Methods of building database to establish flooding map for coastal areas using a combination of artificial intelligence and GIS technology

Abstract

As a country with a coastline stretching from North to South, in recent
years natural disasters, especially floods and inundation, have severely
affected people and properties in Vietnam. In order to prevent and control
natural disasters and adapt to climate change, there have been many
researches to establish the flood-related map in the country. Among the
methods of creating flood maps, the application of AI (Artificial
Intelligence) combined with GIS (Geography Information System) has
outstanding advantages due to its ability to handle a mixture of many
types of input data in a geographical space unification. This method is also
used widely in the world in general and Vietnam in particular. When
applying the aforementioned method, building the input database of
machine learning and artificial intelligence models is an essential issue.
Based on the Sentinel-1, Landsat 8/9 images, digital elevation model
(DEM), and soil maps, the authors have built the input database for
modeling by using AI models. This paper introduces the method of
building the input database for making flood maps using machine
learning, and artificial intelligence combined with GIS. The computation
process is divided into two steps: (1) Editing the component data layers
from input data and (2) Standardization of data to transfer the
component data layers into the same unit with the standard data format
of Weka software. The research’s results are 11 data layers including the
flood map in the past, elevation, slope, slope direction, curvature, terrain
energy, geology, land use, soil, NDVI, NDWI for Quang Nam province