Explore the vast range of titles available.

High‐precision observation of significant wave height (SWH) is crucial for marine research. The Surface Waves Investigation and Monitoring (SWIM) aboard the China France Oceanography Satellite (CFOSAT) provides the ocean wave spectrum that allows for the calculation of the off‐nadir SWH parameters, but there exists a certain bias with the in‐situ SWH values. To improve the accuracy of the SWH calculation bias from the off‐nadir 6°, 8°, 10° wave spectra and the whole combined spectrum, this paper establishes a spatio‐temporal hybrid model that combines convolutional neural network (CNN) and long short‐term memory network (LSTM). Additionally, to further correct bias exhibited under high sea state, we introduce a bias correction module based on deep neural network (DNN) to adjust the SWIM off‐nadir SWH greater than 4 m. The experimental results demonstrate a significant enhancement in the accuracy of corrected SWIM off‐nadir SWH, and the best calibration result is 10° with 0.267 m root mean square error (RMSE), and 0.979 correlation coefficient (R) compared with the ERA5 value. We conducted a comprehensive study and analysis on the performance of the proposed model under different wave heights, extreme sea states, and wind and swell regions. Meanwhile, the buoy and altimeters are leveraged to render further evaluation the RMSE of the corrected SWH is less than 0.5 m. Plain Language Summary The Surface Waves Investigation and Monitoring (SWIM) on the China France Oceanography Satellite (CFOSAT) provides wave data support for ocean research. However, the significant wave height (SWH) parameter calculated from the SWIM off‐nadir spectra has a certain bias from the real value due to the influence of speckle noise. In order to improve the accuracy of the SWIM off‐nadir SWH parameter, we developed a CNN‐LSTM model and introduced a high sea state bias correction network to improve the accuracy of SWH and achieve the purpose of correction. The analysis evaluated the correction performance across various sea conditions, comparing the corrected SWH data with measurements from altimeters and buoys. The findings demonstrated that the root mean square error of the corrected SWH was consistently below 0.5 m, with a correlation coefficient exceeding 0.940. This underscores the effectiveness of our model in enhancing the precision of nadir SWH data bias from SWIM instruments. Key Points A model of convolutional and long short‐term memory neural network is developed to calibrate the surface waves investigation and monitoring (SWIM) off‐nadir significant wave height The corrected SWIM off‐nadir significant wave height achieves comparable accuracy with the Jason‐3, HY‐2B, and buoys The proposed model performs well in the calibration of the wind wave region and the swell region

In modern society, air pollution is an important topic as this pollution exerts a critically bad influence on human health and the environment. Among air pollutants, Particulate Matter (PM2.5) consists of suspended particles with a diameter equal to or less than 2.5 μm. Sources of PM2.5 can be coal-fired power generation, smoke, or dusts. These suspended particles in the air can damage the respiratory and cardiovascular systems of the human body, which may further lead to other diseases such as asthma, lung cancer, or cardiovascular diseases. To monitor and estimate the PM2.5 concentration, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are combined and applied to the PM2.5 forecasting system. To compare the overall performance of each algorithm, four measurement indexes, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) Pearson correlation coefficient and Index of Agreement (IA) are applied to the experiments in this paper. Compared with other machine learning methods, the experimental results showed that the forecasting accuracy of the proposed CNN-LSTM model (APNet) is verified to be the highest in this paper. For the CNN-LSTM model, its feasibility and practicability to forecast the PM2.5 concentration are also verified in this paper. The main contribution of this paper is to develop a deep neural network model that integrates the CNN and LSTM architectures, and through historical data such as cumulated hours of rain, cumulated wind speed and PM2.5 concentration. In the future, this study can also be applied to the prevention and control of PM2.5.

The utilization of monitoring sensors in machinery has led to the mainstream adoption of fault detection and diagnosis in time series data across various industrial applications. Deep learning techniques, specifically in constructing fault diagnosis models by extracting insights from historical equipment fault data, are receiving widespread attention as crucial tools in ensuring the safety and reliability of motor systems. In this study, a CNN-LSTM-based deep learning model is proposed for the detection of electric motor faults. Three distinct sets of accelerometer sensor data are provided as input to the model, enabling a comprehensive evaluation of its performance across various sensor configurations. The model demonstrated a remarkable capacity for generalization, achieving impressive accuracy rates of 99.96% for Accelerometer-1, 98.88% for Accelerometer-2, and 99.37% for Accelerometer-3. This underscores the robustness and adaptability of the proposed CNN-LSTM model in effectively detecting electric motor faults regardless of the specific accelerometer sensor employed.

Water quality prediction is a fundamental and necessary task for the prevention and management of water environment pollution. Due to the fluidity of water, different sections of the same river have similar trends in their water quality. The present water quality prediction methods cannot exploit the correlation between the water quality of each section to deeply capture information because they do not take into account how similar the water quality is between sections. In order to address this issue, this paper constructs a water quality prediction model based on multi-task deep learning, taking the chemical oxygen demand (COD) of the water environment of the Lanzhou portion of the Yellow River as the research object. The multiple sections of correlation are trained and learned in this model at the same time, and the water quality information of each section is shared while retaining their respective heterogeneity, and the hybrid model CNN-LSTM is used for better mining from local to full time series features of water quality information. In comparison to the current single-section water quality prediction, experiments have shown that the model’s mean absolute error (MSE) and root mean square error (RMSE) of the predicted value of the model are decreased by 13.2% and 15.5%, respectively, and that it performs better in terms of time stability and generalization.

The ultrasonic guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects in metallic pipelines. The signal processing of guided waves is often challenging due to the complexity of the operational conditions and environment in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for the signal processing and data classification of complex systems, thus showing great potential for damage detection in critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model was utilized for decoding ultrasonic guided waves for damage detection in metallic pipelines, and twenty-nine features were extracted as input to classify different types of defects in metallic pipes. The prediction capacity of the CNN-LSTM model was assessed by comparing it to those of CNN and LSTM. The results demonstrated that the CNN-LSTM hybrid model exhibited much higher accuracy, reaching 94.8%, as compared to CNN and LSTM. Interestingly, the results also revealed that predetermined features, including the time, frequency, and time–frequency domains, could significantly improve the robustness of deep learning approaches, even though deep learning approaches are often believed to include automated feature extraction, without hand-crafted steps as in shallow learning. Furthermore, the CNN-LSTM model displayed higher performance when the noise level was relatively low (e.g., SNR = 9 or higher), as compared to the other two models, but its prediction dropped gradually with the increase of the noise.

Real-time service (RTS) products are an important guarantee for real-time precise point positioning (RT-PPP), and the RTS outages caused by loss of network connection are a concern. In this paper, a multivariate CNN-LSTM model is proposed for short-term BDS satellite clock offset prediction during the discontinuity in receiving RTS clock offsets, which utilizes the superior feature of convolution neural network (CNN) and long short-term memory (LSTM) for simultaneous prediction of multiple satellite clock offsets by considering the inter-satellite correlation. First, the correlation between satellite clock offsets was analyzed to identify satellites suitable for parallel prediction. Then, to preserve the sequential structure of the features extracted from multiple parallel satellite clock offsets, remove the pooling layer of traditional CNN, and use the convolution layer to learn the relationships and dependencies between clock offsets of different satellites and the LSTM layer to model the temporal dependencies in satellite clock offsets. The experiment results show that the computational efficiency of the proposed model is significantly better than that of autoregressive integrated moving average (ARIMA), wavelet neural network (WNN), and LSTM models. Compared with the linear polynomial (LP), quadratic polynomial model (QP), ARIMA, WNN, and the LSTM models, the prediction accuracy of the multivariate CNN-LSTM model for 5 min, 15 min, 30 min, and 1 h is improved by approximately (84.0, 76.6, 1.5, 8.3, 8.3)%, (72.0, 62.6, 6.0, 15.3, 18.7)%, (57.1, 48.5, 11.3, 18.4, 23.3)%, and (34.9, 35.1, 27.3, 21.8, 26.3)%, respectively.

The large-scale production of edible mushrooms typically requires the use of greenhouses, as the greenhouse environment significantly affects the growth of edible mushrooms. It is crucial to effectively predict the temperature, humidity, and carbon dioxide fluctuations within the mushroom greenhouse for determining the environmental stress and pre-regulation of edible mushrooms. To address the nonlinearity, temporal dynamics, and strong coupling of the edible mushroom greenhouse environment, a temperature, humidity, and carbon dioxide prediction model based on the combination of the attention mechanism, the convolutional neural network, and the long short-term memory neural network (A-CNN-LSTM) is proposed. Experimental data were collected from both the inside and outside of the greenhouse, including environmental data and the on–off data of environmental control devices. After completing missing data using linear interpolation, denoising with Kalman filtering, and normalization, the recurrent neural network (RNN) model, long short-term memory (LSTM) model, and A-CNN-LSTM model were trained and tested on the time series data. These models were used to predict the environmental changes in temperature, humidity, and carbon dioxide inside the greenhouse. The results indicate that the A-CNN-LSTM model outperforms the other two models in terms of denoising, non-denoising, and different prediction time steps. The proposed method accurately predicts temperature, humidity, and carbon dioxide levels with errors of 0.17 °C (R2 = 0.974), 2.06% (R2 = 0.804), and 8.367 ppm (R2 = 0.993), respectively. These results indicate improved prediction accuracy for temperature, humidity, and carbon dioxide values inside the edible mushroom greenhouse. The findings provide a decision basis for the precise control of the greenhouse environment.

Music classification has achieved great progress due to the development of Convolutional Neural Networks (CNNs), which is important for music retrieval and recommendation. However, CNN cannot capture temporal information from music audio, which restricts the prediction performance of the model. To address the issue, we propose a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) model to learn local spatial features by CNN and learn temporal dependencies by LSTM. In addition, the traditional softmax loss function commonly lacks sufficient discrimination in music classification. Therefore, we propose an additive angular margin and cosine margin softmax (AACM-Softmax) loss function to improve classification results, which minimizes intra-class variances and maximizes inter-class variances simultaneously by enforcing combined margin penalties. Furthermore, we combine the CNN-LSTM model with AACM-Softmax loss function to comprehensively improve the classification performance by learning temporal-dependencies-included discriminative essential features. Extensive experiments on music genre datasets and music emotion datasets show that the proposed model consistently outperforms other models.

Soil volumetric water content (VWC) is one of the key factors in hydrological cycles and responsible for inducing droughts and floods. Therefore, the precise prediction of VWC is crucial for the effective management of water resources. However, the complexity in structural characteristics and interaction with several other external meteorological factors cause difficulty in establishing a mathematical model which can predict soil VWC accurately. This study demonstrates the applicability of Convolution Neural Network-Long short-term memory (CNN-LSTM) hybrid model to predict soil VWC (%), concentrating specifically on optimizing the predictors combination using recursive feature elimination (RFE) which results in a more interpretable model with less complexity. The model was developed using the data collected from Benton County of Washington, USA, and generalization capacity of the model was tested in other counties of Washington. To verify the improved prediction ability of the proposed model, the results were compared with the established CNN, LSTM and MLR models. The results reflected that the proposed CNN-LSTM model predicted better than the individual CNN, LSTM and MLR models for the training site as well as for the five testing sites, proving its good generalization capacity.