Complex Spatio-temporal Relationships Research Articles

PSTFormer: A novel parallel spatial-temporal transformer for remaining useful life prediction of aeroengine

One of the significant tasks in aeroengine remaining useful life (RUL) prediction is to address both temporal dependencies and spatial dependencies in multivariate time series (MTS) monitoring data. However, it is difficult for traditional transformer-based methods simultaneously extract both temporal and spatial dependencies due to their mutual interference, limiting the further improvement of prediction performance. To address these issues, this paper proposes a novel Parallel Spatial-Temporal Transformer (PSTFormer) for aeroengine RUL prediction with multi-sensor monitoring data. First, a novel parallel spatial–temporal attention mechanism (PSTAM) is designed, which consists of a temporal attention module (TAM) and a spatial attention module (SAM), to simultaneously capture temporal and spatial dependencies from MTS data. TAM employs multiscale convolution to learn the temporal dependencies at different time scales, while SAM adopts a self-attention mechanism to learn the spatial dependencies among different sensor parameter. Parallel connection between TAM and SAM can effectively avoid the mutual interference between temporal and spatial dependencies, improving the modeling ability of complex spatiotemporal relationships. Second, a task-guided spatiotemporal feature fusion (TG-STFF) module is designed, which adaptively fuses temporal and spatial features according to downstream task. Specifically, based on the RUL prediction characteristic, TG-STFF converts spatial features into attention weights and fuses them with temporal features to extract more representative degradation features. Finally, the effectiveness of PSTFormer is validated by a series of experimental comparisons on the public C-MAPSS dataset. Compared with SOTA methods, PSTFormer exhibits more outstanding prediction performance, and it can effectively address the aforementioned challenges in RUL prediction tasks. Therfore, the development of PSTFormer provides an innovative and effective method for aeroengine RUL prediction, significantly enhancing the efficiency and safety of aeroengine maintenance and operation.

MGSAN: multimodal graph self-attention network for skeleton-based action recognition

Due to the emergence of graph convolutional networks (GCNs), the skeleton-based action recognition has achieved remarkable results. However, the current models for skeleton-based action analysis treat skeleton sequences as a series of graphs, aggregating features of the entire sequence by alternately extracting spatial and temporal features, i.e., using a 2D (spatial features) plus 1D (temporal features) approach for feature extraction. This undoubtedly overlooks the complex spatiotemporal fusion relationships between joints during motion, making it challenging for models to capture the connections between different temporal frames and joints. In this paper, we propose a Multimodal Graph Self-Attention Network (MGSAN), which combines GCNs with self-attention to model the spatiotemporal relationships between skeleton sequences. Firstly, we design graph self-attention (GSA) blocks to capture the intrinsic topology and long-term temporal dependencies between joints. Secondly, we propose a multi-scale spatio-temporal convolutional network for channel-wise topology modeling (CW-TCN) to model short-term smooth temporal information of joint movements. Finally, we propose a multimodal fusion strategy to fuse joint, joint movement, and bone flow, providing the model with a richer set of multimodal features to make better predictions. The proposed MGSAN achieves state-of-the-art performance on three large-scale skeleton-based action recognition datasets, with accuracy of 93.1% on NTU RGB+D 60 cross-subject benchmark, 90.3% on NTU RGB+D 120 cross-subject benchmark, and 97.0% on the NW-UCLA dataset. Code is available at https://github.com/lizaowo/MGSAN.

Dynamic Spatio-Temporal Hypergraph Convolutional Network for Traffic Flow Forecasting

Graph convolutional networks (GCN) are an important research method for intelligent transportation systems (ITS), but they also face the challenge of how to describe the complex spatio-temporal relationships between traffic objects (nodes) more effectively. Although most predictive models are designed based on graph convolutional structures and have achieved effective results, they have certain limitations in describing the high-order relationships between real data. The emergence of hypergraphs breaks this limitation. A dynamic spatio-temporal hypergraph convolutional network (DSTHGCN) model is proposed in this paper. It models the dynamic characteristics of traffic flow graph nodes and the hyperedge features of hypergraphs simultaneously, achieving collaborative convolution between graph convolution and hypergraph convolution (HGCN). On this basis, a hyperedge outlier removal mechanism (HOR) is introduced during the process of node information propagation to hyper-edges, effectively removing outliers and optimizing the hypergraph structure while reducing complexity. Through in-depth experimental analysis on real-world datasets, this method has better performance compared to other methods.

Framing spatiotemporalities of sustainability in new mobility practices and imaginaries

ABSTRACT Transport scholars have treated policy processes, social practices, and systemic changes in transport somewhat separately, whereas these phenomena have complex spatiotemporal relationships. The special issue of Norsk Geografisk Tidsskrift–Norwegian Journal of Geography conceptualises transitions to sustainable transport systems in spatiotemporal terms – analytically, empirically, and ontologically. It addresses the integration of these domains in social science research, drawing on empirical observations of complex socio-technical changes, and on a review of literature too often compartmentalised into a few established heuristic modes. This overview synthesises insights across the six featured articles, arguing for interlinked adjustments across the temporal dimensions of policy, practice and innovation levels of transport systems, and highlighting the need to theorise the study of place-based temporalities. It advances a case to unpack four key aspects of mobility transitions: their diverse temporalities, their spatiality and place, equity and accessibility in mobility systems, and human and non-human learning in socio-technical transitions.

Graph convolutional LSTM algorithm for real-time crash prediction on mountainous freeways

Accurate real-time traffic crash prediction is crucial for proactive traffic safety management. Currently, the majority of real-time models forecast crashes every 5 min to support different intelligent transportation systems. However, these intervals might be too short for practical use in manually implementing proactive traffic safety measures such as deploying traffic law enforcement and emergency rescue resources. Therefore, this study develops hourly crash prediction models to provide network operators with sufficient time to take measures in advance. A section of a mountainous freeway in Guizhou province is divided into homogeneous segments, with crash data, traffic operations data, and meteorological data being collected hourly. As the result is an imbalanced dataset of crash and non-crash instances, the training dataset is resampled using synthetic minority over-sampling technique (SMOTE) to address the issue. To fully capture the complex spatiotemporal relationships in the data and achieve high crash prediction accuracy, a graph convolutional network-long short-term memory (GCN-LSTM) model is constructed for the first time, combining a graph convolutional network (GCN) and long short-term memory (LSTM) neural network. For comparison purposes, LSTM, Extreme Gradient Boosting (XGBoost), and logistic regression (LR) models are developed. The results show that the GCN-LSTM model outperforms other models in hourly traffic crash prediction, and the optimal prediction performance is achieved with the crash-to-non-crash ratio of 1:4. The GCN-LSTM method is found to effectively capture the complex spatiotemporal relationships in prediction data and to handle imbalanced traffic crash data.

Symmetric spatiotemporal learning network with sparse meter graph for short-term energy-consumption prediction in manufacturing systems

Short-term energy-consumption prediction is the basis of anomaly detection, real-time scheduling, and energy-saving control in manufacturing systems. Most existing methods focus on single-node energy-consumption prediction and suffer from difficult parameter collection and modelling. Although several methods have been presented for multinode energy-consumption prediction, their prediction performance needs to be improved owing to a lack of appropriate knowledge guidance and learning networks for complex spatiotemporal relationships. This study presents a symmetric spatiotemporal learning network (SSTLN) with a sparse meter graph (SMG) (SSTLN-SMG) that aims to predict multiple nodes based on energy-consumption time series and general process knowledge. The SMG expresses process knowledge by abstracting production nodes, material flows, and energy usage, and provides initial guidance for the SSTLN to extract spatial features. SSTLN, a symmetrical stack of graph convolutional networks (GCN) and gated linear units (GLU), is devised to achieve a trade-off not only between spatial and temporal feature extraction but also between detail capture and noise suppression. Extensive experiments were performed using datasets from an aluminium profile plant. The experimental results demonstrate that the proposed method allows multinode energy-consumption prediction with less prediction error than state-of-the-art methods, methods with deformed meter graphs, and methods with deformed learning networks.

Aberrant cortical activity, functional connectivity, and neural assembly architecture after photothrombotic stroke in mice.

Despite substantial progress in mapping the trajectory of network plasticity resulting from focal ischemic stroke, the extent and nature of changes in neuronal excitability and activity within the peri-infarct cortex of mice remains poorly defined. Most of the available data have been acquired from anesthetized animals, acute tissue slices, or infer changes in excitability from immunoassays on extracted tissue, and thus may not reflect cortical activity dynamics in the intact cortex of an awake animal. Here, in vivo two-photon calcium imaging in awake, behaving mice was used to longitudinally track cortical activity, network functional connectivity, and neural assembly architecture for 2 months following photothrombotic stroke targeting the forelimb somatosensory cortex. Sensorimotor recovery was tracked over the weeks following stroke, allowing us to relate network changes to behavior. Our data revealed spatially restricted but long-lasting alterations in somatosensory neural network function and connectivity. Specifically, we demonstrate significant and long-lasting disruptions in neural assembly architecture concurrent with a deficit in functional connectivity between individual neurons. Reductions in neuronal spiking in peri-infarct cortex were transient but predictive of impairment in skilled locomotion measured in the tapered beam task. Notably, altered neural networks were highly localized, with assembly architecture and neural connectivity relatively unaltered a short distance from the peri-infarct cortex, even in regions within 'remapped' forelimb functional representations identified using mesoscale imaging with anaesthetized preparations 8 weeks after stroke. Thus, using longitudinal two-photon microscopy in awake animals, these data show a complex spatiotemporal relationship between peri-infarct neuronal network function and behavioral recovery. Moreover, the data highlight an apparent disconnect between dramatic functional remapping identified using strong sensory stimulation in anaesthetized mice compared to more subtle and spatially restricted changes in individual neuron and local network function in awake mice during stroke recovery.

Aberrant cortical activity, functional connectivity, and neural assembly architecture after photothrombotic stroke in mice

Despite substantial progress in mapping the trajectory of network plasticity resulting from focal ischemic stroke, the extent and nature of changes in neuronal excitability and activity within the peri-infarct cortex of mice remains poorly defined. Most of the available data have been acquired from anesthetized animals, acute tissue slices, or infer changes in excitability from immunoassays on extracted tissue, and thus may not reflect cortical activity dynamics in the intact cortex of an awake animal. Here, in vivo two-photon calcium imaging in awake, behaving mice was used to longitudinally track cortical activity, network functional connectivity, and neural assembly architecture for 2 months following photothrombotic stroke targeting the forelimb somatosensory cortex. Sensorimotor recovery was tracked over the weeks following stroke, allowing us to relate network changes to behavior. Our data revealed spatially restricted but long-lasting alterations in somatosensory neural network function and connectivity. Specifically, we demonstrate significant and long-lasting disruptions in neural assembly architecture concurrent with a deficit in functional connectivity between individual neurons. Reductions in neuronal spiking in peri-infarct cortex were transient but predictive of impairment in skilled locomotion measured in the tapered beam task. Notably, altered neural networks were highly localized, with assembly architecture and neural connectivity relatively unaltered a short distance from the peri-infarct cortex, even in regions within ‘remapped’ forelimb functional representations identified using mesoscale imaging with anaesthetized preparations 8 weeks after stroke. Thus, using longitudinal two-photon microscopy in awake animals, these data show a complex spatiotemporal relationship between peri-infarct neuronal network function and behavioral recovery. Moreover, the data highlight an apparent disconnect between dramatic functional remapping identified using strong sensory stimulation in anaesthetized mice compared to more subtle and spatially restricted changes in individual neuron and local network function in awake mice during stroke recovery.

Comprehensive review of Transformer‐based models in neuroscience, neurology, and psychiatry

AbstractThis comprehensive review aims to clarify the growing impact of Transformer‐based models in the fields of neuroscience, neurology, and psychiatry. Originally developed as a solution for analyzing sequential data, the Transformer architecture has evolved to effectively capture complex spatiotemporal relationships and long‐range dependencies that are common in biomedical data. Its adaptability and effectiveness in deciphering intricate patterns within medical studies have established it as a key tool in advancing our understanding of neural functions and disorders, representing a significant departure from traditional computational methods. The review begins by introducing the structure and principles of Transformer architectures. It then explores their applicability, ranging from disease diagnosis and prognosis to the evaluation of cognitive processes and neural decoding. The specific design modifications tailored for these applications and their subsequent impact on performance are also discussed. We conclude by providing a comprehensive assessment of recent advancements, prevailing challenges, and future directions, highlighting the shift in neuroscientific research and clinical practice towards an artificial intelligence‐centric paradigm, particularly given the prominence of Transformer architecture in the most successful large pre‐trained models. This review serves as an informative reference for researchers, clinicians, and professionals who are interested in understanding and harnessing the transformative potential of Transformer‐based models in neuroscience, neurology, and psychiatry.

Does gentrification precede and follow greening? Evidence about the green gentrification cycle in Los Angeles and Chicago

The health benefits of green space have led to calls for equitable access to parks. When new green spaces are built in low-income communities, however, gentrification often ensues. The “green gentrification” literature has paid little attention to gentrification that might occur before greening. In this paper, we explore whether and under which circumstances gentrification might precede and follow greening, a process known as the “green gentrification cycle.” Focusing on Los Angeles and Chicago, we build hedonic models focused on single-family homes sold in 2010–2021 and run post-hoc pairwise comparison tests to assess price changes over time for homes within a half-mile of new parks (treatment) and farther (control). When considering all new parks, we find that gentrification is associated with subsequent greening and, to some extent, that greening is associated with ensuing gentrification in Los Angeles. In Chicago, gentrification is associated with subsequent greening, but new parks are not associated with ensuing gentrification. Models distinguishing larger regional from smaller non-regional parks show evidence of gentrification before and after non-regional parks were built in Los Angeles, but not for regional parks. In Los Angeles, we identify stronger evidence of gentrification preceding greening farther from downtown than closer to downtown, and signals of gentrification after greening near downtown but not farther away. Models focusing on new parks built near transit stations show inconclusive results. Despite methodological limitations (e.g., examining a single measure of gentrification and different park types together), our findings shed light on the complex spatiotemporal relationships between greening and gentrification.

PDED-ConvLSTM: Pyramid Dilated Deeper Encoder–Decoder Convolutional LSTM for Arctic Sea Ice Concentration Prediction

Arctic sea ice concentration plays a key role in the global ecosystem. However, accurate prediction of Arctic sea ice concentration remains a challenging task due to its inherent nonlinearity and complex spatiotemporal correlations. To address these challenges, we propose an innovative encoder–decoder pyramid dilated convolutional long short-term memory network (DED-ConvLSTM). The model is constructed based on the convolutional long short-term memory network (ConvLSTM) and, for the first time, integrates the encoder–decoder architecture of ConvLSTM (ED-ConvLSTM) with a pyramidal dilated convolution strategy. This approach aims to efficiently capture the spatiotemporal properties of the sea ice concentration and to enhance the identification of its nonlinear relationships. By applying convolutional layers with different dilation rates, the PDED-ConvLSTM model can capture spatial features at multiple scales and increase the receptive field without losing resolution. Further, the integration of the pyramid convolution module significantly enhances the model’s ability to understand complex spatiotemporal relationships, resulting in notable improvements in prediction accuracy and generalization ability. The experimental results show that the sea ice concentration distribution predicted by the PDED-ConvLSTM model is in high agreement with ground-based observations, with the residuals between the predictions and observations maintained within a range from −20% to 20%. PDED-ConvLSTM outperforms other models in terms of prediction performance, reducing the RMSE by 3.6% compared to the traditional ConvLSTM model and also performing well over a five-month prediction period. These experiments demonstrate the potential of PDED-ConvLSTM in predicting Arctic sea ice concentrations, making it a viable tool to meet the requirements for accurate prediction and provide technical support for safe and efficient operations in the Arctic region.

Anomaly detection of wind turbine based on norm-linear-ConvNeXt-TCN

The supervisory control and data acquisition (SCADA) system of wind turbines continuously collects a large amount of monitoring data during their operation. These data contain abundant information about the operating status of the turbine components. Utilizing this information makes it feasible to provide early warnings and predict the health status of the wind turbine. However, due to the strong coupling between the various components of the wind turbine, the data exhibits complex spatiotemporal relationships, multiple state parameters, strong non-linearity, and noise interference, which brings great difficulty to anomaly detection of the wind turbine. This paper proposes a new method for detecting abnormal operating conditions of wind turbines, based on a cleverly designed multi-layer linear residual module and the improved temporal convolutional network (TCN) with a new norm-linear-ConvNeXt architecture (NLC-TCN). Initially, the NLC-TCN deep learning reconstruction model is trained with historical data of normal behavior to extract the spatiotemporal features of state parameters under normal operational conditions. Subsequently, the condition score of the unit is determined by calculating the average normalized root mean square error between the reconstructed data and actual data. The streaming peaks-over-threshold real-time calculation of the anomaly warning threshold, based on extreme value theory, is then used for preliminary fault monitoring. Moreover, by shielding the fault alarm for low wind speeds and implementing a continuous delay perception mechanism, issues related to wind speed fluctuations and internal and external interference are addressed, enabling early warning for faulty units. Finally, the effectiveness and reliability of the proposed method are validated through comparative experiments using actual offshore wind farm SCADA data. The performance of the proposed method surpasses that of other compared methods. Additionally, the results of the proposed method were evaluated using the uniform manifold approximation and projection dimensionality reduction technique and kernel density estimation.

Graph neural network-based anomaly detection for river network systems

Background Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology. Anomaly detection is crucial for identifying erroneous patterns in sensor data, but can be a challenging task due to the complexity and variability of the data, even under typical conditions. This paper presents a solution to the challenging task of anomaly detection for river network sensor data, which is essential for accurate and continuous monitoring. Methods We use a graph neural network model, the recently proposed Graph Deviation Network (GDN), which employs graph attention-based forecasting to capture the complex spatio-temporal relationships between sensors. We propose an alternate anomaly threshold criteria for the model, GDN+, based on the learned graph. To evaluate the model’s efficacy, we introduce new benchmarking simulation experiments with highly-sophisticated dependency structures and subsequence anomalies of various types. We also introduce software called gnnad. Results We further examine the strengths and weaknesses of this baseline approach, GDN, in comparison to other benchmarking methods on complex real-world river network data. Conclusions Findings suggest that GDN+ outperforms the baseline approach in high-dimensional data, while also providing improved interpretability.

Exploring the Relationship between Urban Vibrancy and Built Environment Using Multi-Source Data: Case Study in Munich

Urbanization has profoundly reshaped the patterns and forms of modern urban landscapes. Understanding how urban transportation and mobility are affected by spatial planning is vital. Urban vibrancy, as a crucial metric for monitoring urban development, contributes to data-driven planning and sustainable growth. However, empirical studies on the relationship between urban vibrancy and the built environment in European cities remain limited, lacking consensus on the contribution of the built environment. This study employs Munich as a case study, utilizing night-time light, housing prices, social media, points of interest (POIs), and NDVI data to measure various aspects of urban vibrancy while constructing a comprehensive assessment framework. Firstly, the spatial distribution patterns and spatial correlation of various types of urban vibrancy are revealed. Concurrently, based on the 5Ds built environment indicator system, the multi-dimensional influence on urban vibrancy is investigated. Subsequently, the Geodetector model explores the heterogeneity between built environment indicators and comprehensive vibrancy along with its economic, social, cultural, and environmental dimensions, elucidating their influence mechanism. The results show the following: (1) The comprehensive vibrancy in Munich exhibits a pronounced uneven distribution, with a higher vibrancy in central and western areas and lower vibrancy in northern and western areas. High-vibrancy areas are concentrated along major roads and metro lines located in commercial and educational centers. (2) Among multiple models, the geographically weighted regression (GWR) model demonstrates the highest explanatory efficacy on the relationship between the built environment and vibrancy. (3) Economic, social, and comprehensive vibrancy are significantly influenced by the built environment, with substantial positive effects from the POI density, building density, and road intersection density, while mixed land use shows little impact. (4) Interactions among built environment factors significantly impact comprehensive vibrancy, with synergistic interactions among the population density, building density, and POI density generating positive effects. These findings provide valuable insights for optimizing the resource allocation and functional layout in Munich, emphasizing the complex spatiotemporal relationship between the built environment and urban vibrancy while offering crucial guidance for planning.

A Unified Spatio-Temporal Inference Network for Car-Sharing Serial Prediction.

Car-sharing systems require accurate demand prediction to ensure efficient resource allocation and scheduling decisions. However, developing precise predictive models for vehicle demand remains a challenging problem due to the complex spatio-temporal relationships. This paper introduces USTIN, the Unified Spatio-Temporal Inference Prediction Network, a novel neural network architecture for demand prediction. The model consists of three key components: a temporal feature unit, a spatial feature unit, and a spatio-temporal feature unit. The temporal unit utilizes historical demand data and comprises four layers, each corresponding to a different time scale (hourly, daily, weekly, and monthly). Meanwhile, the spatial unit incorporates contextual points of interest data to capture geographic demand factors around parking stations. Additionally, the spatio-temporal unit incorporates weather data to model the meteorological impacts across locations and time. We conducted extensive experiments on real-world car-sharing data. The proposed USTIN model demonstrated its ability to effectively learn intricate temporal, spatial, and spatiotemporal relationships, and outperformed existing state-of-the-art approaches. Moreover, we employed negative binomial regression with uncertainty to identify the most influential factors affecting car usage.

Investigating Atmospheric Responses to and Mechanisms Governing North Atlantic Sea Surface Temperatures over 10-Year Periods

Abstract North Atlantic sea surface temperature (SST) variability plays a critical role in modulating the climate system. However, characterizing patterns of North Atlantic SST variability and diagnosing the associated mechanisms is challenging because they involve coupled atmosphere–ocean interactions with complex spatiotemporal relationships. Here we address these challenges by applying a time-evolving self-organizing map approach to a long preindustrial coupled control simulation and identify a variety of 10-yr spatiotemporal evolutions of winter SST anomalies, including but not limited to those associated with the North Atlantic Oscillation–Atlantic multidecadal variability (NAO–AMV)-like interactions. To assess mechanisms and atmospheric responses associated with various SST spatiotemporal evolutions, composites of atmospheric and oceanic variables associated with these evolutions are investigated. Results show that transient-eddy activities and atmospheric circulation responses exist in almost all the evolutions that are closely correlated to the details of the SST pattern. In terms of the mechanisms responsible for generating various SST evolutions, composites of ocean heat budget terms demonstrate that contributions to upper-ocean temperature tendency from resolved ocean advection and surface heat fluxes rarely oppose each other over 10-yr periods in the subpolar North Atlantic. We further explore the potential for predictability for some of these 10-yr SST evolutions that start with similar states but end with different states. However, we find that these are associated with abrupt changes in atmospheric variability and are unlikely to be predictable. In summary, this study broadly investigates the atmospheric responses to and the mechanisms governing the North Atlantic SST evolutions over 10-yr periods. Significance Statement Climate variability in the North Atlantic Ocean has wide-ranging impacts on global and regional climate. However, the processes involved include interactions between the ocean and atmosphere that vary across both space and time, making it challenging to characterize and predict. Using a novel machine learning approach, this study identifies various time evolutions of North Atlantic sea surface temperature patterns over 10-yr periods. This includes evolutions with similar start states but different trajectories, which have important implications for predictability. Furthermore, we investigate the mechanisms responsible for these evolutions and how different sea surface temperature patterns affect atmospheric circulation through small-scale atmospheric disturbances. These new insights into the complex ocean–atmosphere interactions over time are critical for improving decadal prediction skill.

An adaptive representation model for geoscience knowledge graphs considering complex spatiotemporal features and relationships

An adaptive representation model for geoscience knowledge graphs considering complex spatiotemporal features and relationships

Feature multi-level attention spatio-temporal graph residual network: A novel approach to ammonia nitrogen concentration prediction in water bodies by integrating external influences and spatio-temporal correlations

Accurate prediction of ammonia nitrogen concentration in water is of great significance for urban water quality management and pollution early warning. In order to improve the prediction accuracy of ammonia nitrogen concentration in water, this study developed a novel model based on graph neural networks called Feature Multi-level Attention Spatio-Temporal Graph Residual Network (FMA-STGRN). The FMA-STGRN model utilizes external influencing factors such as meteorological factors and point of interest data, as well as the spatio-temporal correlation information of ammonia nitrogen concentration between water quality monitoring stations, to accurately predict the concentration of ammonia nitrogen in water. The model consists of four main components: feature multi-level attention module, spatial graph convolution module, temporal-domain residual decomposition module, and feature fusion and output module. Through the organic combination of these four modules, FMA-STGRN can more effectively explore the complex spatio-temporal correlation relationships between water quality monitoring stations and more accurately integrate and utilize external influencing factors, thereby improving the prediction accuracy of ammonia nitrogen concentration in water. Experimental results show that the FMA-STGRN model outperforms other benchmark models such as RF, MART, MLP, LSTM, GRU, ST-GCN, and ST-GAT in various aspects. In addition, a series of feature ablation experiments were conducted to further reveal the key contributions of meteorological factors and point of interest data to the model performance. Overall, our research provides a powerful and practical tool for water quality monitoring and urban water management, with broad application prospects.

Graph neural network-based anomaly detection for river network systems

Background: Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology. Anomaly detection is crucial for identifying erroneous patterns in sensor data, but can be a challenging task due to the complexity and variability of the data, even under typical conditions. This paper presents a solution to the challenging task of anomaly detection for river network sensor data, which is essential for accurate and continuous monitoring. Methods: We use a graph neural network model, the recently proposed Graph Deviation Network (GDN), which employs graph attention-based forecasting to capture the complex spatio-temporal relationships between sensors. We propose an alternate anomaly threshold criteria for the model, GDN+, based on the learned graph. To evaluate the model's efficacy, we introduce new benchmarking simulation experiments with highly-sophisticated dependency structures and subsequence anomalies of various types. We also introduce software called gnnad. Results: We further examine the strengths and weaknesses of this baseline approach, GDN, in comparison to other benchmarking methods on complex real-world river network data. Conclusions: Findings suggest that GDN+ outperforms the baseline approach in high-dimensional data, while also providing improved interpretability.

A Novel Cellular Network Traffic Prediction Algorithm Based on Graph Convolution Neural Networks and Long Short-Term Memory through Extraction of Spatial-Temporal Characteristics

In recent years, cellular communication systems have continued to develop in the direction of intelligence. The demand for cellular networks is increasing as they meet the public’s pursuit of a better life. Accurate prediction of cellular network traffic can help operators avoid wasting resources and improve management efficiency. Traditional prediction methods can no longer perfectly cope with the highly complex spatiotemporal relationships of the current cellular networks, and prediction methods based on deep learning are constantly growing. In this paper, a spatial-temporal parallel prediction model based on graph convolution combined with long and short-term memory networks (STP-GLN) is proposed to effectively capture spatial-temporal characteristics and to obtain accurate prediction results. STP-GLN is mainly composed of a spatial module and temporal module. Among them, the spatial module designs dynamic graph data based on the principle of spatial distance and spatial correlation. It uses a graph convolutional neural network to learn the spatial characteristics of cellular network graph data. The temporal module uses three time series based on the principle of temporal proximity and temporal periodicity. It uses three long and short-term memory networks to learn the temporal characteristics of three time series of cellular network data. Finally, the results learned from the two modules are fused with different weights to obtain the final prediction results. The mean absolute error (MAE), root mean square error (RMSE), and R-squared (R2) are used as the performance evaluation metrics of the model in this paper. The experimental results show that STP-GLN can more effectively capture the spatiotemporal characteristics of cellular network data; compared with the most advanced model in the comparison model on the real cellular traffic dataset in one cell, the RMSE can be improved about 81.7%, the MAE is improved about 82.7%, and the R2 is improved about 2.2%.