Abstract
This paper aims to develop a model for debris flow hazard assessment, since Taiwan is a mountainous country subject to bouts of heavy rainfall during the rainy and typhoon seasons and is thus frequently subject to landslide disasters. The database used is comprised of information from actual cases that occurred in areas of Hualien in eastern Taiwan during 2007 and 2008. The Kalman filter model is utilized to assess the occurrence of debris flows from computed indexes, to verify modeling errors. Comparisons are made between two models to determine which one is better in practical applications. The efficiency of the Kalman filter decision system has been proved, showing smaller average relative error and correspondingly larger ratio of success on debris flow assessment when compared to the neural network model. The relative error is calculated between the differences in the ratio of model outputs and that of actual occurrences. Such an error index can be decreased from 4.65 to 3.39% by introducing the concept of geographic divisions to the Kalman filter model, which demonstrates its ability to forecast the occurrence of debris flows for the coming year.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
