Recurrent Graph Research Articles

Routing UAVs in landslides Monitoring: A neural network heuristic for team orienteering with mandatory visits

Unmanned aerial vehicles (UAVs) are widely used for surveillance in both civilian and military scenarios. The utilization of UAVs provides an opportunity for monitoring landslide-prone areas by automatically collecting geological information, thereby reducing the risks and the time required to be working in harsh environments. Due to the maximum travel time limit of UAVs and the geographical dispersion of landslide-prone areas, multiple UAVs are dispatched for surveillance tasks, and landslide-prone areas with high emergency priorities require mandatory visits. Here, we investigate a team orienteering problem with mandatory visits (TOPMV) for routing multi-UAVs to monitor scattered landslide-prone areas, with mandatory visits on those in poorly stable states. The proposed TOPMV aims to plan the optimal multi-UAV paths for maximizing the total amount of collected geological information. To solve the TOPMV with a realistic scale, we develop a large neighborhood search (LNS) algorithm embedding a neural network heuristic (NNH), in which the embedded NNH learns to perform adaptive destroy operators through a hierarchical recurrent graph convolutional network (HRGCN). We consider a real-world case study for monitoring of landslide-prone areas in three counties in southern Shaanxi Province, China. Finally, we test the proposed NNH on both small- and large-scale benchmark instances of the team orienteering problem. The experimental results demonstrate that our proposed NNH exhibits higher efficiency and provides better solution quality than state-of-the-art methods, especially in large-scale settings.

Exploring Delay Propagation Causality in Various Airport Networks with Attention-Weighted Recurrent Graph Convolution Method

Exploring the delay causality between airports and comparing the delay propagation patterns across different airport networks is critical to better understand delay propagation mechanisms and provide effective delay mitigation strategies. A novel attention-based recurrent graph convolutional neural network is proposed to identify the hidden delay causality relationship among airports in three different airport networks of China. The selected three airport networks show great heterogeneities in topological characteristics, such as average intensity, modularity and eigenvector centrality. The modeling results indicate that the identified delay causality networks of three airport networks are greatly varied in terms of complexity, delay propagation distance and efficiency. Moreover, the delay state of each airport is categorized into three levels, and the delay state transition of the three networks is explored. The results indicate that delay state transition in the North China Control Area exhibits an obvious bidirectional transition form that mainly propagates between the large-degree airports and small-degree airports, while severe delays of some hub airports account for a relatively large proportion in the other two networks. The results of this study could better reveal the delay propagation mechanism among airports and help airport operators develop effective strategies to alleviate flight delays and improve airport operation efficiency.

Gated Recurrent Graph Convolutional Attention Network for Traffic Flow Prediction

Traffic flow prediction is an important function of intelligent transportation systems. Accurate prediction results facilitate traffic management to issue early congestion warnings so that drivers can avoid congested roads, thus directly reducing the average driving time of vehicles, which means less greenhouse gas emissions. However, traffic flow data has complex spatial and temporal correlations, which makes it challenging to predict traffic flow accurately. A Gated Recurrent Graph Convolutional Attention Network (GRGCAN) for traffic flow prediction is proposed to solve this problem. The model consists of three components with the same structure, each of which contains one temporal feature extractor and one spatial feature extractor. The temporal feature extractor first introduces a gated recurrent unit (GRU) and uses the hidden states of the GRU combined with an attention mechanism to adaptively assign weights to each time step. In the spatial feature extractor, a node attention mechanism is constructed to dynamically assigns weights to each sensor node, and it is fused with the graph convolution operation. In addition, a residual connection is introduced into the network to reduce the loss of features in the deep network. Experimental results of 1-h traffic flow prediction on two real-world datasets (PeMSD4 and PeMSD8) show that the mean absolute percentage error (MAPE) of the GRGCAN model is as low as 15.97% and 12.13%, and the prediction accuracy and computational efficiency are better than the baselines.

Recurrent graph optimal transport for learning 3D flow motion in particle tracking

Recurrent graph optimal transport for learning 3D flow motion in particle tracking

Semi-Supervised Air Quality Forecasting via Self-Supervised Hierarchical Graph Neural Network

Predicting air quality in fine spatiotemporal granularity is of great importance for air pollution control and urban sustainability. However, existing studies are either focused on predicting station-wise future air quality, or inferring current air quality for unmonitored regions. How to accurately forecast future air quality for these unmonitored regions in a fine granularity remains an unexplored problem. In this paper, we propose the Self-Supervised Hierarchical Graph Neural Network (SSH-GNN), for fine-grained air quality forecasting in a semi-supervised way. Specifically, to augment spatially sparse air quality observations, SSH-GNN first approximates the city-wide air quality distribution based on historical readings and various urban contextual factors (e.g., weather conditions and traffic flows). Then, we propose a hierarchical recurrent graph neural network to make city-wide predictions, which encodes the spatial hierarchy of urban regions for long-range spatiotemporal correlation modeling. Moreover, by leveraging spatiotemporal self-supervision strategies, SSH-GNN exploits both universal topological and contextual patterns to further enhance the forecasting effectiveness. Extensive experiments on two real-world datasets show that SSH-GNN significantly outperforms the state-of-the-art algorithms.

Attention-Based Gated Recurrent Graph Convolutional Network for Short-Term Traffic Flow Forecasting

Traffic flow prediction is the basis of dynamic strategies and applications of intelligent transportation systems (ITS). Accurate traffic flow prediction is of great practical significance in alleviating road congestion and reducing urban road traffic safety hazards. It is challenging since the traffic flow has highly non-linear and complex patterns due to external factors such as time and space. Due to the high stochasticity and uncertainty of traffic flow, the difficulty of traffic flow prediction increases gradually with increasing time steps. The prediction performance of most existing short-term traffic flow prediction methods deteriorates rapidly for longer time steps. In addition, different methods are compared on the same time-granularity dataset, leaving the adaptability and robustness of these methods undervalidated. To address the above challenges, a new traffic forecasting method, named Attention-Based Gated Recurrent Graph Convolutional Network (AGRGCN) is presented for short-term traffic flow prediction. The method can extract spatialtemporal dependencies in traffic flow. In addition, an attention mechanism, which can adaptively capture traffic data relationships at different time steps, is introduced to alleviate the problem of faster deterioration of model prediction performance for longer time steps. Using a road network distance-based graph enables the method better to capture the topological information in traffic flow data. Experiments were conducted on two traffic datasets with different time granularity to predict traffic flow in highway and urban contexts. The experimental results show that our model has certain advantages.

A multi-directional recurrent graph convolutional network model for reconstructing traffic spatiotemporal diagram

ABSTRACT The Time Space Diagram (TSD) can abstractly represent multiple data sources and the macroscopic state of road traffic. However, the TSDs may be incomplete due to missing data, which seriously affects traffic management. Therefore, this paper proposed a Multi-Directional Recurrent Graph Convolutional Network (MDRGCN) for reconstructing TSDs and estimating missing traffic speeds given sparse data. We designed multi-directional RNN layers for scanning the TSDs from horizontal and vertical directions, which can fully exploit the contextual dependencies of the traffic information. In addition, our model includes graph convolution layers for mining potential spatial correlations in the TSDs. The performance of the model reconstructed from TSDs is validated on the NGSIM dataset. We also provided a comparison with other advanced methods, and the experimental results show that our method can perform well at both low and high missing rates, significantly outperforming the baseline methods.

Stream Temperature Prediction in a Shifting Environment: Explaining the Influence of Deep Learning Architecture

AbstractStream temperature is a fundamental control on ecosystem health. Recent efforts incorporating process guidance into deep learning models for predicting stream temperature have been shown to outperform existing statistical and physical models. This performance is in part because deep learning architectures can actively learn spatiotemporal relationships that govern how water and energy propagate through a river network. However, exploration of how spatiotemporal awareness and process guidance influence a model's generalizability under shifting environmental conditions such as climate change is limited. Here, we use Explainable Artificial Intelligence (XAI) to interrogate how differing deep learning architectures affect a model's learned spatial and temporal dependencies, and how those learned dependencies affect a model's ability to maintain high accuracy when applied to unseen environmental conditions. Using the Delaware River Basin in the northeastern United States as a test case, we compare two spatiotemporally aware process‐guided deep learning models for predicting stream temperature (a recurrent graph convolution network—RGCN, and a temporal convolution graph model—Graph WaveNet). Both models achieve equally high predictive performance when testing data are well represented in the training data (test root mean squared errors of 1.64°C and 1.65°C); however, Graph WaveNet significantly outperforms RGCN in 4 out of 5 experiments where test partitions represent different types of unseen environmental conditions. XAI results show that the architecture of Graph WaveNet leads to learned spatial relationships with greater fidelity to physical processes, and that this fidelity improves the generalizability of the model when applied to shifting and/or unseen environmental conditions.

PGSLM: Edge-enabled probabilistic graph structure learning model for traffic forecasting in Internet of vehicles

With the rapid development of the 5G communications, the edge intelligence enables Internet of Vehicles (IoV) to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously. To enhance the forecasting performance, a novel edge-enabled probabilistic graph structure learning model (PGSLM) is proposed, which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network. To obtain the spatio-temporal dependencies of traffic data, the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module. During the training process, a new graph training loss is introduced, which is composed of the K nearest neighbor (KNN) graph constructed by the traffic feature tensors and the graph structure. Detailed experimental results show that, compared with existing models, the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.

Identifying household EV models via weighted power recurrence graphs

Identifying household EV models via weighted power recurrence graphs

A recursive multi-head graph attention residual network for high-speed train wheelset bearing fault diagnosis

Wheelset bearings are a core component of high-speed trains, and their fault diagnosis is the key to smooth operation. Deep learning is widely used in fault diagnosis due to its powerful classification ability. To explicitly fit the features of vibration signals and further explore the relationship between the signals, the graph attention network (GAT) is becoming a focus of research. Unlike traditional graph neural networks, GATs can focus on edges with stronger correlations with vertices, making the model more powerful when fitting graph samples in non-Euclidean space. However, existing GATs have two limitations. Firstly, most graph construction methods do not consider the characteristics of vibration signals, so the graph interpretation is not good. Secondly, the existing methods of graph attention coefficient cannot effectively reflect the importance of edges. To address these issues, a recursive multi-head graph attention residual network (RMHGARN) is proposed. In RMHGARN, vibration signals are transformed into recurrence graphs due to the recursive nature of nonlinear time series. A multi-kernel Gaussian symmetric graph attention mechanism is proposed to obtain the Hilbert spatial distribution between neighboring vertices. In addition, a graph encoding module is proposed to improve the feature representation of input samples. The effectiveness and superiority of RMHGARN under strong noise samples are verified using three wheelset bearing datasets.

Physics-informed gated recurrent graph attention unit network for anomaly detection in industrial cyber-physical systems

Industrial cyber-physical systems (ICPSs) play an important role in many critical infrastructures. To ensure the secure and reliable operation of ICPSs, this work presents a novel end-to-end physics-informed gated recurrent graph attention unit network (PGRGAT) for unsupervised anomaly detection. Different from existing data-driven methods, PGRGAT combines prior knowledge with process data to improve the modeling performance and interpretability. Firstly, a physics-informed graph structure learning module is designed to explicitly model the dependencies among variables into a directed graph. This module learns the Bernoulli distribution on graph edges and generates a discrete graph using Gumbel-softmax sampling. Moreover, prior knowledge is introduced as graph regularization which constrains the graph to adhere to the underlying physics. Then, based on the learned graph structure, a novel gated recurrent graph attention unit network is proposed to simultaneously encode the inter-variable structural dependencies and intra-variable temporal dependencies for anomaly detection. By this means, the information of irrelevant variables can be discarded to improve the sensitivity to anomalies. Finally, the effectiveness of the proposed method is verified through two real-world industrial cases.

A Multichannel MN-GCN for Wheelset-Bearing System Fault Diagnosis

The working condition of high-speed train wheelset bearings is complex and bad, which makes its vibration signal contain strong noise. To obtain more information of samples, signals are constructed into graphs and fit by graph convolution network (GCN). The existing GCN-based models still have some problems, such as insufficient theoretical basis of graph and the unstable and overfitting during training of models, which significantly limits the diagnosis accuracy. To address these issues, first, a weighted <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\varepsilon $ </tex-math></inline-formula> -recurrence network is proposed to construct the recurrence graph (RG). The recurrence relationship between samples is analyzed by the recursive nature of vibration signals. Maximum mean discrepancy (MMD) is used to obtain the regenerated Hilbert spatial distribution distance between two samples to reduce the weight gap between different recursive pairs. Also, the proposed method has better ex ante interpretability. Second, a vertex mean normalization (MN) layer is proposed to normalize individual vertex features to introduce some spatial perturbations and reduce the variance of vertex features, which can improve training stability and reduce overfitting. In addition, multichannel MN-GCN is proposed to fit multiscale graph features. Analyze recurrence nature of samples at different scales through RGs with varying densities of connection to improve the antinoise ability. Experimental results show that the proposed model can obtain spatial topology information accurately and improve the wheelset-bearing system fault diagnosis performance.

Dynamic Representation Learning via Recurrent Graph Neural Networks

A large number of real-world systems generate graphs that are structured data aligned with nodes and edges. Graphs are usually dynamic in many scenarios, where nodes or edges keep evolving over time. Recently, graph representation learning (GRL) has received great success in network analysis, which aims to produce informative and representative features or low-dimensional embeddings by exploring node attributes and network topology. Most state-of-the-art models for dynamic GRL are composed of a static representation learning model and a recurrent neural network (RNN). The former generates the representations of a graph or nodes from one static graph at a discrete time step, while the latter captures the temporal correlation between adjacent graphs. However, the two-stage design ignores the temporal dynamics between contiguous graphs during the learning processing of graph representations. To alleviate this problem, this article proposes a representation learning model for dynamic graphs, called DynGNN. Differently, it is a single-stage model that embeds an RNN into a graph neural network to produce better representations in a compact form. This takes the fusion of temporal and topology correlations into account from low-level to high-level feature learning, enabling the model to capture more fine-grained evolving patterns. From the experimental results on both synthetic and real-world networks, the proposed DynGNN yields significant improvements in multiple tasks compared to the state-of-the-art counterparts.

Application of Recurrent Graph Convolutional Networks to the Neural State Estimation Problem

Neural State Estimation (NSE) is a novel application of deep learning which is concerned with interpolating the state of a distribution power grid from a limited amount of sensor data and can be represented as a non-linear graph time-series nowcasting problem. Although several authors have proposed their solutions for NSE, there is neither a comparison of approaches nor an industry-standard state of the art model yet. The main purpose of this paper is to compare these solutions to a promising new approach: recurrent graph convolutional neural networks. There are theoretical reasons to assume that this class of models is suited for solving NSE. Our experiments verify that they achieve similar performance while also presenting many unique advantages compared to the previously proposed models.

Predicting the evolution trajectory of population-driven connectional brain templates using recurrent multigraph neural networks.

The mapping of the time-dependent evolution of the human brain connectivity using longitudinal and multimodal neuroimaging datasets provides insights into the development of neurological disorders and the way they alter the brain morphology, structure and function over time. Recently, the connectional brain template (CBT) was introduced as a compact representation integrating a population of brain multigraphs, where two brain regions can have multiple connections, into a single graph. Given a population of brain multigraphs observed at a baseline timepoint t1, we aim to learn how to predict the evolution of the population CBT at follow-up timepoints t>t1. Such model will allow us to foresee the evolution of the connectivity patterns of healthy and disordered individuals at the population level. Here we present recurrent multigraph integrator network (ReMI-Net⋆) to forecast population templates at consecutive timepoints from a given single timepoint. In particular, we unprecedentedly design a graph neural network architecture to model the changes in the brain multigraph and identify the biomarkers that differentiate between the typical and atypical populations. Addressing such issues is of paramount importance in diagnosing neurodegenerative disorders at early stages and promoting new clinical studies based on the pinned-down biomarker brain regions or connectivities. In this paper, we demonstrate the design and use of the ReMI-Net⋆ model, which learns both the multigraph node level and time level dependencies concurrently. Thanks to its novel graph convolutional design and normalization layers, ReMI-Net⋆ predicts well-centered, discriminative, and topologically sound connectional templates over time. Additionally, the results show that our model outperforms all benchmarks and state-of-the-art methods by comparing and discovering the atypical connectivity alterations over time. Our ReMI-Net⋆ code is available on GitHub at https://github.com/basiralab/ReMI-Net-Star.

Spatial-Temporal Recurrent Graph Neural Networks for Fault Diagnostics in Power Distribution Systems

Fault diagnostics are extremely important to decide proper actions toward fault isolation and system restoration. The growing integration of inverter-based distributed energy resources imposes strong influences on fault detection using traditional overcurrent relays. This paper utilizes emerging graph learning techniques to build new temporal recurrent graph neural network models for fault diagnostics. The temporal recurrent graph neural network structures can extract the spatial-temporal features from data of voltage measurement units installed at the critical buses. From these features, fault event detection, fault type/phase classification, and fault location are performed. Compared with previous works, the proposed temporal recurrent graph neural networks provide a better generalization for fault diagnostics. Moreover, the proposed scheme retrieves the voltage signals instead of current signals so that there is no need to install relays at all lines of the distribution system. Therefore, the proposed scheme is generalizable and not limited by the number of relays installed. The effectiveness of the proposed method is comprehensively evaluated on the Potsdam microgrid and IEEE 123-node system in comparison with other neural network structures.

Sequence-to-Sequence Recurrent Graph Convolutional Networks for Traffic Estimation and Prediction Using Connected Probe Vehicle Data

Traffic estimation is imperative for conducting fundamental transportation engineering tasks such as transportation planning and traffic safety studies. Additionally, traffic prediction is vital for many data-driven intelligent transportation system applications. Most traffic estimation and prediction methods rely on infrastructure-based sensors to collect traffic parameters. However, infrastructure-based data collection can be costly and time consuming to set up and maintain. Additionally, the spatial distribution of the collected traffic data is limited by the location of the deployed hardware sensors. Probe vehicle data can be used to overcome these limitations. Traffic modeling for estimation and prediction is a complex task due to the stochastic nonlinear spatiotemporal dependencies exhibited by traffic parameters. In this paper, a deep learning-based sequence-to-sequence architecture called Seq2seq GCN-LSTM was proposed to estimate and predict network-wide traffic volume and speed. The proposed method utilizes short-term historical traffic data collected from a low-penetration rate probe vehicle fleet to estimate and predict traffic parameters up to 60-minutes ahead. The method utilizes Graph Convolutional Networks for spatial dependency extraction and Long Short-Term Memory networks to model temporal dependencies. The proposed method generated superior traffic results compared to the baseline models. Additionally, the model demonstrated robustness against perturbations caused by the low rate. Furthermore, the probe vehicle penetration rate was varied to test its effect on the proposed method’s modeling capability. The model was able to maintain traffic volume and speed estimation and prediction performance within a reasonable margin of error using penetration rates as low as 1.5% and 0.5%, respectively.

Forecasting Earthquake Magnitude and Epicenter by Incorporating Spatiotemporal Priors Into Deep Neural Networks

Forecasting earthquake magnitude and epicenter is of great significance for disaster management and hazard mitigation. Existing machine learning-based earthquake forecasting has faced two shortcomings: limited historical earthquake samples for training and lack of explicit consideration of seismic prior knowledge. We propose a novel Spatio-Temporal Priors-Informed Deep Networks (STPiDN) that incorporates seismic spatio-temporal prior knowledge into deep neural networks using limited historical earthquake samples. In our method, a Physics-informed Recurrent Graph Network (PRGN) is developed to extract representations of observed earthquake precursor data in a physics-informed manner. In order to make prior-guided earthquake predictions, we develop seismic prior knowledge activation layers that combine earthquake event representations with prior knowledge (e.g. fault distribution) through activation gates. An adaptive multi-task loss function is proposed to achieve joint magnitude and epicenter forecasting with the consideration of alleviating the magnitude and epicenter imbalance problem. Our empirical evaluation results show that the proposed forecasting method outperforms several competing methods on a real-world earthquake dataset, proving that physics-informed prediction methods have the potential to capture complex earthquake patterns using limited training samples.

SEISMICITY of ARMENIA and ADJACENT TERRITORIES in 2016–2017

A review of seismicity of the Armenia Republic territory and neighboring countries for 20162017 is carried out, information about seismic stations of Armenia network is given. Testing of a new digital seismograph developed in the city of Gyumri was carried out, example of its recording of perceptible earthquake is given. More than 7000 local earthquakes were processed, 2025 of them are included in the consolidated catalog. Within the Republic, the highest level of seismic activity was recorded in the North, in the source zone of Spitak earthquake 1988 with MLV=6.9, I=10. The recurrence graphs for 2016, 2017 and 19932017 have shown, that the long-term coefficient =0.49 corresponds to its normal value for Caucasus, but its values for 2016 and 2017 are somewhat underestimated as regards to its absolute value. The Spitak earthquake zone was active since June.