Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-...Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.展开更多
Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely id...Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.展开更多
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
Surface properties of crystals are critical in many fields,including electrochemistry and photoelectronics,the efficient prediction of which can expedite the design and optimization of catalysts,batteries,alloys etc.H...Surface properties of crystals are critical in many fields,including electrochemistry and photoelectronics,the efficient prediction of which can expedite the design and optimization of catalysts,batteries,alloys etc.However,we are still far from realizing this vision due to the rarity of surface property-related databases,especially for multicomponent compounds,due to the large sample spaces and limited computing resources.In this work,we present a surface emphasized multi-task crystal graph convolutional neural network(SEM-CGCNN)to predict multiple surface properties simultaneously from crystal structures.The model is evaluated on a dataset of 3526 surface energies and work functions of binary magnesium intermetallics obtained through first-principles calculations,and obvious improvements are observed both in efficiency and accuracy over the original CGCNN model.By transferring the pre-trained model to the datasets of pure metals and other intermetallics,the fine-tuned SEM-CGCNN outperforms learning from scratch and can be further applied to other surface properties and materials systems.This study could be a paradigm for the end-to-end mapping of atomic structures to anisotropic surface properties of crystals,which provides an efficient framework to understand and screen materials with desired surface characteristics.展开更多
Compared with traditional energy sources,wind power has a lower environmental impact.However,emissions are still generated across the life cycle of wind turbines,from production to recycling.As wind power rapidly deve...Compared with traditional energy sources,wind power has a lower environmental impact.However,emissions are still generated across the life cycle of wind turbines,from production to recycling.As wind power rapidly develops and deployment increases,these impacts are becoming increasingly evident.A comprehensive understanding of these impacts is crucial for sustainable development.Based on the harmonization of previous detailed life cycle assessment(LCA)studies,this study develops a simplified LCA model that estimates the life cycle environmental impacts of wind turbines based on their nominal power.Using this simplified LCA model,we assess the global warming potential(GWP),acidification potential(AP),and cumulative energy demand(CED)of wind power at the regional scale for 2022 and under three future scenarios(high-power wind turbine promotion,reduced wind curtailment,and a comprehensive development scenario).The results indicate that in 2022,the life cycle GWP,AP,and CED of wind power in western China were 10.76 g CO_(2) eq/kWh,0.177 g SO_(2) eq/kWh,and 17.6 kJ/kWh,respectively.Scenario simulations suggest that reducing wind curtailment is the most effective approach for reducing emissions in Inner Mongolia,Gansu,Qinghai,Ningxia,and Xinjiang,producing average decreases of 8.64%in GWP,8.39%in AP,and 9.26%in CED.In contrast,for Guangxi,Chongqing,Sichuan,Guizhou,Yunnan,Xizang,and Shaanxi,the promotion of high-power wind turbines provides greater environmental benefits than reducing curtailment,producing average decreases of 3.45%,3.09%,and 4.29%in GWP,AP,and CED,respectively.These findings help clarify the environmental impact of wind power across its life cycle at the regional scale and provide theoretical references for the direction of future wind power development and the formulation of related policies.展开更多
Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements...Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements at transceivers and RIS,the codebook based beamforming can be utilized in a computationally efficient manner.However,the codeword selection for analog beamforming is an intractable combinatorial optimization(CO)problem.To this end,by taking the CO problem as a classification problem,a multi-task learning based analog beam selection(MTL-ABS)framework is developed to implement cooperative beam selection concurrently at transceivers and RIS.In addition,residual network and self-attention mechanism are used to combat the network degradation and mine intrinsic THz channel features.Finally,the network convergence is analyzed from a blockwise perspective,and numerical results demonstrate that the MTL-ABS framework greatly decreases the beam selection overhead and achieves near optimal sum-rate compared with heuristic search based counterparts.展开更多
The smart meter communication system has substantial application value for the construction and upgrading of the entire power system.The deployment of the transmitter(Tx)of the smart meter system in the residential sc...The smart meter communication system has substantial application value for the construction and upgrading of the entire power system.The deployment of the transmitter(Tx)of the smart meter system in the residential scenarios is vexed by the need for more theoretical support.This paper mainly studies the communication channel between the Tx at semibasement and receiver(Rx)at outdoor.The design of an effective communication system relies on an accurate understanding of channel characteristics.Channel measurements and ray-tracing channel modeling are conducted to obtain channel data.The influence of different positions at same semi-basement is studied.Typical channel characteristics are analyzed,such as power delay profile(PDP),power angular profile(PAP),root-mean-square(RMS)delay spread(DS),channel capacity,received power,and path loss.The influence of different semi-basement placements and different floor heights is also compared.Besides,the channel measurements and simulation data fit well,which can illustrate the validity and reliability of the acquired channel data.This paper can provide theoretical support for the design and optimization of smart meter communication systems in semi-basement scenarios.展开更多
Ensuring reliable power supply in urban distribution networks is a complex and critical task.To address the increased demand during extreme scenarios,this paper proposes an optimal dispatch strategy that considers the...Ensuring reliable power supply in urban distribution networks is a complex and critical task.To address the increased demand during extreme scenarios,this paper proposes an optimal dispatch strategy that considers the coordination with virtual power plants(VPPs).The proposed strategy improves systemflexibility and responsiveness by optimizing the power adjustment of flexible resources.In the proposed strategy,theGaussian Process Regression(GPR)is firstly employed to determine the adjustable range of aggregated power within the VPP,facilitating an assessment of its potential contribution to power supply support.Then,an optimal dispatch model based on a leader-follower game is developed to maximize the benefits of the VPP and flexible resources while guaranteeing the power balance at the same time.To solve the proposed optimal dispatch model efficiently,the constraints of the problem are reformulated and resolved using the Karush-Kuhn-Tucker(KKT)optimality conditions and linear programming duality theorem.The effectiveness of the strategy is illustrated through a detailed case study.展开更多
Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one....Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks(CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-theart methods by 88.2% on PETA and 83.25% on RAP, respectively.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches...The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches face challenges with data sparsity and information loss due to single-molecule representation limitations and isolated predictive tasks.This research proposes molecular properties prediction with parallel-view and collaborative learning(MolP-PC),a multi-view fusion and multi-task deep learning framework that integrates 1D molecular fingerprints(MFs),2D molecular graphs,and 3D geometric representations,incorporating an attention-gated fusion mechanism and multi-task adaptive learning strategy for precise ADMET property predictions.Experimental results demonstrate that MolP-PC achieves optimal performance in 27 of 54 tasks,with its multi-task learning(MTL)mechanism significantly enhancing predictive performance on small-scale datasets and surpassing single-task models in 41 of 54 tasks.Additional ablation studies and interpretability analyses confirm the significance of multi-view fusion in capturing multi-dimensional molecular information and enhancing model generalization.A case study examining the anticancer compound Oroxylin A demonstrates MolP-PC’s effective generalization in predicting key pharmacokinetic parameters such as half-life(T0.5)and clearance(CL),indicating its practical utility in drug modeling.However,the model exhibits a tendency to underestimate volume of distribution(VD),indicating potential for improvement in analyzing compounds with high tissue distribution.This study presents an efficient and interpretable approach for ADMET property prediction,establishing a novel framework for molecular optimization and risk assessment in drug development.展开更多
This paper proposes that China,under the challenge of balancing its development and security,can aim for the Paris Agreement's goal to limit global warming to no more than 2℃by actively seeking carbonpeak and car...This paper proposes that China,under the challenge of balancing its development and security,can aim for the Paris Agreement's goal to limit global warming to no more than 2℃by actively seeking carbonpeak and carbon-neutrality pathways that align with China's national conditions,rather than following the idealized path toward the 1.5℃target by initially relying on extensive negative-emission technologies such as direct air carbon capture and storage(DACCS).This work suggests that pursuing a 1.5℃target is increasingly less feasible for China,as it would potentially incur 3–4 times the cost of pursuing the 2℃target.With China being likely to achieve a peak in its emissions around 2028,at about 12.8 billion tonnes of anthropogenic carbon dioxide(CO_(2)),and become carbon neutral,projected global warming levels may be less severe after the 2050s than previously estimated.This could reduce the risk potential of climate tipping points and extreme events,especially considering that the other two major carbon emitters in the world(Europe and North America)have already passed their carbon peaks.While natural carbon sinks will contribute to China's carbon neutrality efforts,they are not expected to be decisive in the transition stages.This research also addresses the growing focus on climate overshoot,tipping points,extreme events,loss and damage,and methane reductions in international climate cooperation,emphasizing the need to balance these issues with China's development,security,and fairness considerations.China's pursuit of carbon neutrality will have significant implications for global emissions scenarios,warming levels,and extreme event projections,as well as for climate change hotspots of international concern,such as climate tipping points,the climate crisis,and the notion that the world has moved from a warming to a boiling era.Possible research recommendations for global emissions scenarios based on China's 2℃target pathway are also summarized.展开更多
Precision actuation is a foundational technology in high-end equipment domains,where stroke,velocity,and accuracy are critical for processing and/or detection quality,precision in spacecraft flight trajectories,and ac...Precision actuation is a foundational technology in high-end equipment domains,where stroke,velocity,and accuracy are critical for processing and/or detection quality,precision in spacecraft flight trajectories,and accuracy in weapon system strikes.Piezoelectric actuators(PEAs),known for their nanometer-level precision,flexible stroke,resistance to electromagnetic interference,and scalable structure,have been widely adopted across various fields.Therefore,this study focuses on extreme scenarios involving ultra-high precision(micrometer and beyond),minuscule scales,and highly complex operational conditions.It provides a comprehensive overview of the types,working principles,advantages,and disadvantages of PEAs,along with their potential applications in piezo-actuated smart mechatronic systems(PSMSs).To address the demands of extreme scenarios in high-end equipment fields,we have identified five representative application areas:positioning and alignment,biomedical device configuration,advanced manufacturing and processing,vibration mitigation,micro robot system.Each area is further divided into specific subcategories,where we explore the underlying relationships,mechanisms,representative schemes,and characteristics.Finally,we discuss the challenges and future development trends related to PEAs and PSMSs.This work aims to showcase the latest advancements in the application of PEAs and provide valuable guidance for researchers in this field.展开更多
With the rapid development of virtual reality(VR)and augmented reality(AR)technologies,their application potential in the field of education has become increasingly significant.For a long time,fire safety education in...With the rapid development of virtual reality(VR)and augmented reality(AR)technologies,their application potential in the field of education has become increasingly significant.For a long time,fire safety education in university laboratories has faced numerous challenges,and traditional teaching methods have been insufficiently effective,with high-risk scenarios difficult to realistically recreate.Especially in special scenarios involving hazardous chemicals,conventional training methods struggle to enable learners to achieve deep understanding and behavioral formation.This study systematically integrates immersive technology theory with safety education needs,providing a replicable technical solution for safety education in high-risk environments.Its modular design approach has reference value for expansion into other professional fields,offering practical evidence for innovation in safety education models in the digital age.展开更多
Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progr...Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progress,but the ability to predict their intensity is obviously lagging behind.At present,research on TC intensity prediction takes atmospheric reanalysis data as the research object and mines the relationship between TC-related environmental factors and intensity through deep learning.However,reanalysis data are non-real-time in nature,which does not meet the requirements for operational forecasting applications.Therefore,a TC intensity prediction model named TC-Rolling is proposed,which can simultaneously extract the degree of symmetry for strong TC convective cloud and convection intensity,and fuse the deviation-angle variance with satellite images to construct the correlation between TC convection structure and intensity.For TCs'complex dynamic processes,a convolutional neural network(CNN)is used to learn their temporal and spatial features.For real-time intensity estimation,multi-task learning acts as an implicit time-series enhancement.The model is designed with a rolling strategy that aims to moderate the long-term dependent decay problem and improve accuracy for short-term intensity predictions.Since multiple tasks are correlated,the loss function of 12 h and 24 h are corrected.After testing on a sample of TCs in the Northwest Pacific,with a 4.48 kt root-mean-square error(RMSE)of 6 h intensity prediction,5.78 kt for 12 h,and 13.94 kt for 24 h,TC records from official agencies are used to assess the validity of TC-Rolling.展开更多
Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predispositio...Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predisposition,environmental exposure,unhealthy lifestyle habits,and existing medical conditions.Although existing machine learning-based methods for predicting stroke patients’health status have made significant progress,limitations remain in terms of prediction accuracy,model explainability,and system optimization.This paper proposes a multi-task learning approach based on Explainable Artificial Intelligence(XAI)for predicting the health status of stroke patients.First,we design a comprehensive multi-task learning framework that utilizes the task correlation of predicting various health status indicators in patients,enabling the parallel prediction of multiple health indicators.Second,we develop a multi-task Area Under Curve(AUC)optimization algorithm based on adaptive low-rank representation,which removes irrelevant information from the model structure to enhance the performance of multi-task AUC optimization.Additionally,the model’s explainability is analyzed through the stability analysis of SHAP values.Experimental results demonstrate that our approach outperforms comparison algorithms in key prognostic metrics F1 score and Efficiency.展开更多
As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as...As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.展开更多
Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–...Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–PM_(2.5)and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location.On this point,a multi-task learning(MTL)model,which enables the joint retrieval of PM_(2.5)concentration and AOD,is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager(FY-4A AGRI),and compared to that of two single-task learning models—namely,Random Forest(RF)and Deep Neural Network(DNN).Specifically,MTL achieves a coefficient of determination(R^(2))of 0.88 and a root-mean-square error(RMSE)of 0.10 in AOD retrieval.In comparison to RF,the R^(2)increases by 0.04,the RMSE decreases by 0.02,and the percentage of retrieval results falling within the expected error range(Within-EE)rises by 5.55%.The R^(2)and RMSE of PM_(2.5)retrieval by MTL are 0.84 and 13.76μg m~(-3)respectively.Compared with RF,the R^(2)increases by 0.06,the RMSE decreases by 4.55μg m~(-3),and the Within-EE increases by 7.28%.Additionally,compared to DNN,MTL shows an increase of 0.01 in R^(2)and a decrease of 0.02 in RMSE in AOD retrieval,with a corresponding increase of 2.89%in Within-EE.For PM_(2.5)retrieval,MTL exhibits an increase of 0.05 in R^(2),a decrease of 1.76μg m~(-3)in RMSE,and an increase of 6.83%in Within-EE.The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM_(2.5)retrievals,demonstrating a significant advantage in efficiently capturing the spatial distribution of PM_(2.5)concentration and AOD.展开更多
Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecas...Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.展开更多
Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these c...Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these challenges.Currently,methods for disease severity assessment typically rely on calculating the area proportion of disease segmentation regions or using classification networks for severity assessment.However,these methods require large amounts of labeled data and fail to quantify lesion proportions when using classification networks,leading to inaccurate evaluations.To address these issues,we propose an automated framework for disease severity assessment that combines multi-task learning and knowledge-driven large-model segmentation techniques.This framework includes an image information processor,a lesion and leaf segmentation module,and a disease severity assessment module.First,the image information processor utilizes a multi-task learning strategy to analyze input images comprehensively,ensuring a deep understanding of disease characteristics.Second,the lesion and leaf segmentation module employ prompt-driven large-model technology to accurately segment diseased areas and entire leaves,providing detailed visual analysis.Finally,the disease severity assessment module objectively evaluates the severity of the disease based on professional grading standards by calculating lesion area proportions.Additionally,we have developed a comprehensive database of diseased leaf images from major crops,including several task-specific datasets.Experimental results demonstrate that our framework can accurately identify and assess the types and severity of crop diseases,even without extensive labeled data.Codes and data are available at http://dkp-ads.samlab.cn/.展开更多
基金The National Natural Science Foundation of China(62136008,62293541)The Beijing Natural Science Foundation(4232056)The Beijing Nova Program(20240484514).
文摘Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.
基金supported by the National Natural Science Foundation of China(Grant Nos.42130719 and 42177173)the Doctoral Direct Train Project of Chongqing Natural Science Foundation(Grant No.CSTB2023NSCQ-BSX0029).
文摘Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
基金supported by the National Key R&D Program(No.2021YFB3501002)supported by the Ministry of Science and Technology of China,National Natural Science Foundation of China(No.51825101,52127801).
文摘Surface properties of crystals are critical in many fields,including electrochemistry and photoelectronics,the efficient prediction of which can expedite the design and optimization of catalysts,batteries,alloys etc.However,we are still far from realizing this vision due to the rarity of surface property-related databases,especially for multicomponent compounds,due to the large sample spaces and limited computing resources.In this work,we present a surface emphasized multi-task crystal graph convolutional neural network(SEM-CGCNN)to predict multiple surface properties simultaneously from crystal structures.The model is evaluated on a dataset of 3526 surface energies and work functions of binary magnesium intermetallics obtained through first-principles calculations,and obvious improvements are observed both in efficiency and accuracy over the original CGCNN model.By transferring the pre-trained model to the datasets of pure metals and other intermetallics,the fine-tuned SEM-CGCNN outperforms learning from scratch and can be further applied to other surface properties and materials systems.This study could be a paradigm for the end-to-end mapping of atomic structures to anisotropic surface properties of crystals,which provides an efficient framework to understand and screen materials with desired surface characteristics.
基金supported by the National Key Research and Development Program of China(Grant No.2022YFF1303405).
文摘Compared with traditional energy sources,wind power has a lower environmental impact.However,emissions are still generated across the life cycle of wind turbines,from production to recycling.As wind power rapidly develops and deployment increases,these impacts are becoming increasingly evident.A comprehensive understanding of these impacts is crucial for sustainable development.Based on the harmonization of previous detailed life cycle assessment(LCA)studies,this study develops a simplified LCA model that estimates the life cycle environmental impacts of wind turbines based on their nominal power.Using this simplified LCA model,we assess the global warming potential(GWP),acidification potential(AP),and cumulative energy demand(CED)of wind power at the regional scale for 2022 and under three future scenarios(high-power wind turbine promotion,reduced wind curtailment,and a comprehensive development scenario).The results indicate that in 2022,the life cycle GWP,AP,and CED of wind power in western China were 10.76 g CO_(2) eq/kWh,0.177 g SO_(2) eq/kWh,and 17.6 kJ/kWh,respectively.Scenario simulations suggest that reducing wind curtailment is the most effective approach for reducing emissions in Inner Mongolia,Gansu,Qinghai,Ningxia,and Xinjiang,producing average decreases of 8.64%in GWP,8.39%in AP,and 9.26%in CED.In contrast,for Guangxi,Chongqing,Sichuan,Guizhou,Yunnan,Xizang,and Shaanxi,the promotion of high-power wind turbines provides greater environmental benefits than reducing curtailment,producing average decreases of 3.45%,3.09%,and 4.29%in GWP,AP,and CED,respectively.These findings help clarify the environmental impact of wind power across its life cycle at the regional scale and provide theoretical references for the direction of future wind power development and the formulation of related policies.
文摘Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements at transceivers and RIS,the codebook based beamforming can be utilized in a computationally efficient manner.However,the codeword selection for analog beamforming is an intractable combinatorial optimization(CO)problem.To this end,by taking the CO problem as a classification problem,a multi-task learning based analog beam selection(MTL-ABS)framework is developed to implement cooperative beam selection concurrently at transceivers and RIS.In addition,residual network and self-attention mechanism are used to combat the network degradation and mine intrinsic THz channel features.Finally,the network convergence is analyzed from a blockwise perspective,and numerical results demonstrate that the MTL-ABS framework greatly decreases the beam selection overhead and achieves near optimal sum-rate compared with heuristic search based counterparts.
基金supported by the Natural Science Foundation of Shandong Province under Grant ZR2024MF062the open research fund of National Mobile Communications Research Laboratory,Southeast University under Grants 2025D03+1 种基金the Future Plan Program for Young Scholars of Shandong University,and the Innovation and Technology Support Program for Young Scholars of Colleges and Universities in Shandong Province under Grant 2022KJ009The B6G R&D Group in Shandong University is greatly thanked for channel measurements.
文摘The smart meter communication system has substantial application value for the construction and upgrading of the entire power system.The deployment of the transmitter(Tx)of the smart meter system in the residential scenarios is vexed by the need for more theoretical support.This paper mainly studies the communication channel between the Tx at semibasement and receiver(Rx)at outdoor.The design of an effective communication system relies on an accurate understanding of channel characteristics.Channel measurements and ray-tracing channel modeling are conducted to obtain channel data.The influence of different positions at same semi-basement is studied.Typical channel characteristics are analyzed,such as power delay profile(PDP),power angular profile(PAP),root-mean-square(RMS)delay spread(DS),channel capacity,received power,and path loss.The influence of different semi-basement placements and different floor heights is also compared.Besides,the channel measurements and simulation data fit well,which can illustrate the validity and reliability of the acquired channel data.This paper can provide theoretical support for the design and optimization of smart meter communication systems in semi-basement scenarios.
基金supported by the Science and Technology Project of Sichuan Electric Power Company“Power Supply Guarantee Strategy for Urban Distribution Networks Considering Coordination with Virtual Power Plant during Extreme Weather Event”(No.521920230003).
文摘Ensuring reliable power supply in urban distribution networks is a complex and critical task.To address the increased demand during extreme scenarios,this paper proposes an optimal dispatch strategy that considers the coordination with virtual power plants(VPPs).The proposed strategy improves systemflexibility and responsiveness by optimizing the power adjustment of flexible resources.In the proposed strategy,theGaussian Process Regression(GPR)is firstly employed to determine the adjustable range of aggregated power within the VPP,facilitating an assessment of its potential contribution to power supply support.Then,an optimal dispatch model based on a leader-follower game is developed to maximize the benefits of the VPP and flexible resources while guaranteeing the power balance at the same time.To solve the proposed optimal dispatch model efficiently,the constraints of the problem are reformulated and resolved using the Karush-Kuhn-Tucker(KKT)optimality conditions and linear programming duality theorem.The effectiveness of the strategy is illustrated through a detailed case study.
基金supported by National Key R&D Program of China(-NO.2017YFC0803700)National Nature Science Foundation of China(No.U1736206)+6 种基金National Nature Science Foundation of China(61671336)National Nature Science Foundation of China(61671332)Technology Research Program of Ministry of Public Security(No.2016JSYJA12)Hubei Province Technological Innovation Major Project(-No.2016AAA015)Hubei Province Technological Innovation Major Projec(2017AAA123)National Key Research and Development Program of China(No.2016YFB0100901)Nature Science Foundation of Jiangsu Province(No.BK20160386)
文摘Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks(CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-theart methods by 88.2% on PETA and 83.25% on RAP, respectively.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the research on key technologies for monitoring and identifying drug abuse of anesthetic drugs and psychotropic drugs,and intervention for addiction(No.2023YFC3304200)the program of a study on the diagnosis of addiction to synthetic cannabinoids and methods of assessing the risk of abuse(No.2022YFC3300905)+1 种基金the program of Ab initio design and generation of AI models for small molecule ligands based on target structures(No.2022PE0AC03)ZHIJIANG LAB.
文摘The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches face challenges with data sparsity and information loss due to single-molecule representation limitations and isolated predictive tasks.This research proposes molecular properties prediction with parallel-view and collaborative learning(MolP-PC),a multi-view fusion and multi-task deep learning framework that integrates 1D molecular fingerprints(MFs),2D molecular graphs,and 3D geometric representations,incorporating an attention-gated fusion mechanism and multi-task adaptive learning strategy for precise ADMET property predictions.Experimental results demonstrate that MolP-PC achieves optimal performance in 27 of 54 tasks,with its multi-task learning(MTL)mechanism significantly enhancing predictive performance on small-scale datasets and surpassing single-task models in 41 of 54 tasks.Additional ablation studies and interpretability analyses confirm the significance of multi-view fusion in capturing multi-dimensional molecular information and enhancing model generalization.A case study examining the anticancer compound Oroxylin A demonstrates MolP-PC’s effective generalization in predicting key pharmacokinetic parameters such as half-life(T0.5)and clearance(CL),indicating its practical utility in drug modeling.However,the model exhibits a tendency to underestimate volume of distribution(VD),indicating potential for improvement in analyzing compounds with high tissue distribution.This study presents an efficient and interpretable approach for ADMET property prediction,establishing a novel framework for molecular optimization and risk assessment in drug development.
基金supported by the top-level design of the National Natural Science Foundation of China(NSFC)Major Project“Realization of optimal carbon neutral pathway and coupling of multi-scale interaction patterns of natural-social systems in China”(42341202)the Basic Scientific Research Fund of the Chinese Academy of Meteorological Sciences(2021Z014)。
文摘This paper proposes that China,under the challenge of balancing its development and security,can aim for the Paris Agreement's goal to limit global warming to no more than 2℃by actively seeking carbonpeak and carbon-neutrality pathways that align with China's national conditions,rather than following the idealized path toward the 1.5℃target by initially relying on extensive negative-emission technologies such as direct air carbon capture and storage(DACCS).This work suggests that pursuing a 1.5℃target is increasingly less feasible for China,as it would potentially incur 3–4 times the cost of pursuing the 2℃target.With China being likely to achieve a peak in its emissions around 2028,at about 12.8 billion tonnes of anthropogenic carbon dioxide(CO_(2)),and become carbon neutral,projected global warming levels may be less severe after the 2050s than previously estimated.This could reduce the risk potential of climate tipping points and extreme events,especially considering that the other two major carbon emitters in the world(Europe and North America)have already passed their carbon peaks.While natural carbon sinks will contribute to China's carbon neutrality efforts,they are not expected to be decisive in the transition stages.This research also addresses the growing focus on climate overshoot,tipping points,extreme events,loss and damage,and methane reductions in international climate cooperation,emphasizing the need to balance these issues with China's development,security,and fairness considerations.China's pursuit of carbon neutrality will have significant implications for global emissions scenarios,warming levels,and extreme event projections,as well as for climate change hotspots of international concern,such as climate tipping points,the climate crisis,and the notion that the world has moved from a warming to a boiling era.Possible research recommendations for global emissions scenarios based on China's 2℃target pathway are also summarized.
基金financially supported by the National Key R&D Program of China(Grant No.2022YFC2204203)the National Natural Science Foundation of China(Grant No.52305107)。
文摘Precision actuation is a foundational technology in high-end equipment domains,where stroke,velocity,and accuracy are critical for processing and/or detection quality,precision in spacecraft flight trajectories,and accuracy in weapon system strikes.Piezoelectric actuators(PEAs),known for their nanometer-level precision,flexible stroke,resistance to electromagnetic interference,and scalable structure,have been widely adopted across various fields.Therefore,this study focuses on extreme scenarios involving ultra-high precision(micrometer and beyond),minuscule scales,and highly complex operational conditions.It provides a comprehensive overview of the types,working principles,advantages,and disadvantages of PEAs,along with their potential applications in piezo-actuated smart mechatronic systems(PSMSs).To address the demands of extreme scenarios in high-end equipment fields,we have identified five representative application areas:positioning and alignment,biomedical device configuration,advanced manufacturing and processing,vibration mitigation,micro robot system.Each area is further divided into specific subcategories,where we explore the underlying relationships,mechanisms,representative schemes,and characteristics.Finally,we discuss the challenges and future development trends related to PEAs and PSMSs.This work aims to showcase the latest advancements in the application of PEAs and provide valuable guidance for researchers in this field.
文摘With the rapid development of virtual reality(VR)and augmented reality(AR)technologies,their application potential in the field of education has become increasingly significant.For a long time,fire safety education in university laboratories has faced numerous challenges,and traditional teaching methods have been insufficiently effective,with high-risk scenarios difficult to realistically recreate.Especially in special scenarios involving hazardous chemicals,conventional training methods struggle to enable learners to achieve deep understanding and behavioral formation.This study systematically integrates immersive technology theory with safety education needs,providing a replicable technical solution for safety education in high-risk environments.Its modular design approach has reference value for expansion into other professional fields,offering practical evidence for innovation in safety education models in the digital age.
基金jointly supported by the National Natural Science Foundation of China(Grant Nos.42075138 and 42375147)the Program on Key Basic Research Project of Jiangsu(Grant No.BE2023829)。
文摘Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progress,but the ability to predict their intensity is obviously lagging behind.At present,research on TC intensity prediction takes atmospheric reanalysis data as the research object and mines the relationship between TC-related environmental factors and intensity through deep learning.However,reanalysis data are non-real-time in nature,which does not meet the requirements for operational forecasting applications.Therefore,a TC intensity prediction model named TC-Rolling is proposed,which can simultaneously extract the degree of symmetry for strong TC convective cloud and convection intensity,and fuse the deviation-angle variance with satellite images to construct the correlation between TC convection structure and intensity.For TCs'complex dynamic processes,a convolutional neural network(CNN)is used to learn their temporal and spatial features.For real-time intensity estimation,multi-task learning acts as an implicit time-series enhancement.The model is designed with a rolling strategy that aims to moderate the long-term dependent decay problem and improve accuracy for short-term intensity predictions.Since multiple tasks are correlated,the loss function of 12 h and 24 h are corrected.After testing on a sample of TCs in the Northwest Pacific,with a 4.48 kt root-mean-square error(RMSE)of 6 h intensity prediction,5.78 kt for 12 h,and 13.94 kt for 24 h,TC records from official agencies are used to assess the validity of TC-Rolling.
基金funded by the Excellent Talent Training Funding Project in Dongcheng District,Beijing,with project number 2024-dchrcpyzz-9.
文摘Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predisposition,environmental exposure,unhealthy lifestyle habits,and existing medical conditions.Although existing machine learning-based methods for predicting stroke patients’health status have made significant progress,limitations remain in terms of prediction accuracy,model explainability,and system optimization.This paper proposes a multi-task learning approach based on Explainable Artificial Intelligence(XAI)for predicting the health status of stroke patients.First,we design a comprehensive multi-task learning framework that utilizes the task correlation of predicting various health status indicators in patients,enabling the parallel prediction of multiple health indicators.Second,we develop a multi-task Area Under Curve(AUC)optimization algorithm based on adaptive low-rank representation,which removes irrelevant information from the model structure to enhance the performance of multi-task AUC optimization.Additionally,the model’s explainability is analyzed through the stability analysis of SHAP values.Experimental results demonstrate that our approach outperforms comparison algorithms in key prognostic metrics F1 score and Efficiency.
基金supported by the Key Research and Development Program of Heilongjiang Province(No.2022ZX01A35).
文摘As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.
基金supported by the National Natural Science Foundation of China(Grant Nos.42030708,42375138,42030608,42105128,42075079)the Opening Foundation of Key Laboratory of Atmospheric Sounding,China Meteorological Administration(CMA),and the CMA Research Center on Meteorological Observation Engineering Technology(Grant No.U2021Z03),and the Opening Foundation of the Key Laboratory of Atmospheric Chemistry,CMA(Grant No.2022B02)。
文摘Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–PM_(2.5)and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location.On this point,a multi-task learning(MTL)model,which enables the joint retrieval of PM_(2.5)concentration and AOD,is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager(FY-4A AGRI),and compared to that of two single-task learning models—namely,Random Forest(RF)and Deep Neural Network(DNN).Specifically,MTL achieves a coefficient of determination(R^(2))of 0.88 and a root-mean-square error(RMSE)of 0.10 in AOD retrieval.In comparison to RF,the R^(2)increases by 0.04,the RMSE decreases by 0.02,and the percentage of retrieval results falling within the expected error range(Within-EE)rises by 5.55%.The R^(2)and RMSE of PM_(2.5)retrieval by MTL are 0.84 and 13.76μg m~(-3)respectively.Compared with RF,the R^(2)increases by 0.06,the RMSE decreases by 4.55μg m~(-3),and the Within-EE increases by 7.28%.Additionally,compared to DNN,MTL shows an increase of 0.01 in R^(2)and a decrease of 0.02 in RMSE in AOD retrieval,with a corresponding increase of 2.89%in Within-EE.For PM_(2.5)retrieval,MTL exhibits an increase of 0.05 in R^(2),a decrease of 1.76μg m~(-3)in RMSE,and an increase of 6.83%in Within-EE.The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM_(2.5)retrievals,demonstrating a significant advantage in efficiently capturing the spatial distribution of PM_(2.5)concentration and AOD.
基金the National Key Research and Development Plan of China[Grant No.2023YFB3002400]the Shanghai 2021 Natural Science Foundation[Grant Nos.21ZR1420400 and 21ZR1419800]+1 种基金the Shanghai 2023 Natural Science Foundation[Grant No.23ZR1463000]the Shandong Provincial Meteorological Bureau Scientific Research Project[Grant No.2023SDBD05].
文摘Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.
基金supported by the National Key Research and Development Program of China (2024YFD2001100,2024YFE0214300)the National Natural Science Foundation of China (62162008)+3 种基金Guizhou Provincial Science and Technology Projects ([2024]002, CXTD[2023]027)Guizhou Province Youth Science and Technology Talent Project ([2024]317)Guiyang Guian Science and Technology Talent Training Project ([2024]2-15)the Guizhou Province Graduate Education Innovation Program Project (2024YJSKYJJ096)
文摘Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these challenges.Currently,methods for disease severity assessment typically rely on calculating the area proportion of disease segmentation regions or using classification networks for severity assessment.However,these methods require large amounts of labeled data and fail to quantify lesion proportions when using classification networks,leading to inaccurate evaluations.To address these issues,we propose an automated framework for disease severity assessment that combines multi-task learning and knowledge-driven large-model segmentation techniques.This framework includes an image information processor,a lesion and leaf segmentation module,and a disease severity assessment module.First,the image information processor utilizes a multi-task learning strategy to analyze input images comprehensively,ensuring a deep understanding of disease characteristics.Second,the lesion and leaf segmentation module employ prompt-driven large-model technology to accurately segment diseased areas and entire leaves,providing detailed visual analysis.Finally,the disease severity assessment module objectively evaluates the severity of the disease based on professional grading standards by calculating lesion area proportions.Additionally,we have developed a comprehensive database of diseased leaf images from major crops,including several task-specific datasets.Experimental results demonstrate that our framework can accurately identify and assess the types and severity of crop diseases,even without extensive labeled data.Codes and data are available at http://dkp-ads.samlab.cn/.
