以坡位为空间配置单元的流域管理措施情景优化方法

Using Slope Positions as Spatial Units for Optimizing Spatial Configuration of Watershed Management Practices

基于流域过程模型的BMP情景分析是当前流域管理措施评价、非点源污染控制等研究应用中广泛采用的方法,但其通常采用的BMP空间配置单元(地块、农场、水文响应单元或子流域)与坡面上的地形部位关系较弱,难以有效地根据坡面过程特点表达坡面上多种BMP之间的空间配置关系,影响了BMP情景优化效率和结果的合理性。为此,本文提出以坡位单元作为BMP空间配置单元,将各种BMP在不同坡位间合理的空间配置关系显式表达为基于坡位的空间配置规则,通过结合NSGA-II优化算法建立了一套基于坡位单元的BMP空间配置优化方法。应用案例表明,本文构建的基于坡位单元的BMP情景优化方法可有效利用基于坡位的空间配置规则进行BMP情景优化,优化所得的BMP空间配置方案更为合理,优化效率较高。

Scenario analysis based on watershed process model is a widely used method for evaluating watershed management practices （BMP） and controlling non-point source pollution. The commonly used spatial configuration units in current scenario analysis include fields, farms, hydrologic response units, and sub-basins. The weak spatial relationships between these spatial units and the topographic positions along hillslope make the use of these spatial units difficult to effectively represent the effect of different BMP on hillslope processes, and thus affect the efficiency and reasonability of optimized scenarios. In this paper, slope positions are used as the spatial configuration units of BMP under the framework of spatially distributed watershed process model and intelligent optimization method for BMP scenarios. Thus, the knowledge of the spatial relationships between BMP and slope positions can be explicitly considered during optimization. A spatially distributed watershed process model （i.e., SEIMS） and an intelligent optimization algorithm （i.e., the genetic algorithm NSGA-II） were combined in this framework in this paper. A small watershed of red soil dominant region in the east of Hetian county, Changting city, Fujian province, was selected as the case study area. The BMP knowledge base including the relationship between five BMP used in this area and slope positions was built for the study area. The experimental results showed that slope position units can well support the description and application of the knowledge on the spatial configuration of different BMP, compared with the BMP configuration units of fields with upslope-downslope relationship. The proposed method can use BMP spatial configuration knowledge to provide optimal BMP scenarios reasonably and effectively, compared with the random optimization method, a typical BMP scenario optimization method of using NSGA-II optimization algorithm with operations of population initialization, crossover, and mutation randomly.