A GCM SIMULATION OF THE IMPACT OF AMAZONIAN DEFORESTATION ON CLIMATE USING AN IMPROVED CANOPY REPRESENTATION

To obtain a good estimate of the impact of Amazonian deforestation on local climate it is critical that the representation of the forest canopy within general circulation models (GCMs) is as realistic as possible. Recent measurements from the Amazonian forest have highlighted major weaknesses in the Meteorological Office GCM simulation of the interception of rainfall from the forest canopy. Here, we present results for Amazonia from a new 3-year control experiment which incorporates an improved representation of micrometeorological processes within the forest. A detailed assessment of the control simulation reveals that the adjusted GCM provides a realistic description of the climate of Amazonia. In determining the impact of Amazonian deforestation on climate we present a comprehensive analysis of the simulated climate following the replacement of Amazonian forest by pasture. A comparison of the new results with those from the earlier deforestation experiment carried out by Lean and Warrilow (1989) suggests that the reductions in local rainfall (14%) and evaporation (24%) are smaller than those obtained with the previous formulation of interception. It was concluded by Lean and Warrilow that with a wet canopy, decreases in roughness in the deforested case reduce evaporation. With the introduction of the new interception formulation the canopy is less often wet, and so the effect of deforestation is reduced.