No abstract

Shade-grown coffee (shade coffee) is an important component of the forested tropics, and is essential to the conservation of forest-dependent biodiversity. Despite its importance, shade coffee is challenging to map using remotely sensed data given its spectral similarity to forested land. This paper addresses this challenge in three districts of northern Nicaragua, here leveraging cloud-based computing techniques within Google Earth Engine (GEE) to integrate multi-seasonal Landsat 8 satellite imagery (30 m), and physiographic variables (temperature, topography, and precipitation). Applying a random forest machine learning algorithm using reference data from two field surveys produced a 90.5% accuracy across ten classes of land cover, with an 82.1% and 80.0% user's and producer's accuracy respectively for shade-grown coffee. Comparing classification accuracies obtained from five datasets exploring different combinations of non-seasonal and seasonal spectral data as well as physiographic data also revealed a trend of increasing accuracy when seasonal data were included in the model and a significant improvement (7.8-20.1%) when topographical data were integrated with spectral data. These results are significant in piloting an open-access and user-friendly approach to mapping heterogeneous shade coffee landscapes with high overall accuracy, even in locations with persistent cloud cover.

No abstract

Flooding is a routine occurrence throughout much of the monsoonal tropics. Despite well-developed repertoires of response, agrarian societies have been 'double exposed' to intensifying climate change and agro-industrialization over the past several decades, often in ways that alter both the regularity of flood events and individual and community capacity for response. This paper engages these tensions by exploring everyday experiences of and responses to extreme flood events in a case study village in Southeast Sulawesi, Indonesia, which has also been the site of corporate oil palm development since 2010. We first reconstruct histories of extreme flood events along the Konawe'eha River using oral histories and satellite imagery, describing the role of these events in straining the terms of daily production and reproduction. We then outline the ways smallholder agriculturalists are responding to flood events through alterations in their land use strategies, including through the sale or leasing of flood-prone lands, the relocation of riverine vegetable production to hillside locations, and adoption of new cropping choices and management practices. We highlight the role of such responses as a driver of ongoing land use change, potentially in ways that increase systemic vulnerability to floods moving forward.