In order to achieve the best predictive effect of the Partial Least Squares(PLS) regression model, Particle Swarm Optimization(PSO) algorithm is applied to automatically filter the optimal subset of a set of candidate...In order to achieve the best predictive effect of the Partial Least Squares(PLS) regression model, Particle Swarm Optimization(PSO) algorithm is applied to automatically filter the optimal subset of a set of candidate factors of PLS regression model in this study. An improved version of the Particle Swarm Optimization-Partial Least Squares(PSO-PLS) regression model is applied to the station data of precipitation in Southwest China during flood season.Using the PSO-PLS regression method, the prediction of flood season precipitation in Southwest China has been studied. By introducing the precipitation period series of the mean generating function(MGF) extension as an alternative factor, the MGF improved PSO-PLS regression model was also built up to improve the prediction results.Randomly selected 10%, 20%, 30% of the modeling samples were used as a test trial; random cross validation was conducted on the MGF improved PSO-PLS regression model. The results show that the accuracy of PSO-PLS regression model and the MGF improved PSO-PLS regression model are better than that of the traditional PLS regression model.The training results of the three prediction models with regard to the regional and single station precipitation are considerable, whereas the forecast results indicate that the PSO-PLS regression method and the MGF improved PSO-PLS regression method are much better than the traditional PLS regression method. The MGF improved PSO-PLS regression model has the best forecast performance on precipitation anomaly during the flood season in the southwest of China among three models. The average precipitation(PS score) of 36 stations is 74.7. With the increase of the number of modeling samples, the PS score remained stable. This shows that the PSO algorithm is objective and stable. The MGF improved PSO-PLS regression prediction model is also showed to have good prediction stability and ability.展开更多
The precipitation patterns in flood season over China associated with the EI Nino/Southern Oscillation (ENSO) are investigated, especially in the eastern China, using the rather long period rainfall data in this centu...The precipitation patterns in flood season over China associated with the EI Nino/Southern Oscillation (ENSO) are investigated, especially in the eastern China, using the rather long period rainfall data in this century. The results show that there were remarkable differences between the precipitation patterns in flood seasons of ENSO warm phase (EI Nino year) and cold phase (La Nina year), as well as between the patterns in EI Nino years and their following you. The most parts of China received below normal rainfall in flood season of the onset years of EI Nino events, but the coastal area of Southeast China received above normal amounts. Comparatively, the most parts of China received above normal rainfall in flood season of the following years of EI Nino events, but the eastern part of the reaches among the Huanghe (Yellow) River, the Huaihe River and the Haihe River, and the Northeast China received less. During ENSO cold phase, the reaches of the Changjiang (Yangtze) River and the North China received more amounts than normal lainfall in flood season of the onset years of in Nina events, and the other regions of China received less. In the following years of La Nina events, the coastal area of the Southeast China, the most part of the Northeast China and the regions between the Huanghe River and the Huaihe River received more precipitation during flood seasons, but the other parts received below normal precipitation.展开更多
[Objective]The research aimed to analyze precipitation change and agricultural drought and flood degrees during crop growth season in Binzhou.[Method]Based on monthly rainfall and average temperature data at Binzhou m...[Objective]The research aimed to analyze precipitation change and agricultural drought and flood degrees during crop growth season in Binzhou.[Method]Based on monthly rainfall and average temperature data at Binzhou meteorological observatory during March-November of1981-2010,by using linear regression,climatic tendency rate and dry-wet coefficient,precipitation change and agricultural drought and flood degrees during crop growth season of the past 30 years in Binzhou were analyzed from natural precipitation tendency change and satisfaction degree of agricultural water demand during crop growth season.[Result]In the past 30 years,precipitation during growth season in Binzhou presented increasing tendency.Spring,summer and autumn precipitation all increased somewhat,especially summer precipitation.Monthly average rainfall distribution was very uneven,and rainfall in July and August was more.In the past 30 years,average dry-wet coefficient K value during crop growth season in Binzhou was 0.60,it overall belonged to moderate drought climate type,and occurrence frequency of drought was 97%.It belonged to serious drought climate type in spring and autumn and light drought climate type in summer.Dry-wet coefficient presented rising tendency,illustrating that climate was developing toward wet direction.Seen from mean over the years,except humid in July,it was over light drought in other months.[Conclusion]Climate was overall arid during crop growth season in Binzhou,but precipitation somewhat increased in the past 30 years.Therefore,we suggested that artificial rainfall work should be enhanced.展开更多
基金National Natural Science Foundation of China(41475070,41375049,41330420)
文摘In order to achieve the best predictive effect of the Partial Least Squares(PLS) regression model, Particle Swarm Optimization(PSO) algorithm is applied to automatically filter the optimal subset of a set of candidate factors of PLS regression model in this study. An improved version of the Particle Swarm Optimization-Partial Least Squares(PSO-PLS) regression model is applied to the station data of precipitation in Southwest China during flood season.Using the PSO-PLS regression method, the prediction of flood season precipitation in Southwest China has been studied. By introducing the precipitation period series of the mean generating function(MGF) extension as an alternative factor, the MGF improved PSO-PLS regression model was also built up to improve the prediction results.Randomly selected 10%, 20%, 30% of the modeling samples were used as a test trial; random cross validation was conducted on the MGF improved PSO-PLS regression model. The results show that the accuracy of PSO-PLS regression model and the MGF improved PSO-PLS regression model are better than that of the traditional PLS regression model.The training results of the three prediction models with regard to the regional and single station precipitation are considerable, whereas the forecast results indicate that the PSO-PLS regression method and the MGF improved PSO-PLS regression method are much better than the traditional PLS regression method. The MGF improved PSO-PLS regression model has the best forecast performance on precipitation anomaly during the flood season in the southwest of China among three models. The average precipitation(PS score) of 36 stations is 74.7. With the increase of the number of modeling samples, the PS score remained stable. This shows that the PSO algorithm is objective and stable. The MGF improved PSO-PLS regression prediction model is also showed to have good prediction stability and ability.
文摘The precipitation patterns in flood season over China associated with the EI Nino/Southern Oscillation (ENSO) are investigated, especially in the eastern China, using the rather long period rainfall data in this century. The results show that there were remarkable differences between the precipitation patterns in flood seasons of ENSO warm phase (EI Nino year) and cold phase (La Nina year), as well as between the patterns in EI Nino years and their following you. The most parts of China received below normal rainfall in flood season of the onset years of EI Nino events, but the coastal area of Southeast China received above normal amounts. Comparatively, the most parts of China received above normal rainfall in flood season of the following years of EI Nino events, but the eastern part of the reaches among the Huanghe (Yellow) River, the Huaihe River and the Haihe River, and the Northeast China received less. During ENSO cold phase, the reaches of the Changjiang (Yangtze) River and the North China received more amounts than normal lainfall in flood season of the onset years of in Nina events, and the other regions of China received less. In the following years of La Nina events, the coastal area of the Southeast China, the most part of the Northeast China and the regions between the Huanghe River and the Huaihe River received more precipitation during flood seasons, but the other parts received below normal precipitation.
文摘[Objective]The research aimed to analyze precipitation change and agricultural drought and flood degrees during crop growth season in Binzhou.[Method]Based on monthly rainfall and average temperature data at Binzhou meteorological observatory during March-November of1981-2010,by using linear regression,climatic tendency rate and dry-wet coefficient,precipitation change and agricultural drought and flood degrees during crop growth season of the past 30 years in Binzhou were analyzed from natural precipitation tendency change and satisfaction degree of agricultural water demand during crop growth season.[Result]In the past 30 years,precipitation during growth season in Binzhou presented increasing tendency.Spring,summer and autumn precipitation all increased somewhat,especially summer precipitation.Monthly average rainfall distribution was very uneven,and rainfall in July and August was more.In the past 30 years,average dry-wet coefficient K value during crop growth season in Binzhou was 0.60,it overall belonged to moderate drought climate type,and occurrence frequency of drought was 97%.It belonged to serious drought climate type in spring and autumn and light drought climate type in summer.Dry-wet coefficient presented rising tendency,illustrating that climate was developing toward wet direction.Seen from mean over the years,except humid in July,it was over light drought in other months.[Conclusion]Climate was overall arid during crop growth season in Binzhou,but precipitation somewhat increased in the past 30 years.Therefore,we suggested that artificial rainfall work should be enhanced.
