Temporal Network Research Articles

An optimized surrogate model and algorithm with rapid multi-parameter processing capability for antenna design

A methodology based on an optimized surrogate model and Non-dominated Sorting Genetic Algorithm III(NSGA-III) algorithm is proposed to address the long design cycle issues that conventional antennas encounter, with fast multiple parameters processing capability. A Temporal Convolutional Network (TCN) network model with high fitting efficiency and a simple structure is first developed as a surrogate model for antenna performance prediction, taking antenna dimensional parameters as input and outputting the reflection coefficient (S11) and gain of the antenna. Then, an adaptive NSGA-III algorithm with enhanced search efficiency is presented. By combing it with the prior TCN surrogate model, the parameter optimization for a 5G millimeter-wave antenna design is realized. Results show that the proposed method achieves a remarkable reduction in Mean Squared Error (MSE) by 12.489 % and 3.277 % respectively, while also presents a decreased running time by 2.670 % and 70.419 % respectively, as compared to the Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network models. The proposed method can rapidly and accurately perform the optimization task of multiple antenna parameters, demonstrating its feasibility and effectiveness for antenna applications requiring wide bandwidth, low loss and high gain.

Temporal convolutional network with soft threshold and contractile self-attention mechanism for remaining useful life prediction of rolling bearings

Abstract RUL prediction is an effective approach to prevent system failures and cut maintenance expenditures. Due to the wide receptive field and the avoidance of future information leakage, temporal convolutional neural network (TCN) is widely applied for RUL estimation of bearings. However, the predictive performance of TCN is limited by the loss of degradation features and the breakdown of continuity of timing information. To overcome the above defects, hybrid temporal convolutional neural network with soft threshold and contractile self-attention mechanism (HTCN-SC) is presented. Firstly, the adaptive threshold is determined by the contraction self-attention mechanism with higher interpretability, which captures the contribution of different features to the estimation of RUL. Then, the soft threshold is employed to activate the degraded features. On the one hand, the degeneracy features endowed by the dilated causal convolution with obvious negative values are fully preserved. On the other hand, the noise components that are given low weights are completely suppressed compared to the original TCN. Finally, parallel branch composed of one-dimensional convolutional networks are used to supplement the continuity of time series. Degradation signals from different working conditions and bearings are employed to verify the performance of the HTCN-SC. The results indicate that HTCN-SC with accurate RUL estimation and generalization ability is an effective tool for rolling bearing health monitoring.

Air passenger carbon offset and carbon neutrality strategies: Implementation mechanism by convolutional neural network

To more effectively address the issue of carbon emissions in the aviation industry, this study first analyzes the current development status of carbon offset and carbon neutrality strategies in the aviation industry, as well as examines the existing relevant research findings. Then, optimizations are made to the Convolutional Neural Network to improve the accuracy and efficiency of the prediction model. These optimizations include architectural improvements, the use of attention mechanisms to more accurately focus on important features, as well as the adoption of multiscale feature extraction and advanced optimization algorithms to enhance the model's learning ability and convergence speed. These comprehensive improvements not only enhance the model's generalization ability but also significantly improve its applicability in complex environments. Finally, by comparing the performance of Transformer Networks, Graph Convolutional Networks, Capsule Networks, Generative Adversarial Networks, Temporal Convolutional Networks, and the proposed optimization algorithm on datasets of airline carbon emissions and fuel usage, the performance of the proposed optimization algorithm is validated through comparison of accuracy, precision, recall, and F1-score calculated from the data. Simultaneously, simulation experiments are conducted to validate the effectiveness and feasibility of the proposed optimization algorithm by comparing prediction stability, strategy adaptability, response time, and long-term effectiveness. The experimental results show that the accuracy, precision, recall, and F1-score of the proposed optimized model reach up to 0.942, 0.967, 0.951, and 0.934 respectively, all higher than those of the compared models, validating the good performance of the proposed optimized model. In the comparison of simulation experiments, the scores of prediction stability and strategy adaptability of the proposed optimized model reach up to 0.944 and 0.953 respectively, much higher than those of other models. The response time is only 0.04s when the data volume is 1000, and the computational advantage of the proposed optimized model becomes more apparent with the increase in data volume. In the comparison of long-term effectiveness, the advantage of the proposed optimized model in this aspect also becomes more obvious with the increase in data volume. Through simulation experiments, the performance of the model in actual application scenarios is further evaluated to ensure its practicability. Therefore, this study not only provides a new optimization tool for carbon emission strategies in the aviation industry but also has certain significance for research on environmental sustainability.

Crash risk prediction using sparse collision data: Granger causal inference and graph convolutional network approaches

Applying deep learning techniques in predicting traffic crashes provides a possibility to achieve the vision of “zero fatalities” by implementing a proactive safety countermeasure. The overly sparse distribution of crashes hinders high-precision prediction of crash risks in urban areas. The lack of effective crash association analysis also reduces the interpretability of the prediction model. To address these gaps, this paper proposes a novel method, Priori Spatial and Temporal Causal Graph Convolutional Network (PST-CGCN) for predicting crash risk based on causal inference and graph convolutional network. In PST-CGCN, a data enhancement strategy utilizing historic priori spatial and temporal knowledge is employed to improve the distinguishability between crash data, then a graph convolutional network based on causal association is designed. The focus of this study is to shift attention from using multiple data sources to predict traffic risk to exploring the intrinsic temporal and spatial causal relationship between traffic crashes in different regions. Results from the NYC case study show that PST-CGCN model performs best compared with seven baseline models on three indicators, identifying high crash risk periods and areas in short-term forecasting. The results of ablation experiments on the PST-CGCN demonstrate the rationality of each component in the framework. Besides, gradient analysis combined with causal association is applied to explore directed causal relationships between regions, which enhances the model’s interpretability.

Remaining useful life prediction of rolling bearings based on time convolutional network and transformer in parallel

Abstract Remaining useful life prediction (RUL) is crucial for maintaining the reliability and safety of industrial equipment. Recently, the Transformer has been widely used due to its ability to effectively extract global feature information in rolling bearing RUL prediction. However, the Transformer is weak in acquiring local feature information and cannot extract temporal features from the degradation process. Conversely, a temporal convolutional network (TCN) can effectively extract local features but is weak in global feature extraction. Therefore, to address the above problems, this paper proposes a prediction method based on the parallel combination of TCN and Transformer. The method first extracts the time domain, frequency domain, and time-frequency domain features from the original vibration signals. After screening through the evaluation indices, the features are fused using K-means clustering and principal component analysis (PCA) to construct health indicators (HI) that characterize the degradation of rolling bearings. Then, a TCN-Transformer parallel network model is constructed to extract both local and global features, and a feed-forward neural network (FNN) is used for the prediction of RUL. Finally, experimental validation is carried out on the PHM2012 bearing dataset, and the results show that the method achieves higher RUL prediction accuracy compared to other methods.

An Adaptive Missing Data Restoration Method for UAV Confrontation Based on Deep Regression Model

Completing missions with autonomous decision-making unmanned aerial vehicles (UAV) is a development direction for future battlefields. UAV make decisions based on battlefield situation information collected by sensors and can quickly and accurately perform complex tasks such as path planning, cooperative reconnaissance, cooperative pursuit and attacks. Obtaining real-time situation information of enemy is the basis for realizing autonomous decision-making of the UAV. However, in practice, due to internal sensor failure or interference of enemy, the acquired situation information is prone to be missing, which affects the training and decision-making of autonomous UAV. In this paper, an adaptive missing situation data restoration method for UAV confrontation is proposed. The UAV confrontation situation data are acquired through JSBSim, an open-source UAV simulation platform. By fusing temporal convolutional network and long short-term memory sequences, we establish a deep regression method for missing data restoration and introduce an adaptive mechanism to reduce the training time of the restoration model in response to dynamic changes in the enemy’s strategy during UAV confrontation. In addition, we evaluate the reliability of the proposed method by comparing with different baseline models under different degrees of data missing conditions. The performance of our method is quantified by five metrics. The performance of our proposed method is better than the other benchmark algorithms. The experimental results show that the proposed method can solve the missing data restoration problem and provide reliable situation data while effectively reducing the training time of the restoration model.

Accurate and efficient stock market index prediction: an integrated approach based on VMD-SNNs

The stock market index typically mirrors the financial market's performance. Hence, accurate prediction of stock market index trends is essential for investors aiming to mitigate financial risk and enhance future investment returns. Traditional statistical approaches often struggle with the non-linear nature of stock market index data, leading to potential inaccuracies in long-term predictions. To address this issue, we introduce the TCN-LSTM-SNN (TLSNN) model, a hybrid framework that integrates Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) for robust feature extraction, within a highly efficient Spiking Neural Network (SNN) architecture. Additionally, we employ the Subtraction-Average-Based Optimizer (SABO) to refine the Variational Mode Decomposition (VMD) technique, thereby separating the periodic and trend components of stock indices, reducing noise interference, and establishing a decomposition ensemble framework to bolster the model's resilience. The experimental results show that the VMD-TLSNN hybrid model suggested in this study surpasses other individual benchmark models and their hybrid models in prediction accuracy. Additionally, it demonstrates notably lower energy consumption compared to other hybrid models.

QIGTD: identifying critical genes in the evolution of lung adenocarcinoma with tensor decomposition

BackgroundIdentifying critical genes is important for understanding the pathogenesis of complex diseases. Traditional studies typically comparing the change of biomecules between normal and disease samples or detecting important vertices from a single static biomolecular network, which often overlook the dynamic changes that occur between different disease stages. However, investigating temporal changes in biomolecular networks and identifying critical genes is critical for understanding the occurrence and development of diseases.MethodsA novel method called Quantifying Importance of Genes with Tensor Decomposition (QIGTD) was proposed in this study. It first constructs a time series network by integrating both the intra and inter temporal network information, which preserving connections between networks at adjacent stages according to the local similarities. A tensor is employed to describe the connections of this time series network, and a 3-order tensor decomposition method was proposed to capture both the topological information of each network snapshot and the time series characteristics of the whole network. QIGTD is also a learning-free and efficient method that can be applied to datasets with a small number of samples.ResultsThe effectiveness of QIGTD was evaluated using lung adenocarcinoma (LUAD) datasets and three state-of-the-art methods: T-degree, T-closeness, and T-betweenness were employed as benchmark methods. Numerical experimental results demonstrate that QIGTD outperforms these methods in terms of the indices of both precision and mAP. Notably, out of the top 50 genes, 29 have been verified to be highly related to LUAD according to the DisGeNET Database, and 36 are significantly enriched in LUAD related Gene Ontology (GO) terms, including nuclear division, mitotic nuclear division, chromosome segregation, organelle fission, and mitotic sister chromatid segregation.ConclusionIn conclusion, QIGTD effectively captures the temporal changes in gene networks and identifies critical genes. It provides a valuable tool for studying temporal dynamics in biological networks and can aid in understanding the underlying mechanisms of diseases such as LUAD.

An evolutionary deep learning model based on XGBoost feature selection and Gaussian data augmentation for AQI prediction

Accurate prediction of air quality is crucial for ensuring the scientific validity and effectiveness of air pollution control measures. This study proposes a combined deep learning (DL) model (XGBoost-GDA-TCN-IMRFO-GRU) for predicting hourly air quality index (AQI) data in four cities. The model integrates Extreme gradient boosting (XGBoost) for feature selection, Gaussian data augmentation (GDA), improved manta ray foraging optimization (IMRFO) algorithm, temporal convolutional network (TCN), and gated recurrent unit (GRU). XGBoost calculates the scores of pollutant gases affecting AQI, selecting the top four important pollutants (PM2.5, PM10, NO2, O3) based on their importance rankings. GDA enhances the robustness of the DL models and addresses the limitations of insufficient and overfitting training datasets. Additionally, the IMRFO algorithm, with two improved strategies, is applied to enhance the GRU model. TCN extracts spatiotemporal features of AQI, while GRU constructs a temporal model for efficient computations. Compared to eleven benchmark models, the proposed model demonstrates superior performance in terms of MAE, RMSE, MAPE, and NSE, achieving high accuracy and optimal prediction performance. Specifically, the XGBoost-GDA-TCN-IMRFO-GRU model reduces RMSE, MAE, and MAPE by 33–60 %, 39–68 %, and 39–66 %, respectively, compared to the TCN model. Therefore, the XGBoost-GDA-TCN-IMRFO-GRU model can provide reliable early warnings for air quality, which is of great significance for air pollution prevention and the sustainable development of society.

Comparative Study of Machine Learning Methods for State of Health Estimation of Maritime Battery Systems

Abstract This paper tests two data-driven approaches for predicting the state of health (SOH) of lithium-ion-batteries (LIBs) for the purpose of monitoring maritime battery systems. First, non-sequential approaches are investigated and various models are tested: ridge, lasso, support vector regression, and gradient boosted trees. Binning is proposed for feature engineering for these types of models to capture the temporal structure in the data. Such binning creates histograms for the accumulated time the LIB has been within various voltage, temperature, and current ranges. Further binning to combine these histograms into 2D or 3D histograms is explored in order to capture relationships between voltage, temperature, and current. Second, a sequential approach is explored where different deep learning architectures are tried out: long short-term memory, transformer, and temporal convolutional network. Finally, the various models and the two approaches are compared in terms of their SOH prediction ability. Results indicate that the binning with ridge regression models performed best. The same publicly available sensor data from laboratory cycling tests are used for both approaches.

Deep heterogeneous joint architecture: A temporal frequency surrogate model for fuel performance codes

Fuel performance codes, such as Transuranus, predict fuel behavior and are used to ensure the safe operation of nuclear reactors. These codes are moderately time-consuming and affordable in many applications but may be limited in others, primarily when many fuel rods must be evaluated simultaneously. This work presents how the temporal neural network techniques, Temporal Convolutional Networks, and a Fourier Neural Operator can be combined to form a deep heterogeneous joint architecture as a surrogate model for fuel performance modeling in time-critical situations. We train the model using realistic power histories and corresponding outputs generated using the fuel performance code Transuranus. The ultimate result is a surrogate model for use in time-critical situations that take milliseconds to evaluate for thousands of fuel rods and have a mean test error of unseen data around a few percent.

Identifying Network Ties from Panel Data: Theory and an Application to Tax Competition

Abstract Social interactions determine many economic behaviors, but information on social ties does not exist in most publicly available and widely used datasets. We present results on the identification of social networks from observational panel data that contains no information on social ties between agents. In the context of a canonical social interactions model, we provide sufficient conditions under which the social interactions matrix, endogenous and exogenous social effect parameters are globally identified if networks are constant over time. We also provide an extension of the method for time-varying networks. We then describe how high-dimensional estimation techniques can be used to estimate the interactions model based on the Adaptive Elastic Net Generalized Method of Moments. We employ the method to study tax competition across US states. The identified social interactions matrix implies that tax competition differs markedly from the common assumption of competition between geographically neighboring states, providing further insights into the long-standing debate on the relative roles of factor mobility and yardstick competition in driving tax setting behavior across states. Most broadly, our identification and application show that the analysis of social interactions can be extended to economic realms where no network data exists.

Method for Remaining Useful Life Prediction of Turbofan Engines Combining Adam Optimization-Based Self-Attention Mechanism with Temporal Convolutional Networks

Conducting the remaining useful life (RUL) prediction for an aircraft engines is of significant importance in enhancing aircraft operation safety and formulating reasonable maintenance plans. Addressing the issue of low prediction model accuracy due to traditional neural networks’ inability to fully extract key features, this paper proposes an engine RUL prediction model based on the adaptive moment estimation (Adam) optimized self-attention mechanism–temporal convolutional network (SAM-TCN) neural network. Firstly, the raw data monitored by sensors are normalized, and RUL labels are set. A sliding window is utilized for overlapping sampling of the data, capturing more temporal features while eliminating data dimensionality. Secondly, the SAM-TCN neural network prediction model is constructed. The temporal convolutional network (TCN) neural network is used to capture the temporal dependency between data, solving the mapping relationship of engine degradation characteristics. A self-attention mechanism (SAM) is employed to adaptively assign different weight contributions to different input features. In the experiments, the root mean square error (RMSE) values on four datasets are 11.50, 16.45, 11.62, and 15.47 respectively. These values indicate further reduction in errors compared to methods reported in other literature. Finally, the SAM-TCN prediction model is optimized using the Adam optimizer to improve the training effectiveness and convergence speed of the model. Experimental results demonstrate that the proposed method can effectively learn feature data, with prediction accuracy superior to other models.

Temporal Graph Network for continuous-time dynamic event sequence

Continuous-Time Dynamic Graph (CTDG) methods have shown their superior ability in learning representations for dynamic graph-structured data, the methods split the sequential updating process into discrete batches to reduce the computation costs, as a result, the message constructor in existing CTDG methods cannot be optimized by gradient descent and is designed to be parameter-free. In particular, this layer fails to embed complex event subgraphs and ignores the structure information, while most real-world events are structured and complex. For example, a paper publication event in an academic graph contains different relations like authorship and citations. Furthermore, the corresponding nodes could not receive position-wise messages to make precise representation updates. To tackle this issue, we propose a new method called Temporal Graph Network for continuous-time dynamic Event sequence (TGNE) with a structure-aware message constructor to update node representation with complex event subgraph, by treating message construction and delivery as a message-passing process, in this way, the message constructor can be formalized as a graph neural network layer. TGNE extends the input of CTDG methods to subgraphs with complex structures and preserves more information in message delivery. Extensive experiments demonstrate that the proposed method can achieve competitive performance on traditional tasks on bipartite graphs and event sequence learning tasks on heterogeneous graphs.

Improving streamflow forecasting in semi-arid basins by combining data segmentation and attention-based deep learning

The increasing threats of flash floods and water scarcity in semi-arid regions necessitate high-quality streamflow forecasting with process-based or data-driven models. However, temporal heterogeneity of hydrological patterns and infrequent flood events present challenges for accurate streamflow forecasting. To address this issue, we purpose an effective modeling approach that combines a novel data segmentation method, BPX, with an attention-based deep learning (DL) model. BPX integrates Bai-Perron analysis and XGBoost to accurately identify dry and wet periods from hydro-meteorological variables both in the past and future times. The DL model introduces an attention mechanism to temporal convolutional network (TCN) to enhance its ability in handling heterogeneous time-series data. We demonstrate the effectiveness of our approach using nearly 20 years of hydro-meteorological data from the Wei River basin in China. Various modeling methods are compared, including two process-based models (Xinanjiang and GR4J) and four DL models (classical RNN, GRU, LSTM and TCN) with or without the attention module. After systematic benchmarking, it is found that both the BPX segmentation and the attention mechanism can improve streamflow forecasting with DL. Among the various modeling approaches, BPX-TCN exhibits the best overall performance throughout the prediction period, achieving the highest Kling-Gupta efficiency of 0.91 (compared to 0.45–0.88 for the other models), while BPX-TCN-attention provides more accurate predictions of floods and multi-step predictions. In similar applications in semi-arid regions, our approach may serve as a valuable reference where temporal heterogeneity is significant and poses challenges to traditional modeling methods.

Fusion of Multiple Data Sources for Vehicle Crashworthiness Prediction Using CycleGAN and Temporal Convolutional Networks

Abstract Computer-aided engineering (CAE) models play a pivotal role in predicting crashworthiness of vehicle designs. While CAE models continue to advance in fidelity, an inherent discrepancy between CAE model predictions and the responses of physical tests remains inevitable. Machine learning (ML) models have shown promising potential in improving the prediction accuracy of CAE models. Nevertheless, the scarcity of vehicle crash data poses a significant challenge for the training of such models. This paper overcomes these challenges by fusing multiple data sources from two different types of vehicles. More specifically, the Cycle-Consistent Generative Adversarial Neural networks (CycleGAN) are first employed to translate features of time-series test data from one domain to another using cycle consistency loss. Such a translation allows for the generation of synthetic crash test data for the second vehicle type by leveraging existing tests from both vehicle types. In parallel, an initial temporal convolutional network (TCN) model is trained using CAE simulation data and physical test data of the first vehicle type. This pre-trained TCN model is then fine-tuned using three sources of data from the second vehicle type, namely the CAE data, test data, and the augmented virtual test data generated using CycleGAN. Through these data fusion, the crashworthiness prediction accuracy of the second vehicle type can be improved. The proposed method is demonstrated by a real-world case study with a small-size SUV and a medium-size SUV. Results show enhancements in the predictive performance of the medium-size SUV model.

Short-Term Load Forecasting for Regional Smart Energy Systems Based on Two-Stage Feature Extraction and Hybrid Inverted Transformer

Accurate short-term load forecasting is critical for enhancing the reliability and stability of regional smart energy systems. However, the inherent challenges posed by the substantial fluctuations and volatility in electricity load patterns necessitate the development of advanced forecasting techniques. In this study, a novel short-term load forecasting approach based on a two-stage feature extraction process and a hybrid inverted Transformer model is proposed. Initially, the Prophet method is employed to extract essential features such as trends, seasonality and holiday patterns from the original load dataset. Subsequently, variational mode decomposition (VMD) optimized by the IVY algorithm is utilized to extract significant periodic features from the residual component obtained by Prophet. The extracted features from both stages are then integrated to construct a comprehensive data matrix. This matrix is then inputted into a hybrid deep learning model that combines an inverted Transformer (iTransformer), temporal convolutional networks (TCNs) and a multilayer perceptron (MLP) for accurate short-term load forecasting. A thorough evaluation of the proposed method is conducted through four sets of comparative experiments using data collected from the Elia grid in Belgium. Experimental results illustrate the superior performance of the proposed approach, demonstrating high forecasting accuracy and robustness, highlighting its potential in ensuring the stable operation of regional smart energy systems.

Multi-View Graph Learning for Path-Level Aging-Aware Timing Prediction

As CMOS technology continues to scale down, the aging effect—known as negative bias temperature instability (NBTI)—has become increasingly prominent, gradually emerging as a key factor affecting device reliability. Accurate aging-aware static timing analysis (STA) at the early design phase is critical for establishing appropriate timing margins to ensure circuit reliability throughout the chip lifecycle. However, traditional aging-aware timing analysis methods, typically based on Simulation Program with Integrated Circuit Emphasis (SPICE) simulations or aging-aware timing libraries, struggle to balance prediction accuracy with computational cost. In this paper, we propose a multi-view graph learning framework for path-level aging-aware timing prediction, which combines the strengths of the spatial–temporal Transformer network (STTN) and graph attention network (GAT) models to extract the aging timing features of paths from both timing-sensitive and workload-sensitive perspectives. Experimental results demonstrate that our proposed framework achieves an average MAPE score of 3.96% and reduces the average MAPE by 5.8 times compared to FFNN and 2.2 times compared to PNA, while maintaining acceptable increases in processing time.

Multi-scale RWKV with 2-dimensional temporal convolutional network for short-term photovoltaic power forecasting

Improving the accuracy of Photovoltaic (PV) power forecasting is crucial for optimizing the schedule of power stations and maintaining the grid stability. However, PV power generation exhibits complex periodicity and is significantly influenced by weather conditions, introducing instability, intermittency, and randomness, making accurate PV power forecasting a challenging task. Therefore, this study proposes a multi-scale Receptance Weighted Key Value with 2-Dimensional Temporal Convolutional Network (MSRWKV-2DTCN) for PV power forecasting, which can learn periodicity and interdependencies of data and improve forecasting accuracy. Firstly, the proposed model identifies multi-periodicity of PV power data with the Fast Fourier Transform (FFT). Subsequently, we combine these identified periods with the canonical time mixing block of Receptance Weighted Key Value (RWKV) and introduce a multi-scale time mixing block to learn periodicity of data. Finally, to explore complex interdependencies of historical data, we replace the channel-mixing block of RWKV with a multi-scale 2-Dimensional Temporal Convolutional Network (2D TCN). Experiments were conducted on real-world datasets collected from Yulara solar system in Australia to validate the performance of the proposed model. Comparisons with other PV power forecasting models and ablation studies confirm that the MSRWKV-2DTCN achieves higher accuracy in short-term PV power forecasting.

Inferring Gene Regulatory Networks from Single-Cell Time-Course Data Based on Temporal Convolutional Networks

Background: Time-course single-cell RNA sequencing (scRNA-seq) data represent dynamic gene expression values that change over time, which can be used to infer causal relationships between genes and construct dynamic gene regulatory networks (GRNs). However, most of the existing methods are designed for bulk RNA sequencing (bulk RNA-seq) data and static scRNA-seq data, and only a few methods, such as CNNC and DeepDRIM can be directly applied to time-course scRNA-seq data. Objective: This work aims to infer causal relationships between genes and construct dynamic gene regulatory networks using time-course scRNA-seq data. Methods: We propose an analytical method for inferring GRNs from single-cell time-course data based on temporal convolutional networks (scTGRN), which provides a supervised learning approach to infer causal relationships among genes. scTGRN constructs a 4D tensor representing gene expression features for each gene pair, then inputs the constructed 4D tensor into the temporal convolutional network to train and infer the causal relationship between genes. Results: We validate the performance of scTGRN on five real datasets and four simulated datasets, and the experimental results show that scTGRN outperforms existing models in constructing GRNs. In addition, we test the performance of scTGRN on gene function assignment, and scTGRN outperforms other models. Conclusion: The analysis shows that scTGRN can not only accurately identify the causal relationship between genes, but also can be used to achieve gene function assignment.