Search Results (12)

SA-ConvLSTM is a recently proposed spatiotemporal model for total electron content (TEC) prediction, which effectively catches long-term temporal evolution and global-scale spatial correlations in TEC. However, its reliance on standard convolution limits spatial feature extraction to fixed regular regions, reducing the flexibility for irregular TEC variations. To address this limitation, we enhance SA-ConvLSTM by incorporating deformable convolution, proposing SA-DConvLSTM. This achieves adaptive spatial feature extraction through learnable offsets in convolutional kernels. Building on this improvement, we design ED-SA-DConvLSTM, a TEC spatiotemporal prediction model based on an encoder–decoder architecture with SA-DConvLSTM as its fundamental block. Firstly, the effectiveness of the model improvement was verified through an ablation experiment. Subsequently, a comprehensive quantitative comparison was conducted between ED-SA-DConvLSTM and baseline models (C1PG, ConvLSTM, and ConvGRU) in the region of 12.5° S–87.5° N and 25° E–180° E. The experimental results showed that the ED-SA-DConvLSTM exhibited superior performance compared to C1PG, ConvGRU, and ConvLSTM, with prediction accuracy improvements of 10.27%, 7.65%, and 7.16% during high solar activity and 11.46%, 4.75%, and 4.06% during low solar activity, respectively. To further evaluate model performance under extreme conditions, we tested the ED-SA-DConvLSTM during four geomagnetic storms. The results showed that the proportion of its superiority over the baseline models exceeded 58%. Full article

The ionospheric total electron content (TEC) has complex spatiotemporal variations, making its spatiotemporal prediction challenging. Capturing long-range spatial dependencies is of great significance for improving the spatiotemporal prediction accuracy of TEC. Existing work based on Convolutional Long Short-Term Memory (ConvLSTM) primarily relies on convolutional operations for spatial feature extraction, which are effective at capturing local spatial correlations, but struggle to model long-range dependencies, limiting their predictive performance. Self-Attention Convolutional Long Short-Term Memory (SA-ConvLSTM) can selectively store and focus on long-range spatial dependencies, but it requires the input length and output length to be the same due to its “n vs. n” structure, limiting its application. To solve this problem, this paper proposes an encoder-decoder SA-ConvLSTM, abbreviated as ED-SA-ConvLSTM. It can effectively capture long-range spatial dependencies using SA-ConvLSTM and achieve unequal input-output lengths through encoder–decoder structure. To verify its performance, the proposed ED-SA-ConvLSTM was compared with C1PG, ConvLSTM, and PredRNN from multiple perspectives in the area of 12.5° S–87.5° N, 25° E–180° E, including overall quantitative comparison, comparison across different months, comparison at different latitude regions, visual comparisons, and comparison under extreme situations. The results have shown that, in the vast majority of cases, the proposed ED-SA-ConvLSTM outperforms the comparative models. Full article

The deep learning model has attracted widespread attention in the field of rolling bearing remaining useful life (RUL) prediction due to its advantages of less reliance on prior knowledge, high accuracy, and strong generalization. However, a large number of prediction models use very complicated artificial feature extraction and selection methods to build the original input features of the deep learning model and health indicator. These approaches do not fully exploit the capabilities of deep learning models as they continue to heavily rely on prior knowledge, The accuracy of their predictions largely hinges on the quality of the input features, and the generalization of manually crafted features remains uncertain. To address these challenges, in this paper, an end-to-end prediction model for the remaining useful life of rolling bearings is proposed, which is divided into three modules. First, a short-term Fourier transform module is incorporated into the model to automatically obtain the time–frequency information of the signal. Then, the convolutional next (ConvNext) module, which is a simple and efficient pure convolutional neural network, is utilized to extract features from the spectrogram. Finally, we capture the short-term dependence and long-term dependence by two parallel channels Transformer and self-attention convolutional long short-term memory (SA-ConvLSTM), and the self-attention mechanism is employed for the adaptive prediction of the bearing’s remaining useful life. Through integration with artificial intelligence, this method proposes a high-performance solution for predicting the remaining useful life of bearings. It has minimal reliance on manual labor, stronger fitting capabilities, and can be widely used for predicting the remaining useful life of bearings. Full article

Video prediction, which is the task of predicting future video frames based on past observations, remains a challenging problem because of the complexity and high dimensionality of spatiotemporal dynamics. To address the problems associated with spatiotemporal prediction, which is an important decision-making tool in various fields, several deep learning models have been proposed. Convolutional long short-term memory (ConvLSTM) can capture space and time simultaneously and has shown excellent performance in various applications, such as image and video prediction, object detection, and semantic segmentation. However, ConvLSTM has limitations in capturing long-term temporal dependencies. To solve this problem, this study proposes an encoder–decoder structure using self-attention ConvLSTM (SA-ConvLSTM), which retains the advantages of ConvLSTM and effectively captures the long-range dependencies through the self-attention mechanism. The effectiveness of the encoder–decoder structure using SA-ConvLSTM was validated through experiments on the MovingMNIST, KTH dataset. Full article

To achieve the regional goal of “double carbon”, it is necessary to map the carbon stock prediction for a wide area accurately and in a timely fashion. This paper introduces a long- and short-term memory network algorithm called the Self-Attention Convolutional Long and Short-Term Memory Network (SA-ConvLSTM). This paper takes the Wuhan urban circle of China as the research object, establishes a carbon stock AI prediction model, constructs a carbon stock change evaluation system, and investigates the correlation between carbon stock change and land use change during urban expansion. The results demonstrate that (1) the overall accuracy of the ConvLSTM and SA-ConvLSTM models improved by 4.68% and 4.70%, respectively, when compared to the traditional metacellular automata prediction methods (OS-CA, Open Space Cellular Automata Model), and for small sample categories such as barren land, shrubs, and grassland, the accuracy of SA-ConvLSTM increased by 17.15%, 43.12%, and 51.37%, respectively; (2) from 1999 to 2018, the carbon stock in the Wuhan urban area showed a decreasing trend, with an overall decrease of 6.49 × 10⁶ MgC. The encroachment of arable land due to rapid urbanization is the main reason for the decrease in carbon stock in the Wuhan urban area. From 2018 to 2023, the predicted value of carbon stock in the Wuhan urban area was expected to increase by 9.17 × 10⁴ MgC, mainly due to the conversion of water bodies into arable land, followed by the return of cropland to forest; (3) the historical spatial error model (SEM) indicates that for each unit decrease in carbon stock change, the Single Land Use Dynamic Degree (SLUDD) of water bodies and impervious surfaces will increase by 119 and 33 units, respectively. For forests, grasslands, and water bodies, the future spatial error model (SEM) indicated that for each unit increase in carbon stock change, the SLUDD would increase by 55, 7, and −305 units, respectively. This study demonstrates that we can use deep neural networks as a new method for predicting land use expansion, revealing the key impacts of land use change on carbon stock change from both historical and future perspectives and providing valuable insights for policymakers. Full article

High precision in forecasting travel demand for online car-hailing is crucial for traffic management to schedule vehicles, hence reducing energy consumption and achieving sustainable development. Netflix demand forecasting relies on the capture of spatiotemporal correlations. To extract the spatiotemporal information more fully, this study designs and develops a novel spatiotemporal prediction model with multidimensional inputs (MSACL) by embedding a self-attention memory (SAM) module into a convolutional long short-term memory neural network (ConvLSTM). The SAM module can extract features with long-range spatiotemporal dependencies. The experimental data are derived from the Chengdu City online car-hailing trajectory data set and the external factors data set. Comparative experiments demonstrate that the proposed model has higher accuracy. The proposed model outperforms the Sa-ConvLSTM model and has the highest prediction accuracy, shows a reduction in the mean absolute error (MAE) by 1.72, a reduction in the mean squared error (MSE) by 0.43, and an increase in the R-squared (R²) by 4%. In addition, ablation experiments illustrate the effectiveness of each component, where the external factor inputs have the least impact on the model accuracy, but the removal of the SAM module results in the most significant decrease in model accuracy. Full article

Atmospheric forcings are significant physical factors that influence the variation of sea surface temperature (SST) and are often used as essential input variables for ocean numerical models. However, their contribution to the prediction of SST based on machine-learning methods still needs to be tested. This study presents a prediction model for SST in the East China Sea (ECS) using two machine-learning methods: Random Forest and SA-ConvLSTM algorithms. According to the Random Forest feature importance scores and correlation coefficients R, 2 m air temperature and longwave radiation were selected as the two most important key atmospheric factors that can affect the SST prediction performance of machine-learning methods. Four datasets were constructed as input to SA-ConvLSTM: SST-only, SST-T2m, SST-LWR, and SST-T2m-LWR. Using the SST-T2m and SST-LWR, the prediction skill of the model can be improved by about 9.9% and 9.43% for the RMSE and by about 8.97% and 8.21% for the MAE, respectively. Using the SST-T2m-LWR dataset, the model’s prediction skill can be improved by 10.75% for RMSE and 9.06% for MAE. The SA-ConvLSTM can represent the SST in ECS well, but with the highest RMSE and AE in summer. The findings of the presented study requires much more exploration in future studies. Full article

Accurately predicting actual evapotranspiration (${\mathrm{ET}}_{\mathrm{a}}$) at the regional scale is crucial for efficient water resource allocation and management. While previous studies mainly focused on predicting site-scale ${\mathrm{ET}}_{\mathrm{a}}$, in-depth studies on regional-scale ${\mathrm{ET}}_{\mathrm{a}}$ are relatively scarce. This study aims to address this issue by proposing a MulSA-ConvLSTM model, which combines the multi-headed self-attention module with the Pyramidally Attended Feature Extraction (PAFE) method. By extracting feature information and spatial dependencies in various dimensions and scales, the model utilizes remote sensing data from ERA5-Land and TerraClimate to attain regional-scale ${\mathrm{ET}}_{\mathrm{a}}$ prediction in Shandong, China. The MulSA-ConvLSTM model enhances the efficiency of capturing the trend of ${\mathrm{ET}}_{\mathrm{a}}$ successfully, and the prediction results are more accurate than those of the other contrast models. The Pearson’s correlation coefficient between observed and predicted values reaches 0.908. The study has demonstrated that MulSA-ConvLSTM yields superior performance in forecasting various ${\mathrm{ET}}_{\mathrm{a}}$ scenarios and is more responsive to climatic changes than other contrast models. By using a convolutional network feature extraction method, the PAFE method extracts global features via various convolutional kernels. The customized MulSAM module allows the model to concentrate on data from distinct subspaces, focusing on feature changes in multiple directions. The block-based training method is employed for the large-scale regional ${\mathrm{ET}}_{\mathrm{a}}$ prediction, proving to be effective in mitigating the constraints posed by limited hardware resources. This research provides a novel and effective method for accurately predicting regional-scale ${\mathrm{ET}}_{\mathrm{a}}$. Full article

Accurate prediction of future chlorophyll-a (Chl-a) concentrations is of great importance for effective management and early warning of marine ecological systems. However, previous studies primarily focused on chlorophyll-a inversion and reconstruction, while methods for predicting Chl-a concentrations remain limited. To address this issue, we adopted four deep learning approaches, including Convolutional LSTM Network (ConvLSTM), Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Eidetic 3D LSTM (E3D-LSTM), and Self-Attention ConvLSTM (SA-ConvLSTM) models, to predict Chl-a over the Yellow Sea and Bohai Sea (YBS) in China. Furthermore, 14 environmental variables obtained from the remote sensing data of Moderate-resolution Imaging Spectroradiometer (MODIS) and ECMWF Reanalysis v5 (ERA5) were utilized to predict the Chl-a concentrations in the study area. The results showed that all four models performed satisfactorily in predicting Chl-a concentrations in the YBS, with SA-ConvLSTM exhibiting a closer approximation to true values. Furthermore, we analyzed the impact of the Self-Attention Memory Module (SAM) on the prediction results. Compared to the ConvLSTM model, the SA-ConvLSTM model integrated with the SAM module better captured subtle large-scale variations within the study area. The SA-ConvLSTM model exhibited the highest prediction accuracy, and the one-month Pearson correlation coefficient reached 0.887. Our study provides an available approach for anticipating Chl-a concentrations over a large area of sea. Full article

The attention mechanism in natural language processing and self-attention mechanism in vision transformers improved many deep learning models. An implementation of the self-attention mechanism with the previously developed ConvLSTM sequence-to-one model was done in order to make a comparative evaluation with statistical testing. First, the new ConvLSTM sequence-to-one model with a self-attention mechanism was developed and then the self-attention layer was removed in order to make comparison. The hyperparameters optimization process was conducted by grid search for integer and string type parameters, and with particle swarm optimization for float type parameters. A cross validation technique was used for better evaluating models with a predefined ratio of train-validation-test subsets. Both models with and without a self-attention layer passed defined evaluation criteria that means that models are able to generate the image of the global aerosol thickness and able to find patterns for changes in the time domain. The model obtained by an ablation study on the self-attention layer achieved better outcomes for Root Mean Square Error and Euclidean Distance in regards to developed ConvLSTM-SA model. As part of the statistical test, a Kruskal–Wallis H Test was done since it was determined that the data did not belong to the normal distribution and the obtained results showed that both models, with and without the SA layer, predict similar images with patterns at the pixel level to the original dataset. However, the model without the SA layer was more similar to the original dataset especially in the time domain at the pixel level. Based on the comparative evaluation with statistical testing, it was concluded that the developed ConvLSTM-SA model better predicts without an SA layer. Full article

High-speed trains operate under varying conditions, leading to different distributions of vibration data collected from the wheel bearings. To detect bearing faults in situations where the source and target domains exhibit differing data distributions, the technique of transfer learning can be applied to move the distribution of features gleaned from unlabeled data in the source domain. However, traditional deep transfer learning techniques do not take into account the relationships between subdomains within the same class of different domains, resulting in suboptimal transfer learning performance and limiting the use of intelligent fault diagnosis for wheel bearings under various conditions. In order to tackle this problem, we have developed the Deep Subdomain Transfer Learning Network (DSTLN). This innovative approach transfers the distribution of features by harmonizing the subdomain distributions of layer activations specific to each domain through the implementation of the Local Maximum Mean Discrepancy (LMMD) method. The DSTLN consists of three modules: a feature extractor, fault category recognition, and domain adaptation. The feature extractor is constructed using a newly proposed SA-ConvLSTM model and CNNs, which aim to automatically learn features. The fault category recognition module is a classifier that categorizes the samples based on the extracted features. The domain adaptation module includes an adversarial domain classifier and subdomain distribution discrepancy metrics, making the learned features domain-invariant across both the global domain and subdomains. Through 210 transfer fault diagnosis experiments with wheel bearing data under 15 different operating conditions, the proposed method demonstrates its effectiveness. Full article

As a flourishing basic transportation service in recent years, online car-hailing has made great achievements in metropolitan cities. Accurate spatiotemporal forecasting plays a significant role in the deployment of a network for online car-hailing demand services. A self-attention mechanism in convolutional long short-term memory (ConvLSTM) is proposed to accurately predict the online car-hailing demand. It can more effectively address the disadvantage that ConvLSTM is not good at capturing spatial correlation over a large spatial extent. Furthermore, it can generate features by aggregating pair-wise similarity scores of features at all positions of input and memory, and thus obtain the function of long-range spatiotemporal dependencies. First, the online car-hailing trajectories dataset was converted into images after geographic grid matching, and image enhancement was performed by cropping. Then, the effectiveness of the ConvLSTM embedded with a self-attention mechanism (SA-ConvLSTM) was demonstrated by comparing it to existing models. The experimental results showed that the proposed model performed better than the existing models, and including spatiotemporal information in images would perform better predictions than including spatial information in time-series pixels. Full article