考虑到有机体的生存环境通常存在许多不确定因素,我们用系综平均的方法给出准物种和误差阈的数值模拟。
Considering various uncontrollable factors in the living environment, we use the ensemble average to give the simulation of quasi-species and error threshold.
以穿透降雨为例,其模型模拟结果与实验比较,相对误差不超过2%,与野外观测比较,多次平均相对误差为6%。
Relative errors between simulation results of model and experiment were lower than 2%, and between model and field observation lower than 6% by the example of throughfall.
模拟的结果显示ANN模型比线性回归模型有更好的预测能力,预测的平均相对误差:ANN模型为14.9%,线性回归模型为25.8%。
Simulation results showed that the ANN model gave better predictions than the regressive model. The average relative error of ANN was 14.9% and that of linear regression was 25.8%.
应用推荐