Abstract

Spatial development plans are the basic tool for shaping spatial policy and have an impact on the implementation of the concept of sustainable development. Monitoring the implementation of plans can be difficult where no standard of plans exists that allows for obtaining comprehensive information on the arrangements of the plans, including future land development. The purpose of the research is to integrate spatial development plans by analyzing and classifying their textual content. We use machine learning methods for the processing of the text of plans and their classification. The result is a model, that classifies the texts of findings for individual areas in the plan into defined land use categories. We use machine learning methods in natural language processing for the analyzing of the text part of plans and their classification. The results indicate the best quality of the model when using neural networks. The proposed approach allows for obtaining comprehensive information on the planned land use of the area, derived from many heterogeneous planning documents. Due to the combination of textual arrangements with spatial data, it allows both for the unification of land use classification and then integration of multiple spatial development plans in spatial dimension.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call