【摘要】 为找出河道水沙运移模拟的最优模型,以梯度提升决策树(CatBoost)模型为基础,在鲸鱼算法(WOA中引入Logistic映射、自适应权重和交叉变异处理,得出优化鲸鱼算法(MWOA),构建了MWOA-CatBoost模型,为验证模型精度,将MWOA-CatBoost模型与3种优化CatBoost模型和2种传统提升树模型(极端梯度提升树XGBoost、自适应提升树Ada Boost)进行了对比,结果表明,MWOA-CatBoost模型在所有模型中精度最高,可作为河道水沙模拟的推荐模型使用。更多还原

【Abstract】 In order to find out the optimal model of river water and sediment migration simulation,based on the gradient boosting decision tree model(CatBoost),Logistic mapping,adaptive weight and cross mutation processing are introduced into the Whale Algorithm(WOA)to obtain the whale optimization algorithm(MWOA),and the MWOA-CatBoost model is constructed. To verify the accuracy of the model,the MWOA-CatBoost model is compared with three optimized CatBoost models and two traditional boosting tree models(extreme gradient boosting tree XGBoost and adaptive boosting tree Ada Boost). The results show that MWOA-CatBoost model has the highest accuracy among all models. It can be used as a recommended model for river water and sediment simulation.更多还原