Artificial intelligence-based solution to estimate the spatial accuracy of volunteered geographic data

Abstract

Volunteered geographic information (VGI) provides the ability for non-expert users to act as data producers and consumers. VGI has many advantages, but suffers from a general lack of quality assurance. This study addresses this lack and proposes a new approach for estimating positional accuracy as a data quality aspect in the context of VGI. This approach estimates the positional accuracy of the volunteered data using intrinsic indictors. For this purpose, indicators that influence VGI positional accuracy were extracted. The extracted indicators were applied in a hybrid artificial intelligence-based system to achieve a pattern for the relation between the indicators and the positional accuracy. The pattern was achieved using the volunteered data with corresponding reference data of each study region. The usefulness of the proposed method was demonstrated by applying it to estimation of the positional accuracy of an NCR (no corresponding reference) dataset.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 24 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.