Machine learning and geospatial technologies
Izabela Karsznia · 2023
Machine learning (ML) has recently been recognized as a promising generalization technique and even called by some researchers a new paradigm for cartographic generalization. The research described in this chapter follows this paradigm shift in the map generalization process as it aims to design and verify ML models for automatic settlement selection. First, it outlines the concept of ML as well as ML types and selected ML models. Second, it presents an example study of automatic settlement selection for small-scale maps using ML models. With this example, the chapter shows how to apply deep learning (DL), random forest (RF), decision tree (DT), and decision tree supported with genetic algorithms (DT_GA) models to a varied settlement data sample.