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
Shaw's method used to correlate 40 sections across the Permo-Triassic boundary in South China is applied in the paper. Two steps are adopted to get an Integral Composite Section (ICS) by synthesizing these data : ...Shaw's method used to correlate 40 sections across the Permo-Triassic boundary in South China is applied in the paper. Two steps are adopted to get an Integral Composite Section (ICS) by synthesizing these data : First , South China is divided into five areas and composite section developed for each area . Then the second step . the Changxing composite section is regarded as a composite standard (CSRS) while the ICS is produced by matching the CSRS with composite sections of the other areas. Three biozones in the Changxingian and two biozones in the Griesbachian can be discerned on the basis of computing Z values in the ICS. These biozones are marked by the Z values which quantitatively represent their time ranges ; therefore , they may increase accuracy of stratigraphic time correlation . The mass extinction at the end of the Permian is an abrupt event that is supported by the relative rate of extinction near the P/T boundary . About 90% of invertebrate species died out by the end of the Permian . The duration of the mass extinction is rather short ,approximately 0.018Ma .展开更多
Forest losses or gains have long been recognized as critical processes modulating the carbon flux between the biosphere and the atmosphere. Timely, accurate and spatially explicit information on forest disturbance and...Forest losses or gains have long been recognized as critical processes modulating the carbon flux between the biosphere and the atmosphere. Timely, accurate and spatially explicit information on forest disturbance and recovery history is required for assessing the effectiveness of existing forest management. The major objectives of our research focused on testing the mapping efficacy of the vegetation change tracker （VCT） model over a forested area in China. We used a new version of VCT algorithm built upon the Landsat time series stacks （LTSS）. The LTSS consisted of yearly image acquisitions to map forest disturbance history from 1987 to 2011 over the Ning-Zhen Mountains, Jiangsu Province of east China. The LTSS consisted of TM and ETM＋ scenes with different projec- tions due to distinct data sources （Beijing remote sensing ground station and the USGS EROS Center）. The valida- tion results of the disturbance year maps showed that most spatial agreement measures ranged from 70 to 86 %, comparable with the VCT accuracies reported for many places in USA. Very low accuracies were identified in 1995 （38.3 %） and 1992 （56.2 %） in the current analysis. These resulted from the insensitivity of the VCT algorithm to detect low intensity disturbances and also from the mis- registration errors of the image pairs. Major forest distur- bance types existing in our study area were identified as agricultural expansion （39.8 %）, urbanization （24.9 %）, forest management practice （19.3 %）, and mining （12.8 %）. In general, there was a gradual decreasing trend in forest cover throughout this region, caused principally by China＇s economic, demographic, environmental and political policies and decisions, as well as some weather events. While VCT has largely been used to assess long term changes and trends in the USA, it has great potential for assessing landscape level change elsewhere throughout the world.展开更多
探讨Mann-Kendall检验法、差分自回归移动平均模型(Autoregressive Mobile Average Model,ARIMA)与长短期记忆神经网络(Long and Short-Term Memory,LSTM)的组合模型在《中国的核安全》、《核安全年报》中核电厂运行事件数量的应用,对...探讨Mann-Kendall检验法、差分自回归移动平均模型(Autoregressive Mobile Average Model,ARIMA)与长短期记忆神经网络(Long and Short-Term Memory,LSTM)的组合模型在《中国的核安全》、《核安全年报》中核电厂运行事件数量的应用,对运行事件数量进行趋势分析、突变分析和预测并证明模型的适用性。利用1991⁓2018年核电厂运行事件数量,使用R软件建立ARIMA(2,1,2)模型,得到运行事件数量的线性部分;建立LSTM模型,对偏差序列进行预测,得到运行事件数量的非线性部分;最后建立ARIMA和LSTM组合模型,利用组合模型对运行事件数量进行预测,并根据实测数据对预测结果进行对比验证。实验结果表明:ARIMA和LSTM组合模型可较好地拟合运行事件数量时间序列,并修正单一模型的误差,有效提高预测精度3%,且得到的2019⁓2020年核电厂运行事件数量预测值与《核安全年报》相近。展开更多
Background:With the emergence of the COVID-19 pandemic,all existing health protocols were tested under the worst health crisis humanity has experienced since the Black Death in the 14th century.Countries in Latin Amer...Background:With the emergence of the COVID-19 pandemic,all existing health protocols were tested under the worst health crisis humanity has experienced since the Black Death in the 14th century.Countries in Latin America have been the epicenter of the COVID-19 pandemic,with more than 1.5 million people killed.Worldwide health measures have included quarantines,border closures,social distancing,and mask use,among others.In particular,Chile implemented total or partial quarantine measures depending on the number of infections in each region of the country.Therefore,it is necessary to study the effectiveness of these quarantines in relation to the public health measures implemented by government entities at the national level.Objective:The main objective of this study is to analyze the effectiveness of national-and region-level quarantines in Chile during the pandemic based on information published by the Chilean Ministry of Health,and answers to the following question are sought:Were quarantine measures in Chile effective during the COVID-19 pandemic?Methods:The causal effect between the rates of COVID-19 infections and the population rates in Phase 1 and Phase 2 quarantines in the period from March 2020 to March 2021 in different regions of Chile were evaluated using intervention analyses obtained through Bayesian structural time series models.In addition,the Kendall correlation coefficient obtained through the copula approach was used to evaluate the comovement between these rates.Results:In 75%of the Chilean regions under study(12 regions out of a total of 16),an effective Phase 1 quarantine,which was implemented to control and reduce the number of cases of COVID-19 infection,was observed.The main regions that experienced a decrease in cases were those located in the north and center of Chile.Regarding Phase 2,the COVID-19 pandemic was effectively managed in 31%(5 out of 16)of the regions.In the southcentral and extreme southern regions of Chile,the effectiveness of these phases was null.Conclusion:The findings indicate that in the northern and central regions of Chile,the Phase 1 quarantine application period was an effective strategy to prevent an increase in COVID-19 infections.The same observation was made with respect to Phase 2,which was effective in five regions of northern Chile;in the rest of the regions,the effectiveness of these phases was weak or null.展开更多
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.
文摘Shaw's method used to correlate 40 sections across the Permo-Triassic boundary in South China is applied in the paper. Two steps are adopted to get an Integral Composite Section (ICS) by synthesizing these data : First , South China is divided into five areas and composite section developed for each area . Then the second step . the Changxing composite section is regarded as a composite standard (CSRS) while the ICS is produced by matching the CSRS with composite sections of the other areas. Three biozones in the Changxingian and two biozones in the Griesbachian can be discerned on the basis of computing Z values in the ICS. These biozones are marked by the Z values which quantitatively represent their time ranges ; therefore , they may increase accuracy of stratigraphic time correlation . The mass extinction at the end of the Permian is an abrupt event that is supported by the relative rate of extinction near the P/T boundary . About 90% of invertebrate species died out by the end of the Permian . The duration of the mass extinction is rather short ,approximately 0.018Ma .
基金funded by the following grants:the Forestry Public Welfare Project(201304208)the‘‘948’’Project sponsored by the State Forestry Administration(SFA)of China(2014-4-25)+4 种基金the National Natural Science Foundation of China(31270587,31100414)the PAPD(Priority Academic Program Development)of Jiangsu provincial universitiesperformed while the lead author held a scholarship sponsored the CSC(China Scholarship Council)(201208320553)at the department of Geographical Sciences,University of Marylandawardee of the 2012 Youth Backbone Teachers Support Plan of Jiangsu Provincethe 2012 Youth Talents Support Plan of Nanjing Forestry University
文摘Forest losses or gains have long been recognized as critical processes modulating the carbon flux between the biosphere and the atmosphere. Timely, accurate and spatially explicit information on forest disturbance and recovery history is required for assessing the effectiveness of existing forest management. The major objectives of our research focused on testing the mapping efficacy of the vegetation change tracker （VCT） model over a forested area in China. We used a new version of VCT algorithm built upon the Landsat time series stacks （LTSS）. The LTSS consisted of yearly image acquisitions to map forest disturbance history from 1987 to 2011 over the Ning-Zhen Mountains, Jiangsu Province of east China. The LTSS consisted of TM and ETM＋ scenes with different projec- tions due to distinct data sources （Beijing remote sensing ground station and the USGS EROS Center）. The valida- tion results of the disturbance year maps showed that most spatial agreement measures ranged from 70 to 86 %, comparable with the VCT accuracies reported for many places in USA. Very low accuracies were identified in 1995 （38.3 %） and 1992 （56.2 %） in the current analysis. These resulted from the insensitivity of the VCT algorithm to detect low intensity disturbances and also from the mis- registration errors of the image pairs. Major forest distur- bance types existing in our study area were identified as agricultural expansion （39.8 %）, urbanization （24.9 %）, forest management practice （19.3 %）, and mining （12.8 %）. In general, there was a gradual decreasing trend in forest cover throughout this region, caused principally by China＇s economic, demographic, environmental and political policies and decisions, as well as some weather events. While VCT has largely been used to assess long term changes and trends in the USA, it has great potential for assessing landscape level change elsewhere throughout the world.
文摘探讨Mann-Kendall检验法、差分自回归移动平均模型(Autoregressive Mobile Average Model,ARIMA)与长短期记忆神经网络(Long and Short-Term Memory,LSTM)的组合模型在《中国的核安全》、《核安全年报》中核电厂运行事件数量的应用,对运行事件数量进行趋势分析、突变分析和预测并证明模型的适用性。利用1991⁓2018年核电厂运行事件数量,使用R软件建立ARIMA(2,1,2)模型,得到运行事件数量的线性部分;建立LSTM模型,对偏差序列进行预测,得到运行事件数量的非线性部分;最后建立ARIMA和LSTM组合模型,利用组合模型对运行事件数量进行预测,并根据实测数据对预测结果进行对比验证。实验结果表明:ARIMA和LSTM组合模型可较好地拟合运行事件数量时间序列,并修正单一模型的误差,有效提高预测精度3%,且得到的2019⁓2020年核电厂运行事件数量预测值与《核安全年报》相近。
文摘Background:With the emergence of the COVID-19 pandemic,all existing health protocols were tested under the worst health crisis humanity has experienced since the Black Death in the 14th century.Countries in Latin America have been the epicenter of the COVID-19 pandemic,with more than 1.5 million people killed.Worldwide health measures have included quarantines,border closures,social distancing,and mask use,among others.In particular,Chile implemented total or partial quarantine measures depending on the number of infections in each region of the country.Therefore,it is necessary to study the effectiveness of these quarantines in relation to the public health measures implemented by government entities at the national level.Objective:The main objective of this study is to analyze the effectiveness of national-and region-level quarantines in Chile during the pandemic based on information published by the Chilean Ministry of Health,and answers to the following question are sought:Were quarantine measures in Chile effective during the COVID-19 pandemic?Methods:The causal effect between the rates of COVID-19 infections and the population rates in Phase 1 and Phase 2 quarantines in the period from March 2020 to March 2021 in different regions of Chile were evaluated using intervention analyses obtained through Bayesian structural time series models.In addition,the Kendall correlation coefficient obtained through the copula approach was used to evaluate the comovement between these rates.Results:In 75%of the Chilean regions under study(12 regions out of a total of 16),an effective Phase 1 quarantine,which was implemented to control and reduce the number of cases of COVID-19 infection,was observed.The main regions that experienced a decrease in cases were those located in the north and center of Chile.Regarding Phase 2,the COVID-19 pandemic was effectively managed in 31%(5 out of 16)of the regions.In the southcentral and extreme southern regions of Chile,the effectiveness of these phases was null.Conclusion:The findings indicate that in the northern and central regions of Chile,the Phase 1 quarantine application period was an effective strategy to prevent an increase in COVID-19 infections.The same observation was made with respect to Phase 2,which was effective in five regions of northern Chile;in the rest of the regions,the effectiveness of these phases was weak or null.
