Dissertation > Excellent graduate degree dissertation topics show

Research of Maize Yield Prediction System Based on RS and TSDM

Author: LiXinLei
Tutor: ChenGuiFen
School: Jilin Agricultural University
Course: Applied Computer Technology
Keywords: Remote sensing Time series Measurement of production Model identification
CLC: S513
Type: Master's thesis
Year: 2011
Downloads: 54
Quote: 2
Read: Download Dissertation

Abstract


Countries in the world of precision agriculture research is the rapid development of China in the development of precision agriculture aspects of the investment is constantly increasing. The use of remote sensing technology for the growth of crops conduct dynamic monitoring, crop acreage as well as an estimate for crop yield forecasting precision agriculture in China has become a research hotspot. Remote sensing images used in this article is from tutors national 863 project: \Get remote sensing image can not be directly used, the need for processing of remote sensing image processing software to extract the thematic information. This article uses remote sensing image processing software ENVI, ENVI has a powerful multi-spectral image processing capabilities to fully extract the image information, a complete projection with rich package that can support various projection types. In this paper, Yushu City, Jilin Province maize for the study, the use of remote sensing image processing, data mining technology, the experimental area planted maize crop yield forecast. (1) on the remote sensing image processing, to establish a normalized difference vegetation index and the relationship between corn yield model. Remote Sensing of early maize production is the use of multi-year mission similar phase spectral remote sensing images, which after a series of remote sensing image processing, the use of principal component analysis was applied to select a major factor in corn production decisions. Extract the normalized difference vegetation index and statistical output information based on the relationship, build corn yield and normalized difference vegetation index regression equation. Establish a high accuracy and operability of the corn yield monitor model. (2) Principal component analysis for data dimensionality reduction, the establishment of maize yield time series forecasting model. Remote sensing images can be obtained from the mass of data, even after the principal component analysis method from a few factors affecting maize yield, the amount of data is still large. Reflecting the timing of corn production normalized difference vegetation index has a very significant trend, its analysis is to find the sequence of this trend, and to use this trend for the development of the sequence to make reasonable predictions. Corn production is based on a random non-stationary series, so this paper autoregressive moving average model (ARIMA). (3) on corn yield prediction models for model matching and parameter estimation to determine the precision of the model. Remote sensing images obtained from the timing of the calendar year reflected the impact of corn growth factors as research data, through the corn yield time series autocorrelation function of the partial correlation function analysis, we can determine the ARIMA (p, d, q) model and corn production sequence recognition is better. Six experimental application of the model yield monitor data accuracy test results show that ARIMA (1,2,1) model predicted results were satisfactory, compared with the actual production data, the error is less than 5% precision control.

Related Dissertations

  1. Temperature Drift Modeling and Compensation of Fiber-Optic Gyroscopes,V241.5
  2. Research on Spaceborne Hyperspectral Sensor Simulation,TP391.9
  3. Research on Remote Sensing Image Processing Combining High Fidelity Compression and Resolution Enhancement,TP751
  4. Road extraction algorithm based on region segmentation of remote sensing image,TP751
  5. Modelling Phycocyanin and CDOM Concentration from Hyperspectral Reflectance Data in Lake Taihu,X87
  6. A Study on Building Remote Sensing Retrieval System for Countryside Water-Body Quality Based on ArcGIS Server,S127
  7. Spectral Characteristics of Rice Damaged by Nilaparvata Lugens (St(?)l) and Cnaphalocrocis Medinalis(Guen(?)e),S435.112
  8. Study on Growth Monitoring Technique Based on Pixel Un-Mixing Method and HJ Remote Sensing Images in Paddy Rice,S511
  9. Study on Growth Predicting Technique Based on Integration of Remotely Sensed Information and Crop Model in Rice,S511
  10. Study on Growth Monitoring and Predicting Technique Based on Integration of Remote Sensed Information and Model in Wheat,S512.1
  11. The Estimation on the Total Nitrogen of the Rice Field by Remote Sensing in Lishui County, Nanjing City,S153
  12. Crop Evapotranspiration Study on Evolution Rule and Forecast Model in Chaoyang Area,S161.4
  13. Optical Properties of Chlorphyll-a in Reservoir Water and Its Concentration Inversion Models by Remote Sensing,S127
  14. Land Desertification in Qinghai Lake Landscape Pattern Change,X171
  15. Remote sensing data processing grid platform design and initial implementation,TP79
  16. Web-based scientific computing legacy application sharing technology research,TP393.09
  17. Designing and Realization Integreated Management System of Multi-Source Remote Sensing Image in Mining Area,P208
  18. Based on Data Mining Technologies in Urban Water Supply Analysis and Decision,F299.24;F224
  19. Targets Recognition in High-Resolution Remote Sensing Image,TP751
  20. Design and Implementation of Remote Sensing Image Classification Algorithms for Parallel Computing System,TP751
  21. The Design and Implementation of PGIS on Intelligent Mobile Terminal,TN929.53

CLC: > Agricultural Sciences > Crop > Cereal crops > Corn ( maize )
© 2012 www.DissertationTopic.Net  Mobile