The Relative Importance of Socioeconomic and Environmental Variables in Explaining Land Change in Bolivia, 2001–2010

Annals of the Association of American Geographers (Impact Factor: 2.17). 07/2012; 102:778-807. DOI: 10.1080/00045608.2012.678036

ABSTRACT This study assesses the relationship between trends in land change from 2001 to 2010 and socioeconomic and environmental variables in Bolivia at multiple spatial scales using a nonparametric, tree-based modeling approach. It also explores the theoretical dimensions surrounding the debate over the relative importance of socioeconomic and environmental variables in explaining land change. Results from the land change analysis show several hotspots of dynamic change. The majority of woody vegetation loss occurred in the eastern lowlands of Santa Cruz, Beni, and Pando and was attributable to the expansion of industrial agriculture. Gains in woody vegetation took place in the drylands of Santa Cruz and Beni savanna, and these changes were attributed to shifting patterns in precipitation and fire rather than human-induced change. Other hotspots of woody vegetation gain were attributed to abandonment of agriculture and herbaceous lands in the intermontane valleys of the southern Andes. Regression analyses showed that population and other demographic variables were poor predictors of land change. There is a clear relationship, however, between changes in woody and agriculture/herbaceous vegetation and environmental variables such as precipitation, temperature, and elevation. Municipalities with adequate precipitation and moderate temperature tended to show increases in agriculture and herbaceous vegetation and woody vegetation declines. Woody vegetation tended to increase in municipalities at higher elevations. This study also shows that explanations of only wealth or population as the main drivers of land change undervalue the role that natural features, like topography and precipitation, play in limiting or permitting certain land-use decisions. Este estudio evalúa la relación entre las tendencias de cambios de la tierra de 2001 a 2010 y variables socioeconómicas y ambientales en Bolivia, a escalas espaciales múltiples, utilizando un enfoque de modelo no paramétrico basado en el árbol. El estudio también explora las dimensiones teóricas de rodean el debate sobre la importancia relativa de las variables socioeconómicas y ambientales para explicar las transformaciones de la tierra. Los resultados del análisis del cambio de uso de la tierra muestran varios puntos críticos con cambio dinámico. La mayor parte de la pérdida de vegetación arbórea ocurrió en las tierras bajas orientales de Santa Cruz, Beni y Pando, proceso que se atribuye a la expansión de la agricultura industrial. Lo que se ha ganado en recuperación de vegetación arbórea ocurrió en las tierras secas de Santa Cruz y en la sabana de Beni, cambios que se han atribuido a los cambiantes patrones de precipitaciones y fuego más que a cambios inducidos por el hombre. Otros puntos notables de avance de la vegetación arbórea se atribuyen al abandono de tierras agrícolas y pastizales en los valles intermontanos de los Andes sureños. Los análisis de regresión mostraron que la población y otras variables demográficas resultaron ser pobres vaticinadores de cambios de la tierra. Hay, sin embargo, una relación clara entre los cambios de vegetación arbórea y agricultura/vegetación herbácea y variables ambientales tales como precipitación, temperatura y elevación. Los municipios que tenían precipitación adecuada y temperatura moderada tendían a mostrar incrementos en agricultura y vegetación herbácea, y declinación de la vegetación arbórea. La vegetación herbácea tendía a aumentar en los municipios situados a mayor elevación. Este estudio también muestra que las explicaciones que asignan a la riqueza y a la población la responsabilidad de causar los cambios de la tierra subvaloran el papel que juegan elementos naturales como la topografía y la precipitación para limitar o permitir ciertas decisiones relacionadas con los usos del suelo.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Random Forests were introduced as a Machine Learning tool in Breiman (2001) and have since proven to be very popular and powerful for high-dimensional regression and classifi- cation. For regression, Random Forests give an accurate approximation of the conditional mean of a response variable. It is shown here that Random Forests provide information about the full conditional distribution of the response variable, not only about the con- ditional mean. Conditional quantiles can be inferred with Quantile Regression Forests, a generalisation of Random Forests. Quantile Regression Forests give a non-parametric and accurate way of estimating conditional quantiles for high-dimensional predictor variables. The algorithm is shown to be consistent. Numerical examples suggest that the algorithm is competitive in terms of predictive power.
    Journal of Machine Learning Research. 01/2006; 7:983-999.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The Brazilian Cerrado, a biodiverse savanna ecoregion covering ∼1.8 million km2 south and east of the Amazon rainforest, is in rapid decline because of the expansion of modern agriculture. Previous studies of Cerrado land-use and land-cover (LULC) change imply spatial homogeneity, report widely varying rates of land conversion, use ambiguous LULC categories, and generally do not attempt to validate results. This study addresses this gap in the literature by analyzing moderate-resolution, multi-spectral satellite remote sensing data from 1986 to 2002 in two regions with identical underlying drivers. Unsupervised classification by the ISODATA algorithm indicates that Cerrado was converted to agro-pastoral land covers in 31% (3646 km2) of the study region in western Bahia and 24% (3011 km2) of the eastern Mato Grosso study region, while nearly 40% (4688 km2 and 5217 km2, respectively) of each study region remained unchanged. Although aggregate land change is similar, large and contiguous fragments persist in western Bahia, while smaller fragments remain in eastern Mato Grosso. These findings are considered in the current context of Cerrado land-use policy, which is dominated by the conservation set-aside and command-control policy models. The spatial characteristics of Cerrado remnants create considerable obstacles to implement the models; an alternative approach, informed by countryside biogeography, may encourage collaboration between state officials and farmer-landowners toward conservation land-use policies.
    Land Use Policy. 01/2008;
  • Source
    BioScience. 01/2001; 51(11):933-938.


Available from
Jun 2, 2014