Institutional Repository of Vilnius University
Apklausos duomenų erdvinis interpoliavimas šalies lygmeniu /
Abstract
dc:descriptionArtificial Intelligence (AI) methods can be applied to interpolate the spatial distribution of survey data at the territorial level. The aim of this paper is to develop a universal system based on AI techniques that utilizes survey data and publicly available information sources to identify and predict spatial distribution of indicators at the national level. Experiments carried out: data preparation, training of AI models, application of these models for survey data interpolation, and visualization of the spatial results. A universal system with a user interface was developed, capable of interpolating different types of survey data at the country level. To perform spatial interpolation, three AI methods were applied: random forests, support vector machines, and graph neural networks. The models produced very similar results but did not achieve high metrics, mainly due to the small dataset sizes and imbalanced class distributions. This study outlines the steps required to develop a universal AI-based system capable of processing various datasets and performing survey data interpolation at the national level.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Dovidaitis, Jonas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239030201&prefLang=en_US