Machine learning(ML)and data mining are used in various fields such as data analysis,prediction,image processing and especially in healthcare.Researchers in the past decade have focused on applying ML and data mining ...Machine learning(ML)and data mining are used in various fields such as data analysis,prediction,image processing and especially in healthcare.Researchers in the past decade have focused on applying ML and data mining to generate conclusions from historical data in order to improve healthcare systems by making predictions about the results.Using ML algorithms,researchers have developed applications for decision support,analyzed clinical aspects,extracted informative information from historical data,predicted the outcomes and categorized diseases which help physicians make better decisions.It is observed that there is a huge difference between women depending on the region and their social lives.Due to these differences,scholars have been encouraged to conduct studies at a local level in order to better understand those factors that affect maternal health and the expected child.In this study,the ensemble modeling technique is applied to classify birth outcomes based on either cesarean section(C-Section)or normal delivery.A voting ensemble model for the classification of a birth dataset was made by using a Random Forest(RF),Gradient Boosting Classifier,Extra Trees Classifier and Bagging Classifier as base learners.It is observed that the voting ensemble modal of proposed classifiers provides the best accuracy,i.e.,94.78%,as compared to the individual classifiers.ML algorithms are more accurate due to ensemble models,which reduce variance and classification errors.It is reported that when a suitable classification model has been developed for birth classification,decision support systems can be created to enable clinicians to gain in-depth insights into the patterns in the datasets.Developing such a system will not only allow health organizations to improve maternal health assessment processes,but also open doors for interdisciplinary research in two different fields in the region.展开更多
Predictive analytics have been widely used in the literature with respect to laparoscopic surgery and risk stratification.However,most predictive analytics in this field exploit generalized linearmodels for predictive...Predictive analytics have been widely used in the literature with respect to laparoscopic surgery and risk stratification.However,most predictive analytics in this field exploit generalized linearmodels for predictive purposes,which are limited by model assumptionsdincluding linearity between response variables and additive interactions between variables.In many instances,such assumptions may not hold true,and the complex relationship between predictors and response variables is usually unknown.To address this limitation,machine-learning algorithms can be employed to model the underlying data.The advantage of machine learning algorithms is that they usually do not require strict assumptions regarding data structure,and they are able to learn complex functional forms using a nonparametric approach.Furthermore,two or more machine learning algorithms can be synthesized to further improve predictive accuracy.Such a process is referred to as ensemble modeling,and it has been used broadly in various industries.However,this approach has not been widely reported in the laparoscopic surgical literature due to its complexity in both model training and interpretation.With this technical note,we provide a comprehensive overview of the ensemble-modeling technique and a step-by-step tutorial on how to implement ensemble modeling.展开更多
Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model ...Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.展开更多
This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble lear...This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.展开更多
Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,re...Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.展开更多
With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration predict...With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.展开更多
Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological...Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological fractions of heavy metals and metalloids(HMMs)in TMWs is key to evaluating their leaching potential into the environment;however,traditional experiments are time-consuming and labor-intensive.In this study,10 machine learning(ML)algorithms were used and compared for rapidly predicting the morphological fractions of HMMs in TMWs.A dataset comprising 2376 data points was used,with mineral composition,elemental properties,and total concentration used as inputs and concentration of morphological fraction used as output.After grid search optimization,the extra tree model performed the best,achieving coefficient of determination(R2)of 0.946 and 0.942 on the validation and test sets,respectively.Electronegativity was found to have the greatest impact on the morphological fraction.The models’performance was enhanced by applying an ensemble method to the top three optimal ML models,including gradient boosting decision tree,extra trees and categorical boosting.Overall,the proposed framework can accurately predict the concentrations of different morphological fractions of HMMs in TMWs.This approach can minimize detection time,aid in the safe management and recovery of TMWs.展开更多
Real-time and reliable measurements of the effluent quality are essential to improve operating efficiency and reduce energy consumption for the wastewater treatment process.Due to the low accuracy and unstable perform...Real-time and reliable measurements of the effluent quality are essential to improve operating efficiency and reduce energy consumption for the wastewater treatment process.Due to the low accuracy and unstable performance of the traditional effluent quality measurements,we propose a selective ensemble extreme learning machine modeling method to enhance the effluent quality predictions.Extreme learning machine algorithm is inserted into a selective ensemble frame as the component model since it runs much faster and provides better generalization performance than other popular learning algorithms.Ensemble extreme learning machine models overcome variations in different trials of simulations for single model.Selective ensemble based on genetic algorithm is used to further exclude some bad components from all the available ensembles in order to reduce the computation complexity and improve the generalization performance.The proposed method is verified with the data from an industrial wastewater treatment plant,located in Shenyang,China.Experimental results show that the proposed method has relatively stronger generalization and higher accuracy than partial least square,neural network partial least square,single extreme learning machine and ensemble extreme learning machine model.展开更多
Stomatopods are better known as mantis shrimp with considerable ecological importance in wide coastal waters globally. Some stomatopod species are exploited commercially, including Oratosquilla oratoria in the Northwe...Stomatopods are better known as mantis shrimp with considerable ecological importance in wide coastal waters globally. Some stomatopod species are exploited commercially, including Oratosquilla oratoria in the Northwest Pacific. Yet, few studies have published to promote accurate habitat identification of stomatopods, obstructing scientific management and conservation of these valuable organisms. This study provides an ensemble modeling framework for habitat suitability modeling of stomatopods, utilizing the O. oratoria stock in the Bohai Sea as an example. Two modeling techniques(i.e., generalized additive model(GAM) and geographical weighted regression(GWR)) were applied to select environmental predictors(especially the selection between two types of sediment metrics) that better characterize O. oratoria distribution and build separate habitat suitability models(HSM). The performance of the individual HSMs were compared on interpolation accuracy and transferability.Then, they were integrated to check whether the ensemble model outperforms either individual model, according to fishers’ knowledge and scientific survey data. As a result, grain-size metrics of sediment outperformed sediment content metrics in modeling O. oratoria habitat, possibly because grain-size metrics not only reflect the effect of substrates on burrow development, but also link to sediment heat capacity which influences individual thermoregulation. Moreover, the GWR-based HSM outperformed the GAM-based HSM in interpolation accuracy,while the latter one displayed better transferability. On balance, the ensemble HSM appeared to improve the predictive performance overall, as it could avoid dependence on a single model type and successfully identified fisher-recognized and survey-indicated suitable habitats in either sparsely sampled or well investigated areas.展开更多
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
To enhance the efficiency of vaccine manufacturing,this study focuses on optimizing the microfluidic conditions and lipid mix ratios of messenger RNA-lipid nanoparticles(mRNA-LNP).Different mRNA-LNP formulations(n=24)...To enhance the efficiency of vaccine manufacturing,this study focuses on optimizing the microfluidic conditions and lipid mix ratios of messenger RNA-lipid nanoparticles(mRNA-LNP).Different mRNA-LNP formulations(n=24)were developed using an I-optimal design,where machine learning tools(XGBoost/Bayesian optimization and self-validated ensemble(SVEM))were used to optimize the process and predict lipid mix ratio.The investigation included material attributes,their respective ratios,and process attributes.The critical responses like particle size(PS),polydispersity index(PDI),Zeta potential,pKa,heat trend cycle,encapsulation efficiency(EE),recovery ratio,and encapsulated mRNA were evaluated.Overall prediction of SVEM(>97%)was comparably better than that of XGBoost/Bayesian optimization(>94%).Moreover,in actual experimental outcomes,SVEM prediction is close to the actual data as confirmed by the experimental PS(94-96 nm)is close to the predicted one(95-97 nm).The other parameters including PDI and EE were also close to the actual experimental data.展开更多
Landslides pose a significant threat to both human society and environmental sustainability,yet,their spatiotemporal evolution and impacts on global scales in the context of a warming climate remain poorly understood....Landslides pose a significant threat to both human society and environmental sustainability,yet,their spatiotemporal evolution and impacts on global scales in the context of a warming climate remain poorly understood.In this study,we projected global landslide susceptibility under four shared socioeconomic pathways(SSPs)from 2021 to 2100,utilizing multiple machine learning models based on precipitation data from the Coupled Model Intercomparison Project Phase 6(CMIP6)Global Climate Models(GCMs)and static metrics.Our results indicate an overall upward trend in global landslide susceptibility under the SSPs compared to the baseline period(2001–2020),with the most significant increase of about 1%in the very far future(2081–2100)under the high emissions scenario(SSP5-8.5).Currently,approximately 13%of the world’s land area is at very high risk of landslide,mainly in the Cordillera of the Americas and the Andes in South America,the Alps in Europe,the Ethiopian Highlands in Africa,the Himalayas in Asia,and the countries of East and South-East Asia.Notably,India is the country most adversely affected by climate change,particularly during 2081–2100 under SSP3-7.0,with approximately 590 million people—23 times the global average—living in areas categorized as having very high susceptibility.展开更多
Landslide is a serious natural disaster next only to earthquake and flood,which will cause a great threat to people’s lives and property safety.The traditional research of landslide disaster based on experience-drive...Landslide is a serious natural disaster next only to earthquake and flood,which will cause a great threat to people’s lives and property safety.The traditional research of landslide disaster based on experience-driven or statistical model and its assessment results are subjective,difficult to quantify,and no pertinence.As a new research method for landslide susceptibility assessment,machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models.Taking Western Henan for example,the study selected 16 landslide influencing factors such as topography,geological environment,hydrological conditions,and human activities,and 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination(RFE)method.Five machine learning methods[Support Vector Machines(SVM),Logistic Regression(LR),Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Linear Discriminant Analysis(LDA)]were used to construct the spatial distribution model of landslide susceptibility.The models were evaluated by the receiver operating characteristic curve and statistical index.After analysis and comparison,the XGBoost model(AUC 0.8759)performed the best and was suitable for dealing with regression problems.The model had a high adaptability to landslide data.According to the landslide susceptibility map of the five models,the overall distribution can be observed.The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest,the Xiaoshan Mountain range in the west,and the Yellow River Basin in the north.These areas have large terrain fluctuations,complicated geological structural environments and frequent human engineering activities.The extremely high and highly prone areas were 12043.3 km^(2)and 3087.45 km^(2),accounting for 47.61%and 12.20%of the total area of the study area,respectively.Our study reflects the distribution of landslide susceptibility in western Henan Province,which provides a scientific basis for regional disaster warning,prediction,and resource protection.The study has important practical significance for subsequent landslide disaster management.展开更多
As global warming persistently alters and rapidly reshapes landscapes and habitats, conventional species distribution models relying solely on maintaining static conditions within the current climate are likely to fal...As global warming persistently alters and rapidly reshapes landscapes and habitats, conventional species distribution models relying solely on maintaining static conditions within the current climate are likely to falter, particularly at the genus level. Hence, we hypothesize that climate change will differentially affect ecological niches of the same genus species with various latitudinal positioning and local topography, and the high-latitude species may experience greater niche contraction than low-latitude species, and that mountainous regions with high elevational variability may serve as critical climate refugia. Herein, we simulate niche alterations and integrate an ensemble model(EM) strategy, taking into account species dispersal limitations factors(topography, soil, and ultraviolet), to construct a comprehensive habitat suitability(CHS) model for assessing the future vulnerability of the Betula genus, most of which are timber species in China. Our findings reveal that the niche spatial(geographic distribution) of most species(62%) within the Betula genus will undergo a gradual decline under climate change, supporting our hypothesis of latitudinal differentiation in climate vulnerability. Intriguingly, the projected high-latitude niche reduction within the genus cannot be counterbalanced by the anticipated niche expansion of closely related species in low-latitude regions, even considering the evident latitudinal gradient distribution of species. Nonetheless, the niche spatial of six Betula species in southwestern China remains stable or expands under warming scenarios, strongly supporting our secondary hypothesis about topographic buffering effects, which probably means the unique topography(i.e., the largest elevation difference) of this region may serve as a sanctuary for preserving Betula genetic diversity. Our results underscore the uncertain nature of pre-existing niche systems at the genus level under climate change, emphasizing the need for diligent resource management and conservation planning for vulnerable timber species.展开更多
In order to address the critical security challenges inherent to Wireless Sensor Networks(WSNs),this paper presents a groundbreaking barrier-based machine learning technique.Vital applications like military operations...In order to address the critical security challenges inherent to Wireless Sensor Networks(WSNs),this paper presents a groundbreaking barrier-based machine learning technique.Vital applications like military operations,healthcare monitoring,and environmental surveillance increasingly deploy WSNs,recognizing the critical importance of effective intrusion detection in protecting sensitive data and maintaining operational integrity.The proposed method innovatively partitions the network into logical segments or virtual barriers,allowing for targeted monitoring and data collection that aligns with specific traffic patterns.This approach not only improves the diversit.There are more types of data in the training set,and this method uses more advanced machine learning models,like Convolutional Neural Networks(CNNs)and Long Short-Term Memory(LSTM)networks together,to see coIn our work,we used five different types of machine learning models.These are the forward artificial neural network(ANN),the CNN-LSTM hybrid models,the LR meta-model for linear regression,the Extreme Gradient Boosting(XGB)regression,and the ensemble model.We implemented Random Forest(RF),Gradient Boosting,and XGBoost as baseline models.To train and evaluate the five models,we used four possible features:the size of the circular area,the sensing range,the communication range,and the number of sensors for both Gaussian and uniform sensor distributions.We used Monte Carlo simulations to extract these traits.Based on the comparison,the CNN-LSTM model with Gaussian distribution performs best,with an R-squared value of 99%and Root mean square error(RMSE)of 6.36%,outperforming all the other models.展开更多
Objective: This study investigates the auxiliary role of resting-state electroencephalography (EEG) in the clinical diagnosis of attention-deficit hyperactivity disorder (ADHD) using machine learning techniques. Metho...Objective: This study investigates the auxiliary role of resting-state electroencephalography (EEG) in the clinical diagnosis of attention-deficit hyperactivity disorder (ADHD) using machine learning techniques. Methods: Resting-state EEG recordings were obtained from 57 children, comprising 28 typically developing children and 29 children diagnosed with ADHD. The EEG signal data from both groups were analyzed. To ensure analytical accuracy, artifacts and noise in the EEG signals were removed using the EEGLAB toolbox within the MATLAB environment. Following preprocessing, a comparative analysis was conducted using various ensemble learning algorithms, including AdaBoost, GBM, LightGBM, RF, XGB, and CatBoost. Model performance was systematically evaluated and optimized, validating the superior efficacy of ensemble learning approaches in identifying ADHD. Conclusion: Applying machine learning techniques to extract features from resting-state EEG signals enabled the development of effective ensemble learning models. Differential entropy and energy features across multiple frequency bands proved particularly valuable for these models. This approach significantly enhances the detection rate of ADHD in children, demonstrating high diagnostic efficacy and sensitivity, and providing a promising tool for clinical application.展开更多
In this study,a machine learning-based predictive model was developed for the Musa petti Wind Farm in Sri Lanka to address the need for localized forecasting solutions.Using data on wind speed,air temperature,nacelle ...In this study,a machine learning-based predictive model was developed for the Musa petti Wind Farm in Sri Lanka to address the need for localized forecasting solutions.Using data on wind speed,air temperature,nacelle position,and actual power,lagged features were generated to capture temporal dependencies.Among 24 evaluated models,the ensemble bagging approach achieved the best performance,with R^(2) values of 0.89 at 0 min and 0.75 at 60 min.Shapley Additive exPlanations(SHAP)analysis revealed that while wind speed is the primary driver for short-term predictions,air temperature and nacelle position become more influential at longer forecasting horizons.These findings underscore the reliability of short-term predictions and the potential benefits of integrating hybrid AI and probabilistic models for extended forecasts.Our work contributes a robust and explainable framework to support Sri Lanka’s renewable energy transition,and future research will focus on real-time deployment and uncertainty quantification.展开更多
China’s lowland rural rivers are facing severe eutrophication problems due to excessive phosphorus(P)from anthropogenic activities.However,quantifying P dynamics in a lowland rural river is challenging due to its com...China’s lowland rural rivers are facing severe eutrophication problems due to excessive phosphorus(P)from anthropogenic activities.However,quantifying P dynamics in a lowland rural river is challenging due to its complex interaction with surrounding areas.A P dynamic model(River-P)was specifically designed for lowland rural rivers to address this challenge.This modelwas coupled with the Environmental Fluid Dynamics Code(EFDC)and the Phosphorus Dynamic Model for lowland Polder systems(PDP)to characterize P dynamics under the impact of dredging in a lowland rural river.Based on a two-year(2020-2021)dataset from a representative lowland rural river in the Lake Taihu Basin,China,the coupled model was calibrated and achieved a model performance(R^(2)>0.59,RMSE<0.04 mg/L)for total P(TP)concentrations.Our research in the study river revealed that(1)the time scale for the effectiveness of sediment dredging for P control was~300 days,with an increase in P retention capacity by 74.8 kg/year and a decrease in TP concentrations of 23%after dredging.(2)Dredging significantly reduced P release from sediment by 98%,while increased P resuspension and settling capacities by 16%and 46%,respectively.(3)The sediment-water interface(SWI)plays a critical role in P transfer within the river,as resuspension accounts for 16%of TP imports,and settling accounts for 47%of TP exports.Given the large P retention capacity of lowland rural rivers,drainage ditches and ponds with macrophytes are promising approaches to enhance P retention capacity.Our study provides valuable insights for local environmental departments,allowing a comprehensive understanding of P dynamics in lowland rural rivers.This enable the evaluation of the efficacy of sediment dredging in P control and the implementation of corresponding P control measures.展开更多
To the Editor:We read with interest the article by Wang et al.,titled"Modeling the spread risk of dengue vector Aedes albopictus caused by environmental factors in Shanghai,China"[1].The use of ensemble ecol...To the Editor:We read with interest the article by Wang et al.,titled"Modeling the spread risk of dengue vector Aedes albopictus caused by environmental factors in Shanghai,China"[1].The use of ensemble ecological niche models to map Aedes albopictus distribution in urban Shanghai is both timely and methodologically sound.The identified drivers-vegetation index,temperature,and proximity to water-are well-known contributors to vector proliferation.However,one dimension remains notably underrepresented:human behavioral factors.展开更多
This study examines the performance of coupling the deterministic four-dimensional variational assimilation system （4DVAR） with an ensemble Kalman filter （EnKF） to produce a superior hybrid approach for data assim...This study examines the performance of coupling the deterministic four-dimensional variational assimilation system （4DVAR） with an ensemble Kalman filter （EnKF） to produce a superior hybrid approach for data assimilation. The coupled assimilation scheme （E4DVAR） benefits from using the state-dependent uncertainty provided by EnKF while taking advantage of 4DVAR in preventing filter divergence： the 4DVAR analysis produces posterior maximum likelihood solutions through minimization of a cost function about which the ensemble perturbations are transformed, and the resulting ensemble analysis can be propagated forward both for the next assimilation cycle and as a basis for ensemble forecasting. The feasibility and effectiveness of this coupled approach are demonstrated in an idealized model with simulated observations. It is found that the E4DVAR is capable of outperforming both 4DVAR and the EnKF under both perfect- and imperfect-model scenarios. The performance of the coupled scheme is also less sensitive to either the ensemble size or the assimilation window length than those for standard EnKF or 4DVAR implementations.展开更多
基金Natural Sciences and Engineering Research Council of Canada(NSERC)and New Brunswick Innovation Foundation(NBIF)for the financial support of the global project.These granting agencies did not contribute in the design of the study and collection,analysis,and interpretation of data。
文摘Machine learning(ML)and data mining are used in various fields such as data analysis,prediction,image processing and especially in healthcare.Researchers in the past decade have focused on applying ML and data mining to generate conclusions from historical data in order to improve healthcare systems by making predictions about the results.Using ML algorithms,researchers have developed applications for decision support,analyzed clinical aspects,extracted informative information from historical data,predicted the outcomes and categorized diseases which help physicians make better decisions.It is observed that there is a huge difference between women depending on the region and their social lives.Due to these differences,scholars have been encouraged to conduct studies at a local level in order to better understand those factors that affect maternal health and the expected child.In this study,the ensemble modeling technique is applied to classify birth outcomes based on either cesarean section(C-Section)or normal delivery.A voting ensemble model for the classification of a birth dataset was made by using a Random Forest(RF),Gradient Boosting Classifier,Extra Trees Classifier and Bagging Classifier as base learners.It is observed that the voting ensemble modal of proposed classifiers provides the best accuracy,i.e.,94.78%,as compared to the individual classifiers.ML algorithms are more accurate due to ensemble models,which reduce variance and classification errors.It is reported that when a suitable classification model has been developed for birth classification,decision support systems can be created to enable clinicians to gain in-depth insights into the patterns in the datasets.Developing such a system will not only allow health organizations to improve maternal health assessment processes,but also open doors for interdisciplinary research in two different fields in the region.
基金funding from RUIYI emergency medical research fund(202013)Open Foundation of Artificial Intelligence Key Laboratory of Sichuan Province(2020RYY03)+1 种基金Research project of Health and Family Planning Commission of Sichuan Province(17PJ136)funding from Key Research&Development project of Zhejiang Province(2021C03071).
文摘Predictive analytics have been widely used in the literature with respect to laparoscopic surgery and risk stratification.However,most predictive analytics in this field exploit generalized linearmodels for predictive purposes,which are limited by model assumptionsdincluding linearity between response variables and additive interactions between variables.In many instances,such assumptions may not hold true,and the complex relationship between predictors and response variables is usually unknown.To address this limitation,machine-learning algorithms can be employed to model the underlying data.The advantage of machine learning algorithms is that they usually do not require strict assumptions regarding data structure,and they are able to learn complex functional forms using a nonparametric approach.Furthermore,two or more machine learning algorithms can be synthesized to further improve predictive accuracy.Such a process is referred to as ensemble modeling,and it has been used broadly in various industries.However,this approach has not been widely reported in the laparoscopic surgical literature due to its complexity in both model training and interpretation.With this technical note,we provide a comprehensive overview of the ensemble-modeling technique and a step-by-step tutorial on how to implement ensemble modeling.
基金Supported partially by the Post Doctoral Natural Science Foundation of China(2013M532118,2015T81082)the National Natural Science Foundation of China(61573364,61273177,61503066)+2 种基金the State Key Laboratory of Synthetical Automation for Process Industriesthe National High Technology Research and Development Program of China(2015AA043802)the Scientific Research Fund of Liaoning Provincial Education Department(L2013272)
文摘Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.
基金the University of Transport Technology under the project entitled“Application of Machine Learning Algorithms in Landslide Susceptibility Mapping in Mountainous Areas”with grant number DTTD2022-16.
文摘This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2022R1I1A3063493).
文摘Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.
基金supported by General Scientific Research Funding of the Science and Technology Development Fund(FDCT)in Macao(No.0150/2022/A)the Faculty Research Grants of Macao University of Science and Technology(No.FRG-22-074-FIE).
文摘With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.
基金Project(2024JJ2074) supported by the Natural Science Foundation of Hunan Province,ChinaProject(22376221) supported by the National Natural Science Foundation of ChinaProject(2023QNRC001) supported by the Young Elite Scientists Sponsorship Program by CAST,China。
文摘Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological fractions of heavy metals and metalloids(HMMs)in TMWs is key to evaluating their leaching potential into the environment;however,traditional experiments are time-consuming and labor-intensive.In this study,10 machine learning(ML)algorithms were used and compared for rapidly predicting the morphological fractions of HMMs in TMWs.A dataset comprising 2376 data points was used,with mineral composition,elemental properties,and total concentration used as inputs and concentration of morphological fraction used as output.After grid search optimization,the extra tree model performed the best,achieving coefficient of determination(R2)of 0.946 and 0.942 on the validation and test sets,respectively.Electronegativity was found to have the greatest impact on the morphological fraction.The models’performance was enhanced by applying an ensemble method to the top three optimal ML models,including gradient boosting decision tree,extra trees and categorical boosting.Overall,the proposed framework can accurately predict the concentrations of different morphological fractions of HMMs in TMWs.This approach can minimize detection time,aid in the safe management and recovery of TMWs.
基金supported by National Natural Science Foundation of China (Nos. 61203102 and 60874057)Postdoctoral Science Foundation of China (No. 20100471464)
文摘Real-time and reliable measurements of the effluent quality are essential to improve operating efficiency and reduce energy consumption for the wastewater treatment process.Due to the low accuracy and unstable performance of the traditional effluent quality measurements,we propose a selective ensemble extreme learning machine modeling method to enhance the effluent quality predictions.Extreme learning machine algorithm is inserted into a selective ensemble frame as the component model since it runs much faster and provides better generalization performance than other popular learning algorithms.Ensemble extreme learning machine models overcome variations in different trials of simulations for single model.Selective ensemble based on genetic algorithm is used to further exclude some bad components from all the available ensembles in order to reduce the computation complexity and improve the generalization performance.The proposed method is verified with the data from an industrial wastewater treatment plant,located in Shenyang,China.Experimental results show that the proposed method has relatively stronger generalization and higher accuracy than partial least square,neural network partial least square,single extreme learning machine and ensemble extreme learning machine model.
基金The National Natural Science Foundation of China under contract No.31902375the David and Lucile Packard Foundation+1 种基金the Innovation Team of Fishery Resources and Ecology in the Yellow Sea and Bohai Sea under contract No.2020TD01the Special Funds for Taishan Scholars Project of Shandong Province。
文摘Stomatopods are better known as mantis shrimp with considerable ecological importance in wide coastal waters globally. Some stomatopod species are exploited commercially, including Oratosquilla oratoria in the Northwest Pacific. Yet, few studies have published to promote accurate habitat identification of stomatopods, obstructing scientific management and conservation of these valuable organisms. This study provides an ensemble modeling framework for habitat suitability modeling of stomatopods, utilizing the O. oratoria stock in the Bohai Sea as an example. Two modeling techniques(i.e., generalized additive model(GAM) and geographical weighted regression(GWR)) were applied to select environmental predictors(especially the selection between two types of sediment metrics) that better characterize O. oratoria distribution and build separate habitat suitability models(HSM). The performance of the individual HSMs were compared on interpolation accuracy and transferability.Then, they were integrated to check whether the ensemble model outperforms either individual model, according to fishers’ knowledge and scientific survey data. As a result, grain-size metrics of sediment outperformed sediment content metrics in modeling O. oratoria habitat, possibly because grain-size metrics not only reflect the effect of substrates on burrow development, but also link to sediment heat capacity which influences individual thermoregulation. Moreover, the GWR-based HSM outperformed the GAM-based HSM in interpolation accuracy,while the latter one displayed better transferability. On balance, the ensemble HSM appeared to improve the predictive performance overall, as it could avoid dependence on a single model type and successfully identified fisher-recognized and survey-indicated suitable habitats in either sparsely sampled or well investigated areas.
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
基金supported by the Advance Production of Vaccine Raw Materials(Grant Nos.:20022404 and 20018168)funded by the Ministry of Trade,Industry&Energy(MOTIE,Korea)supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(Grant No.:NRF-2018R1A5A2023127)Dongguk University Research Fund of 2023(Grant No.:S-2023-G0001-00099)。
文摘To enhance the efficiency of vaccine manufacturing,this study focuses on optimizing the microfluidic conditions and lipid mix ratios of messenger RNA-lipid nanoparticles(mRNA-LNP).Different mRNA-LNP formulations(n=24)were developed using an I-optimal design,where machine learning tools(XGBoost/Bayesian optimization and self-validated ensemble(SVEM))were used to optimize the process and predict lipid mix ratio.The investigation included material attributes,their respective ratios,and process attributes.The critical responses like particle size(PS),polydispersity index(PDI),Zeta potential,pKa,heat trend cycle,encapsulation efficiency(EE),recovery ratio,and encapsulated mRNA were evaluated.Overall prediction of SVEM(>97%)was comparably better than that of XGBoost/Bayesian optimization(>94%).Moreover,in actual experimental outcomes,SVEM prediction is close to the actual data as confirmed by the experimental PS(94-96 nm)is close to the predicted one(95-97 nm).The other parameters including PDI and EE were also close to the actual experimental data.
基金supported by the project of National Natural Science Foundation of China(Grant No.42371203 and U21A2032)the project of Sichuan Provincial Science and Technology Department Program Funding(Grant No.2025YFHZ0010)the project of the Science and Technology Program of Aba City(Grant NO.R24YYJSYJ0001).
文摘Landslides pose a significant threat to both human society and environmental sustainability,yet,their spatiotemporal evolution and impacts on global scales in the context of a warming climate remain poorly understood.In this study,we projected global landslide susceptibility under four shared socioeconomic pathways(SSPs)from 2021 to 2100,utilizing multiple machine learning models based on precipitation data from the Coupled Model Intercomparison Project Phase 6(CMIP6)Global Climate Models(GCMs)and static metrics.Our results indicate an overall upward trend in global landslide susceptibility under the SSPs compared to the baseline period(2001–2020),with the most significant increase of about 1%in the very far future(2081–2100)under the high emissions scenario(SSP5-8.5).Currently,approximately 13%of the world’s land area is at very high risk of landslide,mainly in the Cordillera of the Americas and the Andes in South America,the Alps in Europe,the Ethiopian Highlands in Africa,the Himalayas in Asia,and the countries of East and South-East Asia.Notably,India is the country most adversely affected by climate change,particularly during 2081–2100 under SSP3-7.0,with approximately 590 million people—23 times the global average—living in areas categorized as having very high susceptibility.
基金This work was financially supported by National Natural Science Foundation of China(41972262)Hebei Natural Science Foundation for Excellent Young Scholars(D2020504032)+1 种基金Central Plains Science and technology innovation leader Project(214200510030)Key research and development Project of Henan province(221111321500).
文摘Landslide is a serious natural disaster next only to earthquake and flood,which will cause a great threat to people’s lives and property safety.The traditional research of landslide disaster based on experience-driven or statistical model and its assessment results are subjective,difficult to quantify,and no pertinence.As a new research method for landslide susceptibility assessment,machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models.Taking Western Henan for example,the study selected 16 landslide influencing factors such as topography,geological environment,hydrological conditions,and human activities,and 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination(RFE)method.Five machine learning methods[Support Vector Machines(SVM),Logistic Regression(LR),Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Linear Discriminant Analysis(LDA)]were used to construct the spatial distribution model of landslide susceptibility.The models were evaluated by the receiver operating characteristic curve and statistical index.After analysis and comparison,the XGBoost model(AUC 0.8759)performed the best and was suitable for dealing with regression problems.The model had a high adaptability to landslide data.According to the landslide susceptibility map of the five models,the overall distribution can be observed.The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest,the Xiaoshan Mountain range in the west,and the Yellow River Basin in the north.These areas have large terrain fluctuations,complicated geological structural environments and frequent human engineering activities.The extremely high and highly prone areas were 12043.3 km^(2)and 3087.45 km^(2),accounting for 47.61%and 12.20%of the total area of the study area,respectively.Our study reflects the distribution of landslide susceptibility in western Henan Province,which provides a scientific basis for regional disaster warning,prediction,and resource protection.The study has important practical significance for subsequent landslide disaster management.
基金funded by the National Science Foundation for Young Scientists of China(No.32001327)the National Key Research and Development Program of China(No.2021YFD2200304-2).
文摘As global warming persistently alters and rapidly reshapes landscapes and habitats, conventional species distribution models relying solely on maintaining static conditions within the current climate are likely to falter, particularly at the genus level. Hence, we hypothesize that climate change will differentially affect ecological niches of the same genus species with various latitudinal positioning and local topography, and the high-latitude species may experience greater niche contraction than low-latitude species, and that mountainous regions with high elevational variability may serve as critical climate refugia. Herein, we simulate niche alterations and integrate an ensemble model(EM) strategy, taking into account species dispersal limitations factors(topography, soil, and ultraviolet), to construct a comprehensive habitat suitability(CHS) model for assessing the future vulnerability of the Betula genus, most of which are timber species in China. Our findings reveal that the niche spatial(geographic distribution) of most species(62%) within the Betula genus will undergo a gradual decline under climate change, supporting our hypothesis of latitudinal differentiation in climate vulnerability. Intriguingly, the projected high-latitude niche reduction within the genus cannot be counterbalanced by the anticipated niche expansion of closely related species in low-latitude regions, even considering the evident latitudinal gradient distribution of species. Nonetheless, the niche spatial of six Betula species in southwestern China remains stable or expands under warming scenarios, strongly supporting our secondary hypothesis about topographic buffering effects, which probably means the unique topography(i.e., the largest elevation difference) of this region may serve as a sanctuary for preserving Betula genetic diversity. Our results underscore the uncertain nature of pre-existing niche systems at the genus level under climate change, emphasizing the need for diligent resource management and conservation planning for vulnerable timber species.
文摘In order to address the critical security challenges inherent to Wireless Sensor Networks(WSNs),this paper presents a groundbreaking barrier-based machine learning technique.Vital applications like military operations,healthcare monitoring,and environmental surveillance increasingly deploy WSNs,recognizing the critical importance of effective intrusion detection in protecting sensitive data and maintaining operational integrity.The proposed method innovatively partitions the network into logical segments or virtual barriers,allowing for targeted monitoring and data collection that aligns with specific traffic patterns.This approach not only improves the diversit.There are more types of data in the training set,and this method uses more advanced machine learning models,like Convolutional Neural Networks(CNNs)and Long Short-Term Memory(LSTM)networks together,to see coIn our work,we used five different types of machine learning models.These are the forward artificial neural network(ANN),the CNN-LSTM hybrid models,the LR meta-model for linear regression,the Extreme Gradient Boosting(XGB)regression,and the ensemble model.We implemented Random Forest(RF),Gradient Boosting,and XGBoost as baseline models.To train and evaluate the five models,we used four possible features:the size of the circular area,the sensing range,the communication range,and the number of sensors for both Gaussian and uniform sensor distributions.We used Monte Carlo simulations to extract these traits.Based on the comparison,the CNN-LSTM model with Gaussian distribution performs best,with an R-squared value of 99%and Root mean square error(RMSE)of 6.36%,outperforming all the other models.
基金This study received financial support from the Jilin Province Health and Technology Capacity Enhancement Project(Project Number:222Lc132).
文摘Objective: This study investigates the auxiliary role of resting-state electroencephalography (EEG) in the clinical diagnosis of attention-deficit hyperactivity disorder (ADHD) using machine learning techniques. Methods: Resting-state EEG recordings were obtained from 57 children, comprising 28 typically developing children and 29 children diagnosed with ADHD. The EEG signal data from both groups were analyzed. To ensure analytical accuracy, artifacts and noise in the EEG signals were removed using the EEGLAB toolbox within the MATLAB environment. Following preprocessing, a comparative analysis was conducted using various ensemble learning algorithms, including AdaBoost, GBM, LightGBM, RF, XGB, and CatBoost. Model performance was systematically evaluated and optimized, validating the superior efficacy of ensemble learning approaches in identifying ADHD. Conclusion: Applying machine learning techniques to extract features from resting-state EEG signals enabled the development of effective ensemble learning models. Differential entropy and energy features across multiple frequency bands proved particularly valuable for these models. This approach significantly enhances the detection rate of ADHD in children, demonstrating high diagnostic efficacy and sensitivity, and providing a promising tool for clinical application.
文摘In this study,a machine learning-based predictive model was developed for the Musa petti Wind Farm in Sri Lanka to address the need for localized forecasting solutions.Using data on wind speed,air temperature,nacelle position,and actual power,lagged features were generated to capture temporal dependencies.Among 24 evaluated models,the ensemble bagging approach achieved the best performance,with R^(2) values of 0.89 at 0 min and 0.75 at 60 min.Shapley Additive exPlanations(SHAP)analysis revealed that while wind speed is the primary driver for short-term predictions,air temperature and nacelle position become more influential at longer forecasting horizons.These findings underscore the reliability of short-term predictions and the potential benefits of integrating hybrid AI and probabilistic models for extended forecasts.Our work contributes a robust and explainable framework to support Sri Lanka’s renewable energy transition,and future research will focus on real-time deployment and uncertainty quantification.
基金supported by the National Key Research and Development Program of China(No.2021YFD1700600)the National Natural Science Foundation of China(Nos.42222104 and 41971138)+1 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDA23020201)and the Science and Technology Planning Project of NIGLAS(No.NIGLAS2022GS10).
文摘China’s lowland rural rivers are facing severe eutrophication problems due to excessive phosphorus(P)from anthropogenic activities.However,quantifying P dynamics in a lowland rural river is challenging due to its complex interaction with surrounding areas.A P dynamic model(River-P)was specifically designed for lowland rural rivers to address this challenge.This modelwas coupled with the Environmental Fluid Dynamics Code(EFDC)and the Phosphorus Dynamic Model for lowland Polder systems(PDP)to characterize P dynamics under the impact of dredging in a lowland rural river.Based on a two-year(2020-2021)dataset from a representative lowland rural river in the Lake Taihu Basin,China,the coupled model was calibrated and achieved a model performance(R^(2)>0.59,RMSE<0.04 mg/L)for total P(TP)concentrations.Our research in the study river revealed that(1)the time scale for the effectiveness of sediment dredging for P control was~300 days,with an increase in P retention capacity by 74.8 kg/year and a decrease in TP concentrations of 23%after dredging.(2)Dredging significantly reduced P release from sediment by 98%,while increased P resuspension and settling capacities by 16%and 46%,respectively.(3)The sediment-water interface(SWI)plays a critical role in P transfer within the river,as resuspension accounts for 16%of TP imports,and settling accounts for 47%of TP exports.Given the large P retention capacity of lowland rural rivers,drainage ditches and ponds with macrophytes are promising approaches to enhance P retention capacity.Our study provides valuable insights for local environmental departments,allowing a comprehensive understanding of P dynamics in lowland rural rivers.This enable the evaluation of the efficacy of sediment dredging in P control and the implementation of corresponding P control measures.
基金supported by Three-Year Initiative Plan for Strengthening Public Health System Construction in Shanghai(2023-2025)Key Discipline Project(No.GWVI-11.1-12).
文摘To the Editor:We read with interest the article by Wang et al.,titled"Modeling the spread risk of dengue vector Aedes albopictus caused by environmental factors in Shanghai,China"[1].The use of ensemble ecological niche models to map Aedes albopictus distribution in urban Shanghai is both timely and methodologically sound.The identified drivers-vegetation index,temperature,and proximity to water-are well-known contributors to vector proliferation.However,one dimension remains notably underrepresented:human behavioral factors.
基金sponsored by the U.S. National Science Foundation (Grant No.ATM0205599)the U.S. Offce of Navy Research under Grant N000140410471Dr. James A. Hansen was partially supported by US Offce of Naval Research (Grant No. N00014-06-1-0500)
文摘This study examines the performance of coupling the deterministic four-dimensional variational assimilation system （4DVAR） with an ensemble Kalman filter （EnKF） to produce a superior hybrid approach for data assimilation. The coupled assimilation scheme （E4DVAR） benefits from using the state-dependent uncertainty provided by EnKF while taking advantage of 4DVAR in preventing filter divergence： the 4DVAR analysis produces posterior maximum likelihood solutions through minimization of a cost function about which the ensemble perturbations are transformed, and the resulting ensemble analysis can be propagated forward both for the next assimilation cycle and as a basis for ensemble forecasting. The feasibility and effectiveness of this coupled approach are demonstrated in an idealized model with simulated observations. It is found that the E4DVAR is capable of outperforming both 4DVAR and the EnKF under both perfect- and imperfect-model scenarios. The performance of the coupled scheme is also less sensitive to either the ensemble size or the assimilation window length than those for standard EnKF or 4DVAR implementations.
