Evolving Spatially Aggregated Features from Satellite Imagery for Regional Modeling
Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for analysis and actionable insight. In this paper, we propose a novel method of inducing spatial aggregations as a component of the machine learning process, yielding regional model features whose construction is driven by model prediction performance rather than prior assumptions. Our results demonstrate that Genetic Programming is particularly well suited to this type of feature construction because it can automatically synthesize appropriate aggregations, as well as better incorporate them into predictive models compared to other regression methods we tested. In our experiments we consider a specific problem instance and real-world dataset relevant to predicting snow properties in high-mountain Asia.
KeywordsSpatial aggregation Feature construction Genetic programming Symbolic regression
Thanks to Dr. Jeff Dozier (UCSB) for posing the high-mountain Asia SWE problem and providing associated datasets.
- 11.Rees, J., Gibson, A., Harrison, M., Hughes, A., Walsby, J.: Regional modelling of geohazard change. Geol. Soc. Lond. Eng. Geol. Spec. Publ. 22(1), 49–63 (2009)Google Scholar
- 14.Stanislawska, K., Krawiec, K., Vihma, T.: Genetic programming for estimation of heat flux between the atmosphere and sea ice in polar regions. In: Proceedings of the 2015 on Genetic and Evolutionary Computation Conference, pp. 1279–1286. ACM (2015)Google Scholar