---
id: articles/advances-in-geocomputation-and-geoai-for-mapping
about:
  label: >-
    Advances in geocomputation and geospatial artificial intelligence (GeoAI)
    for mapping
  description: >-
    2023 editorial review by Yongze Song and colleagues of how geocomputation
    and GeoAI are used in mapping, with a taxonomy of mapping applications and
    of the data types that feed them.
  tags:
    - geoai
    - geocomputation
    - mapping
    - remote sensing
    - review
article:
  url: 'https://doi.org/10.1016/j.jag.2023.103300'
  published: '2023-04-28'
  publisher: >-
    International Journal of Applied Earth Observation and Geoinformation
    (Elsevier)
  authors:
    - Yongze Song
    - Margaret Kalacska
    - Mateo Gašparović
    - Jing Yao
    - Nasser Najibi
provenance:
  origin: agent
  sources:
    - title: >-
        Advances in geocomputation and geospatial artificial intelligence
        (GeoAI) for mapping
      url: 'https://eprints.gla.ac.uk/317154/'
  created: '2026-10-17'
  reviewed: '2026-10-17'
  reviewed_by: 'Claude, from the sources listed'
  status: draft
import:
  source: openai-linkedin-scrape 2026-10-17
  id: DT001
  kind: survey
  family: research_and_evaluation
  priority: supporting
  verified: true
  posts:
    - P002
  posters:
    - Milan Janosov
domains:
  - places
---
An editorial in the International Journal of Applied Earth Observation and Geoinformation (volume 120, article 103300, published online 28 April 2023) by Yongze Song, Margaret Kalacska, Mateo Gašparović, Jing Yao and Nasser Najibi. It reviews how geocomputation and geospatial artificial intelligence have changed mapping work.

The paper sorts mapping applications into four groups: buildings and infrastructure, land use analysis, natural environment and hazards, and social issues and human activities. It sorts the data that feed them into seven types: in-situ data, geospatial datasets, crowdsourced geospatial data, remote sensing, photogrammetry, lidar and statistical data. It closes with challenges and opportunities, including the difficulty of building the particular properties of geospatial data into GeoAI models.

The published version is openly available from the University of Glasgow's Enlighten repository under a CC BY-NC-ND 4.0 licence.