Due to the heavy withdrawal of underground water for cultivating fishery and industrial factories, the land subsidence
occurred in southwestern Taiwan has resulted in environmental hazard and potential risk. In order to fully realise the
subsidence characteristics and establish a subsidence prediction function for any possible application in the study area,
the height variation was estimated and tested for the representative site of Pei-Kang (PKGM), using some selected
models, i.e. the linear regression, grey theory and artificial neural network. Since different estimation models associate
with different time spans of the data, a series of GPS-based vertical coordinates was categorised into two groups of data
set, namely a long-term (52 weeks) data set and a short-term (5 weeks) data set, both collected at PKGM for around 10
years (from 1996 to 2005). Using short-term data set, the prediction errors showed that a linear regression model works
slightly better than grey theory. Since the land subsidence is possibly related to various natural factors, such as time,
stream flow rate, ground water elevation or underground water level, etc., this paper also investigates the factor
identification based on the height predictions using a multi-variant type of regression model and artificial neural network
model. It was found that the prediction models can present a 1 cm level of height prediction error. Moreover, the most
dominating influence factor was tested to be the variable of time. An artificial neural network operated with the main
factor of time is capable of working with the long-term GPS data set to effectively predicate a 1 cm level of height
variation in a significant land subsidence area.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.