Search Results (200)

Developing short-term forecasting models for global atmospheric temperature and wind in near space is crucial for understanding atmospheric dynamics and supporting human activities in this region. While numerical models have been extensively developed, deep learning techniques have recently shown promise in improving atmospheric forecasting accuracy. In this study, convolutional long short-term memory (ConvLSTM) and convolutional gated recurrent unit (ConvGRU) neural networks were applied to build for short-term global-scale forecasting model of atmospheric temperature and wind in near space based on the MERRA-2 reanalysis dataset from 2010–2022. The model results showed that the ConvGRU model outperforms the ConvLSTM model in the short-term forecast results. The ConvGRU model achieved a root mean square error in the first three hours of approximately 1.8 K for temperature predictions, and errors of 4.2 m/s and 3.8 m/s for eastward and northward wind predictions on all 72 isobaric surfaces. Specifically, at a higher altitude (on the 1.65 Pa isobaric surface, approximately 70 km above sea level), the ConvGRU model achieved a RMSE of about 2.85 K for temperature predictions, and 5.67 m/s and 5.17 m/s for eastward and northward wind. This finding is significantly meaningful for short-term temperature and wind forecasts in near space and for exploring the physical mechanisms related to temperature and wind variations in this region. Full article

Livestock grazing is a major land use in the Great Barrier Reef Catchment Area (GBRCA). Heightened grazing density coupled with inadequate land management leads to accelerated soil erosion and increased sediment loads being transported downstream. Ultimately, these increased sediment loads impact the water quality of the Great Barrier Reef (GBR) lagoon. Ground cover mapping has been adopted to monitor and assess the land condition in the GBRCA. However, accurate prediction of ground cover remains a vital knowledge gap to inform proactive approaches for improving land conditions. Herein, we explored two deep learning-based spatio-temporal prediction models, including convolutional LSTM (ConvLSTM) and Predictive Recurrent Neural Network (PredRNN), to predict future ground cover. The two models were evaluated on different spatial scales, ranging from a small site (i.e., <5 km²) to the entire GBRCA, with different quantities of training data. Following comparisons against 25% withheld testing data, we found the following: (1) both ConvLSTM and PredRNN accurately predicted the next-season ground cover for not only a single site but also the entire GBRCA. They achieved this with a Mean Absolute Error (MAE) under 5% and a Structural Similarity Index Measure (SSIM) exceeding 0.65; (2) PredRNN superseded ConvLSTM by providing more accurate next-season predictions with better training efficiency; (3) The accuracy of PredRNN varies seasonally and spatially, with lower accuracy observed for low ground cover, which is underestimated. The models assessed in this study can serve as an early-alert tool to produce high-accuracy and high-resolution ground cover prediction one season earlier than observation for the entire GBRCA, which enables local authorities and grazing property owners to take preventive measures to improve land conditions. This study also offers a new perspective on the future utilization of predictive spatio-temporal models, particularly over large spatial scales and across varying environmental sites. Full article

Ultra-Wideband (UWB) technology is crucial for indoor localization systems due to its high accuracy and robustness in multipath environments. However, Non-Line-of-Sight (NLoS) conditions can cause UWB signal distortion, significantly reducing positioning accuracy. Thus, distinguishing between NLoS and LoS scenarios and mitigating positioning errors is crucial for enhancing UWB system performance. This research proposes a novel 1D-ConvLSTM-Attention network (1D-CLANet) for extracting UWB temporal channel impulse response (CIR) features and identifying NLoS scenarios. The model combines the convolutional neural network (CNN) and Long Short-Term memory (LSTM) architectures to extract temporal CIR features and introduces the Squeeze-and-Excitation (SE) attention mechanism to enhance critical features. Integrating SE attention with LSTM outputs boosts the model’s ability to differentiate between various NLoS categories. Experimental results show that the proposed 1D-CLANet with SE attention achieves superior performance in differentiating multiple NLoS scenarios with limited computational resources, attaining an accuracy of 95.58%. It outperforms other attention mechanisms and the version of 1D-CLANet without attention. Compared to advanced methods, the SE-enhanced 1D-CLANet significantly improves the ability to distinguish between LoS and similar NLoS scenarios, such as human obstructions, enhancing overall recognition accuracy in complex environments. Full article

While machine learning methods have been successful in predicting air pollution, current deep learning models usually focus only on the time-based connection of air quality monitoring stations or the complex link between PM2.5 levels and explanatory factors. Due to the lack of effective integration of spatial correlation, the prediction model shows poor performance in PM2.5 prediction tasks. Predicting air pollution levels accurately over a long period is difficult because of the changing levels of correlation between past pollution levels and the future. In order to address these challenges, the study introduces a Convolutional Long Short-Term Memory (ConvLSTM) network-based neural network model with multiple feature extraction for forecasting PM2.5 levels in air quality prediction. The technique is composed of three components. The model-building process of this article is as follows: Firstly, we create a complex network layout with multiple branches to capture various temporal features at different levels. Secondly, a convolutional module was introduced to enable the model to focus on identifying neighborhood units, extracting feature scales with high spatial correlation, and helping to improve the learning ability of ConvLSTM. Next, the module for spatiotemporal fusion prediction is utilized to make predictions of PM2.5 over time and space, generating fused prediction outcomes that combine characteristics from various scales. Comparative experiments were conducted. Experimental findings indicate that the proposed approach outperforms ConvLSTM in forecasting PM2.5 concentration for the following day, three days, and seven days, resulting in a lower root mean square error (RMSE). This approach excels in modeling spatiotemporal features and is well-suited for predicting PM2.5 levels in specific regions. Full article

Facial expressions are a universally recognised means of conveying internal emotional states across diverse human cultural and ethnic groups. Recent advances in understanding people’s emotions expressed through verbal and non-verbal communication are particularly noteworthy in the clinical context for the assessment of patients’ health and well-being. Facial expression recognition (FER) plays an important and vital role in health care, providing communication with a patient’s feelings and allowing the assessment and monitoring of mental and physical health conditions. This paper shows that automatic machine learning methods can predict health deterioration accurately and robustly, independent of human subjective assessment. The prior work of this paper is to discover the early signs of deteriorating health that align with the principles of preventive reactions, improving health outcomes and human survival, and promoting overall health and well-being. Therefore, methods are developed to create a facial database mimicking the underlying muscular structure of the face, whose Action Unit motions can then be transferred to human face images, thus displaying animated expressions of interest. Then, building and developing an automatic system based on convolution neural networks (CNN) and long short-term memory (LSTM) to recognise patterns of facial expressions with a focus on patients at risk of deterioration in hospital wards. This research presents state-of-the-art results on generating and modelling synthetic database and automated deterioration prediction through FEs with 99.89% accuracy. The main contributions to knowledge from this paper can be summarized as (1) the generation of visual datasets mimicking real-life samples of facial expressions indicating health deterioration, (2) improvement of the understanding and communication with patients at risk of deterioration through facial expression analysis, and (3) development of a state-of-the-art model to recognize such facial expressions using a ConvLSTM model. Full article

Sea Surface Temperature (SST) is of great importance to study several major phenomena due to ocean interactions with other earth systems. Previous studies on SST based on statistical inference methods were less accurate for longer prediction lengths. A considerable number of studies in recent years involve machine learning for SST modeling. These models were able to mitigate this problem to some length by modeling SST patterns and trends. Sequence analysis by decomposition is used for SST forecasting in several studies. Ensemble Empirical Mode Decomposition (EEMD) has been proven in previous studies as a useful method for this. The application of EEMD in spatiotemporal modeling has been introduced as Multidimensional EEMD (MEEMD). The aim of this study is to employ fast MEEMD methods to decompose the SST spatiotemporal dataset and apply a Convolutional Long Short-Term Memory (ConvLSTM)-based model to model and forecast SST. The results show that the fast MEEMD method is capable of enhancing spatiotemporal SST modeling compared to the Linear Inverse Model (LIM) and ConvLSTM model without decomposition. The model was further validated by making predictions from April to May 2023 and comparing them to original SST values. There was a high consistency between predicted and real SST values. 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

To enhance the safety of grid operations, this paper proposes a high-precision short-term photovoltaic (PV) power forecasting method that integrates information from surrounding PV stations and deep learning prediction models. The proposed method utilizes numerical weather prediction (NWP) data of the target PV station and highly correlated features from nearby stations as inputs. This study first analyzes the correlation between irradiance and power sequences and calculates a comprehensive similarity index based on distance factors. Stations with high-similarity indices are selected as data sources. Subsequently, Bayesian optimization is employed to determine the optimal data fusion ratio. The selected data are then used to model power predictions through the convolutional long short-term memory with attention (Conv-LSTM-ATT) deep neural network. Experimental results show that the proposed model significantly outperforms three classical models in terms of forecasting accuracy. The data fusion strategy determined by Bayesian optimization reduces the root mean square error (RMSE) of the test set by 20.04%, 28.24%, and 30.94% under sunny, cloudy, and rainy conditions, respectively. Full article

Grain is a commodity related to the livelihood of the nation’s people, and the volatility of its futures price affects risk management, investment decisions, and policy making. Therefore, it is very necessary to establish an accurate and efficient futures price prediction model. Aiming at improving the accuracy and efficiency of the prediction model, so as to support reasonable decision making, this paper proposes a Bi-DSConvLSTM-Attention model for grain futures price prediction, which is based on the combination of a bidirectional long short-term memory neural network (BiLSTM), a depthwise separable convolutional long short-term memory neural network (DSConvLSTM), and an attention mechanism. Firstly, the mutual information is used to evaluate, sort, and select the features for dimension reduction. Secondly, the lightweight depthwise separable convolution (DSConv) is introduced to replace the standard convolution (SConv) in ConvLSTM without sacrificing its performance. Then, the self-attention mechanism is adopted to improve the accuracy. Finally, taking the wheat futures price prediction as an example, the model is trained and its performance is evaluated. Under the Bi-DSConvLSTM-Attention model, the experimental results of selecting the most relevant 1, 2, 3, 4, 5, 6, and 7 features as the inputs showed that the optimal number of features to be selected was 4. When the four best features were selected as the inputs, the RMSE, MAE, MAPE, and $R^2$ of the prediction result of the Bi-DSConvLSTM-Attention model were 5.61, 3.63, 0.55, and 0.9984, respectively, which is a great improvement compared with the existing price-prediction models. Other experimental results demonstrated that the model also possesses a certain degree of generalization and is capable of obtaining positive returns. Full article

Short-term precipitation forecasting methods are mainly divided into statistical forecasting, numerical model-based forecasting, and radar image extrapolation techniques. The two methods based on statistical prediction and numerical model have the disadvantages of being unstable and generating large errors. Therefore, this study proposes the use of deep learning for radar image extrapolation for precipitation forecasting, in particular by developing algorithms for ConvLSTM and SmaAT-UNet. The ConvLSTM model is a fusion of a CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory network), which solves the challenge of processing spatial sequence data, which is a task that traditional LSTM models cannot accomplish. At the same time, SmaAT-UNet enhances the traditional UNet structure by incorporating the CBAM (Convolutional Block Attention Module) attention mechanism and replacing the standard convolutional layer with depthwise separable convolution. This innovative approach aims to improve the efficiency and accuracy of short-term precipitation forecasting by improving feature extraction and data processing techniques. Evaluation and analysis of experimental data show that both models exhibit good predictive ability, with the SmaAT-UNet model outperforming ConvLSTM in terms of accuracy. The results show that the performance indicators of precipitation prediction, especially detection probability (POD) and the Critical Success index (CSI), show a downward trend with the extension of the prediction time. This trend highlights the inherent challenges of maintaining predictive accuracy over longer periods of time and highlights the superior performance and resilience of the SmaAT-UNet model under these conditions. Compared with the statistical forecasting method and numerical model forecasting method, its accuracy in short-term rainfall forecasting is improved. Full article

The road passenger transportation enterprise is a complex system, requiring a clear understanding of their active safety situation (ASS), trends, and influencing factors. This facilitates transportation authorities to promptly receive signals and take effective measures. Through exploratory factor analysis and confirmatory factor analysis, we delved into potential factors for evaluating ASS and extracted an ASS index. To predict obtaining a higher ASS information rate, we compared multiple time series models, including GRU (gated recurrent unit), LSTM (long short-term memory), ARIMA, Prophet, Conv_LSTM, and TCN (temporal convolutional network). This paper proposed the WDA-DBN (water drop algorithm-Deep Belief Network) model and employed DEEPSHAP to identify factors with higher ASS information content. TCN and GRU performed well in the prediction. Compared to the other models, WDA-DBN exhibited the best performance in terms of MSE and MAE. Overall, deep learning models outperform econometric models in terms of information processing. The total time spent processing alarms positively influences ASS, while variables such as fatigue driving occurrences, abnormal driving occurrences, and nighttime driving alarm occurrences have a negative impact on ASS. Full article

The rapid and accurate forecasting of two-phase flow in porous media is a critical challenge in oil field development, exerting a substantial impact on optimization and decision-making processes. Although the Convolutional Long Short-Term Memory (ConvLSTM) network effectively captures spatiotemporal dynamics, its generalization in predicting complex engineering problems remains limited. Similarly, although the Fourier Neural Operator (FNO) demonstrates adeptness at learning operators for solving partial differential equations (PDEs), it struggles with three-dimensional, long-term prediction. In response to these limitations, we introduce an innovative hybrid model, the Convolutional Long Short-Term Memory-Fourier Neural Operator (CL-FNO), specifically designed for the long-term prediction of three-dimensional two-phase flows. This model integrates a 3D convolutional encoder–decoder structure to extract and generate hierarchical spatial features of the flow fields. It incorporates physical constraints to enhance the model’s forecasts with robustness through the infusion of prior knowledge. Additionally, a temporal function, constructed using gated memory-forgetting mechanisms, augments the model’s capacity to analyze time series data. The efficacy and practicality of the CL-FNO model are validated using a synthetic three-dimensional case study and application to an actual reservoir model. Full article

In this paper, we propose a global ionospheric total electron content (TEC) maps (GIM) prediction model based on deep learning methods that is both straightforward and practical, meeting the requirements of various applications. The proposed model utilizes an encoder-decoder structure with a Convolution Long Short-Term Memory (ConvLSTM) network and has a spatial resolution of 5° longitude and 2.5° latitude, with a time resolution of 1 h. We utilized the Center for Orbit Determination in Europe (CODE) GIM dataset for 18 years from 2002 to 2019, without requiring any other external input parameters, to train the ConvLSTM models for forecasting GIM 1, 2, and 3 days in advance. Using the CODE GIM data from 1 January 2020 to 31 December 2023 as the test dataset, the performance evaluation results show that the average root mean square errors (RMSE) for 1, 2 and 3 days of forecasts are 2.81 TECU, 3.16 TECU, and 3.41 TECU, respectively. These results show improved performance compared to the IRI-Plas model and CODE’s 1-day forecast product c1pg, and comparable to CODE’s 2-day forecast c2pg. The model’s predictions get worse as the intensity of the storm increases, and the prediction error of the model increases with the lead time. Full article

Quantitative precipitation estimation (QPE) by radar observation data is a crucial aspect of meteorological forecasting operations. Accurate QPE plays a significant role in mitigating the impact of severe convective weather. Traditional QPE methods mainly employ an exponential Z–R relationship to map the radar reflectivity to precipitation intensity on a point-to-point basis. However, this isolated point-to-point transformation lacks an effective representation of convective systems. Deep learning-based methods can learn the evolution patterns of convective systems from rich historical data. However, current models often rely on 2 km-height CAPPI images, which struggle to capture the complex vertical motions within convective systems. To address this, we propose a novel QPE model: combining the classic extrapolation model ConvLSTM with Unet for an encoder-decoder module assembly. Meanwhile, we utilize three-dimensional radar echo images as inputs and introduce the convolutional block attention module (CBAM) to guide the model to focus on individual cells most likely to trigger intense precipitation, which is symmetrically built on both channel and spatial attention modules. We also employ asymmetry in training using weighted mean squared error to make the model concentrate more on heavy precipitation events which are prone to severe disasters. We conduct experiments using radar data from North China and Eastern China. For precipitation above 1 mm, the proposed model achieves 0.6769 and 0.7910 for CSI and HSS, respectively. The results indicate that compared to other methods, our model significantly enhances precipitation prediction accuracy, with a more pronounced improvement in forecasting accuracy for heavy precipitation events. Full article

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 ($R^2$) 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. Full article