Machine learning applications to spatiotemporal land-use change modeling

Emre Tepe

Chapter 13 in Handbook on Big Data, Artificial Intelligence and Cities, 2025, pp 257-276 from Edward Elgar Publishing

Abstract: Recent advancements in GIS and information technologies enable fine-scale spatial data collection for modeling land-use changes (LUC) in urban and rural systems. Managing future land development and safeguarding natural, social, and economic systems requires accurate LUC modeling. Dealing with spatial datasets can pose computational and statistical challenges due to the increased data size. Machine learning (ML) applications, particularly deep learning (DL) models, require significant data for accurate results. In spatial econometric modeling, constructing and using spatial weight matrices for parameter estimations present challenges. Recent computational advancements have made ML a feasible option. ML and DL frameworks can capture non-linear relationships, thereby improving models’ representation of human behaviors and market dynamics. This chapter explores the application of ML and DL methods, such as random forests (RF), extreme gradient boosting (XGBoost), and artificial neural networks (ANN) to LUC models, analyzing their computational and predictive performance.

Keywords: Artificial neural networks; Random forests; Extreme gradient boosting; Spatial dependency; Big data (search for similar items in EconPapers)
Date: 2025
ISBN: 9781803928043
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781803928050.00021 (application/pdf)

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:elg:eechap:21797_13

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Darrel McCalla ().