洪水灾情评价的遗传程序设计方法

洪水灾情评价在洪水灾害分类管理决策中具有重要的指导意义,其关键问题就是在评价模型的结构未确知时,如何建立合适的模型来描述以灾情评价指标值为系统输入与以灾情评价等级值为系统输出之间所隐含的复杂关系。为此,提出了用FORTRAN语言实现洪水灾情评价的遗传程序设计新方法(GP-EFDL)。研究结果说明,GP-EFDL可在较大的程序搜索空间中获取一个最佳函数表达式,来反映洪水灾情评价系统的输入与输出样本数据系列所隐含的关系,在自然灾害系统建模、预测和控制等计算机程序自动设计中具有应用价值。表4,参13。

Genetic programming method for evaluation of flood disaster loss

Evaluation of flood disaster loss is very important to guiding decision-making of classified management of flood disaster, which key problem is how to establish a right model for describe the complex relation hidden in input and output data series of flood disaster loss system when the model structure of the complex flood disaster loss system has been unknown. For this reason, a new method, named GP-EFDL for short, is presented in this paper for evaluation of flood disaster loss based on genetic programming by using FORTRAN programming language. The result of case study shows that a good function expression can be obtained within big programming search space with using GP-EFDL method, which expression can reflect the complex relation hidden in system input and output data series of flood disaster loss system, and that the method can be widely used in automation of computer programming of modeling, prediction and control of natural disaster systems.