A Bayesian network approach to modelling land-use decisions under environmental policy incentives in the Brazilian Amazon

Deforestation driven by agricultural expansion is a major threat to the biodiversity of the Amazon Basin. Modelling how deforestation responds to environmental policy implementation has thus become a policy relevant scientific undertaking. However, empirical parameterization of land-use/cover change (LUCC) models is challenging due to the high complexity and uncertainty of land-use decisions. Bayesian Network (BN) modelling provides an effective framework to integrate various data sources including expert knowledge. In this study, we integrate remote sensing products with data from farm-household surveys and a decision game to model LUCC at the BR-163, in Brazil. Our ‘business as usual’ scenario indicates cumulative forest cover loss in the study region of 8,000 km2 between 2014 and 2030, whereas ‘intensified law-enforcement’ would reduce cumulative deforestation to 1,600 km2 over the same time interval. Our findings underline the importance of conservation law enforcement in modulating the impact of agricultural market incentives on land cover change.