Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost

被引:71
作者
Demir, Selcuk [1 ]
Sahin, Emrehan Kutlug [1 ]
机构
[1] Bolu Abant Izzet Baysal Univ, Dept Civil Engn, TR-14030 Bolu, Turkiye
关键词
CatBoost; Lateral spreading; LightGBM; Liquefaction; Particle swarm optimization; XGBoost; MACHINE LEARNING ALGORITHMS; SOIL LIQUEFACTION; NEURAL-NETWORK; EARTHQUAKES; MODEL;
D O I
10.1007/s11440-022-01777-1
中图分类号
P5 [地质学];
学科分类号
0709 ; 081803 ;
摘要
Liquefaction-induced lateral spreading that has resulted in devastating damages to lifelines and buildings has been widely reported in recent earthquakes. Although it is impossible to preclude the occurrence of earthquakes, it is possible to predict its adverse effects through computer science such as machine learning (ML) algorithms. In this study, the ability of recently developed and powerful ML algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) was investigated to predict the occurrence of liquefaction-induced lateral spreading. A relatively large dataset was used to develop ML models, including 6704 lateral spread observations from the 2011 Christchurch earthquake in New Zealand. The particle swarm optimization (PSO) algorithm is utilized for hyperparameter optimization of the gradient boosting models, called the PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost. For comparison, the prediction results of the PSO optimized gradient boosting models were compared with that of the models using default parameters (i.e., XGBoost, CatBoost, and LightGBM). In addition, the SHapley Additive exPlanations approach is employed to explore the feature importance of the variables included in the dataset. The findings demonstrated that all the three gradient boosting algorithms performed well in predicting lateral spreading occurrence. Moreover, PSO-CatBoost outperformed other state-of-the-art models in terms of performance metrics. However, the PSO-LightGBM model may be considered the best choice for computers with older-gen hardware and important tasks that need to be completed in a short time. This study confirms the effectiveness of the proposed models, and the use of these boosting algorithms especially optimized with PSO is recommended for predicting the occurrence of liquefaction-induced lateral spreading.
引用
收藏
页码:3403 / 3419
页数:17
相关论文
共 76 条
[1]  
Anghel A, 2018, ARXIV
[2]   New formulas for predicting liquefaction-induced lateral spreading: model tree approach [J].
Avval, Yasaman Jafari ;
Derakhshani, Ali .
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (05) :3649-3661
[3]  
Bartlett S.F., 1992, P 4 JAPAN US WORKSHO, P351
[4]   EMPIRICAL PREDICTION OF LIQUEFACTION-INDUCED LATERAL SPREAD [J].
BARTLETT, SF ;
YOUD, TL .
JOURNAL OF GEOTECHNICAL ENGINEERING-ASCE, 1995, 121 (04) :316-329
[5]  
Baziar MH, 2013, INT J CIV ENG, V11, P100
[6]   Evaluation of lateral spreading using artificial neural networks [J].
Baziar, MH ;
Ghorbani, A .
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING, 2005, 25 (01) :1-9
[7]  
Bendtsen, 2022, PACKAGE PSO
[8]   A comparative analysis of gradient boosting algorithms [J].
Bentejac, Candice ;
Csorgo, Anna ;
Martinez-Munoz, Gonzalo .
ARTIFICIAL INTELLIGENCE REVIEW, 2021, 54 (03) :1937-1967
[9]   A Novel Hybrid Soft Computing Model Using Random Forest and Particle Swarm Optimization for Estimation of Undrained Shear Strength of Soil [J].
Binh Thai Pham ;
Qi, Chongchong ;
Lanh Si Ho ;
Trung Nguyen-Thoi ;
Al-Ansari, Nadhir ;
Manh Duc Nguyen ;
Huu Duy Nguyen ;
Hai-Bang Ly ;
Hiep Van Le ;
Prakash, Indra .
SUSTAINABILITY, 2020, 12 (06) :1-16
[10]   Predicting effects of built environment on fatal pedestrian accidents at location-specific level: Application of XGBoost and SHAP [J].
Chang, Iljoon ;
Park, Hoontae ;
Hong, Eungi ;
Lee, Jaeduk ;
Kwon, Namju .
ACCIDENT ANALYSIS AND PREVENTION, 2022, 166