Autocart -- spatially-aware regression trees for ecological and spatial modeling

Abstract

Many ecological and spatial processes are complex in nature and are not accurately modeled by linear models. Regression trees promise to handle the high-order interactions that are present in ecological and spatial datasets, but fail to produce physically realistic characterizations of the underlying landscape. The "autocart" (autocorrelated regression trees) R package extends the functionality of previously proposed spatial regression tree methods through a spatially aware splitting function and novel adaptive inverse distance weighting method in each terminal node. The efficacy of these autocart models, including an autocart extension of random forest, is demonstrated on multiple datasets. This highlights the ability of autocart to model complex interactions between spatial variables while still providing physically realistic representations of the landscape.

arXiv comment20 pages, 10 figures

References in corpus (2)

• Importance of spatial predictor variable selection in machine learning applications -- Moving from data reproduction to spatial prediction
• Soil Property and Class Maps of the Conterminous US at 100 meter Spatial Resolution based on a Compilation of National Soil Point Observations and Machine Learning