학술논문

The Application of Remote Sensing Technology to the Interpretation of Land Use for Rainfall-Induced Landslides Based on Genetic Algorithms and Artificial Neural Networks
Document Type
Periodical
Source
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of. 2(2):87-95 Jun, 2009
Subject
Geoscience
Signal Processing and Analysis
Power, Energy and Industry Applications
Terrain factors
Satellites
Genetic algorithms
Artificial neural networks
Correlation
Remote sensing
Water conservation
Image classification
Geographic Information Systems
genetic algorithms
geographic information system
image classification
landslides
Language
ISSN
1939-1404
2151-1535
Abstract
In this paper, we explore the relationship between land use practices and landslides triggered by rainfall in eastern Taiwan. Before-and-after satellite images, combined with an artificial neural network method, enable the classification of land use and landslide zones. Genetic algorithms are used to evaluate the land use factors causing landslides. Using the geographic information system ArcGIS to support spatial reasoning, predictive maps are produced. The results suggest that the proposed method and procedures can be an effective tool for landslide monitoring and would be easily transferred to other similar applications.