Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Reg...Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Regression models and Neural network models,to perform multi-characteristic coupled displacement prediction because they fail to consider landslide creep characteristics.This paper integrates the creep characteristics of landslides with non-linear intelligent algorithms and proposes a dynamic intelligent landslide displacement prediction method based on a combination of the Biological Growth model(BG),Convolutional Neural Network(CNN),and Long ShortTerm Memory Network(LSTM).This prediction approach improves three different biological growth models,thereby effectively extracting landslide creep characteristic parameters.Simultaneously,it integrates external factors(rainfall and reservoir water level)to construct an internal and external comprehensive dataset for data augmentation,which is input into the improved CNN-LSTM model.Thereafter,harnessing the robust feature extraction capabilities and spatial translation invariance of CNN,the model autonomously captures short-term local fluctuation characteristics of landslide displacement,and combines LSTM's efficient handling of long-term nonlinear temporal data to improve prediction performance.An evaluation of the Liangshuijing landslide in the Three Gorges Reservoir Area indicates that BG-CNN-LSTM exhibits high prediction accuracy,excellent generalization capabilities when dealing with various types of landslides.The research provides an innovative approach to achieving the whole-process,realtime,high-precision displacement predictions for multicharacteristic coupled landslides.展开更多
Active landslides pose a significant threat globally,endangering lives and property.Effective monitoring and forecasting of displacements are essential for the timely warnings and mitigation of these events.Interferom...Active landslides pose a significant threat globally,endangering lives and property.Effective monitoring and forecasting of displacements are essential for the timely warnings and mitigation of these events.Interferometric synthetic aperture radar(InSAR)stands out as an efficient and prevalent tool for monitoring landslide deformation and offers new prospects for displacement prediction.However,challenges such as inherent limitation of satellite viewing geometry,long revisit cycles,and limited data volume hinder its application in displacement forecasting,notably for landslides with near-north-south deformation less detectable by InSAR.To address these issues,we propose a novel strategy for predicting three-dimensional(3D)landslide displacement,integrating InSAR and global navigation satellite system(GNSS)measurements with machine learning(ML).This framework first synergizes InSAR line-of-sight(LOS)results with GNSS horizontal data to reconstruct 3D displacement time series.It then employs ML models to capture complex nonlinear relationships between external triggers,landslide evolutionary states,and 3D displacements,thus enabling accurate future deformation predictions.Utilizing four advanced ML algorithms,i.e.random forest(RF),support vector machine(SVM),long short-term memory(LSTM),and gated recurrent unit(GRU),with Bayesian optimization(BO)for hyperparameter tuning,we applied this innovative approach to the north-facing,slow-moving Xinpu landslide in the Three Gorges Reservoir Area(TGRA)of China.Leveraging over 6.5 years of Sentinel-1 satellite data and GNSS measurements,our framework demonstrates satisfactory and robust prediction performance,with an average root mean square deviation(RMSD)of 9.62 mm and a correlation coefficient(CC)of 0.996.This study presents a promising strategy for 3D displacement prediction,illustrating the efficacy of integrating InSAR monitoring with ML forecasting in enhancing landslide early warning capabilities.展开更多
Mitigating vortex-induced vibrations(VIV)in flexible risers represents a critical concern in offshore oil and gas production,considering its potential impact on operational safety and efficiency.The accurate predictio...Mitigating vortex-induced vibrations(VIV)in flexible risers represents a critical concern in offshore oil and gas production,considering its potential impact on operational safety and efficiency.The accurate prediction of displacement and position of VIV in flexible risers remains challenging under actual marine conditions.This study presents a data-driven model for riser displacement prediction that corresponds to field conditions.Experimental data analysis reveals that the XGBoost algorithm predicts the maximum displacement and position with superior accuracy compared with Support vector regression(SVR),considering both computational efficiency and precision.Platform displacement in the Y-direction demonstrates a significant positive correlation with both axial depth and maximum displacement magnitude.The fourth point displacement exhibits the highest contribution to model prediction outcomes,showing a positive influence on maximum displacement while negatively affecting the axial depth of maximum displacement.Platform displacement in the X-and Y-directions exhibits competitive effects on both the riser’s maximum displacement and its axial depth.Through the implementation of XGBoost algorithm and SHapley Additive exPlanation(SHAP)analysis,the model effectively estimates the riser’s maximum displacement and its precise location.This data-driven approach achieves predictions using minimal,readily available data points,enhancing its practical field applications and demonstrating clear relevance to academic and professional communities.展开更多
Succinylcholine(SC)is a widely used depolarizing muscle relaxant,but improper use can lead to arrhythmias and,in severe cases,pose a life-threatening risk.Additionally,some criminals exploit SC for illicit activities....Succinylcholine(SC)is a widely used depolarizing muscle relaxant,but improper use can lead to arrhythmias and,in severe cases,pose a life-threatening risk.Additionally,some criminals exploit SC for illicit activities.Therefore,rapid SC detection is paramount for clinical practice and public safety.Currently,however,limited methods are available for the rapid detection of SC.A fluorescent indicator displacement assay sensor based on molecular recognition of an amide naphthotube was developed.This sensor enabled the rapid fluorescent detection of SC through competitive binding between SC and methylene blue with the amide naphthotube.The sensor exhibited exceptional sensitivity with a detection limit as low as 1.1μmol/L and a detection range of 1.1~60μmol/L,coupled with outstanding selectivity and robust stability.Furthermore,this sensor accurately determined SC levels in biological samples such as serum.In summary,this research provides a new solution for the rapid and accurate sensing of SC in complex matrices and offers new insights for the swift identification and detection of toxins.展开更多
Imbalanced multiclass datasets pose challenges for machine learning algorithms.They often contain minority classes that are important for accurate predictions.However,when the data is sparsely distributed and overlaps...Imbalanced multiclass datasets pose challenges for machine learning algorithms.They often contain minority classes that are important for accurate predictions.However,when the data is sparsely distributed and overlaps with data points fromother classes,it introduces noise.As a result,existing resamplingmethods may fail to preserve the original data patterns,further disrupting data quality and reducingmodel performance.This paper introduces Neighbor Displacement-based Enhanced Synthetic Oversampling(NDESO),a hybridmethod that integrates a data displacement strategy with a resampling technique to achieve data balance.It begins by computing the average distance of noisy data points to their neighbors and adjusting their positions toward the center before applying random oversampling.Extensive evaluations compare 14 alternatives on nine classifiers across synthetic and 20 real-world datasetswith varying imbalance ratios.This evaluation was structured into two distinct test groups.First,the effects of k-neighbor variations and distance metrics are evaluated,followed by a comparison of resampled data distributions against alternatives,and finally,determining the most suitable oversampling technique for data balancing.Second,the overall performance of the NDESO algorithm was assessed,focusing on G-mean and statistical significance.The results demonstrate that our method is robust to a wide range of variations in these parameters and the overall performance achieves an average G-mean score of 0.90,which is among the highest.Additionally,it attains the lowest mean rank of 2.88,indicating statistically significant improvements over existing approaches.This advantage underscores its potential for effectively handling data imbalance in practical scenarios.展开更多
Diamond is a promising semiconductor material for future space exploration,owing to its unique atomic and electronic structures.However,diamond materials and related devices still suffer from irradiation damage under ...Diamond is a promising semiconductor material for future space exploration,owing to its unique atomic and electronic structures.However,diamond materials and related devices still suffer from irradiation damage under space irradiation involving high-energy irradiating particles.The study of the generation and evolution of point defects can help understand the irradiation damage mechanisms in diamond.This study systematically investigated the defect dynamics of diamond in 162 crystallographic directions uniformly selected on a spherical surface using molecular dynamics simulations,with primary knock-on atom(PKA)energies up to 20 keV,and temperatures ranging from 300 K to 1800 K.The results reveal that the displacement threshold energy of diamond changes periodically with crystallographic directions,which is related to the shape of potential energy surface along that direction.Additionally,the number of residual defects correlates positively with PKA energy.However,temperature has dual competing effects:while it enhances the probability of atomic displacement,it simultaneously suppresses the probability of defect formation by accelerating defect recombination.The calculation of sparse radial distribution function indicates that the defect distribution shows a certain degree of similarity in the short-range region across different PKA energies.As the PKA energy increases,defect clusters tend to become larger in size and more numerous in quantity.This study systematically investigates the anisotropy of displacement threshold energy and elucidates the relationship between various irradiation conditions and the final states of irradiation-induced defects.展开更多
To tackle the difficulties of the point prediction in quantifying the reliability of landslide displacement prediction,a data-driven combination-interval prediction method(CIPM)based on copula and variational-mode-dec...To tackle the difficulties of the point prediction in quantifying the reliability of landslide displacement prediction,a data-driven combination-interval prediction method(CIPM)based on copula and variational-mode-decomposition associated with kernel-based-extreme-learningmachine optimized by the whale optimization algorithm(VMD-WOA-KELM)is proposed in this paper.Firstly,the displacement is decomposed by VMD to three IMF components and a residual component of different fluctuation characteristics.The key impact factors of each IMF component are selected according to Copula model,and the corresponding WOA-KELM is established to conduct point prediction.Subsequently,the parametric method(PM)and non-parametric method(NPM)are used to estimate the prediction error probability density distribution(PDF)of each component,whose prediction interval(PI)under the 95%confidence level is also obtained.By means of the differential evolution algorithm(DE),a weighted combination model based on the PIs is built to construct the combination-interval(CI).Finally,the CIs of each component are added to generate the total PI.A comparative case study shows that the CIPM performs better in constructing landslide displacement PI with high performance.展开更多
This research proposes an innovative solution to the inherent challenges faced by landslide displacement prediction models based on data-driven methods,such as the need for extensive historical datasets for training,t...This research proposes an innovative solution to the inherent challenges faced by landslide displacement prediction models based on data-driven methods,such as the need for extensive historical datasets for training,the reliance on manual feature selection,and the difficulty in effectively utilizing landslide historical data.We have developed a dual-channel deep learning prediction model that integrates multimodal decomposition and an attention mechanism to overcome these challenges and improve prediction performance.The proposed methodology follows a three-stage framework:(1)Empirical Mode Decomposition(EMD)effectively segregates cumulative displacement and feature factors;(2)We have developed a Double Exponential Smoothing(DES)ensemble optimized through a Non-dominated Sorting Genetic Algorithm-II(NSGA-II)to enhance trend prediction;while employing a Bidirectional Long Short-Term Memory-Radial Basis Function(BiLSTM-RBF)network enhanced by a hybrid attention mechanism,which facilitates a global-local synergistic approach to hierarchical feature extraction,thereby improving the prediction of periodic displacements;(3)A bidirectional adaptive feature extraction mechanism aligns attention weights with BiLSTM propagation paths through spatial mapping,complemented by an innovative loss function incorporating Prediction Interval(PI)width optimization.In the comparative experiments of the Baishuihe landslide:the RMSE,MAE,and R^(2) indexes of monitoring point ZG118 are improved by 19.8%,35.2%,and 3.2%compared with the optimal baseline model(RBF-MIC);in the monitoring point ZG93,where the amount of data is less,the three indexes are even more improved by 52.1%,32.3%,and 21.8%compared with the optimal baseline model(GRU-None).These results substantiate the model’s capacity to overcome dual constraints of data paucity and feature engineering limitations in geohazard prediction.展开更多
To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specif...To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specifically based on the Long Short-Term Memory(LSTM)network,to predict temperature-induced girder end displacements of the Dasha Waterway Bridge,a suspension bridge in China.First,to enhance data quality and select target sensors,preprocessing based on the sigma rule and nearest neighbor interpolation is applied to the raw data.Furthermore,to eliminate the high-frequency components from the displacement signal,the wavelet transform is conducted.Subsequently,the linear regression model and ANN model are established,whose results do not meet the requirements and fail to address the time lag effect between temperature and displacements.The study proceeds to develop the LSTM network model and determine the optimal parameters through hyperparameter sensitivity analysis.Finally,the results of the LSTM network model are discussed by a comparative analysis against the linear regression model and ANN model,which indicates a higher accuracy in predicting temperatureinduced girder end displacements and the ability to mitigate the time-lag effect.To be more specific,in comparison between the linear regression model and LSTM network,the mean square error decreases from 6.5937 to 1.6808 and R^(2) increases from 0.683 to 0.930,which corresponds to a 74.51%decrease in MSE and a 36.14%improvement in R^(2).Compared to ANN,with an MSE of 4.6371 and an R^(2) of 0.807,LSTM shows a decrease in MSE of 63.75%and an increase in R^(2) of 13.23%,demonstrating a significant enhancement in predictive performance.展开更多
Irradiation experiments on p-Ga N gate high-electron-mobility transistors(HEMTs) were conducted using neutrons at Back-streaming White Neutron(Back-n) facility at the China Spallation Neutron Source(CSNS).Two groups o...Irradiation experiments on p-Ga N gate high-electron-mobility transistors(HEMTs) were conducted using neutrons at Back-streaming White Neutron(Back-n) facility at the China Spallation Neutron Source(CSNS).Two groups of devices were float-biased,while one group was ON-biased.Post-irradiation analysis revealed that the electrical performance of the devices exhibited progressive degradation with increasing Back-n fluence,with the ON-biased group demonstrating the most pronounced deterioration.This degradation was primarily characterized by a negative shift in the threshold voltage,a significant increase in reverse gate leakage current,and a slight reduction in forward gate leakage.Further analysis of the gate leakage current and capacitance-voltage characteristics indicated an elevated concentration of two-dimensional electron gas(2DEG),attributed to donor-type defects introduced within the barrier layer by Back-n irradiation.These defects act as hole traps,converting into fixed positive charges that deepen the quantum-well conduction band,thereby enhancing the 2DEG density.Additionally,through the trap-assisted tunneling mechanism,these defects serve as tunneling centers,increasing the probability of electron tunneling and consequently elevating the reverse gate leakage current.展开更多
License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition M...License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition Method(DR2M)to address such a problem.This method operates on displaced features compared to the training input observed throughout definite time frames.The technique focuses on detecting features that remain relatively stable under haze,using a frame-based analysis to isolate edges minimally affected by visual noise.The edge detection failures are identified using a bilateral neural network through displaced feature training.The training converges bilaterally towards the minimum edges from the maximum region.Thus,the training input and detected edges are used to identify the displacement between observed image frames to extract and differentiate the license plate region from the other vehicle regions.The proposed method maps the similarity feature between the detected and identified vehicle regions.This aids in leveraging the plate recognition precision with a high F1 score.Thus,this technique achieves a 10.27%improvement in identification precision,a 10.57%increase in F1 score,and a 9.73%reduction in false positive rate compared to baseline methods under maximum displacement conditions caused by haze.The technique attains an identification precision of 95.68%,an F1 score of 94.68%,and a false positive rate of 4.32%,indicating robust performance under haze-affected settings.展开更多
This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-preci...This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-precision laser interferometric displacement measurement.A stable power supply module is designed to provide low-noise voltage to the entire circuit.An analog circuit system is constructed,including key circuits such as photoelectric sensors,I-V amplification,zero adjustment,fully differential amplification,and amplitude modulation filtering.To acquire and process signals,the PMAC Acc24E3 data acquisition card is selected,which realizes phase demodulation through reversible square wave counting,inverts displacement information,and a visual interface for the host computer is designed.Experimental verification shows that the designed system achieves micrometer-level measurement accuracy within a range of 0-10mm,with a maximum measurement error of less than 1.2μm,a maximum measurement speed of 6m/s,and a resolution better than 0.158μm.展开更多
Measurement precision of laser displacement sensor is subject to various factors,among which laser jitter and target tilt will directly lead to the position movement and shape variation of the laser spot,resulting in ...Measurement precision of laser displacement sensor is subject to various factors,among which laser jitter and target tilt will directly lead to the position movement and shape variation of the laser spot,resulting in displacement measurement errors,so that researchers have to do a lot of research on the spot centering algorithm to weaken the above effects,which can treat the symptoms but not the root cause.Starting from the source of the problem,this paper proposes a double focus double peak solution,which uses a reflector to change the direction of the optical path,so that the imaging spots of the designed two optical paths focus on the same CMOS,forming a double peak structure.When laser jitter or target tilt occurs,the center of the two laser spots is shifted,but they move in the same direction,while their relative position remains unchanged.Therefore,the displacement can be characterized by the relative position of the two laser spots,so that laser jitter and target tilt are suppressed from the source.However,the two spots imaged on CMOS form a non-Gaussian distributed double peak structure,so the conventional laser spot centering algorithms are no longer applicable.To this end,a double peak adaptive threshold waveform extraction method combined with grayscale gravity method is proposed for spot centering algorithm,which combines the suppression of laser jitter and target tilt from the source and the improvement of spot positioning precision which represents the displacement measurement precision,and is experimentally verified.展开更多
Rock discontinuities such as joints widely exist in natural rock masses,and wave attenuation through rock masses is mainly caused by discontinuities.The displacement discontinuity model(DDM)has been widely used in the...Rock discontinuities such as joints widely exist in natural rock masses,and wave attenuation through rock masses is mainly caused by discontinuities.The displacement discontinuity model(DDM)has been widely used in theoretical and numerical analysis of wave propagation across rock discontinuity.However,the circumstance under which the DDM is applicable to predict wave propagation across rock discontinuity remains poorly understood.In this study,theoretical analysis and ultrasonic laboratory tests were carried out to examine the theoretical applicability of the DDM for wave propagation,where specimens with rough joints comprising regular rectangular asperities of different spacings and heights were prepared by 3D printing technology.It is found that the theoretical applicability of the DDM to predict wave propagation across rock discontinuity is determined by three joint parameters,i.e.the dimensionless asperity spacing(L),the dimensionless asperity height(H)and the groove density(D).Through theoretical analysis and laboratory tests,the conditions under which the DDM is applicable are derived as follows:and,.With increase in the groove density,the thresholds of the dimensionless asperity spacing and the dimensionless asperity height show a decreasing trend.In addition,the transmission coefficient in the frequency domain decreases with increasing groove density,dimensionless asperity spacing or dimensionless asperity height.The findings can facilitate our understanding of DDM for predicting wave propagation across rock discontinuity.展开更多
Collapses of seismic slopes demonstrate the characteristics of three-dimensional(3D)shapes.Conducting a 3D analysis of seismic slope stability is more complicated than doing a simplified two-dimensional(2D)analysis.Th...Collapses of seismic slopes demonstrate the characteristics of three-dimensional(3D)shapes.Conducting a 3D analysis of seismic slope stability is more complicated than doing a simplified two-dimensional(2D)analysis.The upper-bound solutions derived from limit analysis of seismic slopes using the pseudo-static method are used to generate an approximate solution for the factor of 3D safety through regression analysis.Such a solution can degenerate to a 2D result when the slope width tends to infinity.The approximation method also can be extended for determining the permanent displacements of 3D slopes under seismic loading.The method is non-iterative and relatively accurate through comparisons with analytical results.Involving stochastic ground motions could easily be used to assess the distribution of permanent displacement that is induced in 3D slopes.展开更多
Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,ther...Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.展开更多
The random displacement model(RDM)can efficiently simulate particle transport processes,which are difficult to observe,incorporating stochastic and hydraulic parameters.In recent decades,it has been used in many domai...The random displacement model(RDM)can efficiently simulate particle transport processes,which are difficult to observe,incorporating stochastic and hydraulic parameters.In recent decades,it has been used in many domains,including environments,hydraulics,and ecology.However,the results exhibit significant uncertainties arising from the model resolution,hydrodynamic accuracy,intrinsic characteristics of particles,and boundary conditions.The objective of the present study is to comprehensively interpret the RDM from theory to application,and emphasize essential considerations for users in different domains.The study also provides several application strategies for the model,based on several practical RDM cases.Determining the turbulent diffusivity and velocity profiles in complex flow field is a critical step to precisely simulate particle movement.Furthermore,the physical and biological properties of passive and active particles require fundamental investigation to extend the applicability of the model.Existing studies suggest that flexibly coupling the RDM with other numerical models customized to the characteristics of distinct problems will substantially expand the utility of the RDM and could yield innovative approaches for addressing previously intractable issues.展开更多
The purpose of this study is to establish a multivariate nonlinear regression mathematical model to predict the displacement of tumor during brain tumor resection surgery.And the study will be integrated with augmente...The purpose of this study is to establish a multivariate nonlinear regression mathematical model to predict the displacement of tumor during brain tumor resection surgery.And the study will be integrated with augmented reality technology to achieve three-dimensional visualization,thereby enhancing the complete resection rate of tumor and the success rate of surgery.Based on the preoperative MRI data of the patients,a 3D virtual model is reconstructed and 3D printed.A brain biomimetic model is created using gel injection molding.By considering cerebrospinal fluid loss and tumor cyst fluid loss as independent variables,the highest point displacement in the vertical bone window direction is determined as the dependent variable after positioning the patient for surgery.An orthogonal experiment is conducted on the biomimetic model to establish a predictive model,and this model is incorporated into the augmented reality navigation system.To validate the predictive model,five participants wore HoloLens2 devices,overlaying the patient’s 3D virtual model onto the physical head model.Subsequently,the spatial coordinates of the tumor’s highest point after displacement were measured on both the physical and virtual models(actual coordinates and predicted coordinates,respectively).The difference between these coordinates represents the model’s prediction error.The results indicate that the measured and predicted errors for the displacement of the tumor’s highest point on the X and Y axes range from−0.6787 mm to 0.2957 mm and−0.4314 mm to 0.2253 mm,respectively.The relative errors for each experimental group are within 10%,demonstrating a good fit of the model.This method of establishing a regression model represents a preliminary attempt to predict brain tumor displacement in specific situations.It also provides a new approach for surgeons.By combining augmented reality visualization,it addresses the need for predicting tumor displacement and precisely locating brain anatomical structures in a simple and cost-effective manner.展开更多
The commonly used method for estimating crack opening displacement(COD)is based on analytical models derived from strain transferring.However,when large background noise exists in distributed fiber optic sensing(DFOS)...The commonly used method for estimating crack opening displacement(COD)is based on analytical models derived from strain transferring.However,when large background noise exists in distributed fiber optic sensing(DFOS)data,estimating COD through an analytical model is very difficult even if the DFOS data have been denoised.To address this challenge,this study proposes a machine learning(ML)-based methodology to complete rock's COD estimation from establishment of a dataset with one-to-one correspondence between strain sequence and COD to the optimization of ML models.The Bayesian optimization is used via the Hyperopt Python library to determine the appropriate hyper-parameters of four ML models.To ensure that the best hyper-parameters will not be missing,the configuration space in Hyperopt is specified by probability distribution.The four models are trained using DFOS data with minimal noise while being examined on datasets with different noise levels to test their anti-noise robustness.The proposed models are compared each other in terms of goodness of fit and mean squared error.The results show that the Bayesian optimization-based random forest is promising to estimate the COD of rock using noisy DFOS data.展开更多
The two-phase flow in porous media is affected by multiple factors.In the present study,a two-dimensional numerical model of porous media was developed using the actual pore structure of the core sample.The phase fiel...The two-phase flow in porous media is affected by multiple factors.In the present study,a two-dimensional numerical model of porous media was developed using the actual pore structure of the core sample.The phase field method was utilized to simulate the impact of displacement velocity,the water-gas viscosity ratio,and the density ratio on the flow behavior of two-phase fluids in porous media.The effectiveness of displacement was evaluated by analyzing CO_(2)saturation levels.The results indicate that the saturation of CO_(2)in porous media increased as the displacement velocity increased.When the displacement velocity exceeded 0.01 m/s,there was a corresponding increase in CO_(2)saturation.Conversely,when the displacement velocity was below this threshold,the impact on CO_(2)saturation was minimal.An“inflection point,”M3,was present in the viscosity ratio.When the viscosity of CO_(2)is less than 8.937×10^(-5)Pa·s(viscosity ratio below M3),variations in the viscosity of CO_(2)had little impact on its saturation.Conversely,when the viscosity of CO_(2)exceeded 8.937×10^(-5)Pa·s(viscosity ratio greater than M3),saturation increased with an increase in the viscosity ratio.In terms of the density ratio,the saturation of CO_(2)increased monotonically with an increase in the density ratio.Similarly,increasing density ratios resulted in a monotonic increase in CO_(2)saturation,though this trend was less pronounced in numerical simulations.Analysis results of displacement within dead-end pores using pressure and velocity diagrams reveal eddy currents as contributing factors.Finally,the impact of pore throat structure on the formation of dominant channels was examined.展开更多
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd..(Grant No.H20230317)。
文摘Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Regression models and Neural network models,to perform multi-characteristic coupled displacement prediction because they fail to consider landslide creep characteristics.This paper integrates the creep characteristics of landslides with non-linear intelligent algorithms and proposes a dynamic intelligent landslide displacement prediction method based on a combination of the Biological Growth model(BG),Convolutional Neural Network(CNN),and Long ShortTerm Memory Network(LSTM).This prediction approach improves three different biological growth models,thereby effectively extracting landslide creep characteristic parameters.Simultaneously,it integrates external factors(rainfall and reservoir water level)to construct an internal and external comprehensive dataset for data augmentation,which is input into the improved CNN-LSTM model.Thereafter,harnessing the robust feature extraction capabilities and spatial translation invariance of CNN,the model autonomously captures short-term local fluctuation characteristics of landslide displacement,and combines LSTM's efficient handling of long-term nonlinear temporal data to improve prediction performance.An evaluation of the Liangshuijing landslide in the Three Gorges Reservoir Area indicates that BG-CNN-LSTM exhibits high prediction accuracy,excellent generalization capabilities when dealing with various types of landslides.The research provides an innovative approach to achieving the whole-process,realtime,high-precision displacement predictions for multicharacteristic coupled landslides.
基金jointly supported by the International Research Center of Big Data for Sustainable Development Goals(Grant No.CBAS2022GSP02)the National Natural Science Foundation of China(Grant Nos.42072320 and 42372264).
文摘Active landslides pose a significant threat globally,endangering lives and property.Effective monitoring and forecasting of displacements are essential for the timely warnings and mitigation of these events.Interferometric synthetic aperture radar(InSAR)stands out as an efficient and prevalent tool for monitoring landslide deformation and offers new prospects for displacement prediction.However,challenges such as inherent limitation of satellite viewing geometry,long revisit cycles,and limited data volume hinder its application in displacement forecasting,notably for landslides with near-north-south deformation less detectable by InSAR.To address these issues,we propose a novel strategy for predicting three-dimensional(3D)landslide displacement,integrating InSAR and global navigation satellite system(GNSS)measurements with machine learning(ML).This framework first synergizes InSAR line-of-sight(LOS)results with GNSS horizontal data to reconstruct 3D displacement time series.It then employs ML models to capture complex nonlinear relationships between external triggers,landslide evolutionary states,and 3D displacements,thus enabling accurate future deformation predictions.Utilizing four advanced ML algorithms,i.e.random forest(RF),support vector machine(SVM),long short-term memory(LSTM),and gated recurrent unit(GRU),with Bayesian optimization(BO)for hyperparameter tuning,we applied this innovative approach to the north-facing,slow-moving Xinpu landslide in the Three Gorges Reservoir Area(TGRA)of China.Leveraging over 6.5 years of Sentinel-1 satellite data and GNSS measurements,our framework demonstrates satisfactory and robust prediction performance,with an average root mean square deviation(RMSD)of 9.62 mm and a correlation coefficient(CC)of 0.996.This study presents a promising strategy for 3D displacement prediction,illustrating the efficacy of integrating InSAR monitoring with ML forecasting in enhancing landslide early warning capabilities.
基金The research work was financially supported by the National Natural Science Foundation of China(Grant Nos.51979238 and 52301338)the Sichuan Science and Technology Program(Grant Nos.2023NSFSC1953 and 2023ZYD0140).
文摘Mitigating vortex-induced vibrations(VIV)in flexible risers represents a critical concern in offshore oil and gas production,considering its potential impact on operational safety and efficiency.The accurate prediction of displacement and position of VIV in flexible risers remains challenging under actual marine conditions.This study presents a data-driven model for riser displacement prediction that corresponds to field conditions.Experimental data analysis reveals that the XGBoost algorithm predicts the maximum displacement and position with superior accuracy compared with Support vector regression(SVR),considering both computational efficiency and precision.Platform displacement in the Y-direction demonstrates a significant positive correlation with both axial depth and maximum displacement magnitude.The fourth point displacement exhibits the highest contribution to model prediction outcomes,showing a positive influence on maximum displacement while negatively affecting the axial depth of maximum displacement.Platform displacement in the X-and Y-directions exhibits competitive effects on both the riser’s maximum displacement and its axial depth.Through the implementation of XGBoost algorithm and SHapley Additive exPlanation(SHAP)analysis,the model effectively estimates the riser’s maximum displacement and its precise location.This data-driven approach achieves predictions using minimal,readily available data points,enhancing its practical field applications and demonstrating clear relevance to academic and professional communities.
文摘Succinylcholine(SC)is a widely used depolarizing muscle relaxant,but improper use can lead to arrhythmias and,in severe cases,pose a life-threatening risk.Additionally,some criminals exploit SC for illicit activities.Therefore,rapid SC detection is paramount for clinical practice and public safety.Currently,however,limited methods are available for the rapid detection of SC.A fluorescent indicator displacement assay sensor based on molecular recognition of an amide naphthotube was developed.This sensor enabled the rapid fluorescent detection of SC through competitive binding between SC and methylene blue with the amide naphthotube.The sensor exhibited exceptional sensitivity with a detection limit as low as 1.1μmol/L and a detection range of 1.1~60μmol/L,coupled with outstanding selectivity and robust stability.Furthermore,this sensor accurately determined SC levels in biological samples such as serum.In summary,this research provides a new solution for the rapid and accurate sensing of SC in complex matrices and offers new insights for the swift identification and detection of toxins.
文摘Imbalanced multiclass datasets pose challenges for machine learning algorithms.They often contain minority classes that are important for accurate predictions.However,when the data is sparsely distributed and overlaps with data points fromother classes,it introduces noise.As a result,existing resamplingmethods may fail to preserve the original data patterns,further disrupting data quality and reducingmodel performance.This paper introduces Neighbor Displacement-based Enhanced Synthetic Oversampling(NDESO),a hybridmethod that integrates a data displacement strategy with a resampling technique to achieve data balance.It begins by computing the average distance of noisy data points to their neighbors and adjusting their positions toward the center before applying random oversampling.Extensive evaluations compare 14 alternatives on nine classifiers across synthetic and 20 real-world datasetswith varying imbalance ratios.This evaluation was structured into two distinct test groups.First,the effects of k-neighbor variations and distance metrics are evaluated,followed by a comparison of resampled data distributions against alternatives,and finally,determining the most suitable oversampling technique for data balancing.Second,the overall performance of the NDESO algorithm was assessed,focusing on G-mean and statistical significance.The results demonstrate that our method is robust to a wide range of variations in these parameters and the overall performance achieves an average G-mean score of 0.90,which is among the highest.Additionally,it attains the lowest mean rank of 2.88,indicating statistically significant improvements over existing approaches.This advantage underscores its potential for effectively handling data imbalance in practical scenarios.
基金supported by the Science and Technology Innovation Program of Hunan Province,China(Grant No.2021RC4026)the National Natural Science Foundation of China(Grant Nos.12204538,12104507,and 92365203)Hunan Provincial Science Fund for Distinguished Young Scholars(Grant No.2022JJ10060).
文摘Diamond is a promising semiconductor material for future space exploration,owing to its unique atomic and electronic structures.However,diamond materials and related devices still suffer from irradiation damage under space irradiation involving high-energy irradiating particles.The study of the generation and evolution of point defects can help understand the irradiation damage mechanisms in diamond.This study systematically investigated the defect dynamics of diamond in 162 crystallographic directions uniformly selected on a spherical surface using molecular dynamics simulations,with primary knock-on atom(PKA)energies up to 20 keV,and temperatures ranging from 300 K to 1800 K.The results reveal that the displacement threshold energy of diamond changes periodically with crystallographic directions,which is related to the shape of potential energy surface along that direction.Additionally,the number of residual defects correlates positively with PKA energy.However,temperature has dual competing effects:while it enhances the probability of atomic displacement,it simultaneously suppresses the probability of defect formation by accelerating defect recombination.The calculation of sparse radial distribution function indicates that the defect distribution shows a certain degree of similarity in the short-range region across different PKA energies.As the PKA energy increases,defect clusters tend to become larger in size and more numerous in quantity.This study systematically investigates the anisotropy of displacement threshold energy and elucidates the relationship between various irradiation conditions and the final states of irradiation-induced defects.
基金financially supported by the National Natural Science Foundation of China(Nos.42277149,41502299,41372306)the Research Planning of Sichuan Education Department,China(No.16ZB0105)+3 种基金the State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Independent Research Project(Nos.SKLGP2016Z007,SKLGP2018Z017,SKLGP2020Z009)Chengdu University of Technology Young and Middle Aged Backbone Program(No.KYGG201720)Sichuan Provincial Science and Technology Department Program(No.19YYJC2087)China Scholarship Council。
文摘To tackle the difficulties of the point prediction in quantifying the reliability of landslide displacement prediction,a data-driven combination-interval prediction method(CIPM)based on copula and variational-mode-decomposition associated with kernel-based-extreme-learningmachine optimized by the whale optimization algorithm(VMD-WOA-KELM)is proposed in this paper.Firstly,the displacement is decomposed by VMD to three IMF components and a residual component of different fluctuation characteristics.The key impact factors of each IMF component are selected according to Copula model,and the corresponding WOA-KELM is established to conduct point prediction.Subsequently,the parametric method(PM)and non-parametric method(NPM)are used to estimate the prediction error probability density distribution(PDF)of each component,whose prediction interval(PI)under the 95%confidence level is also obtained.By means of the differential evolution algorithm(DE),a weighted combination model based on the PIs is built to construct the combination-interval(CI).Finally,the CIs of each component are added to generate the total PI.A comparative case study shows that the CIPM performs better in constructing landslide displacement PI with high performance.
基金supported in part by the Guizhou Province Science Technology Support Plan([2024]General 007,[2022]General 264,[2023]General 096,[2023]General 412,and[2023]General 409)in part by the National Natural Science Foundation of China(Grant No.61861007)+2 种基金in part by the Guizhou Province Science and Technology Planning Project(ZK[2021]General 303)in part by the Project of GUIYANG HYDROPOWER INVESTIGATION DESIGN&RESEARCH INSTITUTE CHECC(YJ2022-12)in part by the Science and Technology Project of Power Construction Corporation of China,Ltd.(DJ-ZDXM-2022-44).
文摘This research proposes an innovative solution to the inherent challenges faced by landslide displacement prediction models based on data-driven methods,such as the need for extensive historical datasets for training,the reliance on manual feature selection,and the difficulty in effectively utilizing landslide historical data.We have developed a dual-channel deep learning prediction model that integrates multimodal decomposition and an attention mechanism to overcome these challenges and improve prediction performance.The proposed methodology follows a three-stage framework:(1)Empirical Mode Decomposition(EMD)effectively segregates cumulative displacement and feature factors;(2)We have developed a Double Exponential Smoothing(DES)ensemble optimized through a Non-dominated Sorting Genetic Algorithm-II(NSGA-II)to enhance trend prediction;while employing a Bidirectional Long Short-Term Memory-Radial Basis Function(BiLSTM-RBF)network enhanced by a hybrid attention mechanism,which facilitates a global-local synergistic approach to hierarchical feature extraction,thereby improving the prediction of periodic displacements;(3)A bidirectional adaptive feature extraction mechanism aligns attention weights with BiLSTM propagation paths through spatial mapping,complemented by an innovative loss function incorporating Prediction Interval(PI)width optimization.In the comparative experiments of the Baishuihe landslide:the RMSE,MAE,and R^(2) indexes of monitoring point ZG118 are improved by 19.8%,35.2%,and 3.2%compared with the optimal baseline model(RBF-MIC);in the monitoring point ZG93,where the amount of data is less,the three indexes are even more improved by 52.1%,32.3%,and 21.8%compared with the optimal baseline model(GRU-None).These results substantiate the model’s capacity to overcome dual constraints of data paucity and feature engineering limitations in geohazard prediction.
基金The National Key Research and Development Program of China grant No.2022YFB3706704 received by Yuan Renthe National Natural and Science Foundation of China grant No.52308150 received by Xiang Xu.
文摘To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specifically based on the Long Short-Term Memory(LSTM)network,to predict temperature-induced girder end displacements of the Dasha Waterway Bridge,a suspension bridge in China.First,to enhance data quality and select target sensors,preprocessing based on the sigma rule and nearest neighbor interpolation is applied to the raw data.Furthermore,to eliminate the high-frequency components from the displacement signal,the wavelet transform is conducted.Subsequently,the linear regression model and ANN model are established,whose results do not meet the requirements and fail to address the time lag effect between temperature and displacements.The study proceeds to develop the LSTM network model and determine the optimal parameters through hyperparameter sensitivity analysis.Finally,the results of the LSTM network model are discussed by a comparative analysis against the linear regression model and ANN model,which indicates a higher accuracy in predicting temperatureinduced girder end displacements and the ability to mitigate the time-lag effect.To be more specific,in comparison between the linear regression model and LSTM network,the mean square error decreases from 6.5937 to 1.6808 and R^(2) increases from 0.683 to 0.930,which corresponds to a 74.51%decrease in MSE and a 36.14%improvement in R^(2).Compared to ANN,with an MSE of 4.6371 and an R^(2) of 0.807,LSTM shows a decrease in MSE of 63.75%and an increase in R^(2) of 13.23%,demonstrating a significant enhancement in predictive performance.
基金supported by the National Natural Science Foundation of China (Grant Nos.12120101005,U2030104,12175174,11975174,and 12105229)State Key Laboratory Foundation of Laser Interaction with Matter (Grant Nos.SKLLIM1807 and SKLLIM2106)+1 种基金the Postdoctoral Fellowship Program of CPSF (Grant No.GZC20241372)National Key Laboratory of Intense Pulsed Radiation Simulation and Effect (Grant No.NKLIPR2419)。
文摘Irradiation experiments on p-Ga N gate high-electron-mobility transistors(HEMTs) were conducted using neutrons at Back-streaming White Neutron(Back-n) facility at the China Spallation Neutron Source(CSNS).Two groups of devices were float-biased,while one group was ON-biased.Post-irradiation analysis revealed that the electrical performance of the devices exhibited progressive degradation with increasing Back-n fluence,with the ON-biased group demonstrating the most pronounced deterioration.This degradation was primarily characterized by a negative shift in the threshold voltage,a significant increase in reverse gate leakage current,and a slight reduction in forward gate leakage.Further analysis of the gate leakage current and capacitance-voltage characteristics indicated an elevated concentration of two-dimensional electron gas(2DEG),attributed to donor-type defects introduced within the barrier layer by Back-n irradiation.These defects act as hole traps,converting into fixed positive charges that deepen the quantum-well conduction band,thereby enhancing the 2DEG density.Additionally,through the trap-assisted tunneling mechanism,these defects serve as tunneling centers,increasing the probability of electron tunneling and consequently elevating the reverse gate leakage current.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R848)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabiathe Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia for funding this research work through the project number“NBU-FFR-2025-2932-09”.
文摘License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition Method(DR2M)to address such a problem.This method operates on displaced features compared to the training input observed throughout definite time frames.The technique focuses on detecting features that remain relatively stable under haze,using a frame-based analysis to isolate edges minimally affected by visual noise.The edge detection failures are identified using a bilateral neural network through displaced feature training.The training converges bilaterally towards the minimum edges from the maximum region.Thus,the training input and detected edges are used to identify the displacement between observed image frames to extract and differentiate the license plate region from the other vehicle regions.The proposed method maps the similarity feature between the detected and identified vehicle regions.This aids in leveraging the plate recognition precision with a high F1 score.Thus,this technique achieves a 10.27%improvement in identification precision,a 10.57%increase in F1 score,and a 9.73%reduction in false positive rate compared to baseline methods under maximum displacement conditions caused by haze.The technique attains an identification precision of 95.68%,an F1 score of 94.68%,and a false positive rate of 4.32%,indicating robust performance under haze-affected settings.
文摘This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-precision laser interferometric displacement measurement.A stable power supply module is designed to provide low-noise voltage to the entire circuit.An analog circuit system is constructed,including key circuits such as photoelectric sensors,I-V amplification,zero adjustment,fully differential amplification,and amplitude modulation filtering.To acquire and process signals,the PMAC Acc24E3 data acquisition card is selected,which realizes phase demodulation through reversible square wave counting,inverts displacement information,and a visual interface for the host computer is designed.Experimental verification shows that the designed system achieves micrometer-level measurement accuracy within a range of 0-10mm,with a maximum measurement error of less than 1.2μm,a maximum measurement speed of 6m/s,and a resolution better than 0.158μm.
基金the Biomedical Science and Technology Support Special Project of Shanghai Science and Technology Committee(No.20S31908300)。
文摘Measurement precision of laser displacement sensor is subject to various factors,among which laser jitter and target tilt will directly lead to the position movement and shape variation of the laser spot,resulting in displacement measurement errors,so that researchers have to do a lot of research on the spot centering algorithm to weaken the above effects,which can treat the symptoms but not the root cause.Starting from the source of the problem,this paper proposes a double focus double peak solution,which uses a reflector to change the direction of the optical path,so that the imaging spots of the designed two optical paths focus on the same CMOS,forming a double peak structure.When laser jitter or target tilt occurs,the center of the two laser spots is shifted,but they move in the same direction,while their relative position remains unchanged.Therefore,the displacement can be characterized by the relative position of the two laser spots,so that laser jitter and target tilt are suppressed from the source.However,the two spots imaged on CMOS form a non-Gaussian distributed double peak structure,so the conventional laser spot centering algorithms are no longer applicable.To this end,a double peak adaptive threshold waveform extraction method combined with grayscale gravity method is proposed for spot centering algorithm,which combines the suppression of laser jitter and target tilt from the source and the improvement of spot positioning precision which represents the displacement measurement precision,and is experimentally verified.
基金supported by the National Key R&D Program of China (No.2022YFC3004602)the National Natural Science Foundation of China (No.52325404)the Shenzhen Science and Technology Program (No.JCYJ20220818095605012).
文摘Rock discontinuities such as joints widely exist in natural rock masses,and wave attenuation through rock masses is mainly caused by discontinuities.The displacement discontinuity model(DDM)has been widely used in theoretical and numerical analysis of wave propagation across rock discontinuity.However,the circumstance under which the DDM is applicable to predict wave propagation across rock discontinuity remains poorly understood.In this study,theoretical analysis and ultrasonic laboratory tests were carried out to examine the theoretical applicability of the DDM for wave propagation,where specimens with rough joints comprising regular rectangular asperities of different spacings and heights were prepared by 3D printing technology.It is found that the theoretical applicability of the DDM to predict wave propagation across rock discontinuity is determined by three joint parameters,i.e.the dimensionless asperity spacing(L),the dimensionless asperity height(H)and the groove density(D).Through theoretical analysis and laboratory tests,the conditions under which the DDM is applicable are derived as follows:and,.With increase in the groove density,the thresholds of the dimensionless asperity spacing and the dimensionless asperity height show a decreasing trend.In addition,the transmission coefficient in the frequency domain decreases with increasing groove density,dimensionless asperity spacing or dimensionless asperity height.The findings can facilitate our understanding of DDM for predicting wave propagation across rock discontinuity.
基金National Natural Science Foundation of China under Grant No.52322808the Fundamental Research Funds for the Central Universities under Grant No.B220202013。
文摘Collapses of seismic slopes demonstrate the characteristics of three-dimensional(3D)shapes.Conducting a 3D analysis of seismic slope stability is more complicated than doing a simplified two-dimensional(2D)analysis.The upper-bound solutions derived from limit analysis of seismic slopes using the pseudo-static method are used to generate an approximate solution for the factor of 3D safety through regression analysis.Such a solution can degenerate to a 2D result when the slope width tends to infinity.The approximation method also can be extended for determining the permanent displacements of 3D slopes under seismic loading.The method is non-iterative and relatively accurate through comparisons with analytical results.Involving stochastic ground motions could easily be used to assess the distribution of permanent displacement that is induced in 3D slopes.
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd.(Grant No.H20230317).
文摘Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12402493,U2340216,52020105006 and 12272281)supported by the China Postdoctoral Science Foundation(Grant Nos.2024M752476,2025T180862)the Postdoctoral Project of Hubei Province(Grant No.2024HBBHCXA060).
文摘The random displacement model(RDM)can efficiently simulate particle transport processes,which are difficult to observe,incorporating stochastic and hydraulic parameters.In recent decades,it has been used in many domains,including environments,hydraulics,and ecology.However,the results exhibit significant uncertainties arising from the model resolution,hydrodynamic accuracy,intrinsic characteristics of particles,and boundary conditions.The objective of the present study is to comprehensively interpret the RDM from theory to application,and emphasize essential considerations for users in different domains.The study also provides several application strategies for the model,based on several practical RDM cases.Determining the turbulent diffusivity and velocity profiles in complex flow field is a critical step to precisely simulate particle movement.Furthermore,the physical and biological properties of passive and active particles require fundamental investigation to extend the applicability of the model.Existing studies suggest that flexibly coupling the RDM with other numerical models customized to the characteristics of distinct problems will substantially expand the utility of the RDM and could yield innovative approaches for addressing previously intractable issues.
基金the University of Shanghai for Science and Technology’s Medical Engineering Interdisciplinary Project(No.10-22-308-520)the Ministry of Education’s First Batch of Industry-Education Cooperation Collaborative Education Projects(No.202101042008)+1 种基金the Fundamental Research Funds for the Central Universities(No.YG2019QNA34)the Shanghai Municipal Health Commission for Youth Clinical Research Project(No.20194Y0134)。
文摘The purpose of this study is to establish a multivariate nonlinear regression mathematical model to predict the displacement of tumor during brain tumor resection surgery.And the study will be integrated with augmented reality technology to achieve three-dimensional visualization,thereby enhancing the complete resection rate of tumor and the success rate of surgery.Based on the preoperative MRI data of the patients,a 3D virtual model is reconstructed and 3D printed.A brain biomimetic model is created using gel injection molding.By considering cerebrospinal fluid loss and tumor cyst fluid loss as independent variables,the highest point displacement in the vertical bone window direction is determined as the dependent variable after positioning the patient for surgery.An orthogonal experiment is conducted on the biomimetic model to establish a predictive model,and this model is incorporated into the augmented reality navigation system.To validate the predictive model,five participants wore HoloLens2 devices,overlaying the patient’s 3D virtual model onto the physical head model.Subsequently,the spatial coordinates of the tumor’s highest point after displacement were measured on both the physical and virtual models(actual coordinates and predicted coordinates,respectively).The difference between these coordinates represents the model’s prediction error.The results indicate that the measured and predicted errors for the displacement of the tumor’s highest point on the X and Y axes range from−0.6787 mm to 0.2957 mm and−0.4314 mm to 0.2253 mm,respectively.The relative errors for each experimental group are within 10%,demonstrating a good fit of the model.This method of establishing a regression model represents a preliminary attempt to predict brain tumor displacement in specific situations.It also provides a new approach for surgeons.By combining augmented reality visualization,it addresses the need for predicting tumor displacement and precisely locating brain anatomical structures in a simple and cost-effective manner.
基金The Young Scientists Fund of the National Natural Science Foundation of China(Grant No.42407250)the Fund from Research Centre for Resources Engineering towards Carbon Neutrality(RCRE)of The Hong Kong Polytechnic University(Grant No.No.1-BBEM)the Fund from Natural Science Foundation of Jiangsu Province(Grant No.BK20241211)。
文摘The commonly used method for estimating crack opening displacement(COD)is based on analytical models derived from strain transferring.However,when large background noise exists in distributed fiber optic sensing(DFOS)data,estimating COD through an analytical model is very difficult even if the DFOS data have been denoised.To address this challenge,this study proposes a machine learning(ML)-based methodology to complete rock's COD estimation from establishment of a dataset with one-to-one correspondence between strain sequence and COD to the optimization of ML models.The Bayesian optimization is used via the Hyperopt Python library to determine the appropriate hyper-parameters of four ML models.To ensure that the best hyper-parameters will not be missing,the configuration space in Hyperopt is specified by probability distribution.The four models are trained using DFOS data with minimal noise while being examined on datasets with different noise levels to test their anti-noise robustness.The proposed models are compared each other in terms of goodness of fit and mean squared error.The results show that the Bayesian optimization-based random forest is promising to estimate the COD of rock using noisy DFOS data.
基金National Science Foundation of China,Grant/Award Number:5227090113Shenzhen Science and Technology Program,Grant/Award Numbers:KCXFZ20230731093901003,KCXFZ20211020163816023The Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone,Grant/Award Number:HZQB-KCZYB-2020083。
文摘The two-phase flow in porous media is affected by multiple factors.In the present study,a two-dimensional numerical model of porous media was developed using the actual pore structure of the core sample.The phase field method was utilized to simulate the impact of displacement velocity,the water-gas viscosity ratio,and the density ratio on the flow behavior of two-phase fluids in porous media.The effectiveness of displacement was evaluated by analyzing CO_(2)saturation levels.The results indicate that the saturation of CO_(2)in porous media increased as the displacement velocity increased.When the displacement velocity exceeded 0.01 m/s,there was a corresponding increase in CO_(2)saturation.Conversely,when the displacement velocity was below this threshold,the impact on CO_(2)saturation was minimal.An“inflection point,”M3,was present in the viscosity ratio.When the viscosity of CO_(2)is less than 8.937×10^(-5)Pa·s(viscosity ratio below M3),variations in the viscosity of CO_(2)had little impact on its saturation.Conversely,when the viscosity of CO_(2)exceeded 8.937×10^(-5)Pa·s(viscosity ratio greater than M3),saturation increased with an increase in the viscosity ratio.In terms of the density ratio,the saturation of CO_(2)increased monotonically with an increase in the density ratio.Similarly,increasing density ratios resulted in a monotonic increase in CO_(2)saturation,though this trend was less pronounced in numerical simulations.Analysis results of displacement within dead-end pores using pressure and velocity diagrams reveal eddy currents as contributing factors.Finally,the impact of pore throat structure on the formation of dominant channels was examined.
