Machine learning algorithms such as Random Forest (RF) are being increasingly applied on traditionally geographical topics such as population estimation. Even though RF is a well performing and generalizable algorithm, the vast majority of its implementations are still ‘aspatial’ and may not address spatial heterogenous processes. At the same time, remote sensing (RS) data which are commonly used to model population can be highly spatially heterogeneous. From this scope, we present a novel geographical implementation of RF, named Geographical Random Forest (GRF) as both an predictive and exploratory tool to model population as a function of RS covariates. GRF is a disaggregation of RF into geographical space in the form of local sub-models. From the first empirical results, we conclude that GRF can be more predictive when an appropriate spatial scale is selected to model the data, with reduced residual autocorrelation and lower Root Mean Square Error and Mean Absolute Error values. Finally, and of equal importance, GRF can be used as an effective exploratory tool to visualize the relationship between dependent and independent variables, highlighting interesting local variations and allowing for a better understanding of the processes that may be causing the observed spatial heterogeneity.

This study evaluates the impact of four feature selection (FS) algorithms in an object-based image analysis framework for very-high-resolution land use-land cover classification. The selected FS algorithms, correlation-based feature selection, mean decrease in accuracy, random forest (RF) based recursive feature elimination, and variable selection using random forest, were tested on the extreme gradient boosting, support vector machine, K-nearest neighbor, RF, and recursive partitioningclassifiers, respectively. The results demonstrate that the selection of an appropriate FS method can be crucial to the performance of a machine learning classifier in terms of accuracy but also parsimony. In this scope, we propose a new metric to perform model selection named classification optimization score (COS) that rewards model simplicity and indirectly penalizes for increased computational time and processing requirements using the number of features for a given classification model as a surrogate. Our findings suggest that applying rigorous FS along with utilizing the COS metric may significantly reduce the processing time and the storage space while at the same time producing higher classification accuracy than using the initial dataset.

The aim of this paper is to present developments of an advanced geospatial analytics algorithm that improves the prediction power of a random forest regression model while addressing the issue of spatial dependence commonly found in geographical data. We applied the methodology to a simple model of mean household income in the European Union regions to allow easy understanding and reproducibility of the analysis. The results are encouraging and suggest an improvement in the prediction power compared to previous techniques. The algorithm has been implemented in R and is available in the updated version of the SpatialML package in the CRAN repository.