2020 Volume 76 Issue 2 Pages I_193-I_199
In recent years, the Ministry of Land, Infrastructure, Transport and Tourism is promoting the designation of sediment-related disaster warning areas as one of the measures against frequent sediment-related disasters. However, since the work requires a great deal of time and labor, efficiency improvement is required for continuous implementation.
Therefore, we constructed a system that automatically sets the sediment-related disaster warning area from the topographical data using deep learning, but there was a problem of setteing the sediment-related disaster warning area that does not include the conservation target. In this study, we examined whether it is possible to reconfigure only the sediment-related disaster warning area including the conservation target by filtering the data indicating the building. As a result, it was confirmed that the sediment-related disaster warning area that does not include the conservation target can be deleted, and it was shown that it is useful for improving the efficiency of the work of designating the sediment-related disaster warning area.
