Mapping the global distribution of livestock

Abstract

Livestock contributes directly to the livelihoods and food security of almost a billion people and affects the diet and health of many more. With estimated standing populations of 1.43 billion cattle, 1.87 billion sheep and goats, 0.98 billion pigs, and 19.60 billion chickens, reliable and accessible information on the distribution and abundance of livestock is needed for a many reasons. These include analyses of the social and economic aspects of the livestock sector; the environmental impacts of livestock such as the production and management of waste, greenhouse gas emissions and livestock-related land-use change; and large-scale public health and epidemiological investigations. The Gridded Livestock of the World (GLW) database, produced in 2007, provided modelled livestock densities of the world, adjusted to match official (FAOSTAT) national estimates for the reference year 2005, at a spatial resolution of 3 minutes of arc (about 5×5 km at the equator). Recent methodological improvements have significantly enhanced these distributions: more up-to date and detailed sub-national livestock statistics have been collected; a new, higher resolution set of predictor variables is used; and the analytical procedure has been revised and extended to include a more systematic assessment of model accuracy and the representation of uncertainties associated with the predictions. This paper describes the current approach in detail and presents new global distribution maps at 1 km resolution for cattle, pigs and chickens, and a partial distribution map for ducks. These digital layers are made publically available via the Livestock Geo-Wiki (http://www.livestock.geo-wiki.org), as will be the maps of other livestock types as they are produced.

Figure 1. Overall workflow of GLW modelling.

Figure 2. GLW 2 global distributions of a) cattle; b) pigs; c) chickens; and d) distribution of ducks, excluding South America and Africa.

Figure 3. Thailand, visual comparison of a) poultry distribution as mapped in GLW at 5 km; against b) chicken and c) duck distributions mapped separately in GLW 2 at 1 km spatial resolution.

Figure 4. Uganda, visual comparison of observed cattle data a) in GLW 2007 (level 1) and b) in GLW 2 (level 4), and the resulting predicted distribution c) for GLW 2007 and d) for GLW 2.

Figure 5. Residual Mean Square Error (RMSE) for predicted versus observed cattle distributions in Brazil, and chicken distributions in Thailand, by administrative level of training data.