Linear Variable Convolution and Cross Attention LSTM Method for Radar Echo Extrapolation

The neural network method can obtain a higher precision of radar echo extrapolation than the traditional method. However, its application in radar echo extrapolation is still in the initial stage of exploration, and there is still much room for improvement in the extrapolation accuracy. To improve the utilization of radar echo information and extrapolation accuracy, this paper proposes a radar echo extrapolation model (ADC_Net) based on dilated convolution and attention convolution. In this model, dilated convolution, instead of the pooling operation, is used to downsample the feature matrix obtained after the standard convolution operation. In doing so, the internal data structure of the feature matrix is retained, and the spatial features of radar echo data from different scales are extracted as well. Besides, the attention convolution module is integrated in the ADC_Net model to improve its sensitivity to the target features in the feature matrix and suppress the interference information. The proposed model is tested in the extrapolation of radar echo images in the next 90 min from five aspects—extrapolated image, POD index, CSI index, FAR index, and HSS index. The experimental results show that the model can effectively improve the accuracy of radar echo extrapolation.

In order to forecast some high intensity and rapidly changing phenomena, such as thunderstorms, heavy rain, and hail within 2 h, and reduce the influence brought by destructive weathers, this paper proposes a weather radar echo extrapolation method based on deep learning. The proposed method includes the design and combination of the data preprocessing, convolutional long short-term memory (Conv-LSTM) neuron and encoder–decoder model. We collect eleven thousand weather radar echo data in high spatiotemporal resolution, these data are then preprocessed before they enter the neural network for training to improve the data’s quality and make the training better. Next, the neuron integrates the structure and the advantages of convolutional neural network (CNN) and long short-term memory (LSTM), called Conv-LSTM, is applied to solve the problem that the full-connection LSTM (FC-LSTM) cannot extract the spatial information of input data. This operation replaced the full-connection structure in the input-to-state and state-to-state parts so that the Conv-LSTM can extract the information from other dimensions. Meanwhile, the encoder–decoder model is adopted due to the size difference of the input and output data to combine with the Conv-LSTM neuron. In the neural network training, mean square error (MSE) loss function weighted according to the rate of rainfall is added. Finally, the matrix “point-to-point” test method, including the probability of detection (POD), critical success index (CSI), false alarm ratio (FAR) and spatial test method contiguous rain areas (CRA), is used to examine the radar echo extrapolation’s results. Under the threshold of 30 dBZ, at the time of 1 h, we achieved 0.60 (POD), 0.42 (CSI) and 0.51 (FAR), compared with 0.42, 0.28 and 0.58 for the CTREC algorithm, and 0.30, 0.24 and 0.71 for the TITAN algorithm. Meanwhile, at the time of 1 h, we achieved 1.35 (total MSE ) compared with 3.26 for the CTREC algorithm and 3.05 for the TITAN algorithm. The results demonstrate that the radar echo extrapolation method based on deep learning is obviously more accurate and stable than traditional radar echo extrapolation methods in near weather forecasting.

As the first step of cybersecurity situational awareness, the accuracy of cybersecurity element recognition will directly affect the results of situational understanding and situational prediction. In this paper, we propose a network element recognition method based on the convolutional attention mechanism combined with a long- and short-term memory network. The input network traffic data is successively passed through the convolutional neural network, attention mechanism, and long- and short-term memory network, which not only takes into account the influence degree of different network attributes on different network behaviors but also realizes that the feature information extracted in the early stage can be circulated in the network, thus providing a discriminant basis for the final network behaviors To verify the effectiveness of our proposed method, we perform experimental validation on the KDD-Cup 1999 (kdd-99) dataset. The results show that our proposed method achieves an accuracy of 98.48% in the identification of network security elements. In addition to this, we also compare and analyze our proposed algorithm with other mainstream algorithms, and the results also validate the effectiveness of our proposed method.

In power systems, the destruction of some important nodes may cause cascading faults. If the most important node in the power system can be found, the important node can be protected in advance, thereby avoiding a blackout accident. At present, the evaluation algorithm of node importance is calculated based on the power flow of the power grid, so the calculation results must be lagging behind, and it does not have the ability to provide early warning for the power grid to provide protection signals. Therefore, it is necessary to predict the importance of nodes in the power system. After using a reasonable prediction model to predict the importance of nodes, we can simulate the future state of power system operation and avoid accidents for the dispatching agency of the power grid company according to the prediction results. This paper proposes a prediction model based on convolutional long short-term memory (ConvLSTM) to predict the importance of nodes. This method has obvious advantages over the long short-term memory (LSTM) network. The convolution operation is used to replace the original full connection operation of the LSTM network, which not only utilizes the advantages of convolution to extract spatial features but also retains the ability of LSTM to process time-series features. The simulation results show that the prediction of node importance using the ConvLSTM network is much more accurate than LSTM. Using statistical indicators to compare and analyze the prediction results, it can be seen that ConvLSTM has higher prediction accuracy. Therefore, using the ConvLSTM model to predict node importance has certain significance for grid dispatching agencies to accurately simulate the future state of the power system and avoid risks in advance.

An early warning flood forecasting system that uses machine-learning models can be utilized for saving lives from floods, which are now exacerbated due to climate change. Flood forecasting is carried out by determining the river discharge and water level using hydrologic models at the target sites. If the water level and discharge are forecasted to reach dangerous levels, the flood forecasting system sends warning messages to residents in flood-prone areas. In the past, hybrid Long Short-Term Memory (LSTM) models have been successfully used for the time series forecasting. However, the prediction errors grow exponentially with the forecasting period, making the forecast unreliable as an early warning tool with enough lead time. Therefore, this research aimed to improve the accuracy of flood forecasting models by employing real-time monitoring network datasets and establishing temporal and spatial links between adjacent monitoring stations. We evaluated the performance of the LSTM, the Convolutional Neural Networks LSTM (CNN-LSTM), the Convolutional LSTM (ConvLSTM), and the Spatio-Temporal Attention LSTM (STA-LSTM) models for flood forecasting. The dataset, employed for validation, includes hourly discharge records, from 2012 to 2017, on six stations of the Humber River in the City of Toronto, Canada. Experiments included forecasting for both 6 and 12 h ahead, using discharge data as input for the past 24 h. The STA-LSTM model’s performance was superior to the CNN-LSTM, the ConvLSTM, and the basic LSTM models when the forecast time was longer than 6 h.

The development of Internet-of-Things (IoT) technology promotes the advances of grain condition detection and analysis systems. Temperature monitoring is a main element to maintain grain quality, and effective control of grain temperature is crucial to safe storage of grain. In this article, an encoder–decoder model with attention mechanism is proposed to accurately forecast the temperature of stored grain. Considering that the points on the gradient direction of the temperature surface have a great influence on the temperature of the target point, the Sobel operator is used to extract the local characteristics of the target point. In addition, considering the correlation structure in the sensory data, the attention mechanism is used to extract the global features of the target point. The extracted spatial features are fed into long short-term memory (LSTM) networks to obtain the long-term state information of spatial factors. LSTM unit and convolutional neural network are used to encode the spatial features of the target points. Taking meteorological factors as the external input of the decoder, temporal attention mechanism and LSTM unit are used to complete the decoding process and realize the prediction of grain temperature in the future. The results with real grain storage data show that the proposed model outperforms several schemes, including Kalman-modified the least absolute shrinkage and selection operator (Kalman-modified LASSO), temporal graph convolutional network (T-GCN), LSTM, CNN-LSTM, and convolutional LSTM (Conv-LSTM), with considerable gains.

Time series prediction is a widely used key technology, and traffic flow prediction is its typical application scenario. Traditional time series prediction models such as LSTM (Long Short- Term Memory) and CNN (Convolution Neural Network)-based models have limitations in dealing with complex nonlinear time dependencies and are difficult to capture the complex characteristics of traffic flow data. In addition, traditional methods usually rely on manually designed attention mechanisms and are difficult to adaptively focus on key features. To improve the accuracy of time series prediction, the paper proposes a multiscale convolutional attention long short-term memory model (MSCALSTM), which combines a multiscale convolutional neural network (MSCNN), a multiscale convolutional block attention module (MSCBAM) and LSTM. MSCNN can effectively capture multiscale dynamic patterns in time series data, MSCBAM can adaptively focus on key features, and LSTM is good at modeling complex time dependencies. The MSCALSTM model makes full use of the advantages of the above technologies and greatly improves the accuracy and robustness of time series prediction. Extensive experiments are conducted on a dataset from the California Performance Measurement System (PEMS), and the results show that the proposed MSCALSTM model outperforms the state-of-the-art models. Experiments in the Energy domain show that our model also has strong generalization properties in other time series forecasting domains.

In the task of image captioning, learning the attentive image regions is necessary to adaptively and precisely focus on the object semantics relevant to each decoded word. In this paper, we propose a convolutional attention module that can preserve the spatial structure of the image by performing the convolution operation directly on the 2D feature maps. The proposed attention mechanism contains two components: convolutional spatial attention and cross-channel attention, aiming to determine the intended regions to describe the image along the spatial and channel dimensions, respectively. Both of the two attentions are calculated at each decoding step. In order to preserve the spatial structure, instead of operating on the vector representation of each image grid, the two attention components are both computed directly on the entire feature maps with convolution operations. Experiments on two large-scale datasets (MSCOCO and Flickr30K) demonstrate the outstanding performance of our proposed method.

The development of Internet technology and cloud computing has promoted the rapid development of self-media technology. The self-media technology has better people-friendliness compared to the traditional media communication mode, so it has gained more popularity compared to the traditional media mode. For professional self-media teams, the popularity and clicks of self-media content are very critical. It needs to make corresponding predictions and judgments according to the content and transmission path of the self-media. However, self-media is transmitted in the form of video, which involves a huge amount of data. This team of self-media staff is a more difficult and tedious task. This study uses the atrous convolution and long short-term memory neural network to predict the video content, sound features, and propagation path of self-media technology. Atrous convolution is more suitable for research objects with more data. The research results show that the atrous convolution and LSTM methods have better feasibility and credibility in predicting three special characteristics of self-media. Compared with a single atrous convolution, the feature prediction errors of the three kinds of self-media are smaller by using the atrous convolution and LSTM hybrid method. The largest prediction error is 2.39%, and this part of the error is mainly due to the sound characteristics of self-media technology.

We propose a convolutional long short-term memory(ConvLSTM)-based neural network for video semantic segmentation. The network can capture the timing information between frames through the ConvLSTM module to improve the prediction accuracy. The back-bone network uses dense connection, atrous convolution, and pooling pyramid structure to expand the receptive field. During the training, to avoid over fitting, data augmentation and learning rate attenuation strategies were used. The proposed method is end-to-end trainable and evaluated on the street scene benchmark Cityscapes dataset. Experimental results show that, benefit from the ConvLSTM module, the proposed network can extract temporal information between frames effectively, and thus improve the accuracy of video semantic segmentation, especially for dynamic objects and small obiects. such as truck. pedestrian and pole.

Considering the increased risk of urban flooding and drought due to global climate change and rapid urbanization, the imperative for more accurate methods for streamflow forecasting has intensified. This study introduces a pioneering approach leveraging the available network of real-time monitoring stations and advanced machine learning algorithms that can accurately simulate spatial–temporal problems. The Spatio-Temporal Attention Gated Recurrent Unit (STA-GRU) model is renowned for its computational efficacy in forecasting streamflow events with a forecast horizon of 7 days. The novel integration of the groundwater level, precipitation, and river discharge as predictive variables offers a holistic view of the hydrological cycle, enhancing the model’s accuracy. Our findings reveal that for a 7-day forecasting period, the STA-GRU model demonstrates superior performance, with a notable improvement in mean absolute percentage error (MAPE) values and R-square (R2) alongside reductions in the root mean squared error (RMSE) and mean absolute error (MAE) metrics, underscoring the model’s generalizability and reliability. Comparative analysis with seven conventional deep learning models, including the Long Short-Term Memory (LSTM), the Convolutional Neural Network LSTM (CNNLSTM), the Convolutional LSTM (ConvLSTM), the Spatio-Temporal Attention LSTM (STA-LSTM), the Gated Recurrent Unit (GRU), the Convolutional Neural Network GRU (CNNGRU), and the STA-GRU, confirms the superior predictive power of the STA-LSTM and STA-GRU models when faced with long-term prediction. This research marks a significant shift towards an integrated network of real-time monitoring stations with advanced deep-learning algorithms for streamflow forecasting, emphasizing the importance of spatially and temporally encompassing streamflow variability within an urban watershed’s stream network.

Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few approaches can achieve real-time online object detection in videos. In this paper, based on the attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for real-world detection. Distinct from the previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLSTM, and design a novel structure, including a low-level temporal unit as well as a high-level one for multiscale feature maps. Moreover, we develop a creative temporal analysis unit, namely, attentional ConvLSTM, in which a temporal attention mechanism is specially tailored for background suppression and scale suppression, while a ConvLSTM integrates attention-aware features across time. An association loss and a multistep training are designed for temporal coherence. Besides, an online tubelet analysis (OTA) is exploited for identification. Our framework is evaluated on ImageNet VID dataset and 2DMOT15 dataset. Extensive comparisons on the detection and tracking capability validate the superiority of the proposed approach. Consequently, the developed TSSD-OTA achieves a fast speed and an overall competitive performance in terms of detection and tracking. Finally, a real-world maneuver is conducted for underwater object grasping.

Precipitation nowcasting is extremely important in disaster prevention and mitigation, and can improve the quality of meteorological forecasts. In recent years, deep learning-based spatiotemporal sequence prediction models have been widely used in precipitation nowcasting, obtaining better prediction results than numerical weather prediction models and traditional radar echo extrapolation results. Because existing deep learning models rarely consider the inherent interactions between the model input data and the previous output, model prediction results do not sufficiently meet the actual forecast requirement. We propose a Modified Convolutional Gated Recurrent Unit (M-ConvGRU) model that performs convolution operations on the input data and previous output of a GRU network. Moreover, this adopts an encoder–forecaster structure to better capture the characteristics of spatiotemporal correlation in radar echo maps. The results of multiple experiments demonstrate the effectiveness of the proposed model. The balanced mean absolute error (B-MAE) and balanced mean squared error (B-MSE) of M-ConvGRU are slightly lower than Convolutional Long Short-Term Memory (ConvLSTM), but the mean absolute error (MAE) and mean squared error (MSE) of M-ConvGRU are 6.29% and 10.25% lower than ConvLSTM, and the prediction accuracy and prediction performance for strong echo regions were also improved.

The operations of power systems are becoming more challenging on account of the high penetration of renewable power generation, including photovoltaic systems. One method for improving the power system operation involves making accurate forecasts of day-ahead solar irradiation, enabling operators to minimize uncertainty in managing the balance between generation and load. To overcome the limitations of Long Short-term Memory (LSTM) in a one-dimensional forecasting problem, this work proposes a novel method in forecasting solar irradiation by encoding time-series data into images using the Gramian Angular Field and the Convolutional LSTM (ConvLSTM) network. The pre-processed data become a five-dimensional input tensor that is perfectly suitable for ConvLSTM. The ConvLSTM network uses convolution operations in its input-to-state transition and state-to-state transition. The network thus enables time-series forecasting by a feature-rich approach, which ultimately provides competitive forecasting performance despite the use of a small dataset. The proposed method was evaluated in day-ahead solar irradiation forecasting using a univariate dataset of Global Horizontal Irradiation (GHI) data from Fuhai in Taiwan. The proposed method was resampled using 5×2-fold cross-validation, and assessed using the Wilcoxon signed-rank test to determine the statistical significance of the result. It outperformed benchmark methods such as Autoregressive Integrated Moving Average (ARIMA), Convolutional Neural Network cascaded with Long Short-term Memory (CNN-LSTM), and LSTM cascaded with a fully-connected (FC) network.

Polarimetric high resolution range profile (HRRP) holds great potential for radar automatic target recognition (RATR) owing to its capability of providing both polarimetric and spatial scattering information. Conventional polarimetric HRRP recognition methods generally extract a set of features and put them into a well-trained classifier, which heavily rely on expertise. On the contrary, deep learning can automatically learn deep features of the training data and has obtained state-of-the-art results in many classification tasks. In this article, a novel deep model based on convolutional long short-term memory (ConvLSTM) network and self-attention mechanism is proposed for polarimetric HRRP recognition. In the proposed model, ConvLSTM employs the convolutional operator and recurrent LSTM structure to capture and aggregate target polarimetric and spatial scattering information from different dimensions simultaneously. Self-attention mechanism is introduced before ConvLSTM to make the model focus on the discriminative range cells and help improve the learning capacity of ConvLSTM. Experiment results on the simulated and measured datasets demonstrate the effectiveness of the proposed model for multi-class targets recognition. The results of two expanded experiments also show that this model performs well in noise and small training sample cases, showcasing good potentials in practical applications.