Dissertation > Excellent graduate degree dissertation topics show

Inversion Based on Genetic BP neural network algorithm soil moisture

Author: LiuLiNa
Tutor: ChenYan
School: University of Electronic Science and Technology
Course: Measuring Technology and Instruments
Keywords: Artificial Neural Networks soil moisture inversion genetic algorithm passive microwave remote sensing AIEM model
CLC: S152.7
Type: Master's thesis
Year: 2011
Downloads: 156
Quote: 2
Read: Download Dissertation

Abstract


Soil moisture constitutes only about 0.005% in the global water resources, but it has great significance. Microwave remote sensing can work all-day, not affected by clouds, rain or fog, and has a strong penetrating power. These advantages are not available when using optical and infrared remote sensing methods to monitor the soil moisture. So microwave remote sensing has greatly improved the accuracy and reliability of inversion surface soil moisture. Microwave remote sensing contains passive microwave remote sensing and active microwave remote sensing, compared to passive microwave remote sensing, the advantage of active microwave remote sensing is a high spatial resolution. Especially with a series of satellite that carry active microwave sensor launched successfully, it is easy to get a number of SAR data which provide important basis data researches for soil moisture monitoring.Based on genetic algorithm (GA)and artificial neural networks (ANN), this paper proposes a new retrial algorithm, genetic algorithm to optimize BP network. The first step to make a chromosome which include the BP network hidden layer number and weight of each layer, code it. Then it must be established an appropriate fitness function that based on the need of the problem. After calculating individual fitness values,chromosome is to be selection, crossover and mutation according to the size of value. Finally it gets a set of optimal value. The set of optimal parameter values is assigned to the new BP network. The optimization algorithm is not only getting the best optimal parameter values in the global scope, but also reducing the training time for the BP network. The training data choose improved advanced integral equation(AIEM) model, because it is better than any models, it is effective to simulation the actual scattering surface. When completing training network, the HH polarization and VV polarization backscatter coefficients are input data, soil moisture represented by the topp dielectric model formula.In this paper, the GA-BP algorithm is used to retrieval the bare soil moisture,HH polarization backscattering coefficient and VV polarized backscattering coefficient as input data are measured by indoor scattering measurement system. Comparing inversion results with real samples moisture, relative error value is small. The GA-BP algorithm also uses to be retrieval soil moisture from airborne SAR images and ENVISAT satellite images. Airborne SAR image is a bare soil surface, ENVISAT image is a place covered by vegetation. Both inversion results are close to real samples moisture, although they need some improvement. In short, GA-BP algorithm is an effective inversion method that can be used for large areas of surface soil moisture inversion.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. Attitude Control Law Design Based on Blended Lateral Jets and Aerodynamic Control,V249.1
  3. Research on Control Method of Moving-Mass and Lateral Thrust Combined Missile,TJ765
  4. The Application of Fuzzy Comprehensive Evaluation Based on Genetic Algorithm in Vocational Evaluation of Classroom Teaching,G712
  5. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  6. Drip Irrigation Control System Based on Pulse Width Modulation (PWM),S152.7
  7. The Effect of Water Content in Soil on Photosynthetic Physiological Characteristics of Pear and Fruit Quality,S661.2
  8. Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18
  9. Effects of Different Corn Planting Densities on Soil Moisture and Yield in Rainfed Farming Land of North-east of China,S513
  10. A Preliminary Study on Bare Soil Extraction and Its Moisture Retrieval from High Resolution SAR Data,S152.7
  11. Optical Properties of Chlorphyll-a in Reservoir Water and Its Concentration Inversion Models by Remote Sensing,S127
  12. Remote sensing data processing grid platform design and initial implementation,TP79
  13. Mining resources based on genetic algorithm optimization model of,O224
  14. Stress distribution law FLAC 3D simulation study,TU452
  15. Characteristics of Soil Respiration, Grain Yield and Water Use Efficiency in Crop Fields under Different Mulching Modes and Crop Conditions,S154
  16. The Application of STIR-FLAIR and T2W-SPIR for Diagnosing the Orbital Lesions: a Contrast Study,R777
  17. Research on the Milling Performance and Parameters Optimization with Large Parts of Heavy Machine,TG54
  18. The Study of Inversion of Vegetation Biochemistry Parameters and Authentic Examination Based on High Spectral Remote Sensing,TP79
  19. Based on U-face Model and Genetic Algorithm Face Recognition Technology Research,TP391.41
  20. Intelligent Vehicle Scheduling Model Research and Application in Logistic Distribution,O242.1
  21. Research and Application on Ant Clustering Algorithm,TP18

CLC: > Agricultural Sciences > Agriculture as the foundation of science > Soil > Soil physics > Soil moisture
© 2012 www.DissertationTopic.Net  Mobile