Dissertation > Excellent graduate degree dissertation topics show

Analysis and Multvariate Nonlinear Prediction Model of Ground-level Ozone Time Series in Shanghai

Author: LiuMingHua
Tutor: LeQun
School: East China Normal University
Course: Meteorology
Keywords: Ozone Multivariable Predictive Nonlinear time series Partial Least Squares Regression Support Vector Machine
CLC: O213
Type: Master's thesis
Year: 2009
Downloads: 201
Quote: 1
Read: Download Dissertation

Abstract


In recent years, ozone pollution in eastern China has become the outstanding problems of urban air pollution. With urban development, energy changes in the structure, the city's rapid increase in car ownership, the Shanghai region has also been a high concentration of ozone pollution threat. At a time when preparations for the 2010 World Expo on the occasion, the Shanghai region of the atmospheric environment much people of the world's attention. As the 2008 Beijing Olympics, the ozone concentration in the atmospheric environment quality is also an important indicator. Therefore, the analysis of certain precursors and factors such as weather conditions and the relationship between ozone and law, to carry out ground-level ozone concentrations near Shanghai prediction method is better control of ozone concentrations to avoid photochemical smog events inevitable requirement Shanghai 2010 World Expo was successfully held an important safeguard. In this paper, the Shanghai Environmental Monitoring Center Luwan and Pudong two stations hour ozone concentration time series for the study, changes in ozone concentrations for each station and related factors were analyzed on the basis of time series of ozone concentrations diverse non- linear prediction method is used, the ozone concentration was established multivariate nonlinear time series forecasting model, and achieved better results than a single variable. Specific tasks are as follows: (a) in the use of statistical forecasting methods, the first mechanism of formation of ozone and ozone-related factors were analyzed. Found that high concentrations of ozone in Shanghai in recent years, showed seasonal fluctuations in atmospheric photochemical pollution, and in spring, summer and autumn the most serious, particularly in May and July, the most prominent. Analysis to May with a high concentration of ozone to generate the required strong solar radiation, dry, low relative humidity and other conditions. Solar radiation changes in the ozone concentration plays a key role. 2007 downtown Shanghai Luwan District exist weekends than weekdays high ozone concentrations, and ozone precursors NO, NO 2 concentration is low weekends than weekdays the \This effect does not exist in Pudong. (2) In the filter type variable selection method under the framework of analytical methods and the use of partial least squares regression method to analyze the ozone impact factor. Found near ground-level ozone concentrations in different seasons impact factor is different. Throughout the year the greatest impact on the ozone near the ground is solar radiation and nitrogen oxides. The impact factor of the spring and summer are concentrated solar radiation, nitrogen oxides and relative humidity. (3) non-linear support vector machine approach ability to authenticate and comparative analysis. Through nonlinear neural network based linear regression methods are comparisons of support vector machine modeling has better nonlinear simulation capabilities for high-value point simulation is also good, better than the neural network and gradually regression method. (4) established a near-ground ozone concentration multivariate nonlinear time series forecasting model. CC by correlation integral method to determine the parameters of the phase space reconstruction time delay and embedding dimension after the reconstruction phase space, and then remove redundant information relative to the point, into support vector machine for training and through the establishment of optimal model parameter optimization and predict. The results show that the multivariate nonlinear time series prediction result was better than single-variable nonlinear time series prediction.

Related Dissertations

  1. Study on the Degradation of 2-MIB in Aqueous Solution by ZnOOH Catalized Ozonation,X703
  2. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  3. Research on Autamatic Music Structrue Analysis,TN912.3
  4. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  5. Fault Diagnosis Method Based on Support Vector Machine,TP18
  6. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  7. The Environmental-Friendly Method and Process of Removing Non-Cellulosic Matters from Bamboo for Textile Fiber,TS652
  8. New Technology and Basic Study on the Direet Preparation of PbO Powder from Galena by Selective Leaching Technology,TQ134.33
  9. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  10. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  11. Effects of Ozone on Ascorbic Acid-Glutathione Cycle in Soybean (Glycine Max) Leaves,S565.1
  12. Study on Advanced Oxidation Technology of Ozonation for Berberine Pharmaceutical Wastewater Treatment,X787
  13. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  14. Ozone pre-oxidation and coagulation combined process of removal of arsenic in drinking water,R123.1
  15. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  16. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  17. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. Source Profile and Chemical Reactivity of Volatile Organic Compounds (VOCs) form Vehicle Exhaust and Paints,X51
  20. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  21. Research of Facial Expression Recognition Algorithm,TP391.41

CLC: > Mathematical sciences and chemical > Mathematics > Probability Theory and Mathematical Statistics > Application of statistical mathematics
© 2012 www.DissertationTopic.Net  Mobile