Embedding scale: new thinking of scale in machine learning and geographic representation

May Yuan () and Arlo McKee ()
Additional contact information
May Yuan: University of Texas at Dallas
Arlo McKee: University of Texas at Dallas

Journal of Geographical Systems, 2022, vol. 24, issue 3, No 11, 524 pages

Abstract: Abstract Concepts of scale are at the heart of diverse scientific endeavors that seek to understand processes and how observations and analyses influence our understanding. While disciplinary discretions exist, researchers commonly devise spatial, temporal, and organizational scales in scoping phenomena of interest and determining measurements and representational frameworks in research design. The rise of the Fourth Paradigm for science drives data-intensive computing without preconceived notions regarding at what scale the phenomena or processes of interest operate, or at which level of details meaningful patterns may emerge. While scale is the a priori consideration for theory-driven research to seek ontological and relational affirmations, big data analytics and machine learning embed scale in algorithms and model outputs. In this paper, we examine embedded scale in data-driven machine learning research, connect the embedding scale to scale operating in the general theory of geographic representation in GIS and scaffold our arguments with a study of using machine learning to detect archeological features in drone-collected high-density images.

Keywords: Scale; Machine learning; Geographic representation; High-density measurements; Archeological feature extraction (search for similar items in EconPapers)
JEL-codes: C89 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10109-022-00378-6 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:jgeosy:v:24:y:2022:i:3:d:10.1007_s10109-022-00378-6

Ordering information: This journal article can be ordered from
http://www.springer. ... ce/journal/10109/PS2

DOI: 10.1007/s10109-022-00378-6

Access Statistics for this article

Journal of Geographical Systems is currently edited by Manfred M. Fischer and Antonio Páez

More articles in Journal of Geographical Systems from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().