Search

Acoustic tomography is a widely used non-contact method for visualizing temperature distribution. A temperature distribution reconstruction algorithm based on an improved sparse reconstruction model and multi-scale feature fusion network is proposed. First, the acoustic temperature measurement sparse reconstruction model is improved by combining the error function (ERF) and the iterative reweighting algorithm, and the alternating direction method of multipliers algorithm (ADMM) is used to solve the model to obtain the initial temperature distribution. Then the feature extraction network is constructed to extract multi-scale features of acoustic time of flight (TOF) as prior information. Finally, the feature fusion reconstruction network is constructed to fuse and reconstruct the initial temperature distribution and multi-scale features to obtain a high-precision temperature distribution. Simulation and experimental tests were conducted respectively, and compared with other algorithms. The results show that the average relative error and root mean square error of the simulated temperature distribution reconstruction are 0.073% and 0.1% respectively, the average reconstruction error of the temperature points set in the experimental test is 0.38%, and the reconstruction errors are lower than other algorithms. The proposed method effectively utilizes prior information to correct sparse reconstruction temperature distribution reconstruction results, significantly improving the quality of temperature distribution reconstruction. [Display omitted] • Acoustic tomography technology is used for temperature distribution reconstruction. • The improved sparse reconstruction model can improve the accuracy of initial temperature distribution reconstruction. • The feature extraction network can perform multi-scale feature extraction on the time-of-flight of acoustic waves. • The feature fusion reconstruction network can improve the utilization of prior information. [ABSTRACT FROM AUTHOR]

Acoustic tomography is a widely used non-contact method for visualizing temperature distribution. A temperature distribution reconstruction algorithm based on an improved sparse reconstruction model and multi-scale feature fusion network is proposed. First, the acoustic temperature measurement sparse reconstruction model is improved by combining the error function (ERF) and the iterative reweighting algorithm, and the alternating direction method of multipliers algorithm (ADMM) is used to solve the model to obtain the initial temperature distribution. Then the feature extraction network is constructed to extract multi-scale features of acoustic time of flight (TOF) as prior information. Finally, the feature fusion reconstruction network is constructed to fuse and reconstruct the initial temperature distribution and multi-scale features to obtain a high-precision temperature distribution. Simulation and experimental tests were conducted respectively, and compared with other algorithms. The results show that the average relative error and root mean square error of the simulated temperature distribution reconstruction are 0.073% and 0.1% respectively, the average reconstruction error of the temperature points set in the experimental test is 0.38%, and the reconstruction errors are lower than other algorithms. The proposed method effectively utilizes prior information to correct sparse reconstruction temperature distribution reconstruction results, significantly improving the quality of temperature distribution reconstruction. [Display omitted] • Acoustic tomography technology is used for temperature distribution reconstruction. • The improved sparse reconstruction model can improve the accuracy of initial temperature distribution reconstruction. • The feature extraction network can perform multi-scale feature extraction on the time-of-flight of acoustic waves. • The feature fusion reconstruction network can improve the utilization of prior information. [ABSTRACT FROM AUTHOR]

• NDVI time series predictions for the Yellow River Basin, China. • Proposed multivariate Long-Short Term Memory neural network incorporating climate elements. • The common constraining effects of multiple climatic factors on NDVI are fully accounted for in the model proposed in the study. Accurate prediction of the trend of Normalized Difference Vegetation Index (NDVI) time series in the Yellow River Basin (YRB) is crucial for the assessment of the hydrological and ecological environment in this region. Currently, the NDVI time series prediction model is primarily based on traditional models and single-variable neural network models. Nevertheless, these models present challenges in considering the limitations of multiple factors, causing the NDVI time series prediction results to lack reliability. To predict NDVI time-series in the YRB of China, this study constructed a multilayer multivariate Long-Short Term Memory (LSTM) neural network model including climatic components. The initial important climatic elements in this region were identified using GeoDetector. Then, the relationship between NDVI and climatic factors in the YRB of China is established. Finally, numerical scale data are used to train and predict a multilayer multivariate LSTM model with climatic components. According to the results, the three-layer multivariate LSTM neural network NDVI time series prediction model developed in this study has the best performance among the evaluated indices. When compared to existing time series prediction models, the proposed model in this study takes into account the common constraint effect of various climate factors on NDVI. This leads to a significantly improved prediction accuracy, presenting new opportunities for enhancing the prediction model. By analyzing the NDVI time series prediction outcomes for the YRB, it has been determined that the ecological environment of the area will continuously improve in the future. This study offers significant technological and theoretical backing for assessing the hydrological and ecological environment of the YRB and comparable ecologically vulnerable regions in China. [ABSTRACT FROM AUTHOR]

Gas-liquid two-phase flow is closely related to the production and transportation of energy industries. A flow pattern analysis and identification method based on multi-scale power spectral entropy (MPSE) with pseudo-image encoding (PIE) is proposed. The resistance sensor array is used to collect gas-liquid two-phase flow information from the vertical upward pipeline, and the data is dimensionally reduced to simplify analysis. The MPSE is derived from the power spectrum of reduced-dimensional sequences to characterize the frequency domain complexity of the flow system at different scales. The optimal scale for spectral entropy analysis is further calculated to investigate the transition mechanism of gas-liquid two-phase flow patterns. In addition, the PIE algorithm is used to map the power spectrum into two-dimensional grayscale images to visualize the differences in frequency domain features of flow patterns. Combined with the deep learning model ResNeXt, the flow patterns are classified and compared with the traditional identification scheme. Results show that the proposed method can reveal the dynamic evolution behavior of gas-liquid two-phase flow from the frequency domain and achieve accurate identification of the flow patterns. • Gas/liquid two-phase flow information is collected using a resistance sensor array. • The multi-scale power spectral entropy can effectively reveal the transition mechanism of flow patterns. • Pseudo-image encoding can highlight the differences in frequency domain features between flow patterns. • The ResNeXt model can well distinguish the four patterns of gas/liquid two-phase flow. [ABSTRACT FROM AUTHOR]

Accurate landslide extraction is significant for landslide disaster prevention and control. Remote sensing images have been widely used in landslide investigation, and landslide extraction methods based on deep learning combined with remote sensing images (such as U-Net) have received a lot of attention. However, because of the variable shape and texture features of landslides in remote sensing images, the rich spectral features, and the complexity of their surrounding features, landslide extraction using U-Net can lead to problems such as false detection and missed detection. Therefore, this study introduces the channel attention mechanism called the squeeze-and-excitation network (SENet) in the feature fusion part of U-Net; the study also constructs an attention U-Net landside extraction model combining SENet and U-Net, and uses Sentinel-2A remote sensing images for model training and validation. The extraction results are evaluated through different evaluation metrics and compared with those of two models: U-Net and U-Net Backbone (U-Net Without Skip Connection). The results show that proposed the model can effectively extract landslides based on Sentinel-2A remote sensing images with an F1 value of 87.94%, which is about 2% and 3% higher than U-Net and U-Net Backbone, respectively, with less false detection and more accurate extraction results. [ABSTRACT FROM AUTHOR]

Accurate rainfall measurement with a precise spatial and temporal resolution is essential for making informed decisions during disasters and conducting scientific studies, particularly in regions characterized by intricate terrain and limited coverage of automated weather stations. Retrieval of precipitation with satellite is currently the most effective means to obtain precipitation over large‐scale areas. The key to enhancing the accuracy of precipitation estimation and forecasting in regions with complex terrain lies in effectively integrating satellite data with topographic information. This paper introduces a deep learning approach called AttUnet_R_SFT that utilizes high temporal, spatial, and spectral resolution data obtained from the Fengyun 4A satellite, and incorporates the Deep Spatial Feature Transform (SFT) layer to incorporate geographical data for estimating half‐hourly precipitation in northeastern China. We assess it by compared to operational near‐real‐time satellite precipitation products demonstrated to be successful in estimating precipitation and baseline deep learning models. According to the experimental findings, the AttUnet_R_SFT model outperforms practical precipitation products and baseline deep learning models in both identifying and estimating precipitation. The main enhancement of the model performance is shown in the windward slope of the Greater Khingan Mountains as a result of the successful incorporation of geographical data. Hence, the suggested framework holds the capability to function as a superior and dependable satellite‐derived precipitation estimation solution in regions characterized by intricate terrain and infrequent rainfall. The findings of this study indicate that the utilization of deep learning algorithms for satellite precipitation estimation shows potential as a fruitful avenue for further research. Plain Language Summary: A deep learning model named AttUnet_R_SFT is proposed, which use high temporal, spatial and spectral resolution data from the Fengyun 4A satellite, and combines with the Deep Spatial Feature Transform (SFT) layer to input geographic information for half‐hourly precipitation estimation in the complex terrain region represented by northeast China. The model can provide a reference for improving the performance of precipitation estimation in areas with complex topography. Key Points: A deep‐learning model is proposed to effectively fuse satellite multispectral data of the Fengyun 4A satellite, with topographic informationHalf‐hourly precipitation is estimated with higher temporal resolution, which is closer to the operational needs of weather forecastingAs precipitation in the study area is a non‐high‐frequency event, data enhancement is attempted to use and obtain effective results [ABSTRACT FROM AUTHOR]

The forecast uncertainty, particularly for precipitation, serves as a crucial indicator of the reliability of deterministic forecasts. Traditionally, forecast uncertainty is estimated by ensemble forecasting, which is computationally expensive since the forecast model is run multiple times with perturbations. Recently, deep learning methods have been explored to learn the statistical properties of ensemble prediction systems due to their low computational costs. However, accurately and effectively capturing the uncertainty information in precipitation forecasts remains challenging. In this study, we present a novel spatiotemporal transformer network (ST-TransNet) as an alternative approach to estimate uncertainty with ensemble spread and probabilistic forecasts, by learning from historical ensemble forecasts. ST-TransNet features a hierarchical structure for extracting multiscale features and incorporates a spatiotemporal transformer module with window-based attention to capture correlations in both spatial and temporal dimensions. Additionally, window-based attention can not only extract local precipitation patterns but also reduce computational costs. The proposed ST-TransNet is evaluated on the TIGGE ensemble forecast dataset and Global Precipitation Measurement (GPM) precipitation products. Results show that ST-TransNet outperforms both traditional and deep learning methods across various metrics. Case studies further demonstrate its ability to generate reasonable and accurate spread and probability forecasts from a single deterministic precipitation forecast. It demonstrates the capacity and efficiency of neural networks in estimating precipitation forecast uncertainty. [ABSTRACT FROM AUTHOR]

Accurate and timely precipitation forecasts are critical in modern society, influencing both economic activity and daily life. While deep learning methods leveraging remotely sensed radar data have become prevalent for precipitation nowcasting, longer-term forecasting remains challenging. This is due to accumulated errors in deep learning models and insufficient information about precipitation systems over longer time horizons. To address these challenges, we introduce the Short-Term Precipitation Forecast Network (STPF-Net), a recurrent neural network designed for longer-term precipitation prediction. STPF-Net uses a multi-tier structure with varying temporal resolutions to mitigate the accumulated errors during longer forecasts. Additionally, its transformer-based module incorporates larger spatial contexts, providing more complete information about precipitation systems. We evaluated STPF-Net on radar data from southeastern China, training separate models for 6 and 12 h forecasts. Quantitative results demonstrate STPF-Net achieved superior accuracy and lower errors compared to benchmark deep learning and numerical weather prediction models. Visualized case studies indicate reasonably coherent 6 h predictions from STPF-Net versus other methods. For 12 h forecasts, while STPF-Net outperformed other models, it still struggled with storm initiation over longer forecasting time. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, the most representative deep learning has been applied to various fields, which is greatly influencing human society. However, deep neural networks (DNNs) are still a black-box model, and the process how they make decisions internally is still difficult to understand and control. At the same time, DNNs take up more hardware resources, resulting in high energy consumption. Therefore, it is significant to study the characteristics of deep AI models and deeply understand the interactions between parameters within AI models so as to improve the interpretability of DNNs, optimize their structure and increase their computational efficiency. In this paper, we propose a graph-based interpretability method for deep neural networks (GIMDNN). The running parameters of DNNs are modeled as a graph by using a kernel function or the Graph Transformer Networks (GTN), where the nodes of the graph are obtained by dimensional mapping of the parameters of the DNNs, and the edges are calculated by the Gaussian kernel function. The generated graphs are classified by a graph convolutional network (GCN). The association relationship between the adjacent layers and the running mechanism of DNNs are analyzed, and the importance of the parameters of each layer in the DNNs for the final classification result can be obtained. Convolutional neural networks (CNNs) are one of the most representative models in DNNs. The proposed method is experimentally evaluated on the CNNs. The experimental results show that the proposed method can interpret the associations among the weight parameters as well as the correlation between two adjacent layers. Therefore, the DNNs for special tasks, such as portable applications, edge computing, and so on, can be customized, the number of parameters can be reduced. It is valuable to interpret the operation and principle of CNNs. [ABSTRACT FROM AUTHOR]

Deep learning models based on radar echo extrapolation have been widely used in precipitation nowcasting. However, they face the challenge of insufficient input information when extending the forecast lead time, requiring the incorporation of physics‐based numerical weather prediction (NWP). Given that the strengths of radar and NWP data vary depending on the forecast time, effectively fusing these two data sources in a unified deep learning model remains an open research problem. In this study, we propose a Time‐aware Adaptive Feature Fusion Network (TAFFNet) for very short‐term precipitation forecasts up to 12 hr. TAFFNet fuses features adaptively according to their relative contributions to forecast skill at different times. Experimental results demonstrate that TAFFNet performs the best for very short‐term precipitation forecasts. The case studies show that adaptively fusing NWP with radar can improve the accuracy of precipitation forecasts, especially for predicting the initiation and dissipation of storms at longer lead times. Plain Language Summary: Very short‐term precipitation forecasting aims to predict precipitation for a couple of hours, which is crucial for public safety and emergency management in cities. Recently, deep learning models have been widely used for precipitation nowcasting (0–2 hr) based on observation extrapolation. However, as the forecast time increases, extrapolating historical observations alone is inadequate without incorporating physical constraints. On the contrary, traditional NWP can provide essential physical background, but the prediction accuracy still needs improvement for early forecasting periods. In this study, we proposed a novel deep learning model named TAFFNet to combine both advantages of radar and NWP for very short‐term precipitation forecasts up to 12 hr. The features of radar and NWP are first extracted, respectively. Their features are fused adaptively in the forecasting part through a time‐aware adaptive feature fusion (TAFF) module, according to their relative contributions to forecast skill at different lead times. The feature fusion approach can be optimized adaptively through model training. The proposed model is evaluated on the radar and NWP model data set covering southeast China. Results demonstrate that incorporating NWP into a radar‐based deep learning model can improve very short‐term precipitation forecasts. TAFFNet can better capture the storm's initiation and dissipation during forecasting. Key Points: A novel deep learning model termed Time‐aware Adaptive Feature Fusion Network (TAFFNet) is proposed for very short‐term precipitation forecasts up to 12 hrFeatures from radar and numerical weather prediction are fused adaptively in deep levels based on their relative contributions to forecast at different lead timesTAFFNet can improve very short‐term precipitation forecasts, especially for predicting storms initiation and dissipation at longer times [ABSTRACT FROM AUTHOR]

The speckle noise found in synthetic aperture radar (SAR) images severely affects the efficiency of image interpretation, retrieval and other applications. Thus, effective methods for despeckling SAR image are required. The traditional methods for SAR image despeckling fail to balance in terms of the relationship between the intensity of speckle noise filtering and the retention of texture details. Deep learning based SAR image despeckling methods have been shown to have the potential to achieve this balance. Therefore, this study proposes a self-attention multi-scale convolution neural network (SAMSCNN) method for SAR image despeckling. The advantage of the SAMSCNN method is that it considers both multi-scale feature extraction and channel attention mechanisms for multi-scale fused features. In the SAMSCNN method, multi-scale features are extracted from SAR images through convolution layers with different depths. These are concatenated; then, and an attention mechanism is introduced to assign different weights to features of different scales, obtaining multi-scale fused features with weights. Finally, the despeckled SAR image is generated through global residual noise reduction and image structure fine-tuning. The despeckling experiments in this study involved a variety of scenes using simulated and real data. The performance of the proposed model was analysed using quantitative and qualitative evaluation methods and compared to probabilistic patch-based (PPB), SAR block-matching 3-D (SAR-BM3D) and SAR-CNN methods. The experimental results show that the method proposed in this paper improves the objective indexes and shows great advantages in visual effects compared to these classical methods. The method proposed in this study can provide key technical support for the practical application of SAR images. [ABSTRACT FROM AUTHOR]

• MLP, GRU, CNN and MSCNN for landslide susceptibility mapping were compared. • CNN combined with multi-scale technique can improve feature utilization. • The joint evaluation method of ROC curve and PR curve for LSM was proposed. Landslide susceptibility mapping (LSM) can be used to determine the spatial probability of landslide occurrence. There are many methods for LSM, including statistical methods, traditional machine learning methods and deep learning methods, etc. However, the difference comparison of these methods has been not perfect, especially the comparison of different neural network models for LSM and their application prospects were rarely studied. In this paper, the classical neural net-work multi-layer perceptron (MLP), convolutional neural network (CNN), gated recurrent unit (GRU) and multi-scale convolutional neural network (MSCNN) four models are selected for comparison. Taking Lanzhou city, Gansu Province, China as an example, eight landslide-related influencing factors and historical landslide and non-landslide locations were selected, and the training set and validation set were divided according to 7:3. Through training the four models, four landslide susceptibility maps were generated. The experimental results were verified and compared by the confusion matrix, Kappa coefficient, F1-score and other statistical indicators. The receiver operating characteristic (ROC) curve and Precision-Recall (PR) curve were plotted to evaluate the classification effect and generalization capability of four models. The results show that the constructed MSCNN is the optimal model, which has the best performance both in the training process and in the mapping results. MSCNN model has the highest value of Recall (99.93%), Kappa (0.96) and F1-score (0.98) in the confusion matrix. In addition, ROC curve and PR curve of MSCNN model maintain the maximum area under curve (AUC) on different data sets. In the comparison, MLP and GRU accept sequence features, while CNN and MSCNN accept neighborhood features. In general, the prediction model considering neighborhood features contains more information in the limited input data and is better than the prediction model considering sequence features in all evaluation indicators. Therefore, we think that the neighborhood features can better represent the landslide occurrence characteristics. In the future model design process for LSM, more attention should be paid to the neighborhood features of landslide influencing factors. [ABSTRACT FROM AUTHOR]

The spatial resolution of precipitation predicted by general circulation models is too coarse to meet current research and operational needs. Downscaling is one way to provide finer resolution data at local scales. The single-image super-resolution method in the computer vision field has made great strides lately and has been applied in various fields. In this article, we propose a novel reference-based and gradient-guided deep learning model (RBGGM) to downscale daily precipitation considering the discontinuity of precipitation and ill-posed nature of downscaling. Global Precipitation Measurement Mission (GPM) precipitation data, variables in ERA5 re-analysis data, and topographic data are selected to perform the downscaling, and a residual dense attention block is constructed to extract features of them. By exploring the discontinuous feature of precipitation, we introduce gradient feature to reconstruct precipitation distribution. We also extract the feature of high-resolution monthly precipitation as a reference feature to resolve the ill-posed nature of downscaling. Extensive experimental results on benchmark data sets demonstrate that our proposed model performs better than other baseline methods. Furthermore, we construct a daily precipitation downscaling data set based on GPM precipitation data, ERA5 re-analysis data and topographic data. [ABSTRACT FROM AUTHOR]