Integrating remotely sensed data on land cover with socio-economic data is a key challenge of land change science. This paper has the objective to explore possible links between forest cover change and characteristics of socialecological systems at regional scale based mainly on census data. We assessed relationships between population, poverty, ethnicity, accessibility, land tenure, concessions, protected areas and forest cover change in the last decade for four regions of Bolivia and the Lao PDR, thanks to the calculation of influence areas of communities based on travel time. We found that population density, poverty, ethnicity, accessibility, land tenure and forest cover change are usually interdependent, but do not follow a straightforward model of increasing forest loss with population and poverty. These dependencies were used to elaborate a typology of social-ecological systems in the study areas, identifying three challenging contexts: 1) cash crop expansion areas with high forest loss, less poverty and dominant ethnic groups; 2) smallholder areas with both forest loss and gain, high ethnic diversity and a gradient of market integration, and 3)
remote areas near national borders, with low population and surprisingly high forest loss.