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 is 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 a 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 Squared Error (RMSE) and Mean Absolute Error (MAE) 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.
Frequency of contacts with the family is an indicator of the strength of intergenerational exchange and potential support for older people. Although the availability of children clearly represents a constraint on potential family support, the extent of interaction with and support received from children depends on factors other than demographic availability alone. This study examined the effects of socio-economic and demographic variables on weekly contacts with children in Great Britain, Italy, Finland and The Netherlands using representative survey data which included information on availability of children and extent of contact. Our results confirm the higher level of parent adult-child contact in Italy than in northern European countries, but levels of contact in all the countries considered were high. Multivariate analysis showed that in most countries characteristics such as divorce were associated with a reduced probability of contact between fathers and children; in Finland this also influenced contact between mothers and children. Analyses are also included of possible future scenarios of contact with children that combine the observed effects of the explanatory variables with hypothetical changes in population distribution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.