Machine learning or artificial techniques has been rapidly transforming many areas related to GIS and spatial applications. One example is using web GIS with machine learning algorithms to predict or forecast the success of given potential hotel sites. This has been created into an application called Hotel Location Selection and Analyzing Toolset (HoLSAT). Techniques such as pursuit regression, artificial neural network, and support vector regression allow the tool to determine beneficial hotel locations based on a variety of criteria.
Determining where landslides might occur is also another potential application for machine learning techniques such as decision trees (DT) and adaptive neuro-fuzzy inference methods. The integration of GIS allows both spatially input but also a way to understand how given regions could be affected under different scenarios. In fact, general hazard forecast mapping is increasingly becoming popular in application with machine learning methods. Flood susceptibility assessments, for instance, are another area where spatial data are used with methods such as support vector machine methods with spatial data and inputs that include altitude, slope, curvature, and stream power index to forecast flooding susceptibility.
Other approaches have utilized GIS and real time social media data to understand the spread of influenza. Twitter messages, in this case, were collected and studies for different cities in the US in the 2013–2014 flu season using the Visualizing Information Space in Ontological Networks. Tweets can be scraped and information collected that incorporate spatial information about where outbreaks are reported. Machine learning is used to classify data so that unneeded data are removed.
 For more on this artificial intelligence or machine learning application used for determine optimal hotel locations, see: Yang, Y., Tang, J., Luo, H., & Law, R. (2015). Hotel location evaluation: A combination of machine learning tools and web GIS. International Journal of Hospitality Management, 47, 14–24. https://doi.org/10.1016/j.ijhm.2015.02.008
 For more on using machine learning for understanding landslides, see: Pradhan, B. (2013). A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Computers & Geosciences, 51, 350–365. https://doi.org/10.1016/j.cageo.2012.08.023
 For more on flooding susceptibility and machine learning, see: Tehrany, M. S., Pradhan, B., Mansor, S., & Ahmad, N. (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. CATENA, 125, 91–101. https://doi.org/10.1016/j.catena.2014.10.017
 For more on machine learning techniques using Twitter and GIS, see: Allen, C., Tsou, M.-H., Aslam, A., Nagel, A., & Gawron, J.-M. (2016). Applying GIS and Machine Learning Methods to Twitter Data for Multiscale Surveillance of Influenza. PLOS ONE, 11(7), e0157734. https://doi.org/10.1371/journal.pone.0157734.