By scanning modulated or un-modulated earthquakes spatio-temporally in the region of Sichuan-Yunnan,short-term non-stationary seismic precursory patterns were extracted with significant difference and the characterist...By scanning modulated or un-modulated earthquakes spatio-temporally in the region of Sichuan-Yunnan,short-term non-stationary seismic precursory patterns were extracted with significant difference and the characteristic of non-stationary short-term seismic anomalies were analyzed as well as prediction efficiency of modulated small earthquakes before a strong earthquake. Besides,small earthquake modulation ratios near the region of the epicenter were calculated and sorted by time. The results indicated that there were significant effects using the modulated earthquake method to predict earthquakes greater than MS6. 0 in a short time. Before the MS8. 0 Wenchuan earthquake,there were obvious short-term precursory seismicity gap patterns of modulated small earthquakes.展开更多
The fluctuating planetary gravitational field influences not only activities on the Sun but also on the Earth. A special correlation function describes the harmonics of these fluctuations. Groups of earthquakes form o...The fluctuating planetary gravitational field influences not only activities on the Sun but also on the Earth. A special correlation function describes the harmonics of these fluctuations. Groups of earthquakes form oscillation patterns that differ significantly from randomly chosen control groups. These patterns are suitable as an element of an AI for the probability of earthquakes.展开更多
Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same g...Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.展开更多
Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currentl...Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currently,least squares(LS)+auto-regressive(AR)hybrid method is one of the main techniques of PM prediction.Besides,the weighted LS+AR hybrid method performs well for PM short-term prediction.However,the corresponding covariance information of LS fitting residuals deserves further exploration in the AR model.In this study,we have derived a modified stochastic model for the LS+AR hybrid method,namely the weighted LS+weighted AR hybrid method.By using the PM data products of IERS EOP 14 C04,the numerical results indicate that for PM short-term forecasting,the proposed weighted LS+weighted AR hybrid method shows an advantage over both the LS+AR hybrid method and the weighted LS+AR hybrid method.Compared to the mean absolute errors(MAEs)of PMX/PMY sho rt-term prediction of the LS+AR hybrid method and the weighted LS+AR hybrid method,the weighted LS+weighted AR hybrid method shows average improvements of 6.61%/12.08%and 0.24%/11.65%,respectively.Besides,for the slopes of the linear regression lines fitted to the errors of each method,the growth of the prediction error of the proposed method is slower than that of the other two methods.展开更多
With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning ...With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.展开更多
With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting m...With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.展开更多
BACKGROUND Endometrial cancer(EC)is a common gynecological malignancy that typically requires prompt surgical intervention;however,the advantage of surgical management is limited by the high postoperative recurrence r...BACKGROUND Endometrial cancer(EC)is a common gynecological malignancy that typically requires prompt surgical intervention;however,the advantage of surgical management is limited by the high postoperative recurrence rates and adverse outcomes.Previous studies have highlighted the prognostic potential of circulating tumor DNA(ctDNA)monitoring for minimal residual disease in patients with EC.AIM To develop and validate an optimized ctDNA-based model for predicting shortterm postoperative EC recurrence.METHODS We retrospectively analyzed 294 EC patients treated surgically from 2015-2019 to devise a short-term recurrence prediction model,which was validated on 143 EC patients operated between 2020 and 2021.Prognostic factors were identified using univariate Cox,Lasso,and multivariate Cox regressions.A nomogram was created to predict the 1,1.5,and 2-year recurrence-free survival(RFS).Model performance was assessed via receiver operating characteristic(ROC),calibration,and decision curve analyses(DCA),leading to a recurrence risk stratification system.RESULTS Based on the regression analysis and the nomogram created,patients with postoperative ctDNA-negativity,postoperative carcinoembryonic antigen 125(CA125)levels of<19 U/mL,and grade G1 tumors had improved RFS after surgery.The nomogram’s efficacy for recurrence prediction was confirmed through ROC analysis,calibration curves,and DCA methods,highlighting its high accuracy and clinical utility.Furthermore,using the nomogram,the patients were successfully classified into three risk subgroups.CONCLUSION The nomogram accurately predicted RFS after EC surgery at 1,1.5,and 2 years.This model will help clinicians personalize treatments,stratify risks,and enhance clinical outcomes for patients with EC.展开更多
Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and a...Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and accurate train delay predictions,facilitated by data-driven neural network models,can significantly reduce dispatcher stress and improve adjustment plans.Leveraging current train operation data,these models enable swift and precise predictions,addressing challenges posed by train delays in high-speed rail networks during unforeseen events.Design/methodology/approach-This paper proposes CBLA-net,a neural network architecture for predicting late arrival times.It combines CNN,Bi-LSTM,and attention mechanisms to extract features,handle time series data,and enhance information utilization.Trained on operational data from the Beijing-Tianjin line,it predicts the late arrival time of a target train at the next station using multidimensional input data from the target and preceding trains.Findings-This study evaluates our model’s predictive performance using two data approaches:one considering full data and another focusing only on late arrivals.Results show precise and rapid predictions.Training with full data achieves aMAEof approximately 0.54 minutes and a RMSEof 0.65 minutes,surpassing the model trained solely on delay data(MAE:is about 1.02 min,RMSE:is about 1.52 min).Despite superior overall performance with full data,the model excels at predicting delays exceeding 15 minutes when trained exclusively on late arrivals.For enhanced adaptability to real-world train operations,training with full data is recommended.Originality/value-This paper introduces a novel neural network model,CBLA-net,for predicting train delay times.It innovatively compares and analyzes the model’s performance using both full data and delay data formats.Additionally,the evaluation of the network’s predictive capabilities considers different scenarios,providing a comprehensive demonstration of the model’s predictive performance.展开更多
It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage pre...It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage predictor(EPDor)based on predicting peak ground velocities(PGVs)of sites.The EPDor is composed of three parts:(1)predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models;(2)predicting the PGVs at distant sites based on the empirical ground motion prediction equation;(3)generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in(1)and(2).We apply the EPDor to the 2022 M_(S) 6.9 Menyuan earthquake in Qinghai Province,China to predict its potential damage.Within the initial few seconds after the first station is triggered,the EPDor can determine directly whether there is potential damage for some sites to a certain degree.Hence,we infer that the EPDor has potential application for future earthquakes.Meanwhile,it also has potential in Chinese earthquake early warning system.展开更多
In this paper, the process of medium- and short-term prediction (submitted in special cards) of the Artux earthquake (MS=6.9) and the Usurian earthquake (MS=5.8) in Xinjiang area, is introduced. The imminent seismic r...In this paper, the process of medium- and short-term prediction (submitted in special cards) of the Artux earthquake (MS=6.9) and the Usurian earthquake (MS=5.8) in Xinjiang area, is introduced. The imminent seismic risk regions are judged based on long- and medium-term seismic risk regions and annual seismic risk regions determined by national seismologic analysis, combined with large seismic situation analysis. We trace and analyze the seismic situation in large areas, and judge principal risk regions or belts of seismic activity in a year, by integrating the large area’s seismicity with geodetic deformation evolutional characteristics. As much as possible using information, we study synthetically observational information for long-medium- and short-term (time domain) and large-medium -small dimensions (space domain), and approach the forecast region of forthcoming earthquakes from the large to small magnitude. A better effect has been obtained. Some questions about earthquake prediction are discussed.展开更多
The field of neural network has found solid application in the past ten years and the field itself is still developing rapidly. Neural network is composed of many simple elements operating in parallel. A neural netwo...The field of neural network has found solid application in the past ten years and the field itself is still developing rapidly. Neural network is composed of many simple elements operating in parallel. A neural network can be trained to perform a particular mapping and this is the basis of its application to practical problems. In this paper, new methods for predicting the strong earthquakes are presented based on neural network. Neural network learns from existing earthquake sequences or earthquake precursors how to make medium and short term prediction of strong earthquakes. This paper describes two neural network prediction models. One is the model based on earthquake evolution sequences, which is applied to the modeling of the magnitude evolution sequences in the Mainland of China, the other is based on earthquake precursors, which is applied to the modeling of the occurrence time of strong earthquakes in North China. Test results show that the prediction methods based on neural networks are efficient, and convenient. They would find more application in the future.展开更多
Based on the data recorded by the regional digital seismic network of Yunnan and using new methods, the short-term variations of the ambient stress field of Yunnan and its adjacent areas are monitored in real time. Wi...Based on the data recorded by the regional digital seismic network of Yunnan and using new methods, the short-term variations of the ambient stress field of Yunnan and its adjacent areas are monitored in real time. With the in-depth analyses of the spatial-temporal evolution of the ambient stress field prior to the 2004, Shuangbai M_S5.0 earthquake, concrete procedures for predicting the three elements of the earthquake are presented.展开更多
The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning mode...The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning models have some problems,such as poor nonlinear performance,local optimum and incomplete factors feature extraction.These issues can affect the accuracy of slope stability prediction.Therefore,a deep learning algorithm called Long short-term memory(LSTM)has been innovatively proposed to predict slope stability.Taking the Ganzhou City in China as the study area,the landslide inventory and their characteristics of geotechnical parameters,slope height and slope angle are analyzed.Based on these characteristics,typical soil slopes are constructed using the Geo-Studio software.Five control factors affecting slope stability,including slope height,slope angle,internal friction angle,cohesion and volumetric weight,are selected to form different slope and construct model input variables.Then,the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors.Each slope stability coefficient and its corresponding control factors is a slope sample.As a result,a total of 2160 training samples and 450 testing samples are constructed.These sample sets are imported into LSTM for modelling and compared with the support vector machine(SVM),random forest(RF)and convo-lutional neural network(CNN).The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features.Furthermore,LSTM has a better prediction performance for slope stability compared to SVM,RF and CNN models.展开更多
The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine l...The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine learning(ML)models effectively deal with such challenges.This research paper comprehensively analyses recent advancements in crop yield prediction from January 2016 to March 2024.In addition,it analyses the effectiveness of various input parameters considered in crop yield prediction models.We conducted an in-depth search and gathered studies that employed crop modeling and AI-based methods to predict crop yield.The total number of articles reviewed for crop yield prediction using ML,meta-modeling(Crop models coupled with ML/DL),and DL-based prediction models and input parameter selection is 125.We conduct the research by setting up five objectives for this research and discussing them after analyzing the selected research papers.Each study is assessed based on the crop type,input parameters employed for prediction,the modeling techniques adopted,and the evaluation metrics used for estimatingmodel performance.We also discuss the ethical and social impacts of AI on agriculture.However,various approaches presented in the scientific literature have delivered impressive predictions,they are complicateddue to intricate,multifactorial influences oncropgrowthand theneed for accuratedata-driven models.Therefore,thorough research is required to deal with challenges in predicting agricultural output.展开更多
Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep lear...Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.展开更多
Based on the extraction and calculation of the short-term seismic precursory information magnitude from the 114 major precursory observations in the North China region, and together with consideration of factors such ...Based on the extraction and calculation of the short-term seismic precursory information magnitude from the 114 major precursory observations in the North China region, and together with consideration of factors such as geological structure, seismicity, crustal thickness, and in particular, the current geodynamics of the region, the authors studied the time-space evolution characteristics of the short-term earthquake precursory information magnitude and its relationship with earthquakes and proposed the index and method for the short-term synthetic prediction of earthquakes with M S≥5.0 in the North China region. The inspection through R-value shows that the method is effective to a certain extent for earthquake prediction.展开更多
The peak ground acceleration (PGA), the volume of a sliding mass V, the height of a mountain HL and the slope angle θ of a mountain are four important parameters affecting the horizontal run-out distance of a lands...The peak ground acceleration (PGA), the volume of a sliding mass V, the height of a mountain HL and the slope angle θ of a mountain are four important parameters affecting the horizontal run-out distance of a landslide L. Correlations among them are studied statistically based on field investigations from 67 landslides triggered by the ground shaking and other factors during the Wenchuan earthquake, and then a prediction model for horizontal run-out distance L is developed in this study. This model gives due consideration to the implications of the above four parameters on the horizontal run-out distance L and the validity of the model is verified by the Donghekou and Magong Woqian landslides. At the same time, the advantages of the model are shown by comparing it with two other common prediction methods. The major findings drawn from the analyses and comparisons are: (1) an exponential relationship exists between L and log V, L and log HL, L and log PGA separately, but a negative exponential relationship exists between L and log tan0, which agrees with the statistical results; and (2) according to the analysis results of the relative relationship between the height of a mountain (H) and the place where the landslides occur, the probabilities at distances of2H/3-H, H/3-2H/3, and O-H/3 are 70.8%, 15.4%, and 13.8%, respectively, revealing that most landslides occurred at a distance of H/2-H. This prediction model can provide an effective technical support for the prevention and mitigation of landslide hazards.展开更多
The ratio of P- to S-wave velocities (Vp/Vs) is regarded as one of the most diagnostic properties of natural rocks. It has been used as a discriminant of composition for the continental crust and provides valuable c...The ratio of P- to S-wave velocities (Vp/Vs) is regarded as one of the most diagnostic properties of natural rocks. It has been used as a discriminant of composition for the continental crust and provides valuable constraints on its formation and evolution processes. Furthermore, the spatial and temporal changes in Vp/Vs before and after earthquakes are probably the most promising avenue to understanding the source mechanics and possibly predicting earthquakes. Here we calibrate the variations in Vp/Vs in dry, anisotropic crustal rocks and provide a set of basic information for the interpretation of future seismic data from the Wenchuan earthquake Fault zone Scientific Drilling (WFSD) project and other surveys. Vp/Vs is a constant (Ф0) for an isotropic rock. However, most of crustal rocks are anisotropic due to lattice-preferred orientations of anisotropic minerals (e.g., mica, amphibole, plagioclase and pyroxene) and cracks as well as thin compositional layering. The Vp/Vs ratio of an anisotropic rock measured along a selected pair of propagation-vibration directions is an apparent value (Фy) that is significantly different from the value for its isotropic counterpart (Ф0). The usefulness of apparent Vp/Vs ratios as a diagnostic of crustal composition depends largely on rock seismic anisotropy. A 5% of P- and S-wave velocity anisotropy is sufficient to make it impossible to determine the crustal composition using the conventional criteria (Vp/Vs≤1.756 for felsic rocks, 1.756〈Vp/Vs≤1.809 for intermediate rocks, 1.809〈Vp/Vs≤1.944 for mafic rocks, and Vp/V2〉1.944 fluidfilled porous/fractured or partially molten rocks) if the information about the wave propagation-polarization directions with respect to the tectonic framework is unknown. However, the variations in Vp/Vs measured from borehole seismic experiments can be readily interpreted according to the orientations of the ray path and the polarization of the shear waves with respect to the present-day principal stress directions (i.e., the orientation of cracks) and the frozen fabric (i.e., foliation and lineation).展开更多
The relation between plate tectonics and earthquake evolution is analyzed systematically on the basis of 1998-2010 absolute and relative gravity data from the Crustal Movement Observation Network of China. Most earthq...The relation between plate tectonics and earthquake evolution is analyzed systematically on the basis of 1998-2010 absolute and relative gravity data from the Crustal Movement Observation Network of China. Most earthquakes originated in the plate boundary or within the fault zone. Tectonic deformation was most intense and exhibited discontinuity within the tectonically active fault zone because of the differential movement; the stress accumulation produced an abrupt gravity change, which was further enhanced by the earthquake. The gravity data from China's Mainland since 2000 obviously reflected five major earthquakes (Ms 〉 7), all of which were better reflected than before 2000. Regional gravity anomalies and a gravity gradient change were observed in the area around the epicenter about 2 or 3 years before the earthquake occurred, suggesting that gravity change may be a seismic precursor. Furthermore, in this study, the medium-term predictions of the Ms7.3 Yutian, Ms8.0 Wenchuan, and Ms7.0 Lushan earthquakes are analytically pre- sented and evaluated, especially to estimate location of earthquake.展开更多
The study in this paper analyzes and compares the distribution on the global engine active seismic zone and cooling seismic belt basing on the ANSS earthquake catalog from Northern California Earthquake Data Center. A...The study in this paper analyzes and compares the distribution on the global engine active seismic zone and cooling seismic belt basing on the ANSS earthquake catalog from Northern California Earthquake Data Center. An idea of the seismogenesis and earthquake prediction research is achieved by showing the stratigraphic structure in the hot engine belt. The results show that the main engine and its seismic cones are the global seismic activity area, as well as the subject of global geological disaster. Based on the conjecture of other stratum structure, the energy of crustal strong earthquake and volcano activities probably originates from the deep upper mantle. It is suggested that the research on earthquake and volcano prediction should focus on the monitor and analysis on the sub-crustal earthquake activities.展开更多
基金supported by the National Basic ResearchProgram (973 Program),entitled Global deep geophysical field and the relation between its geodynamic effect and Wenchuan Earthquake
文摘By scanning modulated or un-modulated earthquakes spatio-temporally in the region of Sichuan-Yunnan,short-term non-stationary seismic precursory patterns were extracted with significant difference and the characteristic of non-stationary short-term seismic anomalies were analyzed as well as prediction efficiency of modulated small earthquakes before a strong earthquake. Besides,small earthquake modulation ratios near the region of the epicenter were calculated and sorted by time. The results indicated that there were significant effects using the modulated earthquake method to predict earthquakes greater than MS6. 0 in a short time. Before the MS8. 0 Wenchuan earthquake,there were obvious short-term precursory seismicity gap patterns of modulated small earthquakes.
文摘The fluctuating planetary gravitational field influences not only activities on the Sun but also on the Earth. A special correlation function describes the harmonics of these fluctuations. Groups of earthquakes form oscillation patterns that differ significantly from randomly chosen control groups. These patterns are suitable as an element of an AI for the probability of earthquakes.
基金funded by the Fujian Province Science and Technology Plan,China(Grant Number 2019H0017).
文摘Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.
基金supported by National Natural Science Foundation of China,China(No.42004016)HuBei Natural Science Fund,China(No.2020CFB329)+1 种基金HuNan Natural Science Fund,China(No.2023JJ60559,2023JJ60560)the State Key Laboratory of Geodesy and Earth’s Dynamics self-deployment project,China(No.S21L6101)。
文摘Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currently,least squares(LS)+auto-regressive(AR)hybrid method is one of the main techniques of PM prediction.Besides,the weighted LS+AR hybrid method performs well for PM short-term prediction.However,the corresponding covariance information of LS fitting residuals deserves further exploration in the AR model.In this study,we have derived a modified stochastic model for the LS+AR hybrid method,namely the weighted LS+weighted AR hybrid method.By using the PM data products of IERS EOP 14 C04,the numerical results indicate that for PM short-term forecasting,the proposed weighted LS+weighted AR hybrid method shows an advantage over both the LS+AR hybrid method and the weighted LS+AR hybrid method.Compared to the mean absolute errors(MAEs)of PMX/PMY sho rt-term prediction of the LS+AR hybrid method and the weighted LS+AR hybrid method,the weighted LS+weighted AR hybrid method shows average improvements of 6.61%/12.08%and 0.24%/11.65%,respectively.Besides,for the slopes of the linear regression lines fitted to the errors of each method,the growth of the prediction error of the proposed method is slower than that of the other two methods.
文摘With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.
基金funded by Liaoning Provincial Department of Science and Technology(2023JH2/101600058)。
文摘With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.
文摘BACKGROUND Endometrial cancer(EC)is a common gynecological malignancy that typically requires prompt surgical intervention;however,the advantage of surgical management is limited by the high postoperative recurrence rates and adverse outcomes.Previous studies have highlighted the prognostic potential of circulating tumor DNA(ctDNA)monitoring for minimal residual disease in patients with EC.AIM To develop and validate an optimized ctDNA-based model for predicting shortterm postoperative EC recurrence.METHODS We retrospectively analyzed 294 EC patients treated surgically from 2015-2019 to devise a short-term recurrence prediction model,which was validated on 143 EC patients operated between 2020 and 2021.Prognostic factors were identified using univariate Cox,Lasso,and multivariate Cox regressions.A nomogram was created to predict the 1,1.5,and 2-year recurrence-free survival(RFS).Model performance was assessed via receiver operating characteristic(ROC),calibration,and decision curve analyses(DCA),leading to a recurrence risk stratification system.RESULTS Based on the regression analysis and the nomogram created,patients with postoperative ctDNA-negativity,postoperative carcinoembryonic antigen 125(CA125)levels of<19 U/mL,and grade G1 tumors had improved RFS after surgery.The nomogram’s efficacy for recurrence prediction was confirmed through ROC analysis,calibration curves,and DCA methods,highlighting its high accuracy and clinical utility.Furthermore,using the nomogram,the patients were successfully classified into three risk subgroups.CONCLUSION The nomogram accurately predicted RFS after EC surgery at 1,1.5,and 2 years.This model will help clinicians personalize treatments,stratify risks,and enhance clinical outcomes for patients with EC.
基金supported in part by the National Natural Science Foundation of China under Grant 62203468in part by the Technological Research and Development Program of China State Railway Group Co.,Ltd.under Grant Q2023X011+1 种基金in part by the Young Elite Scientist Sponsorship Program by China Association for Science and Technology(CAST)under Grant 2022QNRC001in part by the Youth Talent Program Supported by China Railway Society,and in part by the Research Program of China Academy of Railway Sciences Corporation Limited under Grant 2023YJ112.
文摘Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and accurate train delay predictions,facilitated by data-driven neural network models,can significantly reduce dispatcher stress and improve adjustment plans.Leveraging current train operation data,these models enable swift and precise predictions,addressing challenges posed by train delays in high-speed rail networks during unforeseen events.Design/methodology/approach-This paper proposes CBLA-net,a neural network architecture for predicting late arrival times.It combines CNN,Bi-LSTM,and attention mechanisms to extract features,handle time series data,and enhance information utilization.Trained on operational data from the Beijing-Tianjin line,it predicts the late arrival time of a target train at the next station using multidimensional input data from the target and preceding trains.Findings-This study evaluates our model’s predictive performance using two data approaches:one considering full data and another focusing only on late arrivals.Results show precise and rapid predictions.Training with full data achieves aMAEof approximately 0.54 minutes and a RMSEof 0.65 minutes,surpassing the model trained solely on delay data(MAE:is about 1.02 min,RMSE:is about 1.52 min).Despite superior overall performance with full data,the model excels at predicting delays exceeding 15 minutes when trained exclusively on late arrivals.For enhanced adaptability to real-world train operations,training with full data is recommended.Originality/value-This paper introduces a novel neural network model,CBLA-net,for predicting train delay times.It innovatively compares and analyzes the model’s performance using both full data and delay data formats.Additionally,the evaluation of the network’s predictive capabilities considers different scenarios,providing a comprehensive demonstration of the model’s predictive performance.
基金financially supported by the National Natural Science Foundation of China (U2039209, U1839208, and 51408564)the Natural Science Foundation of Heilongjiang Province (LH2021E119)+1 种基金Spark Program of Earthquake Science (XH23027YB)the National Key Research and Development Program of China (2018YFC1504003).
文摘It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage predictor(EPDor)based on predicting peak ground velocities(PGVs)of sites.The EPDor is composed of three parts:(1)predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models;(2)predicting the PGVs at distant sites based on the empirical ground motion prediction equation;(3)generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in(1)and(2).We apply the EPDor to the 2022 M_(S) 6.9 Menyuan earthquake in Qinghai Province,China to predict its potential damage.Within the initial few seconds after the first station is triggered,the EPDor can determine directly whether there is potential damage for some sites to a certain degree.Hence,we infer that the EPDor has potential application for future earthquakes.Meanwhile,it also has potential in Chinese earthquake early warning system.
文摘In this paper, the process of medium- and short-term prediction (submitted in special cards) of the Artux earthquake (MS=6.9) and the Usurian earthquake (MS=5.8) in Xinjiang area, is introduced. The imminent seismic risk regions are judged based on long- and medium-term seismic risk regions and annual seismic risk regions determined by national seismologic analysis, combined with large seismic situation analysis. We trace and analyze the seismic situation in large areas, and judge principal risk regions or belts of seismic activity in a year, by integrating the large area’s seismicity with geodetic deformation evolutional characteristics. As much as possible using information, we study synthetically observational information for long-medium- and short-term (time domain) and large-medium -small dimensions (space domain), and approach the forecast region of forthcoming earthquakes from the large to small magnitude. A better effect has been obtained. Some questions about earthquake prediction are discussed.
文摘The field of neural network has found solid application in the past ten years and the field itself is still developing rapidly. Neural network is composed of many simple elements operating in parallel. A neural network can be trained to perform a particular mapping and this is the basis of its application to practical problems. In this paper, new methods for predicting the strong earthquakes are presented based on neural network. Neural network learns from existing earthquake sequences or earthquake precursors how to make medium and short term prediction of strong earthquakes. This paper describes two neural network prediction models. One is the model based on earthquake evolution sequences, which is applied to the modeling of the magnitude evolution sequences in the Mainland of China, the other is based on earthquake precursors, which is applied to the modeling of the occurrence time of strong earthquakes in North China. Test results show that the prediction methods based on neural networks are efficient, and convenient. They would find more application in the future.
基金the Key Science andTechnology R&D Project of the 10th "Five-Year Plan" of Yunnan Province , entitled "Study of Med- and Short-term Prediction Techniques for Strong Earthquakein Yunnan"(2001NG46) andthe construction of Earthquake Monitoring andPrevention Center of West Yunnan (YN150105T037-045)
文摘Based on the data recorded by the regional digital seismic network of Yunnan and using new methods, the short-term variations of the ambient stress field of Yunnan and its adjacent areas are monitored in real time. With the in-depth analyses of the spatial-temporal evolution of the ambient stress field prior to the 2004, Shuangbai M_S5.0 earthquake, concrete procedures for predicting the three elements of the earthquake are presented.
基金funded by the National Natural Science Foundation of China (41807285)。
文摘The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning models have some problems,such as poor nonlinear performance,local optimum and incomplete factors feature extraction.These issues can affect the accuracy of slope stability prediction.Therefore,a deep learning algorithm called Long short-term memory(LSTM)has been innovatively proposed to predict slope stability.Taking the Ganzhou City in China as the study area,the landslide inventory and their characteristics of geotechnical parameters,slope height and slope angle are analyzed.Based on these characteristics,typical soil slopes are constructed using the Geo-Studio software.Five control factors affecting slope stability,including slope height,slope angle,internal friction angle,cohesion and volumetric weight,are selected to form different slope and construct model input variables.Then,the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors.Each slope stability coefficient and its corresponding control factors is a slope sample.As a result,a total of 2160 training samples and 450 testing samples are constructed.These sample sets are imported into LSTM for modelling and compared with the support vector machine(SVM),random forest(RF)and convo-lutional neural network(CNN).The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features.Furthermore,LSTM has a better prediction performance for slope stability compared to SVM,RF and CNN models.
文摘The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine learning(ML)models effectively deal with such challenges.This research paper comprehensively analyses recent advancements in crop yield prediction from January 2016 to March 2024.In addition,it analyses the effectiveness of various input parameters considered in crop yield prediction models.We conducted an in-depth search and gathered studies that employed crop modeling and AI-based methods to predict crop yield.The total number of articles reviewed for crop yield prediction using ML,meta-modeling(Crop models coupled with ML/DL),and DL-based prediction models and input parameter selection is 125.We conduct the research by setting up five objectives for this research and discussing them after analyzing the selected research papers.Each study is assessed based on the crop type,input parameters employed for prediction,the modeling techniques adopted,and the evaluation metrics used for estimatingmodel performance.We also discuss the ethical and social impacts of AI on agriculture.However,various approaches presented in the scientific literature have delivered impressive predictions,they are complicateddue to intricate,multifactorial influences oncropgrowthand theneed for accuratedata-driven models.Therefore,thorough research is required to deal with challenges in predicting agricultural output.
基金funded by the Natural Science Foundation of Fujian Province,China (Grant No.2022J05291)Xiamen Scientific Research Funding for Overseas Chinese Scholars.
文摘Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.
文摘Based on the extraction and calculation of the short-term seismic precursory information magnitude from the 114 major precursory observations in the North China region, and together with consideration of factors such as geological structure, seismicity, crustal thickness, and in particular, the current geodynamics of the region, the authors studied the time-space evolution characteristics of the short-term earthquake precursory information magnitude and its relationship with earthquakes and proposed the index and method for the short-term synthetic prediction of earthquakes with M S≥5.0 in the North China region. The inspection through R-value shows that the method is effective to a certain extent for earthquake prediction.
基金NSF of China under Contract No. 41030742NBRP of China (973 Program) under Grant No.2011CB013605Scientific Research Foundation of Graduate School of Southwest Jiaotong University
文摘The peak ground acceleration (PGA), the volume of a sliding mass V, the height of a mountain HL and the slope angle θ of a mountain are four important parameters affecting the horizontal run-out distance of a landslide L. Correlations among them are studied statistically based on field investigations from 67 landslides triggered by the ground shaking and other factors during the Wenchuan earthquake, and then a prediction model for horizontal run-out distance L is developed in this study. This model gives due consideration to the implications of the above four parameters on the horizontal run-out distance L and the validity of the model is verified by the Donghekou and Magong Woqian landslides. At the same time, the advantages of the model are shown by comparing it with two other common prediction methods. The major findings drawn from the analyses and comparisons are: (1) an exponential relationship exists between L and log V, L and log HL, L and log PGA separately, but a negative exponential relationship exists between L and log tan0, which agrees with the statistical results; and (2) according to the analysis results of the relative relationship between the height of a mountain (H) and the place where the landslides occur, the probabilities at distances of2H/3-H, H/3-2H/3, and O-H/3 are 70.8%, 15.4%, and 13.8%, respectively, revealing that most landslides occurred at a distance of H/2-H. This prediction model can provide an effective technical support for the prevention and mitigation of landslide hazards.
基金funded by the Natural Sciences and Engineering Council of Canada and the Geological Survey of China
文摘The ratio of P- to S-wave velocities (Vp/Vs) is regarded as one of the most diagnostic properties of natural rocks. It has been used as a discriminant of composition for the continental crust and provides valuable constraints on its formation and evolution processes. Furthermore, the spatial and temporal changes in Vp/Vs before and after earthquakes are probably the most promising avenue to understanding the source mechanics and possibly predicting earthquakes. Here we calibrate the variations in Vp/Vs in dry, anisotropic crustal rocks and provide a set of basic information for the interpretation of future seismic data from the Wenchuan earthquake Fault zone Scientific Drilling (WFSD) project and other surveys. Vp/Vs is a constant (Ф0) for an isotropic rock. However, most of crustal rocks are anisotropic due to lattice-preferred orientations of anisotropic minerals (e.g., mica, amphibole, plagioclase and pyroxene) and cracks as well as thin compositional layering. The Vp/Vs ratio of an anisotropic rock measured along a selected pair of propagation-vibration directions is an apparent value (Фy) that is significantly different from the value for its isotropic counterpart (Ф0). The usefulness of apparent Vp/Vs ratios as a diagnostic of crustal composition depends largely on rock seismic anisotropy. A 5% of P- and S-wave velocity anisotropy is sufficient to make it impossible to determine the crustal composition using the conventional criteria (Vp/Vs≤1.756 for felsic rocks, 1.756〈Vp/Vs≤1.809 for intermediate rocks, 1.809〈Vp/Vs≤1.944 for mafic rocks, and Vp/V2〉1.944 fluidfilled porous/fractured or partially molten rocks) if the information about the wave propagation-polarization directions with respect to the tectonic framework is unknown. However, the variations in Vp/Vs measured from borehole seismic experiments can be readily interpreted according to the orientations of the ray path and the polarization of the shear waves with respect to the present-day principal stress directions (i.e., the orientation of cracks) and the frozen fabric (i.e., foliation and lineation).
基金jointly funded by the Shanxi Science and Technology Plan Projects(2014K13-04)the Special Earthquake Research Project Grant offered by the China Earthquake Administration(201508009)the Crustal Movement Observation Network of China
文摘The relation between plate tectonics and earthquake evolution is analyzed systematically on the basis of 1998-2010 absolute and relative gravity data from the Crustal Movement Observation Network of China. Most earthquakes originated in the plate boundary or within the fault zone. Tectonic deformation was most intense and exhibited discontinuity within the tectonically active fault zone because of the differential movement; the stress accumulation produced an abrupt gravity change, which was further enhanced by the earthquake. The gravity data from China's Mainland since 2000 obviously reflected five major earthquakes (Ms 〉 7), all of which were better reflected than before 2000. Regional gravity anomalies and a gravity gradient change were observed in the area around the epicenter about 2 or 3 years before the earthquake occurred, suggesting that gravity change may be a seismic precursor. Furthermore, in this study, the medium-term predictions of the Ms7.3 Yutian, Ms8.0 Wenchuan, and Ms7.0 Lushan earthquakes are analytically pre- sented and evaluated, especially to estimate location of earthquake.
文摘The study in this paper analyzes and compares the distribution on the global engine active seismic zone and cooling seismic belt basing on the ANSS earthquake catalog from Northern California Earthquake Data Center. An idea of the seismogenesis and earthquake prediction research is achieved by showing the stratigraphic structure in the hot engine belt. The results show that the main engine and its seismic cones are the global seismic activity area, as well as the subject of global geological disaster. Based on the conjecture of other stratum structure, the energy of crustal strong earthquake and volcano activities probably originates from the deep upper mantle. It is suggested that the research on earthquake and volcano prediction should focus on the monitor and analysis on the sub-crustal earthquake activities.