[Objective]The aim was to research influence of climate conditions on potato yield and establish the forecasting model of potato yield.[Method]SPSS（Statistical Package for the Social Sciences） was used to separate p...[Objective]The aim was to research influence of climate conditions on potato yield and establish the forecasting model of potato yield.[Method]SPSS（Statistical Package for the Social Sciences） was used to separate potato output into meteorological yield and tendency yield over the years,and analysis of the relation between potato climate yield and meteorological factors was carried out.[Result]The result showed that affecting yield factor consisted of the universality and regional.The universality included vapour pressure or relative humidity of air in last August-September,precipitation in late June to early July and in mid-August;The regional is including precipitation in January and in early to mid April,vapour pressure of air in May.Prediction model about yield was established by using stepwise regression method,which qualified rates of fitting better quality.[Conclusion]Because of its long effective period,high accuracy and simplicity to dalculate,the method provided a guarantee for weather service on the crop farming of potatoes.展开更多
Prediction of melt index （MI）, the most important parameter in determining the product＇s grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model ...Prediction of melt index （MI）, the most important parameter in determining the product＇s grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model with principal component analysis （PCA）, radial basis function （RBF） networks, and multi-scale analysis （MSA） is proposed to infer the MI of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, MSA is introduced to a^quire much more information and to reduce the uncertainty of the system, and RBF networks are used to characterize the nonlinearity of the process. The research results show that the proposed method provides promising prediction reliability and accuracy, and supposed to have extensive application prospects in propylene polymerization processes.展开更多
Spatial and temporal distribution characteristics and scale range of two significant areas were obtained by analyzing the relationship among summer rainfall in Yunnan province, height field and SST field (40°S –...Spatial and temporal distribution characteristics and scale range of two significant areas were obtained by analyzing the relationship among summer rainfall in Yunnan province, height field and SST field (40°S – 40°N, 30 °E – 70°W) across the North Hemisphere at 200 hPa, 500 hPa and 850 hPa for Jan. to May and correlation, and field wave structure. Remote key regions among summer rainfall in Yunnan province, height field and SST field (40°S – 40°N, 30°E – 70°W) across the North Hemisphere at 200 hPa, 500 hPa and 850 hPa were studied through further analyzing of the circulation system and its climate / weather significance. The result shows that the forecast has dependable physical basis when height and SST fields were viewed as predictors and physical models of impacts on rainy season precipitation in Yunnan are preliminarily concluded.展开更多
In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradien...In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradient, the length of the neutral line, and the number of singular points are extracted from SOHO/MDI longitudinal magnetograms as measures. Based on these pa- rameters, the sliding-window method is used to form the sequential data by adding three days evolutionary information. Con- sidering the imbalanced problem in dataset, the K-means clustering, as an unsupervised clustering algorithm, is used to convert imbalanced data to balanced ones. Finally, the learning vector quantity is employed to predict the flares level within 48 hours. Experimental results indicate that the performance of the proposed flare forecasting model with sequential data is improved.展开更多
基金Supported by National Natural Science Foundation of China(40675071)~~
文摘[Objective]The aim was to research influence of climate conditions on potato yield and establish the forecasting model of potato yield.[Method]SPSS（Statistical Package for the Social Sciences） was used to separate potato output into meteorological yield and tendency yield over the years,and analysis of the relation between potato climate yield and meteorological factors was carried out.[Result]The result showed that affecting yield factor consisted of the universality and regional.The universality included vapour pressure or relative humidity of air in last August-September,precipitation in late June to early July and in mid-August;The regional is including precipitation in January and in early to mid April,vapour pressure of air in May.Prediction model about yield was established by using stepwise regression method,which qualified rates of fitting better quality.[Conclusion]Because of its long effective period,high accuracy and simplicity to dalculate,the method provided a guarantee for weather service on the crop farming of potatoes.
基金Supported by the National Natural Science Foundation of China (No. 20106008)National HI-TECH Industrialization Program of China (No. Fagai-Gaoji-2004-2080)Science Fund for Distinguished Young Scholars of Zhejiang University (No. 111000-581645).
文摘Prediction of melt index （MI）, the most important parameter in determining the product＇s grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model with principal component analysis （PCA）, radial basis function （RBF） networks, and multi-scale analysis （MSA） is proposed to infer the MI of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, MSA is introduced to a^quire much more information and to reduce the uncertainty of the system, and RBF networks are used to characterize the nonlinearity of the process. The research results show that the proposed method provides promising prediction reliability and accuracy, and supposed to have extensive application prospects in propylene polymerization processes.
基金Key Foundation Project of Yunnan Province (2003D0014Z)Natural Science Foundation ofChina (40065001)
文摘Spatial and temporal distribution characteristics and scale range of two significant areas were obtained by analyzing the relationship among summer rainfall in Yunnan province, height field and SST field (40°S – 40°N, 30 °E – 70°W) across the North Hemisphere at 200 hPa, 500 hPa and 850 hPa for Jan. to May and correlation, and field wave structure. Remote key regions among summer rainfall in Yunnan province, height field and SST field (40°S – 40°N, 30°E – 70°W) across the North Hemisphere at 200 hPa, 500 hPa and 850 hPa were studied through further analyzing of the circulation system and its climate / weather significance. The result shows that the forecast has dependable physical basis when height and SST fields were viewed as predictors and physical models of impacts on rainy season precipitation in Yunnan are preliminarily concluded.
基金supported by the National Natural Science Foundation of China (Grant No. 10973020)the Funding Project for Academic Human Resources Development in Institutions of Higher Learning under the Jurisdiction of Beijing Municipality (Grant No. PHR200906210)+1 种基金the Funding Project for Base Construction of Scientific Research of Beijing Municipal Commission of Education (Grant No. WYJD200902)Beijing Philosophy and Social Science Planning Project (Grant No. 09BaJG258)
文摘In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradient, the length of the neutral line, and the number of singular points are extracted from SOHO/MDI longitudinal magnetograms as measures. Based on these pa- rameters, the sliding-window method is used to form the sequential data by adding three days evolutionary information. Con- sidering the imbalanced problem in dataset, the K-means clustering, as an unsupervised clustering algorithm, is used to convert imbalanced data to balanced ones. Finally, the learning vector quantity is employed to predict the flares level within 48 hours. Experimental results indicate that the performance of the proposed flare forecasting model with sequential data is improved.
