期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：11
页码：232-239
出版社：Science and Information Society (SAI)
摘要：Floods have been a recurring problem for a
number of countries around the world including Pakistan. It is
believed that densely populated forests at river banks can
prevent floods from spreading towards settlements and
farmlands. The role of forest in flood spread has been an area of
research for a while but the role of predictive modeling in this
area is yet to be investigated in detail. In this study, we have used
predictive analytics and satellite imagery to develop an
environmental model that can predict the flood spread by
considering forest cover at river bank and month of the year as
parameters. We have used the satellite images of an area situated
in the northern region of Pakistan i.e. Dera Ghazi Khan from the
USGS’s Land Sat program. These images comprised of a section
of the Indus River and its adjoining areas. We want to analyze
the forest bank at various section of the Indus River. We
developed and trained our predictive model by using the satellite
imagery data and tested it on a separate dataset to determine
error percentage. The model showed significant promise and
predicted the flood spread with an average accuracy of above
80%.
