期刊名称：Journal of Advances in Modeling Earth Systems
电子版ISSN：1942-2466
出版年度：2012
卷号：4
期号：1
页码：1-26
DOI：10.1029/2011MS000084
出版社：John Wiley & Sons, Ltd.
摘要：An advection scheme, which maintains the initial monotonic characteristics of a tracer field being transported and at the same time produces low numerical diffusion, is implemented in the Coupled Chemistry‐Aerosol‐Tracer Transport model to the Brazilian developments on the Regional Atmospheric Modeling System (CCATT‐BRAMS). Several comparisons of transport modeling using the new and original (non‐monotonic) CCATT‐BRAMS formulations are performed. Idealized 2‐D non‐divergent or divergent and stationary or time‐dependent wind fields are used to transport sharply localized tracer distributions, as well as to verify if an existent correlation of the mass mixing ratios of two interrelated tracers is kept during the transport simulation. Further comparisons are performed using realistic 3‐D wind fields. We then perform full simulations of real cases using data assimilation and complete atmospheric physics. In these simulations, we address the impacts of both advection schemes on the transport of biomass burning emissions and the formation of secondary species from non‐linear chemical reactions of precursors. The results show that the new scheme produces much more realistic transport patterns, without generating spurious oscillations and under‐ and overshoots or spreading mass away from the local peaks. Increasing the numerical diffusion in the original scheme in order to remove the spurious oscillations and maintain the monotonicity of the transported field causes excessive smoothing in the tracer distribution, reducing the local gradients and maximum values and unrealistically spreading mass away from the local peaks. As a result, huge differences (hundreds of %) for relatively inert tracers (like carbon monoxide) are found in the smoke plume cores. In terms of the secondary chemical species formed by non‐linear reactions (like ozone), we found differences of up to 50% in our simulations.
