We performed a multi-date composite change detection technique using a dense-time stack of Landsat data to map land-use and land-cover change (LCLUC) in Mainland Southeast Asia (MSEA) with a focus on the expansion of boom crops, primarily tree crops. The supervised classification was performed using Support Vector Machines (SVM), which are supervised non-parametric statistical learning techniques. To select the most suitable SMV classifier and the related parameter settings, we used the training data and performed a two-dimensional grid search with a three-fold internal cross-validation. We worked in seven Landsat footprints and found the linear kernel to be the most suitable for all footprints, but the most suitable regularization parameter C varied across the footprints. We distinguished a total of 41 LCLUCs (13 to 31 classes per footprint) in very dynamic and heterogeneous landscapes. The approach proved useful for distinguishing subtle changes over time and to map a variety of land covers, tree crops, and transformations as long as sufficient training points could be collected for each class. While to date, this approach has only been applied to mapping urban extent and expansion, this study shows that it is also useful for mapping change in rural settings, especially when images from phenologically relevant acquisition dates are included. Full article

This study explores the relationships between forest cover change and the village resettlement and land planning policies implemented in Laos, which have led to the relocation of remote and dispersed populations into clustered villages with easier access to state services and market facilities. We used the Global Forest Cover Change (2000–2012) and the most recent Lao Agricultural Census (2011) datasets to assess forest cover change in resettled and non-resettled villages throughout the country. We also reviewed a set of six case studies and performed an original case study in two villages of Luang Prabang province with 55 households, inquiring about relocation, land losses and intensification options. Our results show that resettled villages have greater baseline forest cover and total forest loss than most villages in Laos but not significant forest loss relative to that baseline. Resettled villages are consistently associated with forested areas, minority groups, and intermediate accessibility. The case studies highlight that resettlement coupled with land use planning does not necessarily lead to the abandonment of shifting cultivation or affect forest loss but lead to a re-spatialization of land use. This includes clustering of forest clearings, which might lead to fallow shortening and land degradation while limited intensification options exist in the resettled villages. This study provides a contribution to studying relationships between migration, forest cover change, livelihood strategies, land governance and agricultural practices in tropical forest environments. Full article

The aim of this paper is to explore possible links between forest cover change and characteristics of social-ecological systems at sub-national scale based mainly on census data. We assessed relationships between population density, poverty, ethnicity, accessibility and forest cover change during the last decade for four regions of Bolivia and the Lao PDR, combining a parcel-based with a cell-based approach. We found that accessibility is a key driver of forest cover change, yet it has the effect of intensifying other economic and policy-related underlying drivers, like colonization policies, cash crop demand, but also policies that lead to forest gain in one case. Poverty does not appear as a driver of deforestation, but the co-occurrence of poverty and forest loss driven by external investments appears critical in terms of social-ecological development. Ethnicity was found to be a moderate explanatory of forest cover change, but appears as a cluster of converging socio-economic characteristics related with settlement history and land resource access. The identification of such clusters can help ordering communities into a typology of social-ecological systems, and discussing their possible outcomes in light of a critical view on forest transition theory, as well as the relevance and predictive power of the variables assessed. Résumé: L’objectif de cet article est d’explorer les liens entre le changement de la couverture forestière et les caractéristiques des systèmes socio-écologiques à l’échelle nationale, principalement à l’aide de données de recensement. Nous avons évalué les relations entre la densité de population, la pauvreté, l’ethnicité, l’accessibilité et le changement de la couverture forestière pendant la dernière décennie pour quatre régions de Bolivie et du Laos, en combinant des approches par parcelles et par cellules. Nous avons constaté que l’accessibilité est un facteur clé du changement de la couverture forestière, tandis qu’elle a pour effet d'intensifier d'autres facteurs économiques et politiques sous-jacents, comme les politiques de colonisation, la demande de cultures de rente, mais aussi, dans un cas, des politiques conduisant à un accroissement de la forêt. La pauvreté n’apparait pas comme un facteur de déforestation, mais la co-occurrence de la pauvreté et de la perte de forêt entrainée par les investissements extérieurs semble critique en termes de développement socio-écologique. L'ethnicité se révèle être modérément explicative du changement de la couverture forestière, mais elle apparait comme un ensemble de caractéristiques socio-économiques convergentes liées à l'histoire de l’implantation humaine et à l'accès aux ressources foncières. L'identification de tels ensembles peut aider à classer les communautés selon une typologie des systèmes socio-écologiques, et à discuter leurs possibles impacts sur la forêt avec un point de vue critique sur la théorie de la transition forestière, ainsi que la pertinence et la puissance prédictive des variables évaluées. Full article

The delineation of shifting cultivation landscapes using remote sensing in mountainous regions is challenging. On the one hand, there are difficulties related to the distinction of forest and fallow forest classes as occurring in a shifting cultivation landscape in mountainous regions. On the other hand, the dynamic nature of the shifting cultivation system poses problems to the delineation of landscapes where shifting cultivation occurs. We present a two-step approach based on an object-oriented classification of Advanced Land Observing Satellite, Advanced Visible and Near-Infrared Spectrometer (ALOS AVNIR) and Panchromatic Remote-sensing Instrument for Stereo Mapping (ALOS PRISM) data and landscape metrics. When including texture measures in the object-oriented classification, the accuracy of forest and fallow forest classes could be increased substantially. Based on such a classification, landscape metrics in the form of land cover class ratios enabled the identification of crop-fallow rotation characteristics of the shifting cultivation land use practice. By classifying and combining these landscape metrics, shifting cultivation landscapes could be delineated using a single land cover dataset. Full article