Search

This study addresses the limitations of existing indirect bridge damage identification methods that are based on the vehicle–bridge coupled vibration theory of highway bridges. To overcome these shortcomings, we propose an extended approach that incorporates various types of deep-learning models with vehicle–bridge coupled vibration responses. The proposed method is demonstrated using a three-span continuous beam bridge as a case study. First, a vehicle and bridge analysis model is established, and bridge damage is simulated using unit stiffness reduction, considering different damage scenarios. Next, to account for road roughness randomness, vehicle–bridge coupling vibration analysis is performed under various road roughness conditions, yielding the vertical acceleration vibration signal of the vehicle. Subsequently, we employ an end-to-end damage recognition method, utilizing the vehicle acceleration response as the network input, to construct two types of deep-learning models: one-dimensional convolutional neural network (1D-CNN) and convolutional long short-term memory neural network (CNN-LSTM). The recognition performance of both models is compared and analyzed. Taking Zhengzhou Taohuayu Self-Anchored Suspension Bridge in China as an example, this study delves into the capability of bridge damage identification using deep learning. The results demonstrate that the one-dimensional convolutional neural network achieves excellent recognition performance in terms of both damage location and severity. [ABSTRACT FROM AUTHOR]

The timely and accurate acquisition of information on the distribution of the crop planting structure in the Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in Western China, is crucial for promoting fine management of agriculture and ensuring food security. This study uses multi-temporal high-resolution remote sensing images to determine optimal segmentation scales for various crops, employing the estimation of scale parameter 2 (ESP2) tool and the Ratio of Mean Absolute Deviation to Standard Deviation (RMAS) model. The Canny edge detection algorithm is then applied for multi-scale image segmentation. By incorporating crop phenological factors and using the L1-regularized logistic regression model, we optimized 39 spatial feature factors—including spectral, textural, geometric, and index features. Within a multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model are used to classify the cropping patterns in four test areas based on the multi-scale segmented images. The results indicate that integrating the Canny edge detection algorithm with the optimal segmentation scales calculated using the ESP2 tool and RMAS model produces crop parcels with more complete boundaries and better separability. Additionally, optimizing spatial features using the L1-regularized logistic regression model, combined with phenological information, enhances classification accuracy. Within the OBIC framework, the RF classifier achieves higher accuracy in classifying cropping patterns. The overall classification accuracies for the four test areas are 91.93%, 94.92%, 89.37%, and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of the shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields. [ABSTRACT FROM AUTHOR]

Thunderstorm gusts are a common form of severe convective weather in the warm season in North China, and it is of great importance to correctly forecast them. At present, the forecasting of thunderstorm gusts is mainly based on traditional subjective methods, which fails to achieve high-resolution and high-frequency gridded forecasts based on multiple observation sources. In this paper, we propose a deep learning method called Thunderstorm Gusts TransU-net (TG-TransUnet) to forecast thunderstorm gusts in North China based on multi-source gridded product data from the Institute of Urban Meteorology (IUM) with a lead time of 1 to 6 h. To determine the specific range of thunderstorm gusts, we combine three meteorological variables: radar reflectivity factor, lightning location, and 1-h maximum instantaneous wind speed from automatic weather stations (AWSs), and obtain a reasonable ground truth of thunderstorm gusts. Then, we transform the forecasting problem into an image-to-image problem in deep learning under the TG-TransUnet architecture, which is based on convolutional neural networks and a transformer. The analysis and forecast data of the enriched multi-source gridded comprehensive forecasting system for the period 2021–23 are then used as training, validation, and testing datasets. Finally, the performance of TG-TransUnet is compared with other methods. The results show that TG-TransUnet has the best prediction results at 1–6 h. The IUM is currently using this model to support the forecasting of thunderstorm gusts in North China. [ABSTRACT FROM AUTHOR]

In order to fully exploit the relationship between temporal features in photovoltaic power generation data and improve the prediction accuracy of photovoltaic power generation, a photovoltaic power generation forecasting method is proposed based on a hybrid model of the convolutional neural network (CNN) and extreme gradient boost (XGBoost). Taking the historical data of China's photovoltaic power plants as a sample, the high-dimensional mapping relationship of photovoltaic power generation variables is extracted based on the convolutional layer and pooling layer of the CNN network to construct a high-dimensional time-series feature vector, which is an input for the XGBoost. A photovoltaic power generation prediction model is established based on CNNXGBoost by training CNN and XGBoost parameters. Since it is difficult for a single model to achieve optimal prediction accuracy under different weather conditions, the k-means clustering algorithm is used to group the power datasets and train independent models to improve prediction accuracy. Through the actual data verification of photovoltaic power plants, the proposed photovoltaic power generation prediction model can accurately predict the power, which shows high prediction accuracy and generalization ability compared with other methods. [ABSTRACT FROM AUTHOR]

Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels. The development of computer vision has greatly promoted structural health monitoring. This study proposes a novel encoder–decoder structure, CrackRecNet, for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture. An image acquisition equipment is designed based on a camera, 3-dimensional printing (3DP) bracket and two laser rangefinders. A tunnel concrete structure crack (TCSC) image data set, containing images collected from a double-shield tunnel boring machines (TBM) tunnel in China, was established. Through data preprocessing operations, such as brightness adjustment, pixel resolution adjustment, flipping, splitting and annotation, 2880 image samples with pixel resolution of 448 × 448 were prepared. The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs. In the experiments, the proposed CrackRecNet showed better prediction performance than U-Net, TernausNet, and ResU-Net. This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification. [ABSTRACT FROM AUTHOR]

Jiuzhaigou is situated on a mountain-canyon region and is famous for frequent tectonic activities. An abundance of loose co-seismic landslides and collapses were produced on gullies after the Jiuzhaigou Earthquake on August 8, 2017, which was served as material source for debris flow in later years. Debris flow appears frequently which are seriously endangering the safety of people's lives and properties. Even the earliest debris flow appeared in areas where no case ever reported before. The debris flow susceptibility evaluation (DFSE) is used for predicting the areas prone to debris flow, which is urgently required to avoid hazards and help to guide the strategy of preventive measures. Therefore, this work employs debris flow in Jiuzhaigou to reveal the characteristics of disaster-pregnant environment and to explore the application of machine learning in DFSE. Some new viewpoints are suggested: (i) Material density factor of debris flow is first adopted in this work, and it is proved to be a critical factor for triggering debris flows by sensitivity analysis method. (ii) Deep neural network and convolutional neural network (CNN) achieve relatively good area under the curve (AUC) values and are 0.021–0.024 higher than traditional machine learning methods. (iii) Watershed units combined with CNN-based model can achieve more accurate, reliable and practical susceptibility map. This work provides an idea for prevention of debris flow in mountainous lands. [ABSTRACT FROM AUTHOR]

Nowadays, there is an increase in attention to the college student's mental health, and to enhance the awareness related to college students' mental health, colleges and universities have executed an immense range of mental health publicity activities. In order to better combine deep learning with classroom teaching, this paper puts forward a deep learning algorithm formulated on convolutional neural networks. The purpose of this research is to investigate the development and use of a cultivation mechanism for mental health education of college students in campus culture creation from the perspective of deep learning. The study's primary goal is to comprehend college students' mental health training in campus culture creation. The study's objective is to develop experimental outcomes of college students utilizing mental health education courses as an optional or mandatory course. Finally, investigations related to college students' mental health from the current situation in China, the investigation, statistics and analysis related to the college students in China are carried out in this situation. The experimental results of this study show that 62 of the 156 schools and universities assessed provide courses on mental health education for college students that are both obligatory and optional. According to the students questionnaire survey, 86.7% of respondents believe that it is critical to establish mental health related educational courses, 61.9% believe that compulsory courses should be established, and students want to add group guidance or activities to the teaching process to improve their experience and participation. [ABSTRACT FROM AUTHOR]

Due to the periodic changes of climate, cracks are widely developed in expansive soils, leading to the destruction of soil integrity, the deterioration of physical strength, and eventually the instability of the expansive soil slope and other disasters. In this paper, a deep learning-based modeling method was proposed for soil crack networks characterization through steps of segmentation, quantification and simulation. Inspired by the U-Net convolutional neural network, a dilated convolution module was added to the backbone to enhance the crack segmentation capability and a subpixel edge detection algorithm was followed for accurate crack edge detection. Then, a deterministic or stochastic method was designed for crack network simulation. A case study of an expansive soil slope on the bank of Wadong Main Canal in the Pi-Shi-Hang Irrigation District, China, was conducted. Results show that the dilated U-Net model gained 0.24 and 0.25 improvement in F1-score and IoU (Intersection over Union) comparing to the conventional segmentation method (Otsu) and crack edge precision was further improved by 5.38%. The performances of proposed method including the image labeling, effect of crack thickness and environmental conditions, etc., are also explored. To validate the simulated crack network, crack areas at different depths were measured through X-ray images. Comparing with the simulation result, mean error rate of 1.05% was achieved. Thus, the proposed method can efficiently characterize soil crack networks using the field acquired crack images. [ABSTRACT FROM AUTHOR]

Forest fires have a significant impact on terrestrial ecosystems, leading to harm to biodiversity and environment. To mitigate the ecological damage caused by forest fires, it was necessary to develop prediction models of fire risk. In this study, by evolving the optimal architecture and parameters using the particle swarm optimization (PSO) algorithm, a convolutional neural network (CNN) deep learning model was proposed to predict forest fire risk on a national scale. Utilizing fire data and fire risk factors from 2001 to 2020 in China, the PSO-CNN-based deep learning model (PSO-CNN) was utilized and tested. Compared to logistic regression, random forest, support vector machine, k-nearest neighbors, and CNN models, the PSO-CNN model exhibited superior performance with an accuracy of 82.2% and an AUC value of 0.92. These results clearly highlighted the effectiveness of the PSO-CNN model in enhancing the accuracy of forest fire prediction. Furthermore, the forest fire risk prediction level estimated by the proposed model on a national scale for the entire country was mostly consistent with actual fire data distribution, indicating its potential to be used as an important direction for deep learning in forest fire prediction research. [ABSTRACT FROM AUTHOR]

Revealing the mechanism of hydrological and agricultural drought has been challenging and vital in the environment under extreme weather and water resource shortages. To explore the evolution process from meteorological to hydrological and agricultural drought further, multi-source remote sensing data, including the Gravity Recovery and Climate Experiment (GRACE) product, were collected in the Huaihe River basin of China during 2002–2020. Three machine learning methods, including long short-term memory neural network (LSTM), convolutional neural network (CNN), and categorical boosting (CatBoost), were constructed for hydrological and agricultural drought forecasting. The propagation time from meteorological drought to surface water storage and terrestrial water storage drought, evaluated by the standardized precipitation evapotranspiration index, was 8 and 11 months with Pearson correlation coefficients (R) of 0.68 and 0.48, respectively. Groundwater storage drought was correlated with evapotranspiration and vegetation growth with a 12-month lag time, respectively. In addition, vegetation growth was affected by the drought of soil moisture at depths ranging from 100 to 200 cm with an 8-month lag time with an R of −0.39. Although the forecasting performances of terrestrial water storage drought were better than those of groundwater storage drought and agricultural drought, CNN always performed better than LSTM and CatBoost models, with Nash–Sutclife efficiency values during testing ranging from 0.28 to 0.70, 0.26 to 0.33, and −0.10 to −0.40 for terrestrial water storage drought, groundwater storage drought, and agricultural drought at lead times of 0–3 months, respectively. Furthermore, splitting training and testing data at random significantly improved the performances of CNN and CatBoost methods for drought forecasting rather than in chronological order splitting for non-stationary data. [ABSTRACT FROM AUTHOR]

Evapotranspiration is one of the most critical features in hydrology. In order to address the prediction of evapotranspiration accurately and scientifically, this study proposes a novel deep learning-based evapotranspiration prediction model, the CNN-BiLSTM-Attention model, using the climatically complex Mount Tai region in China as a case study. The model integrates the feature extraction capabilities of Convolutional Neural Networks (CNN), the temporal dependency capturing of Bidirectional Long Short-Term Memory Networks (BiLSTM), and the feature weighting abilities of the Attention mechanism. In order to enhance prediction accuracy with fewer climate parameters, various input parameter combinations are explored and compared with other classical models in this study. The model's performance is assessed across daily, weekly, and monthly time increments, using evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2). This study holds significant implications for mountain hydrological cycles, as accurate evapotranspiration prediction aids in more informed decision-making for agricultural production, water resource management, and climate change research. [ABSTRACT FROM AUTHOR]

Objectives: Imaging interpretation of the benignancy or malignancy of parotid gland tumors (PGTs) is a critical consideration prior to surgery in view of therapeutic and prognostic values of such discrimination. This study investigates the application of a deep learning‐based method for preoperative stratification of PGTs. Materials and Methods: Using the 3D DenseNet‐121 architecture and a dataset consisting of 117 volumetric arterial‐phase contrast‐enhanced CT scans, we developed a binary classifier for PGT distinction and tested it. We compared the discriminative performance of the model on the test set to that of 12 junior and 12 senior head and neck clinicians. Besides, potential clinical utility of the model was evaluated by measuring changes in unassisted and model‐assisted performance of junior clinicians. Results: The model finally reached the sensitivity, specificity, PPV, NPV, F1‐score of 0.955 (95% CI 0.751–0.998), 0.667 (95% CI 0.241–0.940), 0.913 (95% CI 0.705–0.985), 0.800 (95% CI 0.299–0.989) and 0.933, respectively, comparable to that of practicing clinicians. Furthermore, there were statistically significant increases in junior clinicians' specificity, PPV, NPV and F1‐score in differentiating benign from malignant PGTs when unassisted and model‐assisted performance of junior clinicians were compared. Conclusion: Our results provide evidence that deep learning‐based method may offer assistance for PGT's binary distinction. [ABSTRACT FROM AUTHOR]

Landslides are one of the most common geological disasters in China, characterized by suddenness and uncertainty. Traditional methods are not sufficient for the accurate identification, early warning, and forecasting of landslide disasters. As high-resolution remote sensing satellites and interferometric synthetic aperture radar (InSAR) surface deformation monitoring technology have been leaping forward, the traditional methods of landslide monitoring data sources are limited, and there have been few effective methods to excavate the characteristics of the spatial distribution of landslide hazards and their triggering factors, etc. In this study, an area extending 10 km from the VII isobar of the Gengma earthquake was taken as the study area, and 13 evaluation factors were screened out by integrating the factors of InSAR surface deformation, topography, and geological environment. Landslide susceptibility was evaluated through the Bayesian optimized convolutional neural network (BO-CNN), and the Bayesian optimized random forests (BO-RF) and particle swarm optimization support vector machines (PSO-SVM) models were selected for comparative analyses. The accuracy of the model was evaluated by using three indices, including the ROC curve, the AUC value, and the FR value. Specifically, the ROC curves of PSO-SVM, BO-RF, and BO-CNN were close to the upper-left corner, indicating excellent model performance. Moreover, the AUC values were computed as 0.9388, 0.9529, and 0.9535, respectively, and the FR value of landslides in the high susceptibility area of BO-CNN reached up to 14.9 and exceeded those of PSO-SVM and BO-RF, respectively. Furthermore, the mentioned values of the SVM and BO-RF models were 4.55 and 3.69 higher. The experimental results indicated that, compared with other models, the BO-CNN model used in this study had a better effect on landslide susceptibility evaluation, and the research results are of great significance to the disaster prevention and mitigation measures of local governments. [ABSTRACT FROM AUTHOR]

Deformation can effectively reflect the structural state of concrete dams and, thus, establishing na accurate concrete dam deformation prediction model is important for dam health monitoring and early warning strategies. To address the problem that the spatial coordinates introduced in the traditional multi-point deformation prediction model of dams not being able to accurately and efficiently reflect the spatial correlation of multiple-measuring points, a 2D-1D-CNN model is proposed which expresses the spatial correlation between each measuring point through spatial feature vectors, replacing the spatial coordinates in the traditional multi-point model. First, the spatial feature vector is extracted from the historical spatio-temporal panel series of deformation values of measuring points via a Two-Dimensional Convolutional Neural Network (2D-CNN); second, the vector is combined with the environmental impact factor of dam deformation to form the final input factor of fused spatial features; and, thirdly, this vector is combined with the environmental impact factors of dam deformation to form the final input factor of fused spatial features, and the non-linear linkage between the factors and the measured displacement values is constructed by the efficient feature processing capability of a One-Dimensional Convolutional Neural Network (1D-CNN) to obtain the prediction results. Finally, the actual monitoring data of a concrete dam in China are used as an example to verify the validity of the model. The results show that the proposed model outperforms the other models in most cases, respectively, which verifies the effectiveness of the proposed model in this paper. [ABSTRACT FROM AUTHOR]

Context: Evaluating the impacts of future urban expansion on natural habitats in China is important for achieving sustainable development goals. However, existing models cannot reliably and effectively simulate future urban expansion in China, which causes great uncertainties in evaluating the impacts of future urban expansion on natural habitats. Objectives: The objective of this study was to simulate future urban expansion and evaluate its impacts on natural habitats in China. Methods: First, the Land Use Scenario Dynamics-urban (LUSD-urban) model was improved by coupling localized Shared Socioeconomic Pathways (SSPs) and a convolutional neural network (CNN). Then, urban expansion in China was simulated from 2020 to 2050 by using the improved LUSD-urban model. Finally, we evaluated the potential impacts of future urban expansion on natural habitats. Results: The localized SSPs could more reliably represent future socioeconomic development trends in China, and the CNN could fully extract the multiscale neighborhood information of nonurban pixels. By combining the advantages of the localized SSPs and the CNN, the simulation accuracy of the improved LUSD-urban model increased by 15–32% compared with that of other models. From 2020 to 2050, urban land is projected to increase by 6.84 (3.94–9.03) × 104 km2 and cause a 2.21 (1.23–2.95) × 104 km2 loss of natural habitat. Compared with the 1990–2020 period, the impacts of future urban expansion on natural habitats will intensify. Natural habitat loss during 2020–2050 will be 1.23 (1.22 to 1.64) times greater than that during 1990–2020. In addition, grasslands will experience the most serious losses under the influence of future urban expansion. Conclusions: We suggest that relevant policies be issued to protect important natural habitats during urbanization to achieve Sustainable Development Goals and biodiversity conservation targets in China. [ABSTRACT FROM AUTHOR]

The coronavirus first appeared in China in 2019, and the World Health Organization (WHO) named it COVID-19. Then WHO announced this illness as a worldwide pandemic in March 2020. The number of cases, infections, and fatalities varied considerably worldwide. Because the main characteristic of COVID-19 is its rapid spread, doctors and specialists generally use PCR tests to detect the COVID-19 virus. As an alternative to PCR, X-ray images can help diagnose illness using artificial intelligence (AI). In medicine, AI is commonly employed. Convolutional neural networks (CNN) and deep learning models make it simple to extract information from images. Several options exist when creating a deep CNN. The possibilities include network depth, layer count, layer type, and parameters. In this paper, a novel Xception-based neural network is discovered using the genetic algorithm (GA). GA finds better alternative networks and parameters during iterations. The best network discovered with GA is tested on a COVID-19 X-ray image dataset. The results are compared with other networks and the results of papers in the literature. The novel network of this paper gives more successful results. The accuracy results are 0.996, 0.989, and 0.924 for two-class, three-class, and four-class datasets, respectively. [ABSTRACT FROM AUTHOR]

Landslide risk assessment (LRA) is of great significance to hazard prevention and mitigation. However, the historical landslide information is incomplete in most areas, which makes the landslide quantitative risk assessment (LQRA) extremely difficult. This research proposed a set of frameworks for LQRA, so as to achieve LQRA in areas with incomplete historical landslide information. Firstly, we constructed the convolutional neural network (CNN) model suitable for landslide susceptibility assessment (LSA) by studying the structure and hyperparameters optimization of CNN. Secondly, we proposed a method to calculate the temporal probability by using the Poisson model based on the time range of historical landslides occurrence, and then conducted landslide hazard assessment (LHA). Then, we established a mathematical model for landslide intensity of shallow landslide based on landslide area and slope, aiming at solving the problem that it is difficult to calculate landslide intensity due to the lack of landslide volume and velocity. Based on the landslide intensity and the hazard-resistant capacity of the element at risk, we assessed the landslide vulnerability. Finally, population risk map and economic risk map are obtained based on the landslide hazard, vulnerability, and estimated value of the elements at risk. The proposed LQRA framework was applied to Tumen City, China for testing and field validation. From the results, the CNN model built can help improve the accuracy of LSA. The proposed temporal probability calculation method is conducive to the completion of LHA in areas with incomplete historical landslide information. The established landslide intensity mathematical model has certain credibility. Since the landslide risk map is obtained through appropriate simplification and substitution estimation, its final value cannot be used as an accurate prediction of future losses, but it can be used as a reference for the extent of potential losses, so as to determine the areas where hazard prevention and mitigation measures need to be taken. [ABSTRACT FROM AUTHOR]

We studied China's Common Prosperity process by assessing and comparing the level of Common Prosperity in different regions of China and made some beneficial recommendations to government departments. The research data comes from the China Statistical Yearbook, which includes data from 31 provinces and cities from 2015 to 2020. According to the relevant research, eleven evaluation indicators were selected. We combined GRA with the TOPSIS method for scoring and the K-means clustering algorithm for dividing the GRA-TOPSIS scoring results into three evaluation levels. Then, the convolutional neural network model was used to predict and simulate the level of common prosperity. Taking 2020 as an example, the results show: (1) From 2015 to 2020, China's Common Prosperity level reached its highest point in 2020. Due to the impact of COVID-19 in 2019, the scores of 31 regions are generally lower than in the previous four years. The situation changed in 2020; (2) In terms of regional distribution, the economic development of Beijing, Shanghai, and other eastern regions is relatively good, with a higher degree of Common Prosperity than that of other regions; (3) The average prediction accuracy is high in our model. It can be close to 100%, indicating that the model has a good prediction effect. In addition, we made recommendations based on the research results, which have good references for actively promoting common prosperity. [ABSTRACT FROM AUTHOR]

Winter jujube (Ziziphus jujuba Mill. cv. Dongzao) has been cultivated in China for a long time and has a richly abundant history, whose maturity grade determined different postharvest qualities. Traditional methods for identifying the fundamental quality of winter jujube are known to be time-consuming and labor-intensive, resulting in significant difficulties for winter jujube resource management. The applications of deep learning in this regard will help manufacturers and orchard workers quickly identify fundamental quality information. In our study, the best fundamental quality of winter jujube from the correlation between maturity and fundamental quality was determined by testing three simple physicochemical indexes: total soluble solids (TSS), total acid (TA) and puncture force of fruit at five maturity stages which classified by the color and appearance. The results showed that the fully red fruits (the 4th grade) had the optimal eating quality parameter. Additionally, five different maturity grades of winter jujube were photographed as datasets and used the ResNet-50 model and the iResNet-50 model for training. And the iResNet-50 model was improved to overlap double residuals in the first Main Stage, with an accuracy of 98.35%, a precision of 98.40%, a recall of 98.35%, and a F1 score of 98.36%, which provided an important basis for automatic fundamental quality detection of winter jujube. This study provided ideas for fundamental quality classification of winter jujube during harvesting, fundamental quality screening of winter jujube in assembly line production, and real-time monitoring of winter jujube during transportation and storage. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is essential for the spatial prediction of landslides and risk prevention. Physically based LSM models are confined by oversimplifications of physical processes and limited information about soil properties. Data-driven LSM models may give reliable results only when the training and the testing data have high similarity, and application in regions with different geological conditions is often inapplicable. This paper proposes four hybrid data-driven and physical models and compares these models in terms of cross-regional generalization ability and prediction uncertainty. The effects of physical module performance on the hybrid model are analyzed. For the physical modules of the four hybrid models, two-dimensional (2D) physically based models, TRIGRS and the infinite-slope stability models (ISSMs), and the three-dimensional (3D) physically based model, Scoops3D, are adopted. The data-driven modules all adopt the convolutional neural network (CNN) model. Two towns in the Three-Gorge Reservoir area of China are used as the training and testing areas. The results show that all hybrid models have better generalization ability than using the data-driven module exclusively. The prediction uncertainty is significantly reduced by pre-selecting training samples using the physical module. The optimal hybrid model is the one that integrates CNN and ISSM (under the saturated condition). It is then applied to a new region (Wushan County) to further validate the generalization ability. It can make accurate predictions without calibrating the trained model using new data from the validation area. Finally, the effectiveness of model averaging for improving the prediction performance is verified. Using model averaging, the AUC value in the validation area yields 0.834, which is even higher than the original realizations, with AUC values ranging from 0.683 to 0.817. Therefore, the optimal hybrid model can be directly used for LSM in the Three-Gorge Reservoir, and the findings can provide valuable guidance for generalization ability improvement and prediction uncertainty reduction of LSM models in other countries and regions. [ABSTRACT FROM AUTHOR]

Automatic weed identification and detection are crucial for precision weeding operations. In recent years, deep learning (DL) has gained widespread attention for its potential in crop weed identification. This paper provides a review of the current research status and development trends of weed identification in crop fields based on DL. Through an analysis of relevant literature from both within and outside of China, the author summarizes the development history, research progress, and identification and detection methods of DL-based weed identification technology. Emphasis is placed on data sources and DL models applied to different technical tasks. Additionally, the paper discusses the challenges of time-consuming and laborious dataset preparation, poor generality, unbalanced data categories, and low accuracy of field identification in DL for weed identification. Corresponding solutions are proposed to provide a reference for future research directions in weed identification. [ABSTRACT FROM AUTHOR]

The analysis and evaluation of landslide susceptibility are of great significance in preventing and managing geological hazards. Aiming at the problems of insufficient information caused by the limited number of landslide datasets, complex information of landslide evaluation factors, and low prediction accuracy of landslide susceptibility, a landslide susceptibility evaluation method based on the deep attention dilated residual convolutional neural network (DADRCNN) is proposed. First, the dilated convolution unit (DCU) is used to increase the network receptive field, aggregate multi-scale information, and enhance the model ability to capture the characteristics of landslide evaluation factors. Second, the deep residual module (DRM) is used to solve the issue of gradient disappearance and better extract data features by overlaying the residual function mapping layer and increasing the network depth. Finally, the channel attention residual module (CARM) is introduced to learn the varying importance of different landslide evaluation factors, and assign different weights to improve the susceptibility prediction accuracy. The experimental results show that the DADRCNN method can extract features around the sample points, expand the receptive field, and deeply mine the information. It mitigates the lack of sample information in training, focuses on important feature information, and significantly improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

In-season crop-type maps are required for a variety of agricultural monitoring and decision-making applications. The earlier the crop type maps of the current growing season are obtained, the more beneficial it is for agricultural decision-making and management. With the availability of a large amount of high spatiotemporal resolution remote sensing data, different data sources are expected to increase the frequency of data acquisition, which can provide more information in the early season. To explore the potential of integrating different data sources, a Dual-1DCNN algorithm was built based on the CNN model in this study. Moreover, an incremental training method was used to attain the network on each data acquisition date and obtain the best detection date for each crop type in the early season. A case study for Hengshui City in China was conducted using time series of Sentinel-1A (S1A) and Sentinel-2 (S2) attained in 2019. To verify this method, the classical methods support vector machine (SVM), random forest (RF), and Mono-1DCNN were implemented. The input for SVM and RF was S1A and S2 data, and the input for Mono-1DCNN was S2 data. The results demonstrated the following: (1) Dual-1DCNN achieved an overall accuracy above 85% at the earliest time.; (2) all four types of models achieved high accuracy (F1s were greater than 90%) on summer maize after sowing one month later; (3) for cotton and common yam rhizomes, Dual-1DCNN performed best, with its F1 reaching 85% within 2 months after cotton sowing, 15 days, 20 days, and 45 days ahead of Mono-1DCNN, SVM, and RF, respectively, and its extraction of the common yam rhizome was achieved 1–2 months earlier than other methods within the acceptable accuracy. These results confirmed that Dual-1DCNN offered significant potential in the in-season detection of crop types. [ABSTRACT FROM AUTHOR]

Strengthening regulations on carbon emissions from ships is important for ensuring that China can achieve its dual carbon aims of reaching peak carbon emissions before 2030 and achieving carbon neutrality before 2060. Currently, the primary means of monitoring ship exhaust emissions are the sniffing method and non-imaging optical remote sensing; however, these methods suffer from a low prediction efficiency and high cost. We developed a method for predicting the CO2 content of ship exhaust that uses a convolutional neural network and mid-infrared spectral images. First, a bench experiment was performed to synchronously obtain mid-wave infrared spectral images of the ship exhaust plume and true values for the CO2 concentration from the online monitoring of eight spectral channels. Then, the ResNet50 residual neural network, which is suitable for image prediction tasks, was selected to predict the CO2 content. The preprocessed mid-infrared spectral image of each channel and the corresponding true value for the CO2 content were input to the neural network, and convolution was applied to extract the radiation characteristics. The neural network then mapped the relationship between the true CO2 content and the radiation characteristics for each channel, which it used to predict the CO2 content in the ship exhaust. The results demonstrated that the predicted and true CO2 contents had a root mean square error of <0.2, mean absolute error of <0.15, and mean absolute percentage error of <3.5 for all eight channels. The developed model demonstrated a high prediction accuracy with one channel in particular demonstrating the best performance. This study demonstrates that the method used for predicting the CO2 content of ship exhaust based on convolutional neural networks and mid-infrared spectral images is feasible and has reference significance for the remote monitoring of ship exhaust emissions. [ABSTRACT FROM AUTHOR]

Simple Summary: Spinal metastases are a common occurrence, and many patients do not have a clear history of primary tumors when diagnosed with spinal metastases. Patients with cancer of unknown primary often undergo comprehensive and invasive diagnostic work-ups, which can be expensive and time-consuming. To narrow down the search for primary tumor sites in spinal metastases patients with cancer of unknown primary, an artificial intelligence model that can assess tumor origin on MRI may be beneficial. Our work builds upon the considerable interest in investigating the feasibility of using a ResNet-50 convolutional neural network model based on MRI in predicting primary tumor sites in spinal metastases. In this preliminary study, for the 5-class classification of spinal metastases originating from the lung, kidney, prostate, and mammary or thyroid glands, the AUC-ROC and top-1 accuracy of the ResNet-50 model were 0.77 and 52.97%, respectively. Therefore, we believe that the ResNet-50 CNN model for predicting primary tumor sites in spinal metastases using MRI has the potential to help prioritize examinations and treatments in cases of unknown primary for radiologists and oncologists. We aim to investigate the feasibility and evaluate the performance of a ResNet-50 convolutional neural network (CNN) based on magnetic resonance imaging (MRI) in predicting primary tumor sites in spinal metastases. Conventional sequences (T1-weighted, T2-weighted, and fat-suppressed T2-weighted sequences) MRIs of spinal metastases patients confirmed by pathology from August 2006 to August 2019 were retrospectively analyzed. Patients were partitioned into non-overlapping sets of 90% for training and 10% for testing. A deep learning model using ResNet-50 CNN was trained to classify primary tumor sites. Top-1 accuracy, precision, sensitivity, area under the curve for the receiver-operating characteristic (AUC-ROC), and F1 score were considered as the evaluation metrics. A total of 295 spinal metastases patients (mean age ± standard deviation, 59.9 years ± 10.9; 154 men) were evaluated. Included metastases originated from lung cancer (n = 142), kidney cancer (n = 50), mammary cancer (n = 41), thyroid cancer (n = 34), and prostate cancer (n = 28). For 5-class classification, AUC-ROC and top-1 accuracy were 0.77 and 52.97%, respectively. Additionally, AUC-ROC for different sequence subsets ranged between 0.70 (for T2-weighted) and 0.74 (for fat-suppressed T2-weighted). Our developed ResNet-50 CNN model for predicting primary tumor sites in spinal metastases at MRI has the potential to help prioritize the examinations and treatments in case of unknown primary for radiologists and oncologists. [ABSTRACT FROM AUTHOR]

Copyright of Advances in New & Renewable Energy is the property of Editorial Office of Advances in New & Renewable Energy and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Monitoring and mapping vegetation dynamics using remote sensing data are essential for our understanding of land surface processes. Most current satellite-based methods process vegetation index time-series data from a series of images to retrieve key points that correspond to vegetation phenophases. As deep learning approaches have been found to be powerful in processing individual images, we tested the applicability of convolutional neural network (CNN) in mapping vegetation growth days (VGD) and the start of growing season (SOS) from each Landsat image at fine-spatial-resolution. To provide references for both model training and testing, we applied the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) to fuse image pairs of Landsat 8 Operational Land Imager (OLI) and Moderate-resolution Imaging Spectroradiometer (MODIS) for four Landsat tiles in China. We then applied a first derivative method to retrieve VGD for the fused satellite data at fine-spatial-resolution. The CNN model was trained using each fused individual image as the model inputs and derived VGD as the targets. The trained model was further used to map VGD from individual Landsat image. The result could match the reference map well as indicated by the evaluation metrics. In terms of VGD, the method achieved a coefficient of determination of 0.85 and a root mean squared error of 8.17 days. In terms of SOS, the method achieved a coefficient of determination of 0.75 and a root mean squared error of 4.09 days. Compared with existing methods that require time series of satellite data spanning the entire growth cycles to retrieve phenological metrics, this study provides an alternative method to map VGD as well as SOS using individual Landsat image. Our study highlights the power of deep learning models in extracting phenological features from individual remote sensing images. Researchers can use our methods to predict near real-time VGD and SOS in the future. [ABSTRACT FROM AUTHOR]

Accurate prediction of wind power is of great significance to the stable operation of the power system and the vigorous development of the wind power industry. In order to further improve the accuracy of ultra-short-term wind power forecasting, an ultra-short-term wind power forecasting method based on the CGAN-CNN-LSTM algorithm is proposed. Firstly, the conditional generative adversarial network (CGAN) is used to fill in the missing segments of the data set. Then, the convolutional neural network (CNN) is used to extract the eigenvalues of the data, combined with the long short-term memory network (LSTM) to jointly construct a feature extraction module, and add an attention mechanism after the LSTM to assign weights to features, accelerate model convergence, and construct an ultra-short-term wind power forecasting model combined with the CGAN-CNN-LSTM. Finally, the position and function of each sensor in the Sole du Moulin Vieux wind farm in France is introduced. Then, using the sensor observation data of the wind farm as a test set, the CGAN-CNN-LSTM model was compared with the CNN-LSTM, LSTM, and SVM to verify the feasibility. At the same time, in order to prove the universality of this model and the ability of the CGAN, the model of the CNN-LSTM combined with the linear interpolation method is used for a controlled experiment with a data set of a wind farm in China. The final test results prove that the CGAN-CNN-LSTM model is not only more accurate in prediction results, but also applicable to a wide range of regions and has good value for the development of wind power. [ABSTRACT FROM AUTHOR]

Manually pre-sowing of seed pieces cannot fully meet the large-scale potato production in China in recent years, due to the low-level mechanization, high labor costs, and intensity. Automated equipment can be expected to realize potato seed cutting. However, the potato seed eyes cannot be accurately positioned during processing using mechanized equipment, resulting in serious waste. Particularly, accurate and rapid target detection is highly required to identify the potato seed eyes, due to the small target objects. It is also necessary for the high recognition of small targets with fewer forward inference parameters. In this study, a target detection model was proposed to rapidly, accurately, and real-time recognize the potato seed eyes in the block-cutting equipment using a lightweight convolutional neural network (CNN). Firstly, a lightweight feature extraction network (GhostNetV2) was selected to replace the CSPDarkNet-53 in the backbone network of YOLOv4, in order to reduce the forward inference parameters of the model for the more focus on small target objects. Secondly, the depthwise separable convolution (DW) modules were used to further reduce the computational complexity in the neck network of YOLOv4. Finally, the bounding box loss function was changed to the SCYLLA-IoU (SIoU) loss function with the angle cost. The impact of the uncertain position was avoided in the prediction box on the convergence speed and the overall detection performance of the model. The experimental results indicated that the parameter size was 12.04 M, when the GhostNetV2 model was utilized as the backbone feature extraction network for the YOLOv4. The test dataset was also collected from the experimental platform. A better performance was achieved in the average precision of 89.13%, where the time required to detect a single image using a CPU on a laptop was 0.148 s. The F1 scores were 0.80 and 0.99 for the buds and potatoes, respectively. The improved backbone network presented approximately one-third of the original parameter size, with an increase in the detection accuracy of 1.85 percentage points, and a decrease in the detection time of 0.279 s, compared with the CSPDarkNet-53 backbone network before improvement. Furthermore, the GhostNetV2 backbone network improved the detection accuracy by 0.75, 2.67, 4.17, and 1.89 percentage points, compared with the lightweight backbone networks, including MobileNetV1, MobileNetV2, MobileNetV3, and GhostNetV1. The F1 values were also improved by 0.06, 0.07, 0.12, and 0.08 for the buds, respectively. The SIoU bounding box loss function showed detection accuracy improvements of 2.97, 4.33, 2.38, and 3.18 percentage points, compared with the GIoU, CIoU, DIoU, and EIoU ones, respectively. Moreover, the improved YOLOv4 object detection model shared the higher recognition accuracy, with increases of 23.26, 27.45, 10.51, 18.09, and 2.13 percentage points, respectively, compared with similar object detection models, such as SSD, Faster-RCNN, EfficientDet, CenterNet, and YOLOv7. In terms of the detection time, the improved YOLOv4 object detection model reduced the detection times by 0.007, 6.754, 1.891, 1.745, 0.422, and 0.326 s, compared with the SSD, Faster-RCNN, EfficientDet, CenterNet, YOLOv7, and YOLOv4, respectively. In model parameter size, the improved detection model was only 12.04M parameters. Overall, the finding can also provide new technical support for the recognition and model deployment of small target objects, such as the potato buds. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Tea Science is the property of Journal of Tea Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Chinese calligraphy is an important part of Chinese national culture and art and part of the essence of Chinese national culture. Stone calligraphy is one of the important elements of Chinese calligraphy art. Stone carved calligraphy characters have high cultural and artistic value. Therefore, accurately recognizing stone carved calligraphy characters are of great importance. Stone carved calligraphy can identify hard-to-preserve stone calligraphy paper materials in electronic data that can be preserved for a long time, thereby offering important reference materials for the study of the historical development of Chinese calligraphy art. Moreover, with the development of science and technology and the investment of China in cultural and artistic undertakings, computer-aided calligraphy character recognition technology is also constantly improving, and its application in calligraphy recognition is becoming increasingly extensive. This article aims to study a method of stone inscription calligraphy recognition based on convolutional neural networks. In this paper, we use an image recognition and optimization method consisting of a convolutional neural network to carry out an experiment with stone inscription calligraphy characters. It was concluded that the recognition accuracy of stone calligraphy characters by the convolutional neural network reached 99.2%, indicating that this stone calligraphy character recognition method based on a convolutional neural network has a good ability to recognize stone calligraphy characters. [ABSTRACT FROM AUTHOR]

The brain tumor is an abnormal and hysterical growth of brain tissues, and the leading cause of death affected patients worldwide. Even in this technology-based arena, brain tumor images with proper labeling and acquisition still have a problem with the accurate and reliable generation of realistic images of brain tumors that are completely different from the original ones. The artificially created medical image data would help improve the learning ability of physicians and other computer-aided systems for the generation of augmented data. To overcome the highlighted issue, a Generative Adversarial Network (GAN) deep learning technique in which two neural networks compete to become more accurate in creating artificially realistic data for MRI images. The GAN network contains mainly two parts known as generator and discriminator. Commonly, a generator is the convolutional neural network, and a discriminator is the deconvolutional neural network. In this research, the publicly accessible Contrast-Enhanced Magnetic Resonance Imaging (CE-MRI) dataset collected from 2005-to 2020 from different hospitals in China consists of four classes has been used. Our proposed method is simple and achieved an accuracy of 96%. We compare our technique results with the existing results, indicating that our proposed technique outperforms the best results associated with the existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Lung cancer manifests as pulmonary nodules in the early stage. Thus, the early and accurate detection of these nodules is crucial for improving the survival rate of patients. We propose a novel two-stage model for lung nodule detection. In the candidate nodule detection stage, a deep learning model based on 3D context information roughly segments the nodules detects the preprocessed image and obtain candidate nodules. In this model, 3D image blocks are input into the constructed model, and it learns the contextual information between the various slices in the 3D image block. The parameters of our model are equivalent to those of a 2D convolutional neural network (CNN), but the model could effectively learn the 3D context information of the nodules. In the false-positive reduction stage, we propose a multi-scale shared convolutional structure model. Our lung detection model has no significant increase in parameters and computation in both stages of multi-scale and multi-view detection. The proposed model was evaluated by using 888 computed tomography (CT) scans from the LIDC-IDRI dataset and achieved a competition performance metric (CPM) score of 0.957. The average detection sensitivity per scan was 0.971/1.0 FP. Furthermore, an average detection sensitivity of 0.933/1.0 FP per scan was achieved based on data from Shanghai Pulmonary Hospital. Our model exhibited a higher detection sensitivity, a lower false-positive rate, and better generalization than current lung nodule detection methods. The method has fewer parameters and less computational complexity, which provides more possibilities for the clinical application of this method. [ABSTRACT FROM AUTHOR]

Background: Dental age (DA) estimation using two convolutional neural networks (CNNs), VGG16 and ResNet101, remains unexplored. In this study, we aimed to investigate the possibility of using artificial intelligence-based methods in an eastern Chinese population. Methods: A total of 9586 orthopantomograms (OPGs) (4054 boys and 5532 girls) of the Chinese Han population aged from 6 to 20 years were collected. DAs were automatically calculated using the two CNN model strategies. Accuracy, recall, precision, and F1 score of the models were used to evaluate VGG16 and ResNet101 for age estimation. An age threshold was also employed to evaluate the two CNN models. Results: The VGG16 network outperformed the ResNet101 network in terms of prediction performance. However, the model effect of VGG16 was less favorable than that in other age ranges in the 15–17 age group. The VGG16 network model prediction results for the younger age groups were acceptable. In the 6-to 8-year-old group, the accuracy of the VGG16 model can reach up to 93.63%, which was higher than the 88.73% accuracy of the ResNet101 network. The age threshold also implies that VGG16 has a smaller age-difference error. Conclusions: This study demonstrated that VGG16 performed better when dealing with DA estimation via OPGs than the ResNet101 network on a wholescale. CNNs such as VGG16 hold great promise for future use in clinical practice and forensic sciences. [ABSTRACT FROM AUTHOR]

Mineral prospectivity mapping (MPM) mainly focuses on searching prospective areas for a particular type of mineral deposits. However, MPM is typically subject to uncertainties originated from conceptual mineral deposit models, geoscience data, and prediction models. This study utilizes a hybrid model combining a direct sampling algorithm and a convolutional neural network to quantify the uncertainty associated with the evidence layers in MPM. Specifically, a direct sampling algorithm was first used to simulate equiprobable evidence layers that followed the similar pattern of geological features. A convolutional neural network was then employed to produce mineral prospectivity maps by integrating the simulated evidence layers. The initial risk–return analysis was conducted based on the obtained mineral prospectivity maps to search for areas linked to high potential and low risk. Finally, a Markowitz mean–variance model was adopted to further outline prior prospective areas to support future mineral exploration in the high-potential areas. A case study of mapping mineral prospectivity for gold polymetallic deposits in the Middle–Lower Yangtze River Valley metallogenic belt in the southeastern Hubei Province of China was implemented. The comparative results indicated that the hybrid model of the direct sampling algorithm and convolutional neural network, which considered the uncertainty of evidence layers, achieved a higher success rate and prediction accuracy than the deterministic framework. [ABSTRACT FROM AUTHOR]

In China, patients usually determine their medical specialty before they register the corresponding specialists in the hospitals. This process usually requires a lot of medical knowledge for the patients. As a result, many patients do not register the correct specialty for the first time if they do not receive help from the hospitals. In this study, we try to automatically direct the patients to the appropriate specialty based on the symptoms they described. As far as we know, this is the first study to solve the problem. We propose a neural network-based model based on a hybrid model integrated with an attention mechanism. To prove the actual effect of this hybrid model, we utilized a data set of more than 40,000 items, including eight departments, such as Otorhinolaryngology, Pediatrics, and other common departments. The experiment results show that the hybrid model achieves more than 93.5% accuracy and has a high generalization capacity, which is superior to traditional classification models. [ABSTRACT FROM AUTHOR]

An accurate extraction of the crop spatial distribution is of great significance for the decision-making on management measures in modern agriculture. Fortunately, the remote sensing images can be widely used as the important data sources for the spatial distribution of crops at present. It is a high demand to extract the high-quality features from the spatial distribution of crops using the remote sensing images. In this study, the Sentinel-2A images were selected to extract the high-precision spatial distribution of winter wheat, in order to avoid the data scale reduction and feature fusion. Firstly, the red edge resource was utilized to classify the important features of winter wheat. The visible light and red edge bands were also combined to effectively reduce the misclassification of pixels for the high accuracy. A downscale model Red Edge Down Scale (REDS) was then established to balance the spatial scale of the data in the Sentinel-2A images, due to the different band resolution between the red edge (20m) and the visible light (10m). The generative countermeasure network was constructed using the three red edge bands of B5, B6 and B7. More importantly, the spatial resolution of B11 shortwave infrared band was reduced from 20 to 10 m, in order to obtain the better consistence in the spatial resolution of visible light and red edge band. The edge blur of image was also prevented from the interpolation (nearest neighbor interpolation). Secondly, the inputs of REDS consisted of the low- and high-resolution channel, correspondingly to the spectral and texture information, respectively. The spatial structure information was then input from the high- into the low-resolution channel. As such, the improved model was achieved in the image data from the high-resolution red edge and short-wave infrared (SWIR) channel. Secondly, the original data was extracted, and then combined into the basic input data, including the three red edge bands after scaling down, the visible light band with a resolution of 10m, and three remote-sensing index products, namely Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Red-Edge1 (NDRE1). Thirdly, the semantic feature extraction model was constructed as the Red Edge and Vegetation Index Feature Network (REVINet) using convolutional neural network. The coding and decoding units were constructed in the REVINet model using residual network. The linear model was used to fuse the multi-scale features for the output by the decoding units. SoftMax function was used as a classifier for the pixel-by-pixel classification. Finally, the segmentation, and the spatial distribution of winter wheat were generated to verify the REVINet model, compared with the ERFNet, U-Net, and RefineNet models. The experimental results show that the smoother contour edge was extracted from the planting area of winter wheat, particularly with the less misclassification. Meanwhile, the recall (92.15%), precision (93.74%), accuracy (93.09%), and F1 score (92.94%) were better than the rest models, indicating the ideal performance. The spatial distribution of the whole research area demonstrated that the winter wheat in China was mainly distributed in the south of the Great Wall in 2022. The relatively high accuracy of extracted areas was achieved with the better coincidence degree, compared with the standard released by the National Statistical Department in 2021. Therefore, the data organization and feature extraction can be expected to serve as the spatial distribution of winter wheat using the Sentinel-2A. The finding can also provide the technical reference for the Sentinel-2A data in the agricultural field. [ABSTRACT FROM AUTHOR]

Developing novel techniques for freshness assessment are of the utmost importance in yield and trade of aquatic products. The crayfish (Prokaryophyllus clarkii) is one of the most popular freshwater products in China, and its food safety should be a serious concern. In this study, a convolutional neural network (CNN)‐based portable computer vision system for freshness assessment of crayfish method was proposed. A portable microscope was utilized to collect the microscopic images of crayfish with different freshness levels. The convolutional neural network was constructed and then optimized to extract features from the microscopic images. For the pictures from the portable microscope, the prediction accuracies of freshness could be 86.5% and 83.3% when the optimized networks were applied. The results indicate that the convolutional neural network‐based portable computer vision system may provide an alternative way for the freshness assessment in the crayfish industrial chain. Practical Application: Portable computer vision system was constructed by a portable microscope connected to a mobile phone. The freshness of crayfish could be rapidly assessed by analyzing the pictures of crayfish using the system. The convolutional neural network‐based portable computer vision system may provide an alternative way for the freshness assessment in the crayfish industrial chain. [ABSTRACT FROM AUTHOR]

As a traditional edible and medicinal fungus in China, Oudemansiella raphanipes has high economic benefits. In order to achieve the automatic classification of Oudemansiella raphanipes into four quality levels using their image dataset, a quality grading algorithm based on neural network models was proposed. At first, the transfer learning strategy and six typical convolution neural network models, e.g., VGG16, ResNet50, InceptionV3, NasNet-Mobile, EfficientNet, and MobileNetV2, were used to train the datasets. Experiments show that MobileNetV2 has good performance considering both testing accuracy and detection time. MobileNetV2 only needs 37.5 ms to classify an image, which is shorter by 11.76%, 28.57%, 46.42%, 59.45%, and 79.73%, respectively, compared with the classification times of InceptionV3, EfficientNetB0, ResNet50, NasNet-Mobile, and VGG16. Based on the original MobileNetV2 model, four optimization methods, including data augmentation, hyperparameter selecting, an overfitting control strategy, and a dynamic learning rate strategy, were adopted to improve the accuracy. The final classification accuracy can reach as high as 98.75%, while the detection time for one image is only 22.5 ms and the model size is only 16.48 MB. This quality grading algorithm based on an improved MobileNetV2 model is feasible and effective for Oudemansiella raphanipes, satisfying the needs in the production line. [ABSTRACT FROM AUTHOR]

In recent years, with the development of geological prospecting from shallow ore to deep and hidden ore, the difficulty of prospecting is increasing day by day, so the application of computer technology and new methods of geological and mineral exploration is paid more and more attention. The mining and prediction of geological prospecting information based on deep learning have become the frontier field of earth science. However, as a deep artificial intelligence algorithm, deep learning still has many problems to be solved in the big data mining and prediction of geological prospecting, such as the small number of training samples of geological and mineral images, the difficulty of building deep learning network models, and the universal applicability of deep learning models. In this paper, the training samples and convolutional neural network models suitable for geochemical element data mining are constructed to solve the above problems, and the model is successfully applied to the prediction research of gold, silver, lead and zinc polymetallic metallogenic areas in South China. Taking the Pangxidong research area in the west of Guangdong Province as an example, this paper carries out prospecting target prediction research based on a 1:50000 stream sediment survey original data. Firstly, the support vector machine (SVM) model and statistical method were used to determine the ore-related geochemical element assemblage. Secondly, the experimental data of geochemical elements were augmented and a dataset was established. Finally, ResNet-50 neural network model is used for data training and prediction research. The experimental results show that the areas numbered 9, 29, 38, 40, 95, 111, 114, 124, 144 have great metallogenic potential, and this method would be a promising tool for metallogenic prediction. By applying the ResNet-50 neural network in metallogenic prediction, it can provide a new idea for the future exploration of mineral resources. In order to verify the generality of the research method in this paper, we conducted experimental tests on the geochemical dataset of B area, another deposit research area in South China. The results show that 100% of the prediction area obtained by using the proposed method covers the known ore deposit area. This model also provides method support for further delineating the prospecting target area in study area B. [ABSTRACT FROM AUTHOR]

Passenger flow is an important benchmark for measuring tourism benefits, and accurate tourism passenger flow prediction is of great significance to the government and related tourism enterprises and can promote the sustainable development of China's tourism industry. For daily passenger flow time series data, a passenger flow forecasting method based on convolutional neural network (CNN) and improved quantile regression long short-term memory network (QRLSTM), denoted as CNN-IQRLSTM, is proposed with reconstructed correlation features and in the form of sliding windows as inputs. First, four discrete variables such as whether the day is a weekend and holiday are created by time; then, a sliding window of width 42 is used to pass the passenger flow data into the network sequentially; finally, the loss function of the sparse Laplacian improved QRLSTM is introduced for passenger flow prediction, and the point prediction and interval prediction results under different quartiles are obtained. The application of quantile regression captures the overall picture of the data, enhances the robustness, fit, predictive power and nonlinear processing capability of neural networks, and fills the gap between quantile regression and neural network methods in the field of passenger flow prediction. CNN can effectively handle complex input data, and the improved nonlinear QR model can provide passenger flow quantile prediction information. The method is applied to the tourism traffic prediction of four 5A scenic spots in Jilin Province, and the effectiveness of the method is verified. The results show that the method proposed in this paper fits best in point prediction and has higher prediction accuracy. The MAPE of the Changbai Mountain dataset was 0.07, the MAPE of the puppet palace museum dataset was 0.05, the fit of the Sculpture Park dataset reached 93%, and the fit of the net moon lake dataset was as high as 99%. Meanwhile, the interval prediction results show that the method has a larger interval coverage as well as a smaller interval average width, which improves the prediction efficiency. In 95% of the interval predictions, the interval coverage of Changbai Mountain data is 99% and the interval average width is 0.49. It is a good reference value for the management of different scenic spots. [ABSTRACT FROM AUTHOR]

In order to improve precipitation forecast from GRAPES_Meso V4.0 in China, we propose a 1–6‐h rolling correction solution, based on infrared (IR) channels from geostationary meteorological satellite and surface observation data. In particular, we design a deep learning extrapolation model to predict the evolution of cloud clusters based on convolutional neural networks and long short‐term memory networks. The predicted cloud clusters, together with the relationship between the rainfall area and the cloud position, are applied to correct the 1–6‐h precipitation forecast. We conduct comprehensive experiments to evaluate the proposed solution over China. Experimental results show that the deep learning model can successfully capture spatial characteristics and temporal variations between the sequences, and achieve reliable predictions of cloud clusters. The analysis further indicates that the rolling correction solution via the predicted cloud clusters has improved the precipitation forecast in China. The distribution of corrected precipitation forecast is more consistent with the observed precipitation compared to GRAPES_Meso forecast. In particular, the rolling correction model could enhance the forecast on "rain/no‐rain" events, light rain, and moderate rain according to TS, ETS, BIAS, and FAR metrics. [ABSTRACT FROM AUTHOR]

Mapping of lithological units is a significant challenge for geological tasks. Stream sediment geochemical survey data contain abundant geological information that can help delineate lithological units. In this study, a convolutional neural network (CNN) was applied to map the lithological units in the Daqiao gold District, West Qinling Orogen, China, based on stream sediment geochemical data, in which each sample includes the concentrations of 15 trace elements (Cu, Pb, Zn, Ag, Mo, Sn, W, Mn, Ba, As, Sb, Bi, Cd, Au, and Hg). The training samples were firstly constructed with a certain window size by randomly selecting locations within each lithological unit. A CNN model was then established based on AlexNet to classify the lithologic categories. The classification map showed that 7 lithological units were correctly distinguished with an overall classification accuracy of 90.0%, suggesting that (1) stream sediment geochemical survey data of only trace element concentrations are useful for lithological mapping, and (2) a CNN can extract effectively geochemical characteristics from geochemical survey data. This study confirms the potential of a CNN as an effective method for geological mapping based on geochemical survey data. [ABSTRACT FROM AUTHOR]

Minority ethnic patterns in China, reflecting diverse cultures, serve as symbols of ethnic identity and cultural heritage. However, the current artistic domain of minority ethnic patterns faces dual challenges: limited artistic styles and insufficient innovation efficiency. In addressing these issues, this study proposes a novel approach for ethnic pattern innovation, named Fast Style Transfer for Ethnic Pattern Innovation (FST-EPI), aiming to enhance innovation efficiency and diversify artistic styles. FST-EPI comprises three key modules: background generation, background fusion, and fast transfer. Firstly, the background generation module utilizes the Visual Geometry Group network (VGGNet) to extract features from images, generating a background image with the desired style while preserving the necessary stylistic attributes. Subsequently, textile patterns are fused with the stylized background image, forming a content-background fusion image. Finally, the selected stylistic patterns, along with the content-background fusion image, are input into the fast transfer module to produce the ultimate innovative pattern. Experimental results demonstrate that the generated images not only fully retain the core features and cultural elements of minority ethnic patterns but also successfully integrate the unique styles from one or more reference images. This proposed method exhibits outstanding efficiency and feasibility in a broad range of experiments related to ethnic pattern style transfer, as evidenced by thorough comparisons with state-of-the-art methods. Ultimately, the processing speed of this method achieves a real-time output at the level of seconds, reducing processing time by nearly 50% compared to traditional approaches. [ABSTRACT FROM AUTHOR]

• A Transformer model is applied to evaluate crash risk based on non-aggregated abnormal driving events (ADEs). • The proposed Transformer model outperforms other commonly used methods. • Impacts of the acceleration, speed, duration, and type of ADEs on crash risk are quantified. • A time-decay function is proposed to fit the temporal impacts of ADEs on crash risk. • Crash risk spatial–temporal decay and collective superposition effect of multiple ADEs are revealed. A crash risk evaluation model aims to estimate crash occurrence possibility by establishing the relationships between traffic flow status and crash occurrence. Based upon which, Proactive Traffic Safety Management (PTSM) systems have been developed and implemented. The current crash risk evaluation models relied on high dense traffic detectors, which limited the applications of PTSM to infrastructures with enough sensing devices. To address such application limitation issue, this study employed the widespread abnormal driving event information that is generated by emerging driving monitoring and vehicle connection techniques to develop the crash risk evaluation model. Specifically, to characterize abnormal driving events, a six-tuple embedding method was proposed to store their space, time and kinetics features. Given their irregular and discrete distributions on roadways, a Transformer model with self-attention mechanism was proposed to extract the spatial distribution characteristics. In addition, a time-decay function was integrated to fit the temporal impacts of abnormal driving events on crash risk. Empirical data from a freeway in China were utilized for the analyses. The results showed that abnormal driving events with lower speed, larger acceleration and duration are more likely to cause crashes. The accumulation of multiple events in the time period of less than 3 min would lead to a sharp increase of crash risk. Besides, compared to the average metrics of the widely adopted Convolutional Neural Network (CNN), XGBoost, and logistic regression models, the proposed model achieved higher accuracy (0.841) and AUC (0.777), with average improvement of 2.5 % and 9.1 % respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Most management methods for poultry farming currently rely on human labor. Such management is labor-intensive and inefficient, especially in identifying poultry growth stages. Given the lack of a high-precision artificial method for chick's day-age detection, a high-performance day-age classification and detection model for chicks was proposed based on artificial intelligent techniques. This method can detect and classify chicks in six different living stages from 1 to 32 day-ages, and the accuracy is 95.2%, superior to other current ones. In order to apply this method in practical scenarios, it has been deployed into an application based on the IOS system, which can recoganize the day-age of chicks by capturing real-time photos. The system is currently deployed in Rizhao City, Shandong Province, China. It helps chicken farm staff automatically detect the behavior of chickens, whose excellent working effect proves the robust availibility of the proposed method. Thanks to the boom of computer vision techniques and artificial intelligence algorithms, it is more available to achieve artificial rearing for animals in real production scenarios. Improving the accuracy of chicken day-age detection is one of the instances, which is of great importance for chicken rearing. To solve this problem, we proposed an attention encoder structure to extract chicken image features, trying to improve the detection accuracy. To cope with the imbalance of the dataset, various data enhancement schemes such as Cutout, CutMix, and MixUp were proposed to verify the effectiveness of the proposed attention encoder. This paper put the structure into various mainstream CNN networks for comparison and multiple ablation experiments. The final experimental results show that by applying the attention encoder structure, ResNet-50 can improve the accuracy of chicken age detection to 95.2%. Finally, this paper also designed a complete image acquisition system for chicken houses and a detection application configured for mobile devices. [ABSTRACT FROM AUTHOR]

Many hydrological applications related to water resource planning and management primarily rely on a succession of streamflow forecasts with extensive lead times. In this study, two innovative models, termed as DirCNN and DRCNN, are proposed for multi-step-ahead (MSA) monthly streamflow forecasting based on the direct (Dir) and direct-recursive (DR) strategies and using the convolutional neural network (CNN) to automatically extract input variables. Compared to traditional MSA forecasting models, DirCNN and DRCNN can automatically extract input variables and predict streamflow for multiple lead times simultaneously. Xiangjiaba Hydropower Station, Huanren Reservoir, and Fengman Reservoir in China were included as case studies, and three artificial neural networks based models are used as comparative models. The most important results are highlighted below. First, the proposed DirCNN and DRCNN exhibit comparable prediction performances but outperform the comparison models. Second, with the increase in lead time, DirCNN and DRCNN demonstrate good consistency in forecasting accuracy. Third, the stacking order of candidate sequences has little effect on the DirCNN and DRCNN forecasting accuracy. These results suggest that DirCNN and DRCNN could be ahead of MSA monthly streamflow forecasting and thus would be helpful in the judicious use of water resources. [ABSTRACT FROM AUTHOR]

A hybrid framework by integrating stacking ensemble with two deep learning methods of convolutional neural network (CNN) and recurrent neural network (RNN) is introduced in this paper for landslide spatial prediction in the Three Gorges Reservoir area, China. The proposed framework is summarized in following steps. First, a spatial database consists of 20 landslide conditioning factors and 196 landslide polygons was established. Then, landslide and non-landslide pixels were randomly divided into training (70% of the total) and test (30%) sets. Next, a stacking ensemble method that integrates CNN and RNN was constructed using the training set. Finally, the proposed stacking framework was applied for landslide susceptibility mapping and evaluated. Experimental results demonstrated that the proposed framework can obtain the best predictive capability (0.918) than CNN (0.904), RNN (0.900) and logistic regression (0.877) in terms of area under the receiver operating characteristic curve (AUC). Therefore, it can be useful for landslide disaster management and assessment. [ABSTRACT FROM AUTHOR]

Copyright of South China Fisheries Science is the property of South China Fisheries Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)