Search

Summary: In China, catering O2O takeout develops rapidly; thus, there is the fierce competition in the catering O2O industry. More and more catering O2O takeout platforms focus on customer experience, especially service experience in distribution link, so it is extremely necessary to evaluate customer experience of catering O2O takeout in China scientifically and reasonably. This paper establishes a customer experience evaluation index system from the perspectives of O2O takeout platform, delivery staff, and distribution process. This paper uses the BP Neural Network Model to evaluate customer experience of catering O2O takeout, uses Principal Component Analysis to extract principal components as the input of BP neural network model, and uses the model of MATLAB Neural Network Toolbox to conduct the training simulation with customer experience data. The results show that the model can evaluate customer experience of catering O2O takeout. The analysis in this paper provides a new evaluation method of customer experience for catering O2O takeout in China. [ABSTRACT FROM AUTHOR]

Drought is an important meteorological event in China and can cause severe damage to both livelihoods and socio‐ecological systems, but current seasonal prediction skill for drought is far from successful. This study used convolutional neural network (CNN) to build an effective seasonal forecast model for the summer consecutive dry days (CDD) over China. The principal components (PC) of the six leading empirical orthogonal function modes of CDD anomaly were predicted by CNN, using the previous winter precipitation, 2‐m temperature and 500 hPa geopotential height as predictors. These predicted PCs were then projected onto the observed spatial patterns to obtain the final predicted summer CDD anomaly over China. In the independent hindcast period of 2007–2018, the interannual variabilities of first six PCs were significantly predicted by CNN. The spatial patterns of CDD were then skillfully predicted with anomaly correlation coefficient skills generally higher than 0.2. The interannual variability of summer CDD over the middle and lower Yangtze River valley, northwestern China and northern China were significant predicted by our CNN model three months in advance. CNN identified that the previous winter precipitation was the important predictor for PC1–PC3, whereas the previous winter 2‐m temperature and 500 hPa geopotential height were important for the prediction of PC4–PC6. This research provides a new and effective method for the seasonal prediction of summer drought. Plain Language Summary: Drought can cause serious agricultural and ecosystem disasters, so its forecast is valuable for preventing and mitigating related natural disasters and regional socioeconomic sustainability. However, current prediction skill for drought is far from successful since its extreme feature. The gradually emerging deep learning methods offer new possibilities, but how to effectively apply deep learning models in climate prediction with a small sample size remains an open question. In this paper, we build seasonal prediction convolutional neural network model for summer consecutive dry days over China using previous winter predictors. This model achieves significant prediction skill three months in advance. The empirical orthogonal function decomposition is used to reduce the dimensionality of consecutive dry days data in our model. Our research provides a new perspective for drought prediction, and it is expected that such method will be also useful for other seasonal climate prediction problems. Key Points: Convolutional neural network (CNN) skillfully predicts summer consecutive dry days (CDD) over China three months in advanceThe principal components of CDD are predicted by CNN and then projected on the observed spatial patternsPrevious winter 2‐m temperature, geopotential height at 500 hPa and precipitation are the essential predictors in CNN [ABSTRACT FROM AUTHOR]

Copyright of Irrigation & Drainage is the property of Wiley-Blackwell 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.)

The carbon trading market has become a powerful weapon in alleviating carbon emissions in China, and the carbon price is at the core of its operation. Hence, the carbon trading market serves as an indispensable component in forecasting the carbon price accurately in advance. This paper innovatively explores an ensemble‐driven long short‐term memory network (LSTM) model based on complementary ensemble empirical mode decomposition (CEEMD) for carbon price forecasting, applying it to all eight carbon trading pilots in China. The CEEMD was initially implemented for mode transformation in order to decompose the original complicated mode into a set of simple modes. Then, the partial autocorrelation function selected time‐lagged features as inputs for each mode. Subsequently, the LSTM was used to model the mapping between time‐lagged factors as well as each mode's target values, constructing multiple LSTM models for ensemble learning. Finally, the inverse CEEMD computation was introduced to integrate the anticipated results of the multi‐mode into the final results. Its practical application simultaneously embraced all eight carbon pilots in China, covering their corresponding carbon price data over a considerably long period. The obtained results illustrated that the proposed model driven by ensemble learning possessed sufficient accuracy in carbon price forecasting in China compared with the single LSTM model as well as other conventional artificial neural network models. Furthermore, according to the scope of its application, the innovative model exhibited strong stability and universality. [ABSTRACT FROM AUTHOR]

Fault section diagnosis (FSD) is significant for the power system dispatching. Artificial neural network (ANN)‐based FSD method has strong fault tolerance but it looks like a black box and lacks the interpretability to the diagnosis outputs. In addition, when the topology of power systems changes, the ANN structure needs to be reconstructed and retrained, and thus has low adaptive capability. In order to tackle these challenges, in this paper, an ANN‐based FSD method by constructing universal transparent diagnosis models is proposed. The diagnosis models are constructed for the transmission line, transformer, and bus types rather than for a specific power system section. They can express the logical relations among sections, protective relays (PRs) and circuit breakers (CBs) clearly and intuitively. In addition, fuzzy values are used to model the uncertainties of PRs and CBs, and to determine the inputs of diagnosis models. Furthermore, the differential evolution algorithm is employed to optimize the network parameters of diagnosis models. The proposed method is verified on the IEEE 30‐bus test system and an actual local power system in Jilin Province of China. [ABSTRACT FROM AUTHOR]

Learning analytics (LA) has been widely adopted in research on education. However, most studies in the area have conducted LA after computer‐supported collaborative learning (CSCL) activities rather than during CSCL. To address this problem, this study proposed a LA‐based real‐time feedback approach based on a deep neural network model to improve CSCL performance. In total, 72 university students participated in the study and were randomly assigned to an experimental or control group. The students in the experimental group learned with the LA‐based real‐time feedback approach, whereas the students in the control group learned with the conventional online collaborative learning approach. To analyse the data, both quantitative and qualitative methods were adopted. The results indicated that the LA‐based real‐time feedback approach significantly promoted knowledge convergence, knowledge elaboration, interactive relationships and group performance. The interview results also confirmed the effectiveness of the proposed approach. Practitioner notesWhat is already known regarding this topic Learning analytics (LA) has been widely used in education.Most studies in the area have presented LA results only after collaborative learning and have lacked real‐time analysis and feedback.What this paper adds A LA‐based real‐time feedback approach was proposed and validated in the computer‐supported collaborative learning (CSCL) context.The experimental results indicated that the LA‐based real‐time feedback approach significantly promoted knowledge elaboration, knowledge convergence, interactive relationships and group performance.Implications for practice and/or policy To shed light on progress in CSCL, real‐time LA are recommended.Deep neural network models, such as bidirectional encoder representations from transformers, can be adopted to automatically analyse online discussion transcripts.Real‐time feedback based on LA results can promote CSCL performance. [ABSTRACT FROM AUTHOR]

The self-adaptive intelligence gray predictive model (SAIGM) has an alterable-flexible model structure, and it can build a dynamic structure to fit different external environments by adjusting the parameter values of SAIGM. However, the order number of the raw SAIGM model is not optimal, which is an integer. For this, a new SAIGM model with the fractional order accumulating operator (SAIGM_FO) was proposed in this paper. Specifically, the final restored expression of SAIGM_FO was deduced in detail, and the parameter estimation method of SAIGM_FO was studied. After that, the Particle Swarm Optimization algorithm was used to optimize the order number of SAIGM_FO, and some steps were provided. Finally, the SAIGM_FO model was applied to simulate China's electricity consumption from 2001 to 2008 and forecast it during 2009 to 2015, and the mean relative simulation and prediction percentage errors of the new model were only 0.860% and 2.661%, in comparison with the ones obtained from the raw SAIGM model, the GM(1, 1) model with the optimal fractional order accumulating operator and the GM(1, 1) model, which were (1.201%, 5.321%), (1.356%, 3.324%), and (2.013%, 23.944%), respectively. The findings showed both the simulation and the prediction performance of the proposed SAIGM_FO model were the best among the 4 models. [ABSTRACT FROM AUTHOR]

Ice clouds are mostly composed of different ice crystal habits. It is of great importance to classify ice crystal habits seeing as they could greatly impact single‐scattering properties of ice crystal particles. The single‐scattering properties play an important role in the study of cloud remote sensing and the Earth's atmospheric radiation budget. However, there are countless ice crystals with different shapes in ice clouds, and the task of empirical classification based on naked‐eye observations is unreliable, time consuming and subjective, which leads to classification results having obvious uncertainties and biases. In this paper, the images of ice crystals observed from airborne Cloud Particle Imager in China are used to establish an ice crystal data set called Ice Crystals Database in China, which consists of 10 habit categories containing over 7,000 images. We propose an automatic classification model of ice crystal habits, called TL‐ResNet152, which is a deep convolutional neural network based on the newly developed method of transfer learning. The results show that the TL‐ResNet152 model could achieve reliable performance in ice crystal habits classification with the accuracy of 96%, which is far more accurate than traditional classification methods. Achieving high‐precision automatic classification of ice crystal habits will help us better understand the radiation characteristics of ice clouds. Plain Language Summary: In recent years, Convolutional Neural Networks (CNNs), as one of the representative algorithms used in deep learning, have been widely applied in the field of image classification and have achieved remarkable results. However, to the best of our knowledge, there are few studies regarding the application of deep CNNs to ice crystal image classification. In this paper, we propose an automatic classification model of ice crystal habits called TL‐ResNet152, which is a deep CNN based on a newly developed method of transfer learning. Using the TL‐ResNet152 model, high precision and automatic classification of ice crystal habits could be achieved, furthering our understanding of radiation characteristics of ice clouds. We have set up an ice crystal data set, called Ice Crystals Database in China, which consists of 10 habit categories with 7,282 images. As far as we know, it is the first publicly available ice crystals data set in China, pertaining to ice crystals observed in natural ice clouds. The publication of this database will promote more and more researches into understanding the physical process of ice clouds based on ice crystal habits classification. Key Points: An ice crystal data set called Ice Crystals Database in China (ICDC) containing over 7,000 images has been first establishedWe propose an automatic classification model of ice crystal habits, TL‐ResNet152, which is a convolutional neural network created using transfer learningThe high‐precision automatic classification of ice crystal habits is achieved by using this classification model [ABSTRACT FROM AUTHOR]

Objects: This study aims to explore the Cancer antigen 724 (CA724) reference values spatial distribution characteristics in healthy Chinese adults. The study can provide regional reference for medical diagnosis. Study Design: The relationship between CA724 and 25 geographical environmental factors was analyzed firstly. Artificial neural network simulation training was used to construct the prediction model. The national forecast distribution map of the CA724 reference values was obtained by the geostatistical mapping method. Analyzing and exploring the influence mechanism of geographical environment factors on CA724 reference values. Methods: Collecting 34470 cases from more than 106 cities healthy adults CA724 reference values via several paper databases in 10 recent years. Correlation analysis, RBF artificial neural networks and trend surface analysis were applied to explore if there was any tendency of spatial variation. The Kriging interpolation of geostatistical analysis was developed to reveal the spatial distribution characteristics of the CA724 reference values. Results: The distribution of CA724 reference values of Chinese healthy adults shows a downward trend from south to north. CA724 reference values have negative correlations with latitude, annual sunshine duration and topsoil cation exchange capacity in clay. CA724 have positive correlations with annual mean air temperature, annual mean relative humidity, and annual precipitation amount. High temperature and high humidity environment will reduce gastrointestinal function and breeze various mold bacteria. Lack of sunshine can easily lead to vitamin C deficiency in the body. These will increase the incidence of gastrointestinal diseases and gastric cancer, then increase the CA724 value. Conclusion: CA724 reference values show spatial autocorrelation and regional variation. There are some geographical environment factors effected Chinese healthy adults CA724 reference values. Geographic factors such as sunshine, temperature, and humidity have effects on CA724 reference values can provide new ideas and directions of prevention and clinical diagnosis in the future. [ABSTRACT FROM AUTHOR]

In recent years, research on intelligent systems is becoming more and more popular in academe. Intelligent systems research mainly involves the field of artificial intelligence. There are many research groups engaged in the research of intelligent systems in the world, and a variety of achievements have been made. In this paper, the main research institutions in China as well as their main research topics are introduced. [ABSTRACT FROM AUTHOR]

In this work, a machine translation framework is proposed to tackle the flight plan generation in the air transport field. Diverging from the traditional human expert‐based way, a novel sequence‐to‐sequence transfer transformer network to automatic flight plan generation with enhanced operational acceptability is presented. It allows the user to translate the departure and arrival airport pairs denoted as test sentences, into the flyable waypoint sequences denoted as the corresponding source sentences. The approach leverages deep neural networks to autonomously learn air transport specialized knowledge and human expert insights from industry legacy data. Moreover, a multi‐head attention mechanism is adopted to model the complex correlation between airport pairs. Besides, we introduce an innovative waypoint embedding layer to learn effective embeddings for waypoint sequences. Additionally, an extensive flight plan dataset is constructed utilizing real‐world data in China spanning from July to September 2019. Employing the proposed model, rigorous training and testing procedures are conducted on this dataset, yielding remarkably favourable outcomes based on automatic evaluation metrics that are BLEU and METEOR, which outperform other popular approaches. More importantly, the proposed approach achieves high performance in the operational validation and visualization, showing its application potential for real‐world air traffic operation. [ABSTRACT FROM AUTHOR]

Urbanization, especially in developing countries, has led to numerous concerns, such as air pollution, traffic congestion and habitat destruction. Within this context, it is important to evaluate urban development as sustainable, and various sustainability assessment methods have been developed, including fuzzy logic approaches. However, predefined fuzzy rules and simple linear membership functions were used, which are largely based on the knowledge of subject experts. Therefore, this paper aims to introduce an adaptive neuro‐fuzzy inference systems (ANFIS) approach for urban sustainability assessment. With collected training samples from the Urban China Initiative, and the ANFIS approach was used to rank 185 selected cities in China. The results show that the ANFIS approach is appropriate for assessing urban sustainability, and the nonlinear membership functions fit the training samples better than the linear membership functions. Further discussion indicates that future research on sustainability assessment should be more integrated. [ABSTRACT FROM AUTHOR]

Opinion words are crucial information for sentiment analysis. In some text, however, opinion words are absent or highly ambiguous. The resulting implicit opinions are more difficult to extract and label than explicit ones. In this paper, cutting-edge machine-learning approaches - deep neural network and word-embedding - are adopted for implicit opinion mining at the snippet and clause levels. Hotel reviews written in Chinese are collected and annotated as the experimental data set. Results show the convolutional neural network models not only outperform traditional support vector machine models, but also capture hidden knowledge within the raw text. The strength of word-embedding is also analyzed. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to analyze publications on artificial intelligence (AI) for falls in older people from a bibliometric perspective. Methods: The Web of Science database was searched for titles of English‐language articles containing the words "artificial intelligence," "deep learning," "machine learning," "natural language processing,", "neural artificial network," "fall," "geriatric," "elderly," "aging," "older," and "old age." An R‐based application (Biblioshiny for bibliometrics) and VOSviewer software were used for analysis. Results: Thirty‐seven English articles published between 2018 and 2024 were included. The year 2023 is the year with the most publications with 16 articles. The most productive research field was "Engineering Electrical Electronic" with seven articles. The most productive country was the United States, followed by China. The most common words were "injuries," "people," and "risk factors." Conclusion: Publications on AI and falls in the elderly are both few in number and the number of publications has increased in recent years. Future research should include relevant analyses in scientific databases, such as Scopus and PubMed. [ABSTRACT FROM AUTHOR]

Summary: Motivated by the long‐standing interest of economists in understanding the nexus between firm productivity and export behavior, this paper develops a novel structural framework for control‐function‐based nonparametric identification of the gross production function and latent firm productivity in the presence of endogenous export opportunities that is robust to recent unidentification critiques of proxy estimators. We provide a workable identification strategy, whereby the firm's degree of export orientation provides the needed (excluded) relevant independent exogenous variation in endogenous freely varying inputs, thus allowing us to identify the production function. We estimate our fully nonparametric instrumental variable model using the Landweber–Fridman regularization with the unknown functions approximated via artificial neural network sieves with a sigmoid activation function, which are known for their superior performance relative to other popular sieve approximators, including the polynomial series favored in the literature. Using our methodology, we obtain robust productivity estimates for manufacturing firms from 28 industries in China during the 1999–2006 period to take a close look at China's exporter productivity puzzle, whereby exporters are found to exhibit lower productivity levels than nonexports. [ABSTRACT FROM AUTHOR]

Aim: This study was conducted to understand the research hotspots, research trends and research frontiers for hypothermia in surgical patients and provide a reference for developing effective measures to reduce the incidence of hypothermia in these patients. Design: Using CiteSpace software, a visual analysis of 1288 included articles related to hypothermia in surgical patients was performed. Methods: CiteSpace software is a Java application that supports knowledge research, data visualization and analysis of literature databases. The following data were retrieved: title, abstract, year, keywords, author, academic institution, journal and citations. The included literature was analysed using CiteSpace visualization software, knowledge mapping, collaborative network analysis, cluster analysis and highlighting keywords for visualization. Results: A total of 1288 articles related to hypothermia in surgical patients were included, with the largest number of articles published in the United States (448), followed by in Germany (104) and China (102). The top three institutions, journals and authors were from the United States. The most common keywords were perioperative 'hypothermia', 'risk factors' and 'anesthesia'. [ABSTRACT FROM AUTHOR]

Aim: To develop and validate models based on logistic regression and artificial intelligence for prognostic prediction of molar survival in periodontally affected patients. Materials and Methods: Clinical and radiographic data from four different centres across four continents (two in Europe, one in the United States, and one in China) including 515 patients and 3157 molars were collected and used to train and test different types of machine‐learning algorithms for their prognostic ability of molar loss over 10 years. The following models were trained: logistic regression, support vector machine, K‐nearest neighbours, decision tree, random forest, artificial neural network, gradient boosting, and naive Bayes. In addition, different models were aggregated by means of the ensembled stacking method. The primary outcome of the study was related to the prediction of overall molar loss (MLO) in patients after active periodontal treatment. Results: The general performance in the external validation settings (aggregating three cohorts) revealed that the ensembled model, which combined neural network and logistic regression, showed the best performance among the different models for the prediction of MLO with an area under the curve (AUC) = 0.726. The neural network model showed the best AUC of 0.724 for the prediction of periodontitis‐related molar loss. In addition, the ensembled model showed the best calibration performance. Conclusions: Through a multi‐centre collaboration, both prognostic models for the prediction of molar loss were developed and externally validated. The ensembled model showed the best performance in terms of both discrimination and validation, and it is made freely available to clinicians for widespread use in clinical practice. [ABSTRACT FROM AUTHOR]

The ionospheric total electron content (TEC) is an important ionospheric parameter, and it is widely utilized in research such as space weather prediction and precise positioning. However, it is still challenging to develop an ionospheric TEC prediction model with high accuracy. In this study, a new ionospheric TEC model over China was developed using the bidirectional long short‐term memory (bi‐LSTM) method and observations from 257 ground‐based global navigation satellite system (GNSS) stations in the Crustal Movement Observation Network of China from January 2018 to December 2021. The root mean square errors of the bi‐LSTM‐based model's 1 and 2 hr ahead predictions on the test data set (from June 2021 to December 2021) are 1.12 and 1.68 TECU, respectively, which are 75/50/32% and 72/48/22% smaller than those of the IRI‐2016, artificial neural network and LSTM‐based models, correspondingly. The bi‐LSTM‐based model shows the best performance, which is most likely due to the fact that the sequence information in both forward and backward directions is taken into consideration in the new model. In addition, the diurnal variation, seasonal variation of the ionospheric TEC, and variations under geomagnetic storm conditions are successfully captured by the bi‐LSTM‐based model. Moreover, the TEC maps resulting from the bi‐LSTM model agree well with those obtained from the final ionospheric product from the Chinese Academy of Sciences. Hence, the new model can be a good choice for the investigation of the spatiotemporal variation trend in the ionosphere and GNSS navigation. Plain Language Summary: The ionospheric total electron content (TEC) is the total number of free electrons along a signal propagation path in a cross section of one square meter, and the ionospheric delay error of the signal from the global navigation satellite system (GNSS) is proportional to the value of TEC. The variation of the ionospheric TEC can also be used to study the variations in space weather. In this study, a new ionospheric TEC model over China based on the bidirectional long short‐term memory (bi‐LSTM) method and long‐term ground‐based observations at 257 GNSS stations from the Crustal Movement Observation Network of China was developed and subsequently validated. The main reason for the selection of the bi‐LSTM model is for its consideration of the sequence information in both forward and backward directions. The prediction results of the new model show that in comparison with that of three other models, including the artificial neural network, LSTM, and traditional IRI‐2016 models, the new model is the best performer. Furthermore, the bi‐LSTM model also successfully captures the diurnal and seasonal variations of the ionospheric TEC and the TEC variations under geomagnetic storm conditions. Key Points: The bidirectional long short‐term memory (bi‐LSTM) method is adopted to predict the ionospheric total electron content maps over China using long‐term ground‐based global positioning system observations from the Crustal Movement Observation Network of ChinaThe bi‐LSTM‐based model outperforms the IRI‐2016, artificial neural network and long short‐term memory‐based modelsThe bi‐LSTM‐based model can predict the ionospheric response during geomagnetic storm periods, such as the 4–7 November 2021 G3 storm period [ABSTRACT FROM AUTHOR]

Energy efficiency of data centers (DCs) is of great concern due to their large amount of energy consumption and the foreseeable growth in the demand of digital services in the future. The past decade witnessed improvements of the energy efficiency of DCs from an extensive margin—a shift from small to large, more efficient DCs. Improvements from the intensive margin, that is, from more efficient operation, would be critical in limiting the energy consumption and environmental impact of DCs in the upcoming period. Machine learning algorithms have advantages in optimizing the operation of DCs to improve energy efficiency as they have shown the potential of discovering control strategies not found by traditional method, and producing working condition‐dependent control strategies. This study proposes ready‐to‐use machine learning methods with practical details to decrease the most commonly used energy efficiency metric—power usage effectiveness in DCs. We achieved an accurate prediction by properly selecting the features used in the proposed prediction models established by neural network, light gradient boosting machine, recurrent neural network, and random forests. The proposed approaches are implemented in one of the largest hyperscale DCs in China—Tencent Tianjin DC, to optimize the set points of controllable variables in the cooling system and to detect and adjust the unreasonable working conditions in the modular data centers. The lower bound of PUE reduction was 0.005 with the proposed approaches, leading to about 1500 MWh (0.24% of the total designed electricity consumption of this DC) of energy saved per year in this hyperscale DC. The proposed methods have the potential to be transferred to DCs of similar scale, and the framework of our work could serve as a guide for machine learning‐based optimization of environmental indicators in other complex product/service systems. [ABSTRACT FROM AUTHOR]

Rainfall prediction is of vital importance in water resources management. Accurate long‐term rainfall prediction remains an open and challenging problem. Machine learning techniques, as an increasingly popular approach, provide an attractive alternative to traditional methods. The main objective of this study was to improve the prediction accuracy of machine learning‐based methods for monthly rainfall, and to improve the understanding of the role of large‐scale climatic variables and local meteorological variables in rainfall prediction. One regression model autoregressive integrated moving average model (ARIMA) and five state‐of‐the‐art machine learning algorithms, including artificial neural networks, support vector machine, random forest (RF), gradient boosting regression, and dual‐stage attention‐based recurrent neural network, were implemented for monthly rainfall prediction over 25 stations in the East China region. The results showed that the ML models outperformed ARIMA model, and RF relatively outperformed other models. Local meteorological variables, humidity, and sunshine duration, were the most important predictors in improving prediction accuracy. 4‐month lagged Western North Pacific Monsoon had higher importance than other large‐scale climatic variables. The overall output of rainfall prediction was scalable and could be readily generalized to other regions. [ABSTRACT FROM AUTHOR]

The hydrological model is one of the key methods in hydrological research and management, which can be divided into physical model and mathematical model. In order to explore the applicability of different models in hydrological simulation, the physical model Hydrologic Simulation Program‐FORTRAN (HSPF), the mathematical models Autoregressive Integrated Moving Average (ARIMA) and Back Propagation Neural Network (BPNN) are built to simulate the hydrological process of Sanya River, China. First, the result shows that all three models have good performance, but the HSPF model has the best performance followed by the ARIMA and the BPNN model with the lowest performance. Next, the effect of time step on the performance of the BPNN and ARIMA models is obviously greater than for the HSPF model. Finally, the applicability of various models is discussed by combining the modeling process and data requirements of the model, and the applicability of the mathematical model in the hydrological simulation of watersheds with insufficient data is confirmed. [ABSTRACT FROM AUTHOR]

The reliability of long‐term precipitation estimates is vital for climatology and hydrometeorology applications. Different climatic zones and high rain gauge network (more than 800) of China are a suitable topography for performance evaluation of different long‐term precipitation datasets. In this study, seven long‐term precipitation datasets are tested against in situ observations at different time scales (1981–2016) at 813 grid points. Well‐known statistical indicators and Fast‐frugal tree (FFt) decision model are employed to identify the best long‐term datasets. Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks Climate Data Record is the only datasets that did not perform well in the study area. Asian Precipitation‐Highly‐Resolved Observational Data Integration Towards Evaluation (APHRODITE), Global Precipitation Climatology Centre (GPCC), and Climate Prediction Center (CPC‐Global) estimates are comparable with in situ observations. Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), National Centers for Environmental Prediction (NCEP2) overestimate the precipitation extremes in the region. There exists a difference of 100–250 mm among precipitation datasets at an annual scale. All of the seven long‐term datasets underestimate the rxdays across China. The minimum range of rxdays (maximum precipitation amount in under defined days: 1 day or 5 days) captured by datasets is comparable except PERSIANN‐CDR. The maximum range calculated with PERSIANN‐CDR is 55.01 (rx1day), and 129.67 (rx5day), much less than the in situ rxdays. This analysis shows that datasets failed to capture maximum precipitation intensity in the region as well. FFt decision model results show that APHRODITE ranked first based on calculated consecutive dry days among all six other datasets in the most climatic zones. Overall, results indicate that data assimilation, the spatial coverage of ground stations, and interpolation techniques used to develop the datasets may limit the reliability of precipitation datasets in the study area. [ABSTRACT FROM AUTHOR]

Multi‐source remote sensing precipitation products are being used more and more frequently for rainfall analysis and hydrological applications around the world. The aim of the present study was to assess the variances and uncertainty of long‐term precipitation and corresponding hydrological simulations from 1984 to 2016 using rain gauge measurements, two satellite rainfall products retrieved from the Climate Prediction Center (CPC) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks – Climate Data Record (PERSIANN‐CDR) respectively, along with rainfall reanalysis data from the ERA‐Interim over the lower Yangtze River basin, China. The results indicated overestimation from ERA‐Interim and PERSIANN‐CDR on seasonal rainfall. CPC rainfall estimation had marginal bias with rain gauge measurements among all the remote sensing rainfall products on a daily scale, while the ERA‐Interim tended to overestimate when the rainfall rate was less than 50 mm. On a monthly scale, CPC rainfall estimations were very close to the rain gauge measurements, with a correlation coefficient of 0.96, whilst the ERA‐Interim rainfall products showed significant overestimation in February, March and September. Nevertheless, all remote sensing rainfall products achieved good performance in June and July, showing promising potential to be an alternative to rainfall data for long‐term water resource analysis. Furthermore, ERA‐Interim rainfall products did not perform as well as the other rainfall sources in flow simulations, as evidenced by the large root‐mean‐square error and bias. CPC rainfall products outperformed all other rainfall sources in terms of the Nash–Sutcliffe coefficient at all temporal scales. In addition, the skill scores suggested that the performance of the streamflow simulation improved significantly on a monthly scale, with a higher Nash–Sutcliffe coefficient and smaller total streamflow errors. [ABSTRACT FROM AUTHOR]

An increasing number of terrestrial‐ and space‐based radio‐communication systems are influenced by the ionospheric space weather, making the ionospheric state increasingly important to forecast. In this study, a novel extended encoder‐decoder long short‐term memory extended (ED‐LSTME) neural network, which can predict ionospheric total electron content (TEC) is proposed. Useful inherent features were automatically extracted from the historical TEC by LSTM layers, and the performance of the proposed model was enhanced by considering solar flux and geomagnetic activity data. The proposed ED‐LSTME model was validated using 15‐min TEC values from GPS measurements over one solar cycle (from January 2006 to July 2018) collected at 15 GPS stations in China. Different assessment experiments were conducted in different geographical locations and seasons as well as under varying geomagnetic activities, to comprehensively evaluate the model's performance. These comparative experiments were conducted using an ED‐LSTM, a traditional LSTM, a deep neural network, autoregressive integrated moving average, and the 2016 International Reference Ionosphere models. The results indicated that the ED‐LSTME model is superior to the other statistical models, with R2 and root mean square error values of 0.89 and 12.09 TECU, respectively. In addition, TEC was adequately predicted under different ionospheric conditions, and satisfactory results were obtained even under geomagnetically disturbed conditions. These results suggest that the prediction performance could be significantly improved by utilizing auxiliary data. These observations confirm that the proposed model outperforms several state‐of‐the‐art models in making predictions at different times and under diverse conditions. Key Points: A novel extended encoder‐decoder long short‐term memory neural network (ED‐LSTME) for ionospheric total electron content (TEC) forecasting over China is developedED‐LSTME shows a strong capability in improving TEC forecasting at different geographical locations, seasons, and geomagnetic conditionsED‐LSTME is robust and outperforms all the six selected baselines when comparing with the models in terms of their performance [ABSTRACT FROM AUTHOR]

Background: Psoriasis is a chronic inflammatory skin disease, which holds a high incidence in China. However, professional dermatologists who can diagnose psoriasis early and correctly are insufficient in China, especially in the rural areas. A smart approach to identify psoriasis by pictures would be highly adaptable countrywide and could play a useful role in early diagnosis and regular treatment of psoriasis. Objectives: Design and evaluation of a smart psoriasis identification system based on clinical images (without relying on a dermatoscope) that works effectively similar to a dermatologist. Methods: A set of deep learning models using convolutional neural networks (CNNs) was explored and compared in the system for automatic identification of psoriasis. The work was carried out on a standardized dermatological dataset with 8021 clinical images of 9 common disorders including psoriasis along with full electronic medical records of patients built over the last 9 years in China. A two‐stage deep neural network was designed and developed to identify psoriasis. In the first stage, a multilabel classifier was trained to learn the visual patterns for each individual skin disease. In the second stage, the output of the first stage was utilized to distinguish psoriasis from other skin diseases. Results: The area under the curve (AUC) of the two‐stage model reached 0.981 ± 0.015, which outperforms a single‐stage model. And, the classifier showed superior performance (missed diagnosis rate: 0.03, misdiagnosis rate: 0.04) than 25 Chinese dermatologists (missed diagnosis rate: 0.19, misdiagnosis rate: 0.10) in the diagnosis of psoriasis on 100 clinical images. Conclusions: Using clinical images to identify psoriasis is feasible and effective based on CNNs, which also builds a solid technical base for smart care of skin diseases especially psoriasis using mobile/tablet applications for teledermatology in China. [ABSTRACT FROM AUTHOR]

Detecting and measuring the damage on historic glazed tiles plays an important role in the maintenance and protection of historic buildings. However, the current visual inspection method for identifying and assessing superficial damage on historic buildings is time and labor intensive. In this article, a novel two‐level object detection, segmentation, and measurement strategy for large‐scale structures based on a deep‐learning technique is proposed. The data in this study are from the roof images of the Palace Museum in China. The first level of the model, which is based on the Faster region‐based convolutional neural network (Faster R‐CNN), automatically detects and crops two types of glazed tile photographs from 100 roof images (2,488 × 3,264 pixels). The average precision values (AP) for roll roofing and pan tiles are 0.910 and 0.890, respectively. The cropped images are used to form a dataset for training a Mask R‐CNN model. The second level of the model, which is based on Mask R‐CNN, automatically segments and measures the damage based on the cropped historic tile images; the AP for the damage segmentation is 0.975. Based on Mask R‐CNN, the predicted pixel‐level damage segmentation result is used to quantitatively measure the morphological features of the damage, such as the damage topology, area, and ratio. To verify the performance of the proposed method, a comparative study was conducted with Mask R‐CNN and a fully convolutional network. This is the first attempt at employing a two‐level strategy to automatically detect, segment, and measure large‐scale superficial damage on historic buildings based on deep learning, and it achieved good results. [ABSTRACT FROM AUTHOR]

With continued increasing construction of both electrified facilities and buried high‐strength pipelines in China, stray current corrosion defects have become an nonignorable threat for these pipelines. A comprehensive investigation on a new failure pressure prediction model for high‐strength pipes with stray current corrosion defects was conducted in this study. The mechanism of stray current corrosion in steel pipes was firstly elaborated in brief. After that, a parameterized finite element model for stress analysis of pipes with external corrosion defects was programmed by APDL code developed by general software ANSYS. By comparing numerical results with full‐scale experimental results, both the numerical model and the failure criteria for pipe burst were proven to be reasonable. Based on the finite element model, parametric analysis was performed using a calculation matrix set by orthogonal testing method to investigate the effects of three main dimensionless factors, that is, ratio of pipe diameter to wall thickness, nondimensional corrosion defect length, and nondimensional corrosion defect depth on pipe's failure pressure. Utilizing the parametric analysis results as database, a multilayer feed‐forward artificial neural network (ANN) was developed for failure pressure prediction. By comparison with experimental burst test results and results of previous failure pressure estimation model, the ANN model results were proven to have both high accuracy and efficiency, which could be referenced in residual strength or safety assessment of high‐strength pipes with corrosion defects. [ABSTRACT FROM AUTHOR]

At the mean annual scale, water availability of a basin is substantially determined by how much precipitation will be partitioned into evapotranspiration and run‐off. The Budyko framework provides a simple but efficient tool to estimate precipitation partitioning at the basin scale. As one form of the Budyko framework, Fu's equation has been widely used to model long‐term basin‐scale water balance. The major difficulty in applications of Fu's equation is determining how to estimate the curve shape parameter ω efficiently. Previous studies have suggested that the parameter ω is closely related to the long‐term vegetation coverage on large river basins globally. However, on small basins, the parameter ω is difficult to estimate due to the diversity of controlling factors. Here, we focused on the estimation of ω for small basins in China. We identified the major factors controlling the basin‐specific (calibrated) ω from nine catchment attributes based on a dataset from 206 small basins (≤50,000 km2) across China. Next, we related the calibrated ω to the major factors controlling ω using two statistical models, that is, the multiple linear regression (MLR) model and artificial neural network (ANN) model. We compared and validated the two statistical models using an independent dataset of 80 small basins. The results indicated that in addition to vegetation, other landscape factors (e.g., topography and human activity) need to be considered to capture the variability of ω on small basins better. Contrary to previous findings reached on large basins worldwide, the basin‐specific ω and remote sensing‐based vegetation greenness index exhibit a significant negative correlation. Compared with the default ω value of 2.6 used in the Budyko curve method, the two statistical models significantly improved the mean annual ET simulations on validation basins by reducing the root mean square error from 114 mm/year to 74.5 mm/year for the MLR model and 70 mm/year for the ANN model. In comparison, the ANN model can provide a better ω estimation than the MLR model. [ABSTRACT FROM AUTHOR]

The article discusses a research which investigates the application of BP Neural Network Model in fracturing productivity prediction of Fuyu tight oil reservoir in the horizontal well development area in northern Honggang, Jilin Oilfield in China. Details about the proposed neural network prediction method that is based on horizontal well classification are noted. Also discussed is the complexity of the geological conditions of tight reservoir.

ABSTRACT: A new satellite‐based precipitation data set, Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks‐Climate Data Record (PERSIANN‐CDR), with long‐term time series dating back to 1983, can be one valuable data set for climate studies. This study investigates the feasibility of using PERSIANN‐CDR as a reference data set for climate studies. Sixteen Coupled Model Intercomparison Projection Phase 5 (CMIP5) models are evaluated over the Xiang River basin, southern China, by comparing their performance on precipitation projection and streamflow simulation, particularly on extreme precipitation and streamflow events. The results show PERSIANN‐CDR is a valuable data set for climate studies, even on extreme precipitation events. The precipitation estimates and their extreme events from CMIP5 models are improved significantly compared with rain gauge observations after bias correction by the PERSIANN‐CDR precipitation estimates. Given streamflows simulated with raw and bias‐corrected precipitation estimates from 16 CMIP5 models, 10 out of 16 are improved after bias correction. The impact of bias correction on extreme events for streamflow simulations are unstable, with 8 out of 16 models can be clearly claimed they are improved after the bias correction. Concerning the performance of raw CMIP5 models on precipitation, IPSL‐CM5A‐MR excels the other CMIP5 models, while MRI‐CGCM3 outperforms on extreme events with its better performance on six extreme precipitation metrics. Case studies also show that raw CCSM4, CESM1‐CAM5, and MRI‐CGCM3 outperform other models on streamflow simulation, while MIROC5‐ESM‐CHEM, MIROC5‐ESM, and IPSL‐CM5A‐MR behave better than the other models after bias correction. [ABSTRACT FROM AUTHOR]

There is a need for more detailed spatial information on soil organic carbon (SOC) for the accurate estimation of SOC stock and earth system models. As it is effective to use environmental factors as auxiliary variables to improve the prediction accuracy of spatially distributed modeling, a combined method (HASM_EF) was developed to predict the spatial pattern of SOC across China using high accuracy surface modeling (HASM), artificial neural network (ANN), and principal component analysis (PCA) to introduce land uses, soil types, climatic factors, topographic attributes, and vegetation cover as predictors. The performance of HASM_EF was compared with ordinary kriging (OK), OK, and HASM combined, respectively, with land uses and soil types (OK_LS and HASM_LS), and regression kriging combined with land uses and soil types (RK_LS). Results showed that HASM_EF obtained the lowest prediction errors and the ratio of performance to deviation (RPD) presented the relative improvements of 89.91%, 63.77%, 55.86%, and 42.14%, respectively, compared to the other four methods. Furthermore, HASM_EF generated more details and more realistic spatial information on SOC. The improved performance of HASM_EF can be attributed to the introduction of more environmental factors, to explicit consideration of the multicollinearity of selected factors and the spatial nonstationarity and nonlinearity of relationships between SOC and selected factors, and to the performance of HASM and ANN. This method may play a useful tool in providing more precise spatial information on soil parameters for global modeling across large areas. [ABSTRACT FROM AUTHOR]

Agricultural, environmental and ecological modeling requires soil cation exchange capacity (CEC) that is difficult to measure. Pedotransfer functions (PTFs) are thus routinely applied to predict CEC from easily measured physicochemical properties ( e.g., texture, soil organic matter, pH). This study developed the support vector machines (SVM)-based PTFs to predict soil CEC based on 208 soil samples collected from A and B horizons in Qingdao City, Shandong Province, China. The database was randomly split into calibration and validation datasets in proportions of 3:1 using the bootstrap method. The optimal SVM parameters were searched by applying the genetic algorithm (GA). The performance of SVM models was compared to those of multiple stepwise regression (MSR) and artificial neural network (ANN) models. Results show that the accuracy of CEC predicted by SVM improves considerably over those predicted by MSR and ANN. The performance of SVM for B horizon ( R2 = 0.85) is slightly better than that for A horizon ( R2 = 0.81). The SVM is a powerful approach in the simulation of nonlinear relationship between CEC and physicochemical properties of widely distributed samples from different soil horizons. Sensitivity analysis was also conducted to explore the influence of each input parameter on the CEC predictions by SVM. The clay content is the most sensitive parameter, followed by soil organic matter and pH, while sand content has the weakest influence. This suggests that clay is the most important predictor for predicting CEC of both soil horizons. [ABSTRACT FROM AUTHOR]

Mappings of the stimuli effects and the input and output estimates of artificial neural networks (ANN) are obtained via combinations of nonlinear functions. This approach offers the advantages of self-learning, self-organization, self-adaptation, and fault tolerance as well as the potential for use in flood forecasting applications. Furthermore, the ANN technology allows the use of multiple variables in both the input and output layers. This capability is very important for flood calculation because the stage, discharge, and other hydrological variables often are functions of many influential variables. Herein, we propose a flood forecasting system with related application, based on ANN. This method offers better performance and efficiency. [ABSTRACT FROM AUTHOR]

Wheat is one of the most consumed grains in the world. The identification of wheat based on surface characteristics is important for the market. This study is aimed at identifying unsound kernels (Triticum durum Desf), including 710 black germ kernels, 627 broken kernels and 1169 sound kernels from several seed distributors in China. The system is mainly composed of a liner charge-coupled device for image capture and a software package for extracting various morphological, colour and texture features. The models built by partial least squares discriminate analysis, support vector machine discrimination analysis (SVMDA) and principal component analysis-artificial neural networks for identifying the unsound kernels have been explored. After comparisons of these three methods, it has been found that SVMDA got the best accuracy: 95.1%, 96.0% and 98.3% (black germ kernels, broken kernels and sound kernels). Obviously, the experimental results have shown that SVMDA is the most feasible and effective choice for the identification. [ABSTRACT FROM AUTHOR]

The article discusses the study which aims to analyze the necessity and complexity of neural networks (NN) classification in obtaining mangrove landscape characteristics for monitoring the travel environment quality on the Beihai Coast of Guangxi, China. It notes that the network includes distribution of information storage and data handling. Results indicated that the bigger the output layer network, the greater the learning ability will be acquired.

The article focuses on the findings from a study that explored the use of artificial neural networks (ANN) model in estimating reference evapotranspiration (ET), an essential component of the hydrologic cycle and irrigation water requirements estimation, based on climatic factors as applied in some areas of the Inner Monglia region of China. ANN model was tested and trained for arid, semi-arid and sub-humid areas. The climatic elements considered in the study include air temperature (T), relative humidity (RH) and wind velocity (U). The implication of the results is also discussed.

The article presents a study on the prediction of Young's modulus, and shear modulus for the accurate assessment of elastic properties of coal rocks in Qinshui Basin, China using artificial neural networks. The use of traditional methods to obtain the compressive strength and elastic modulus is tackled. The applicability of artificial neural network to predict the Young's Modulus is also revealed.

This article discusses a simulation model for the spring discharges of karst aquifers in semiarid regions in China using an artificial neural network. According to the authors, spring discharges reflect the variability of ground water storage and the fluctuation of ground water levels in the basins. They treated the karst spring aquifer as a non-linear input and output system and simulated the effects of precipitation on karst spring flow at the Niangziguan Springs in east Shanxi Province. They concluded that the artificial neural network model performed better than the time-lag linear model.

In real‐world wetland vegetation morphology (WVM) detection, large scene variations such as those due to landform, vegetation, sunlight, weather, and sky, as well as camera parameter settings such as focal length and shooting angle, require systematic and complicated artificial intelligence technology to accurately discriminate inter and intra‐class wetland objections. To deal with these challenges, we introduced a deep‐level discriminative model based on convolutional neural networks (CNN) for classifying the images of DongZhai Harbor intertidal, Lashi Lake alpine, Yancheng coastal and Zoige plateau wetlands in China. A 96‐dimensional convolution operation with kernel sizes of 11×11×3 first applied to the resized 227×227 WVM input pictures to acquire the effective morphologic features. The perceptron layers of the rectified linear unit and the batch normalization were used in the middle layer to achieve the better gradient propagation property during the training process. The WVM features were down‐sampled by the pooling networks to reduce the neuron dimensions. The fully connected layer linked to the output of the convolutional and pooling layers to obtain the high‐level WVM species information for the final WVM classification purpose. The deep‐level CNN‐based method was compared with the traditional shallow‐level feature‐designed algorithms of conditional maximum entropy regression, multilayer perceptron and support vector machine. The deep‐level algorithm showed the superior performance for detecting the WVM species, which provided a superior alternative routine for accurate artificial intelligence classification of WVM in the ecological engineering application. Recommendations for Resource ManagersThis proposed artificial intelligence model can be used to effectively help people understand the macroscopic scene changes of ecological elements from the wetland vegetation morphology images.The detection results show the robustness of the discriminative model, for it is not affected by the complex natural factors such as landform, vegetation, sunlight, weather, and sky, as well as human factors such as camera parameter settings of focal length and shooting angle to some extent.The deep‐level model based on the cascade convolution framework can be used to extract more distinguishing detailed ecological features from the original wetland vegetation morphology images compared with the shallow‐level algorithms using a single convolutional layer. [ABSTRACT FROM AUTHOR]