesting that the LST is highly influenced by its local geographical location, incorporating natural and human-induced variables. The results of this study have substantial implications for designing methods to mitigate LST across the three buffer zones in the Beijing Region.

Data‐Driven Predictive Modeling of Citywide Crowd Flow for Urban Safety Management: A Case Study of Beijing, China

ABSTRACTCrowd flow forecasting is vital for urban planning, resource allocation, and public safety, particularly in the context of the COVID‐19 pandemic. However, traditional predictive models struggle to capture the complex, nonlinear spatial–temporal relationships inherent in crowd flow data due to its irregular volatility. To address these limitations, this paper proposes the innovative citywide crowd flow prediction (CCFP) model, which merges statistical rules with machine learning techniques (XGBoost, LightGBM, and CatBoost). The CCFP model is specifically designed to leverage spatial dependencies and two‐level periodicity (weekly and daily) in population flow to predict crowd flow indexes ( ) within specific areas. We employ an urban area graph created using the Node2Vec algorithm to capture the temporal and spatial nuances of human flow patterns. Notably, this study innovatively incorporates migration, weather, and epidemic data into machine‐learning models for feature extraction. Moreover, it introduces weighted factors— , and —to enhance the accuracy of prediction. Among the combined models, CCFP outperforms others with remarkable scientific precision (root mean squared error, ; mean absolute error, ; mean absolute percentage error, ). Overall, the CCFP model represents a significant advancement in crowd flow prediction, offering valuable insights for urban safety management and city planning during pandemics.

Semi-supervised spatial-temporal calibration and semantic refinement network for video polyp segmentation

Automated video polyp segmentation (VPS) was of vitality for the early prevention and diagnosis of colorectal cancer (CRC). However, existing deep learning-based automatic polyp segmentation methods mainly focused on independent static images and struggled to perform well due to neglecting spatial–temporal relationships among successive video frames, while requiring massive frame-by-frame annotations. To better alleviate these challenges, we proposed a novel semi-supervised spatial–temporal calibration and semantic refinement network (STCSR-Net) dedicated to VPS, which simultaneously considered both the inter-frame temporal consistency in video clips and intra-frame semantic-spatial information. It was composed of a segmentation pathway and a propagation pathway by use of a co-training scheme for supervising the predictions on un-annotated images in a semi-supervised learning fashion. Specifically, we proposed an adaptive sequence calibration (ASC) block in segmentation pathway and a dynamic transmission calibration (DTC) block in propagation pathway to fully take advantage of valuable temporal cues and maintain the prediction temporally consistent among consecutive frames. Meanwhile, in these two branches, we introduced residual block (RB) to suppress irrelevant noisy information and highlight rich local boundary details of polyp lesions, while constructed multi-scale context extraction (MCE) module to enhance multi-scale high-level semantic feature expression. On that basis, we designed progressive adaptive context fusion (PACF) module to gradually aggregate multi-level features under the guidance of reinforced high-level semantic information for eliminating semantic gaps among them and promoting the discrimination capacity of features for targeting polyp objects. Through synergistic combination of RB, MCE and PACF modules, semantic-spatial correlations on polyp lesions within each frame could be established. Coupled with the context-free loss, our model merged feature representations of neighboring frames to diminish the dependency on varying contexts within consecutive frames and strengthen its robustness. Extensive experiments substantiated that our model with 100% annotation ratio achieved state-of-the-art performance on challenging datasets. Even trained under 50% annotation ratio, our model exceled significantly existing state-of-the-art image-based and video-based polyp segmentation models on the newly-built local TRPolyp dataset by at least 1.3% and 0.9% enhancements in both mDice and mIoU, whilst exhibited comparable performance to top rivals attained through using fully supervised approach on publicly available CVC-612, CVC-300 and ASU-Mayo-Clinic benchmarks. Notably, our model showcased exceptionally well in videos containing complex scenarios like motion blur and occlusion. Beyond that, it also harvested approximately 0.794 mDice and 0.707 mIoU at an inference of 0.036 s per frame in endoscopist-machine competition, which outperformed junior and senior endoscopists as well as almost matched with those of expert ones. The strong capability of the proposed STCSR-Net held promise in improving quality of VPS, accentuating model’s adaptability and potential in real-world clinical scenarios.

Key Frame Selection for Temporal Graph Optimization of Skeleton-Based Action Recognition

Graph neural networks (GNNs) are extensively utilized to capture the spatial–temporal relationships among human body parts for skeleton-based action recognition. However, due to the inefficient information propagation caused by redundant sampling of video frames in the temporal domain, we focus on refining temporal graphs through key frame selection. To this end, we propose a multi-stage key frame selection (MSKFS) method, aiming to find the most representative frames as the graph nodes to learn compact temporal graph representations of human skeletons for action recognition. The MSKFS progressively selects key frames in two stages: (1) salient posture frame selection based on the global dynamics of body parts and (2) key frame refinement and alignment according to intra-frame correlations. The first stage captures the most salient information and aligns the corresponding information of skeleton sequences within the same category. The second stage enriches the subtle information for the integrity of the information derived by the salient frames. Moreover, variational inference is applied to differentiate the key frame refinement and alignment procedure, allowing the end-to-end optimization of arbitrary graph-based models to represent the obtained compact graph for skeleton-based action recognition. Our MSKFS method achieves state-of-the-art performances on two challenging action recognition datasets.

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction

This paper proposes a dynamic multi-scale spatial-temporal graph convolutional network (DS-STGCN) for traffic flow prediction. The network aims to comprehensively extract global and local dependencies in dynamic spatial-temporal data by inputting traffic network flow data to construct node feature graphs, topology graphs, and time slot feature graphs, capturing the complexity and dynamics of traffic flow. DS-STGCN interprets feature information of the traffic network from both spatial and temporal dimensions through dynamic multi-scale graph convolutional blocks. In the spatial dimension, these blocks use constraints at different levels to balance fine-grained local features and extensive global features, revealing the intrinsic structure of traffic flow data. In the temporal dimension, these blocks jointly learn with temporal convolutional blocks to capture multi-frequency time patterns and handle long sequence data, effectively extracting potential dependencies of time series. Furthermore, DS-STGCN effectively models the changing spatial-temporal relationships in road network flow by constructing dynamically adaptive updated adjacency tensors, generating dynamic graph structures to address the challenge of changing spatial-temporal relationships in the transportation system. Experimental results show that our method significantly outperforms other competing methods on five real traffic datasets (PEMS03, PEMS04, PEMS07, PEMS08 and METR-LA).

Spatial–Temporal-Correlation-Constrained Dynamic Graph Convolutional Network for Traffic Flow Forecasting

Accurate traffic flow prediction in road networks is essential for intelligent transportation systems (ITS). Since traffic data are collected from the road network with spatial topological and time series sequences, the traffic flow prediction is regarded as a spatial–temporal prediction task. With the powerful ability to model the non-Euclidean data, the graph convolutional network (GCN)-based models have become the mainstream framework for traffic forecasting. However, existing GCN-based models either use the manually predefined graph structure to capture the spatial features, ignoring the heterogeneity of road networks, or simply perform 1-D convolution with fixed kernel to capture the temporal dependencies of traffic data, resulting in insufficient long-term temporal feature extraction. To solve those issues, a spatial–temporal correlation constrained dynamic graph convolutional network (STC-DGCN) is proposed for traffic flow forecasting. In STC-DGCN, a spatial–temporal embedding encoder module (STEM) is first constructed to encode the dynamic spatial relationships for road networks at different time steps. Then, a temporal feature encoder module with heterogeneous time series correlation modeling (TFE-HCM) and a spatial feature encoder module with dynamic multi-graph modeling (SFE-DCM) are designed to generate dynamic graph structures for effectively capturing the dynamic spatial and temporal correlations. Finally, a spatial–temporal feature fusion module based on a gating fusion mechanism (STM-GM) is proposed to effectively learn and leverage the inherent spatial–temporal relationships for traffic flow forecasting. Experimental results from three real-world traffic flow datasets demonstrate the superior performance of the proposed STC-DGCN compared with state-of-the-art traffic flow forecasting models.

STAFGCN:A spatial-temporal attention-based fusion graph convolution network for pedestrian trajectory prediction

Pedestrian trajectory prediction provides crucial data support for the development of smart cities. Existing pedestrian trajectory prediction methods often overlook the different types of pedestrian interactions and the micro-level spatial-temporal relationships when handling the interaction information in spatial dimension and temporal dimension. The model employs a spatial-temporal attention-based fusion graph convolutional framework to predict future pedestrian trajectories. For the different types of local and global relationships between pedestrians, it first employs spatial-temporal attention mechanisms to capture dependencies in pedestrian sequence data, obtaining the social interactions of pedestrians in spatial contexts and the movement trends of pedestrians over time. Subsequently, a fusion graph convolutional module merges the temporal weight matrix and the spatial weight matrix into a spatial-temporal fusion feature map. Finally, a decoder section utilizes TimeStacked Convolutional Neural Networks to predict future trajectories. The final validation on the ETH and UCY datasets yielded experimental results with an Average Displacement Error(ADE) of 0.34 and an Final Displacement Error(FDE) of 0.55. The visualization results further demonstrated the rationality of the model.

Research on the Spatial-Temporal Evolution of Changsha’s Surface Urban Heat Island from the Perspective of Local Climate Zones

Optimizing urban spatial morphology is one of the most effective methods for improving the urban thermal environment. Some studies have used the local climate zones (LCZ) classification system to examine the relationship between urban spatial morphology and Surface Urban Heat Islands (SUHIs). However, these studies often rely on single-time-point data, failing to consider the changes in urban space and the time-series LCZ mapping relationships. This study utilized remote sensing data from Landsat 5, 7, and 8–9 to retrieve land surface temperatures in Changsha from 2005 to 2020 using the Mono-Window Algorithm. The spatial-temporal evolution of the LCZ and the Surface Urban Heat Island Intensity (SUHII) was then examined and analyzed. This study aims to (1) propose a localized, long-time LCZ mapping method, (2) investigate the spatial-temporal relationship between the LCZ and the SUHII, and (3) develop a more convenient SUHI assessment method for urban planning and design. The results showed that the spatial-temporal evolution of the LCZ reflects the sequence of urban expansion. In terms of quantity, the number of built-type LCZs maintaining their original types is low, with each undergoing at least one type change. The open LCZs increased the most, followed by the sparse and the composite LCZs. Spatially, the LCZs experience reverse transitions due to urban expansion and quality improvements in central urban areas. Seasonal changes in the LCZ types and the SUHI vary, with differences not only among the LCZ types but also in building heights within the same type. The relative importance of the LCZ parameters also differs between seasons. The SUHI model constructed using Boosted Regression Trees (BRT) demonstrated high predictive accuracy, with R2 values of 0.911 for summer and 0.777 for winter. In practical case validation, the model explained 97.86% of the data for summer and 96.77% for winter. This study provides evidence-based planning recommendations to mitigate urban heat and create a comfortable built environment.

Constructing Spatial Relationship and Temporal Relationship Oriented Composite Fuzzy Cognitive Maps for Multivariate Time Series Forecasting

Constructing Spatial Relationship and Temporal Relationship Oriented Composite Fuzzy Cognitive Maps for Multivariate Time Series Forecasting

Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data.

Despite significant results achieved by Contrastive Language-Image Pretraining (CLIP) in zero-shot image recognition, limited effort has been made exploring its potential for zero-shot video recognition. This paper presents Open-VCLIP++, a simple yet effective framework that adapts CLIP to a strong zero-shot video classifier, capable of identifying novel actions and events during testing. Open-VCLIP++ minimally modifies CLIP to capture spatial-temporal relationships in videos, thereby creating a specialized video classifier while striving for generalization. We formally demonstrate that training Open-VCLIP++ is tantamount to continual learning with zero historical data. To address this problem, we introduce Interpolated Weight Optimization, a technique that leverages the advantages of weight interpolation during both training and testing. Furthermore, we build upon large language models to produce fine-grained video descriptions. These detailed descriptions are further aligned with video features, facilitating a better transfer of CLIP to the video domain. Our approach is evaluated on three widely used action recognition datasets, following a variety of zero-shot evaluation protocols. The results demonstrate that our method surpasses existing state-of-the-art techniques by significant margins. Specifically, we achieve zero-shot accuracy scores of 88.1%, 58.7%, and 81.2% on UCF, HMDB, and Kinetics-600 datasets respectively, outpacing the best-performing alternative methods by 8.5%, 8.2%, and 12.3%. We also evaluate our approach on the MSR-VTT video-text retrieval dataset, where it delivers competitive video-to-text and text-to-video retrieval performance, while utilizing substantially less fine-tuning data compared to other methods.

GC-STCL: A Granger Causality-Based Spatial-Temporal Contrastive Learning Framework for EEG Emotion Recognition.

EEG signals capture information through multi-channel electrodes and hold promising prospects for human emotion recognition. However, the presence of high levels of noise and the diverse nature of EEG signals pose significant challenges, leading to potential overfitting issues that further complicate the extraction of meaningful information. To address this issue, we propose a Granger causal-based spatial-temporal contrastive learning framework, which significantly enhances the ability to capture EEG signal information by modeling rich spatial-temporal relationships. Specifically, in the spatial dimension, we employ a sampling strategy to select positive sample pairs from individuals watching the same video. Subsequently, a Granger causality test is utilized to enhance graph data and construct potential causality for each channel. Finally, a residual graph convolutional neural network is employed to extract features from EEG signals and compute spatial contrast loss. In the temporal dimension, we first apply a frequency domain noise reduction module for data enhancement on each time series. Then, we introduce the Granger-Former model to capture time domain representation and calculate the time contrast loss. We conduct extensive experiments on two publicly available sentiment recognition datasets (DEAP and SEED), achieving 1.65% improvement of the DEAP dataset and 1.55% improvement of the SEED dataset compared to state-of-the-art unsupervised models. Our method outperforms benchmark methods in terms of prediction accuracy as well as interpretability.

Shades of green: Unveiling the impact of municipal green bonds on the environment

Green bonds allocate proceeds towards environmentally beneficial projects and sustainable development goals, distinguishing themselves from traditional bonds primarily in the use of proceeds determination. However, investors often find it challenging to assess the carbon reduction potential of these bonds because of the lack of standardised environmental impact reporting. In response to this, our research constructs a unique set of indicators derived from financial and environmental datasets, using multivariate analysis techniques that can accommodate the detection of both linear and non-linear relationships. A novel method combining kernel Principal Component Analysis (kPCA) and Canonical Correlation Analysis (CCA) is applied to detect spatial–temporal cross-correlation in multivariate datasets. This approach handles variable comparability issues and the differential treatment of categorical and numerical variables. A significant finding of this study emerges when this methodology is applied to financial attributes obtained from green bonds issued by municipal agencies (muni bonds), pollution data and environmental (climate) data from nine California counties.The results of the detailed analysis indicate that there is measurable evidence to indicate relationships between green bond issuance and their use of proceeds for pollution reduction efforts. In particular, the results show a clear and interpretable correlation directly linked to the amount of green bond issuance and the effect this is having on pollution reduction, underscoring the tangible impact these financial instruments have on pollution reduction efforts in California.Conversely, when it comes to detecting spatial–temporal relationships between the use of proceeds from green bond issuance and positive climate change effects, this is inconclusive from the current studies’ analysis. It was found that there were weaker cross-correlation relationships observed between climate and green bond financial data set attributes which is perhaps indicative of the fact that climate change effects take a much longer time frame to occur. As such the findings of the analysis in this regard may not indicate that positive climate change effects are not occurring from green bond initiatives, but rather that the ability to measure detectable improvements to climate with regard to the issuance of green bonds is currently limited and will take longer for such effects to manifest in a statistically detectable fashion from the given data. This is particularly likely to be the case given green bonds are only in their infancy as a financial market, having had the earliest issuance only occurring in the last 15-20 years and only substantial growth in the market over the last 10 years. Therefore, this aspect of the research investigating longer-term climate effects with regard to green bond issuance will take longer to develop.

Incorporating the Third Law of Geography with Spatial Attention Module–Convolutional Neural Network–Transformer for Fine-Grained Non-Stationary Air Quality Predictive Learning

Accurate air quality prediction is paramount in safeguarding public health and addressing air pollution control. However, previous studies often ignore the geographic similarity among different monitoring stations and face challenges in dynamically capturing different spatial–temporal relationships between stations. To address this, an air quality predictive learning approach incorporating the Third Law of Geography with SAM–CNN–Transformer is proposed. Firstly, the Third Law of Geography is incorporated to fully consider the geographical similarity among stations via a variogram and spatial clustering. Subsequently, a spatial–temporal attention convolutional network that combines the spatial attention module (SAM) with the convolutional neural network (CNN) and Transformer is designed. The SAM is employed to extract spatial–temporal features from the input data. The CNN is utilized to capture local information and relationships among each input feature. The Transformer is applied to capture time dependencies across long-distance time series. Finally, Shapley’s analysis is employed to interpret the model factors. Numerous experiments with two typical air pollutants (PM2.5, PM10) in Haikou City show that the proposed approach has better comprehensive performance than baseline models. The proposed approach offers an effective and practical methodology for fine-grained non-stationary air quality predictive learning.

Deforestation and Bovine Rabies Outbreaks in Costa Rica, 1985-2020.

In Latin America, rabies virus has persisted in a cycle between Desmodus rotundus vampire bats and cattle, potentially enhanced by deforestation. We modeled bovine rabies virus outbreaks in Costa Rica relative to land-use indicators and found spatial-temporal relationships among rabies virus outbreaks with deforestation as a predictor.

ST-AGNet: Dynamic power system state prediction with spatial–temporal attention graph-based network

Accurate and timely prediction of power system states is one of the most important challenging tasks in modern power systems. Considering the integration of renewable energy sources, recent deep learning-based models have been well studied and found to have benefits in exploiting spatial–temporal relationships in power system data. However, the complexity of different power system topology structures is not substantially captured since the existing models did not fully consider the graph-based information retrieved from power networks. To resolve the problem, a spatial–temporal attention graph-based network (ST-AGNet), an adaptive power system state prediction approach that utilizes graph-based information data to account various typologies of complex power systems, is proposed. Initially, the power flow model is used for generating historical system state data. With the graph-based topology information, the input dataset with the spatial and temporal features is fed into the proposed network for the training and validating process. Meanwhile, the connectivity of the time-varying graph-based information are accounted in the proposed model. Case studies demonstrate the superiority of the ST-AGNet model over the existing baselines under four different scales of complex systems, which can significantly support dynamic power system analysis and operational tasks.