F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM...F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.展开更多
The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome t...The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome the limitations of the traditional direct NNI inversion method(NNI_(T1))of the vegetation index and traditional indirect NNI inversion method(NNI_(T2))by inverting intermediate variables including the aboveground dry biomass(AGB)and plant N concentration(PNC),this study proposed a new NNI remote sensing index(NNI_(RS)).A remote-sensing-based critical N dilution curve(Nc_(_RS))was set up directly from two vegetation indices and then used to calculate NNI_(RS).Field data including AGB,PNC,and canopy hyperspectral data were collected over four growing seasons(2012–2013(Exp.1),2013–2014(Exp.2),2014–2015(Exp.3),2015–2016(Exp.4))in Beijing,China.All experimental datasets were cross-validated to each of the NNI models(NNI_(T1),NNI_(T2)and NNI_(RS)).The results showed that:(1)the NNI_(RS)models were represented by the standardized leaf area index determining index(sLAIDI)and the red-edge chlorophyll index(CI_(red edge))in the form of NNI_(RS)=CI_(red edge)/(a×sLAIDI~b),where"a"equals 2.06,2.10,2.08 and 2.02 and"b"equals 0.66,0.73,0.67 and 0.62 when the modeling set data came from Exp.1/2/4,Exp.1/2/3,Exp.1/3/4,and Exp.2/3/4,respectively;(2)the NNI_(RS)models achieved better performance than the other two NNI revised methods,and the ranges of R2 and RMSE were 0.50–0.82 and 0.12–0.14,respectively;(3)when the remaining data were used for verification,the NNI_(RS)models also showed good stability,with RMSE values of 0.09,0.18,0.13 and 0.10,respectively.Therefore,it is concluded that the NNI_(RS)method is promising for the remote assessment of crop N status.展开更多
The upconversion luminescence in Er 3+ doped tellurite glasses (MKT: TeO_2-MgO-K_2O) were performed. Two green emission bands at 521 and 550 nm, corresponding to the 2H_ 11/2→4I_ 15/2 and 4S_ 3/2→4I_ 15/2 transition...The upconversion luminescence in Er 3+ doped tellurite glasses (MKT: TeO_2-MgO-K_2O) were performed. Two green emission bands at 521 and 550 nm, corresponding to the 2H_ 11/2→4I_ 15/2 and 4S_ 3/2→4I_ 15/2 transitions, respectively, were observed. Coordinate field index, which was proposed by deducing from Pauling′s rules on the basis of Zachariasen′s random network theory, can be used to rationalize the remarkable variation in the intensity of upconversion luminescence.展开更多
Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced b...Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.展开更多
With the decrease of global temperature, glacial epoch came over the earth and global climate fluctuated over a great range since the beginning of Quaternary. Paleoclimotologists of various countries have focussed att...With the decrease of global temperature, glacial epoch came over the earth and global climate fluctuated over a great range since the beginning of Quaternary. Paleoclimotologists of various countries have focussed attention to the periodic characteristics and dynamics of climatic fluctuation in the past many years (Berger, 1977; Imbrie and Hays, 1984; Ding Zhongli et al., 1990; Yu Zhiwei et al., 1992; Liu Youmei et al., 1996). Although some of the workers have paid their attention to the nonlinear characteristics of the global Quaternary environmental evolution (Nicolis and Nicolis, 1984; Lu Houyuan et al., 1993), it is worth while to do this kind of work in some special areas in the world, for example the Qinghai\|Tibet Plateau.\; Using R/S analysis, the authors calculated the Hurst indexes H of some geochemical proxies, including organic carbon, FeO, Fe\-2O\-3 and FeO/ Fe\-2O\-3, from the Tianshuihai Lake core in West Kunlun Mountain of the Qinghai\|Tibet Plateau. The proxies satisfy the Hurst law with H\-\{org.carbon\}=0.735, H\-\{Fe\-2O\-3\}=0.757, H\-\{FeO\}=0.848 and H\-\{FeO/Fe\-2O\-3\}=0.646. All the indexes are greater than 0.5, meaning that from 240 to 15 ka B.P., there were some long\|run dependencies\|persistence in the climatic and environmental evolution around the Tianshuihai Lake area. This is in accordance with the climate there from 240 to 15 ka B.P. (Yu Suhua et al., 1996). The paleo\|climate and paleo\|environment evolution around the Tianshuihai Lake area is of persistence as well as of fluctuation and is a combination of these two components. There are some differences between the four Hurst indexes, which probably resulted from the different intensities of persistence of the four proxies, organic carbon, FeO, Fe\-2O\-3 and FeO/ Fe\-2O\-3, or from the change of drainage system around the Tianshuihai Lake area from openness to closeness(Li Bingyuan et al., 1991; Sun Honglie, 1996; Shi Yafeng et al., 1998).\; The Qinghai\|Tibet plateau was the starter and sensor of the climatic and environmental variation of the surrounding areas (Yao Tandong et al., 1991; Feng Song et al., 1998) and some other scientists even regarded it as the driver and amplifier of global climatic variations (Pan Baotian and Li Jijun, 1996). The persistence in which the climate and environment around the Tianshuihai Lake area evolved from 240 to 15 ka B.P. is probably a function of the continuous uplift of the plateau in the same period of time.展开更多
文摘F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.
基金supported by the earmarked fund for China Agriculture Research System(CARS-03)the National Key Research and Development Program of China(2017YFD0201501 and 2016YFD020060306)the National Natural Science Foundation of China(41701375 and 61661136003)。
文摘The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome the limitations of the traditional direct NNI inversion method(NNI_(T1))of the vegetation index and traditional indirect NNI inversion method(NNI_(T2))by inverting intermediate variables including the aboveground dry biomass(AGB)and plant N concentration(PNC),this study proposed a new NNI remote sensing index(NNI_(RS)).A remote-sensing-based critical N dilution curve(Nc_(_RS))was set up directly from two vegetation indices and then used to calculate NNI_(RS).Field data including AGB,PNC,and canopy hyperspectral data were collected over four growing seasons(2012–2013(Exp.1),2013–2014(Exp.2),2014–2015(Exp.3),2015–2016(Exp.4))in Beijing,China.All experimental datasets were cross-validated to each of the NNI models(NNI_(T1),NNI_(T2)and NNI_(RS)).The results showed that:(1)the NNI_(RS)models were represented by the standardized leaf area index determining index(sLAIDI)and the red-edge chlorophyll index(CI_(red edge))in the form of NNI_(RS)=CI_(red edge)/(a×sLAIDI~b),where"a"equals 2.06,2.10,2.08 and 2.02 and"b"equals 0.66,0.73,0.67 and 0.62 when the modeling set data came from Exp.1/2/4,Exp.1/2/3,Exp.1/3/4,and Exp.2/3/4,respectively;(2)the NNI_(RS)models achieved better performance than the other two NNI revised methods,and the ranges of R2 and RMSE were 0.50–0.82 and 0.12–0.14,respectively;(3)when the remaining data were used for verification,the NNI_(RS)models also showed good stability,with RMSE values of 0.09,0.18,0.13 and 0.10,respectively.Therefore,it is concluded that the NNI_(RS)method is promising for the remote assessment of crop N status.
文摘The upconversion luminescence in Er 3+ doped tellurite glasses (MKT: TeO_2-MgO-K_2O) were performed. Two green emission bands at 521 and 550 nm, corresponding to the 2H_ 11/2→4I_ 15/2 and 4S_ 3/2→4I_ 15/2 transitions, respectively, were observed. Coordinate field index, which was proposed by deducing from Pauling′s rules on the basis of Zachariasen′s random network theory, can be used to rationalize the remarkable variation in the intensity of upconversion luminescence.
文摘Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.
文摘With the decrease of global temperature, glacial epoch came over the earth and global climate fluctuated over a great range since the beginning of Quaternary. Paleoclimotologists of various countries have focussed attention to the periodic characteristics and dynamics of climatic fluctuation in the past many years (Berger, 1977; Imbrie and Hays, 1984; Ding Zhongli et al., 1990; Yu Zhiwei et al., 1992; Liu Youmei et al., 1996). Although some of the workers have paid their attention to the nonlinear characteristics of the global Quaternary environmental evolution (Nicolis and Nicolis, 1984; Lu Houyuan et al., 1993), it is worth while to do this kind of work in some special areas in the world, for example the Qinghai\|Tibet Plateau.\; Using R/S analysis, the authors calculated the Hurst indexes H of some geochemical proxies, including organic carbon, FeO, Fe\-2O\-3 and FeO/ Fe\-2O\-3, from the Tianshuihai Lake core in West Kunlun Mountain of the Qinghai\|Tibet Plateau. The proxies satisfy the Hurst law with H\-\{org.carbon\}=0.735, H\-\{Fe\-2O\-3\}=0.757, H\-\{FeO\}=0.848 and H\-\{FeO/Fe\-2O\-3\}=0.646. All the indexes are greater than 0.5, meaning that from 240 to 15 ka B.P., there were some long\|run dependencies\|persistence in the climatic and environmental evolution around the Tianshuihai Lake area. This is in accordance with the climate there from 240 to 15 ka B.P. (Yu Suhua et al., 1996). The paleo\|climate and paleo\|environment evolution around the Tianshuihai Lake area is of persistence as well as of fluctuation and is a combination of these two components. There are some differences between the four Hurst indexes, which probably resulted from the different intensities of persistence of the four proxies, organic carbon, FeO, Fe\-2O\-3 and FeO/ Fe\-2O\-3, or from the change of drainage system around the Tianshuihai Lake area from openness to closeness(Li Bingyuan et al., 1991; Sun Honglie, 1996; Shi Yafeng et al., 1998).\; The Qinghai\|Tibet plateau was the starter and sensor of the climatic and environmental variation of the surrounding areas (Yao Tandong et al., 1991; Feng Song et al., 1998) and some other scientists even regarded it as the driver and amplifier of global climatic variations (Pan Baotian and Li Jijun, 1996). The persistence in which the climate and environment around the Tianshuihai Lake area evolved from 240 to 15 ka B.P. is probably a function of the continuous uplift of the plateau in the same period of time.
