Premium
A Genetic Algorithm for Tributary Selection with Consideration of Multiple Factors
Author(s) -
Zhang Ling,
Guilbert Eric
Publication year - 2017
Publication title -
transactions in gis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.721
H-Index - 63
eISSN - 1467-9671
pISSN - 1361-1682
DOI - 10.1111/tgis.12205
Subject(s) - tributary , drainage , generalization , drainage network , selection (genetic algorithm) , fitness function , genetic algorithm , computer science , algorithm , data mining , aggregate (composite) , drainage system (geomorphology) , drainage basin , hydrology (agriculture) , geography , artificial intelligence , geology , cartography , mathematics , machine learning , ecology , geotechnical engineering , biology , materials science , composite material , mathematical analysis
Drainage systems are important components in cartography and Geographic Information Systems (GIS), and achieve different drainage patterns based on the form and texture of their network of stream channels and tributaries due to local topography and subsurface geology. The drainage pattern can reflect the geographical characteristics of a river network to a certain extent. To preserve the drainage pattern during the generalization process, this article proposes a solution to deal with many factors, such as the tributary length and the order in river tributary selection. This leads to a multi‐objective optimization problem solved with a Genetic Algorithm. In the multi‐objective model, different weights are used to aggregate all objective functions into a fitness function. The method is applied on a case study to evaluate the importance of each factor for different types of drainage and results are compared with a manually generalized network. The result can be controlled by assigning different weights to the factors. From this work, different weight settings according to drainage patterns are proposed for the river network generalization.