Abstract
Geographical factors have influenced the distributions and densities of global human population distributions for centuries. Climatic regimes have made some regions more habitable than others, harsh topography has discouraged human settlement, and transport links have encouraged population growth. A better understanding of these types of relationships enables both improved mapping of population distributions today and modelling of future scenarios. However, few comprehensive studies of the relationships between population spatial distributions and the range of drivers and correlates that exist have been undertaken at all, much less at high spatial resolutions, and particularly across the low- and middle-income countries. Here, we quantify the relative importance of multiple types of drivers and covariates in explaining observed population densities across 32 low- and middle-income countries over four continents using machine-learning approaches. We find that, while relationships between population densities and geographical factors show some variation between regions, they are generally remarkably consistent, pointing to universal drivers of human population distribution. Here, we find that a set of geographical features relating to the built environment, ecology and topography consistently explain the majority of variability in population distributions at fine spatial scales across the low- and middle-income regions of the world.
Highlights
While archaeologists have long stated that settlement patterns are complex and multi-factorial, geography has always been a determinant of the location of human settlements with humans primarily settling where resources are available, such as coastal areas and arable lands [1,2,3,4,5]
We find that a set of geographical features relating to the built environment, ecology and topography consistently explain the majority of variability in population distributions at fine spatial scales across the low- and middle-income regions of the world
We took the random forest (RF) regression model objects for each sample country which were trained at the administrative unit level of the corresponding census-based population data, extracted the covariate importance metrics, standardized what the covariates were representing to facilitate comparisons across models and analysed these data for differences between and within covariate classes as well as within each covariate class between all countries, between regions and within regions to begin to address the possibility of geographic variability in these relationships
Summary
While archaeologists have long stated that settlement patterns are complex and multi-factorial, geography has always been a determinant of the location of human settlements with humans primarily settling where resources are available, such as coastal areas and arable lands [1,2,3,4,5]. Sometimes humans have modified the environment in ways that make it less habitable, such as through pollution and desertification, or no longer habitable, such as in the cases of radiation in areas surrounding Chernobyl or desiccation of the Aral Sea [8,12,13]. With these changes, settlements and urban areas and populations continue to grow and their spatial distributions continue to evolve [14,15,16]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
