Effects of Tree-crop Farming on Land-cover Transitions in a Mosaic Landscape in the Eastern Region of Ghana

Abstract

Tree crops such as cocoa and oil palm are important to smallholders' livelihoods and national economies of tropical producer countries. Governments seek to expand tree-crop acreages and improve yields. Existing literature has analyzed socioeconomic and environmental effects of tree-crop expansion, but its spatial effects on the landscape are yet to be explored. This study aims to assess the effects of tree-crop farming on the composition and the extent of land-cover transitions in a mixed cocoa/oil palm landscape in Ghana. Land-cover maps of 1986 and 2015 produced through ISODATA, and maximum likelihood classification were validated with field reference, Google Earth data, and key respondent interviews. Post-classification change detection was conducted and the transition matrix analyzed using intensity analysis. Cocoa and oil palm areas have increased in extent by 8.9% and 11.2%, respectively, mainly at the expense of food-crop land and forest. The intensity of forest loss to both tree crops is at a lower intensity than the loss of food-crop land. There were transitions between cocoa and oil palm, but the gains in oil palm outweigh those of cocoa. Cocoa and oil palm have increased in area and dominance. The main cover types converted to tree-crop areas are food-crop land and off-reserve forest. This is beginning to have serious implications for food security and livelihood options that depend on ecosystem services provided by the mosaic landscape. Tree-crop policies should take account of the geographical distribution of tree-commodity production at landscape level and its implications for food production and ecosystems services.

Keywords: Ghana; Tree crops; cocoa; intensity analysis; land-cover transitions; mosaic landscape; oil palm.

Fig. 1

Location of the Akyemansa–Kwaebibrem landscape in the cocoa- and oil palm- growing regions in Ghana (Shapefile sources: Ghana at a glance, EPA and DIVA-GIS)

Fig. 2

Clips of land-cover types (extracted from Google Earth), representing a forest, b food crop and fallow, c cocoa, d oil palm, e citrus, f water, and g built-up/bare area

Fig. 3

The land-cover mapping process

Fig. 4

a Classified land-cover map of 1986 (data source for classification: Landsat 5 1986). b Proportions of the land-cover types in the landscape

Fig. 5

a Classified land-cover map 2015 (data source for classification: Landsat 8 2015). b Proportions of the land-cover types in the landscape

Fig. 6

Category level intensities for 1986–2015

Fig. 7

Transition level intensities for crop land (losses on the left and gains on the right)

Fig. 8

Transition level intensities for forest (losses on the left and gains on the right)

Fig. 9

Transition level intensities for oil palm (losses on the left and gains on the right)

Fig. 10

Transition level intensities for cocoa (losses on the left and gains on the right)