Resumen
The complexity of a road network must be reduced after a scale change, so that the legibility of the map can be maintained. However, deciding whether to show a particular road section on the map is a very complex process. This process, called selection, constitutes the first step in a sequence of further generalization operations and it is a prerequisite to effective road network generalization. So far, not many comprehensive solutions have been developed for effective road selection specifically at small scales as the studies have mainly dealt with large-scale maps. The paper presents an experiment using machine learning (ML), specifically decision-tree-based (DT) models, to optimize the selection of the roads from 1:250,000 to 1:500,000 and 1:1,000,000 scales. The scope of this research covers designing and verifying road selection models on the example of three selected districts in Poland. The aim is to consider the problem of road generalization holistically, including numerous semantic, geometric, topological, and statistical road characteristics. The research resulted in a list of measurable road attributes that comprehensively describe the rank of a particular road section. The outcome also includes attribute weights, attribute correlation calculated for roads, and machine learning models designed for automatic road network selection. The performance of the machine learning models is very high and ranges from 80.94% to 91.23% for the 1:500,000 target scale and 98.21% to 99.86% for the 1:1,000,000 scale.