LVRF: A Latent Variable Based Approach for Exploring Geographic Datasets

Geographic datasets are usually accompanied by spatial non-stationarity – a phenomenon that the relationship between features varies across space. Naturally, nonstationarity can be interpreted as the underlying rule that decides how data are generated and alters over space. Therefore, traditional machine learning algorithms are not suitable for handling non-stationary geographic datasets, as they only render a single global model. To solve this problem, researchers often adopt the multiple-local-model approach, which uses different models to account for different sub-regions of space. This approach has been proven efficient but not optimal, as it is inherently difficult to decide the size of subregions. Additionally, the fact that local models are only trained on a subset of data also limits their potential. This paper proposes an entirely different strategy that interprets nonstationarity as a lack of data and addresses it by introducing latent variables to the original dataset. Backpropagation is then used to find the best values for these latent variables. Experiments show that this method is at least as efficient as multiple-local-model-based approaches and has even greater potential.

Back-propagation, Geographically Weighted Regression (GWR), Latent Variable, Machine Learning Algorithm, Nonstationary, Random Forest

1. ISO/TC 211 committee, “ISO/TC 211,” https:// www.iso.org/committee/54904.html, 2011.

2. C. Beath, I. Becerra-Fernandez, J. Ross, and J. Short, “Finding value in the information explosion,” MIT Sloan Management Review, vol. 53, pp. 18–20, 06 2012.

3. E. Spyrou and Y. Avrithis, “A region thesaurus approach for high-level concept detection in the natural disaster domain,” vol. 4816, 12 2007, pp. 74– 77.

4. P. Partsinevelos and Z. Mitraka, “Change detection of surface mining activity and reclamation based on a machine learning approach of multitemporal landsat tm imagery,” Geocarto International, vol. 28, pp. 1–20, 01 2012.

5. A. Wheeler and W. Steenbeek, “Mapping the risk terrain for crime using machine learning,” 01 2020.

6. Y. Meidan, M. Bohadana, A. Shabtai, J. D. Guarnizo, M. Ochoa, N. O. Tippenhauer, and Y. Elovici, “Profiliot: A machine learning approach for iot device identification based on network traffic analysis,” in Proceedings of the Symposium on Applied Computing, ser. SAC ’17. New York, NY, USA: Association for Computing Machinery, 2017, p. 506–509. [Online]. Available: https://doi.org/10.1145/3019612.3019878

7. C. Brunsdon, A. S. Fotheringham, and M. E. Charlton, “Geographically weighted regression: A method for exploring spatial nonstationarity,” Geographical Analysis, vol. 28, no. 4, pp. 281–298, 1996. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10. 1111/j.1538-4632.1996.tb00936.x

8. S. Georganos, T. Grippa, A. N. Gadiaga, C. Linard, M. Lennert, S. Vanhuysse, N. Mboga, E. Wolff, and S. Kalogirou, “Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling,” Geocarto International, pp. 1–16, 2019.

9. A. S. Fotheringham, W. Yang, and W. Kang, “Multiscale geographically weighted regression (mgwr),” Annals of the American Association of Geographers, vol. 107, no. 6, pp. 1247–1265, 2017.

10. J. Morgan, R. Dougherty, A. Hilchie, and B. Carey, “Sample size and modeling accuracy with decision tree based data mining tools,” Acad Inf Manag Sci J, vol. 6, 01 2003.

...