水力发电学报2024，Vol.43Issue(7)：85-96,12.DOI:10.11660/slfdxb.20240708
土石坝风险等级智能预测分析及模型优化研究
Study on intelligent predictions and analysis of earth-rock dam risk levels as well as model optimization
摘要
Abstract
Dam failure often causes an enormous loss of life and property and huge environmental damage.Accurate and fast estimation of the risk level of earth-rock dams is of great significance for controlling their failure hazards.This paper develops a fast prediction model of the earth-rock dam risk grade based on GA-LightGBM,using the K-Nearest Neighbor(KNN)algorithm to fill a large amount of missing data in the database,and adopting a Genetic Algorithm(GA)to optimize the hyperparameters of Light Gradient Boosting Machine(LightGBM).The model accuracy is verified using the receiver operating characteristic(ROC)curves,the area under the curve(AUC),and other evaluation indexes;and it is compared with the traditional machine learning model.The results show that this new model has a high accuracy of 89.95%and its AUC value is 0.977,indicating it is better in terms of applicability and accuracy.Analysis of global influencing factors and case studies using Shapley Additive Explanations(SHAP)show the frequency of inspection is one of the most important factors leading to the risk of earth-rock dams.关键词
风险等级/遗传算法/GA-LightGBM/快速预测模型/SHAP分析Key words
risk level/genetic algorithm/GA-LightGBM/fast prediction model/SHAP analysis分类
水利科学引用本文复制引用
李炎隆,张雨春,王婷,殷乔刚,刘云贺..土石坝风险等级智能预测分析及模型优化研究[J].水力发电学报,2024,43(7):85-96,12.基金项目
国家自然科学基金重点项目(52039008) （52039008）
国家杰出青年科学基金项目(52125904) （52125904）
