Abstract
This paper is a methodological guide to using machine learning in the spatial context. It provides an overview of the existing spatial toolbox proposed in the literature: unsupervised learning, which deals with clustering of spatial data, and supervised learning, which displaces classical spatial econometrics. It shows the potential of using this developing methodology, as well as its pitfalls. It catalogues and comments on the usage of spatial clustering methods (for locations and values, both separately and jointly) for mapping, bootstrapping, cross-validation, GWR modelling and density indicators. It provides details of spatial machine learning models, which are combined with spatial data integration, modelling, model fine-tuning and predictions to deal with spatial autocorrelation and big data. The paper delineates “already available” and “forthcoming” methods and gives inspiration for transplanting modern quantitative methods from other thematic areas to research in regional science.
Highlights
Since its growth on the 1980s, machine learning (ML) has attracted the attention of many disciplines which are based on quantitative methods
The goal of this paper is to present a methodological overview of machine learning in the spatial context
Machine learning approaches to the dependency between variables are demonstrated by another class of models, which differ from traditional econometrics in following ways: (a) even if the input data (x and y) seem similar, the structure of the model itself is much less transparent; (b) as the machine learning modelling searches numerically for the best model, the forecasts are mostly much better than in classical theory- and user-feeling-driven approaches; and (c) due to data selection via boosting, sampling, bootstrapping, etc., the machine learning model can work with much bigger datasets
Summary
Since its growth on the 1980s, machine learning (ML) has attracted the attention of many disciplines which are based on quantitative methods. One can gather data from Open Street Map and Google Maps (in the form of background maps, points of interest (POI), roads and traffic, for example), as well as from geo-referenced images (such as satellite photographs (Rolf et al 2021), night light photographs and drone photographs), geo-tagged social media posts on Twitter and climate sensors This type of data requires powerful computational methods due to its complexity, diversity and volume. The goal of this paper is to present a methodological overview of machine learning in the spatial context It outlines the nature of the information ML gives us, and concludes if ML is substitutive or complementary to the traditional methods. General overview of these methods is presented in “Appendix 1” and their R implementation in “Appendix 3”
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
