1. State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalian 116024, China 2. Department of Civil Engineering, University of Engineering and Technology Peshawar (Bannu Campus), Bannu 28100, Pakistan 3. School of Economics & Management, Dalian University of Technology, Dalian 116024, China 4. Department of Civil Engineering, Abasyn University, Peshawar 25000, Pakistan
The unprecedented liquefaction-related land damage during earthquakes has highlighted the need to develop a model that better interprets the liquefaction land damage vulnerability (LLDV) when determining whether liquefaction is likely to cause damage at the ground’s surface. This paper presents the development of a novel comprehensive framework based on select case history records of cone penetration tests using a Bayesian belief network (BBN) methodology to assess seismic soil liquefaction and liquefaction land damage potentials in one model. The BBN-based LLDV model is developed by integrating multi-related factors of seismic soil liquefaction and its induced hazards using a machine learning (ML) algorithm-K2 and domain knowledge (DK) data fusion methodology. Compared with the C4.5 decision tree-J48 model, naive Bayesian (NB) classifier, and BBN-K2 ML prediction methods in terms of overall accuracy and the Cohen’s kappa coefficient, the proposed BBN K2 and DK model has a better performance and provides a substitutive novel LLDV framework for characterizing the vulnerability of land to liquefaction-induced damage. The proposed model not only predicts quantitatively the seismic soil liquefaction potential and its ground damage potential probability but can also identify the main reasons and fault-finding state combinations, and the results are likely to assist in decisions on seismic risk mitigation measures for sustainable development. The proposed model is simple to perform in practice and provides a step toward a more sophisticated liquefaction risk assessment modeling. This study also interprets the BBN model sensitivity analysis and most probable explanation of seismic soil liquefied sites based on an engineering point of view.
gravelly sand to dense sand clean sand silty sand or sand with silt sandy silt
Ic<1.31 1.31≤Ic<1.61 1.61≤Ic<2.40 2.40 ≤Ic<2.60
site condition
vertical effective stress, s'v (kPa)
4
super big medium small
150 ≤s'v 100≤s'v< 150 50 ≤s'v<100 0 ≤s'v<50
groundwater table depth, Dw (m)
3
deep medium shallow
4≤Dw 2 <Dw<4 Dw≤2
depth of soil deposit, Ds (m)
3
deep medium shallow
10 ≤Ds< 20 5≤Ds<10 0 ≤Ds<5
thickness of soil layer, Ts (m)
3
thick medium thin
10≤Ts 5≤Ts<10 0 <Ts<5
liquefaction state and its land damage vulnerability
liquefaction potential (LP)
2
no yes
0 1
liquefaction potential index (LPI)
4
very low low high very high
0 0<LPI≤5 5 <LPI≤15 15 <LPI
liquefaction land damage vulnerability (LLDV)
5
little to none low moderate high very high
– – – – –
Tab.2
grade
explanation of land damage status
little to non
No expression of liquefaction. There is no ground failure and sand boils phenomenon.
low
Few sand boils with volume lesser than 0.2 m3, but there is no ground failure.
moderate
Medium sand boils with volume lesser than 0.5 m3 and few ground cracks occur, but there is no lateral spreading.
high
Frequent sand boils phenomenon with volume lesser than 1.0 m3, undulations and moderate ground cracks and lateral spreading occur.
very high
Serious sand boils phenomenon with volume may larger than 1.0 m3, widespread surface largely ground cracks, lateral spreading and severe settlements of structures and damage to services.
Tab.3
Fig.3
Fig.4
method
description
C4.5 decision tree (DT)-J48
A C4.5 decision tree (DT)-J48 [39] recursively partitions the training data by means of attribute splits and generates a pruned or unpruned tree using the information-theoretical concept of entropy.
Naive Bayesian (NB) classifier
Naive Bayesian classifier [40] is designed to predict accurately the class of test cases and in which the training cases contain class information using kernal estimation.
K2 machine learning
K2 [17] adds arcs with a fixed topological ordering of variables. In this method, the ordering is initially set as a naïve Bayes network where the target class variable is fixed the first in the ordering.
Tab.4
kappa statistic
interpretation
0.81–1.00
almost perfect
0.61–0.80
substantial
0.41–0.60
moderate
0.21–0.40
fair
0.00–0.20
slight
-1.00–0.00
poor
Tab.5
method
data set
correctly classified classes
incorrectly classified classes
overall accuracy (%)
kappa statistic
BBN-K2 and DK
training
26
3
89.667
0.853
testing
5
1
83.333
0.739
C4.5 (DT)-48
training
25
4
86.207
0.804
testing
5
1
83.333
0.739
BBN-K2
training
24
5
82.759
0.751
testing
4
2
66.667
0.500
Naive Bayesian (NB) classifier
training
25
4
86.207
0.804
testing
5
1
83.333
0.714
Tab.6
Fig.5
Fig.6
Fig.7
Fig.8
Fig.9
node
mutual info
percent
variance of beliefs
liquefaction land damage vulnerability
2.32133
100.000000
0.6397658
liquefaction potential index
0.00139
0.059900
0.0000866
groundwater table
0.00072
0.030900
0.0000429
liquefaction potential
0.00070
0.030100
0.0000408
peak ground acceleration
0.00049
0.020900
0.0000300
soil behavior type index
0.00047
0.020300
0.0000277
depth of soil deposit
0.00028
0.012200
0.0000168
vertical effective stress
0.00024
0.010400
0.0000146
equivalent clean sand penetration resistance
0.00015
0.006330
0.0000088
thickness of soil layer
0.00009
0.003820
0.0000050
earthquake magnitude
0.00002
0.000764
0.0000010
fines content
0.00001
0.000272
0.0000004
Tab.7
1
P K Robertson, C E Wride. Evaluating cyclic liquefaction potential using cone penetration test. Canadian Geotechnical Journal, 1998, 35(3): 442–459 https://doi.org/10.1139/t98-017
2
R E Moss, R B Seed, R E Kayen, J P Stewart, K A Der, K O Cetin. CPT-based probabilistic and deterministic assessment of in situ seismic soil liquefaction potential. Journal of Geotechnical and Geoenvironmental Engineering, 2006, 132(8): 1032–1051
3
I M Idriss, R W Boulanger. Soil liquefaction during earthquakes Earthquake. Oakland, CA: Earthquake Engineering Research Institute, 2008
4
T Iwasaki, K Tokida, F Tatsuoka, S Watanabe, S Yasuda, H Sato. Microzonation for soil liquefaction potential using simplified methods. In: Proceedings of the 3rd international conference on microzonation. Seattle: Wash, 1982, 1319–1330
B W Maurer, R A Green, M Cubrinovski, B A Bradley. Evaluation of the liquefaction potential index for assessing liquefaction hazard in Christchurch, New Zealand. Journal of Geotechnical and Geoenvironmental Engineering, 2014, 140(7): 04014032 https://doi.org/10.1061/(ASCE)GT.1943-5606.0001117
8
Tonkin and Taylor Ltd. Liquefaction Vulnerability Study. Report to Earthquake Commission. 2013
9
C Hsein Juang, H Yuan, D K Li, S H Yang, R A Christopher. Estimating severity of liquefaction-induced damage near foundation. Soil Dynamics and Earthquake Engineering, 2005, 25(5): 403–411 https://doi.org/10.1016/j.soildyn.2004.11.001
10
K M Hamdia, G Hamid, Z Xiaoying, A Naif, T. RabczukComputational machine learning representation for the flexoelectricity effect in truncated pyramid structures. Computers, Materials & Continua, 2019, 59(1): 79–87
11
C Anitescu, E Atroshchenko, N Alajlan, T. Rabczuk Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 2019, 59(1): 345–359
12
H Guo, X Zhuang, T Rabczuk. A deep collocation method for the bending analysis of Kirchhoff plate. Computers, Materials & Continua, 2019, 59(2): 433–456 https://doi.org/10.32604/cmc.2019.06660
13
T Singh, M Pal, V K Arora. Modeling oblique load carrying capacity of batter pile groups using neural network, random forest regression and M5 model tree. Frontiers of Structural and Civil Engineering, 2019, 13(3): 674–685 https://doi.org/10.1007/s11709-018-0505-3
14
A R Ghanizadeh, M Rahrovan. Modeling of unconfined compressive strength of soil-RAP blend stabilized with Portland cement using multivariate adaptive regression spline. Frontiers of Structural and Civil Engineering, 2019, 13(4): 787–799 https://doi.org/10.1007/s11709-019-0516-8
15
S Tesfamariam, Z Liu. Handbook of seismic risk analysis and management of civil infrastructure systems. Cambridge, UK: Woodhead Publishing Limited, 2013, 175–208
16
J Pearl. Probabilistic Reasoning in Intelligent Systems. San Mateo, CA: Morgan Kaufmann Publishers, 1988
17
F G Cooper, E Herskovits. A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 1992, 9(4): 309–347 https://doi.org/10.1007/BF00994110
18
D J Spiegelhalter, S L Lauritzen. Sequential updating of conditional probabilities on directed graphical structures. Networks International Journal, 1990, 20(5): 579–605 https://doi.org/10.1002/net.3230200507
19
S L Lauritzen. The EM algorithm for graphical association models with missing data. Computational Statistics & Data Analysis, 1995, 19(2): 191–201 https://doi.org/10.1016/0167-9473(93)E0056-A
20
S Sushil. Interpreting the interpretive structural model. Global Journal of Flexible Systems Management, 2012, 13(2): 87–106 https://doi.org/10.1007/s40171-012-0008-3
21
D Tranfield, D Denyer, P Smart. Towards a methodology for developing evidence-informed management knowledge by means of systematic review. British Journal of Management, 2003, 14(3): 207–222 https://doi.org/10.1111/1467-8551.00375
22
J W Warfield. Developing inter connected matrices in structural modeling. IEEE Transactions on Systems, Man, and Cybernetics, 1974, 4(1): 51–81
23
C Okoli, K Schabram. A Guide to Conducting a Systematic Literature Review of Information Systems Research. Sprouts: Working Papers on Information Systems, 2010
24
L Y Zhang. Predicting seismic liquefaction potential of sands by optimum seeking method. Soil Dynamics and Earthquake Engineering, 1998, 17(4): 219–226 https://doi.org/10.1016/S0267-7261(98)00004-9
25
J L Hu, X W Tang, J N Qiu. Assessment of seismic liquefaction potential based on Bayesian network constructed from domain knowledge and history data. Soil Dynamics and Earthquake Engineering, 2016, 89: 49–60 https://doi.org/10.1016/j.soildyn.2016.07.007
26
F Yi. Case study of CPT application to evaluate seismic settlement in dry sand. In: The 2nd International symposium on Cone Penetration Testing. Huntington Beach, CA, 2010
27
M Ahmad, X W Tang, J N Qiu, F Ahmad. Evaluating seismic soil liquefaction potential using Bayesian belief network and C4.5 decision tree approaches. Applied Sciences (Basel, Switzerland), 2019, 9(20): 4226 https://doi.org/10.3390/app9204226
28
M Ahmad, X W Tang, J N Qiu, F Ahmad. Interpretive structural modeling and MICMAC analysis for identifying and benchmarking significant factors of seismic soil liquefaction. Applied Sciences (Basel, Switzerland), 2019, 9(2): 233 https://doi.org/10.3390/app9020233
29
M Ahmad, X Tang, J Qiu, W Gu, F Ahmad. A hybrid approach for evaluating CPT-based seismic soil liquefaction potential using Bayesian belief networks. Journal of Central South University, 2020, 27(2): 500–516 https://doi.org/10.1007/s11771-020-4312-3
30
M J Bennett, J C III Tinsley. Geotechnical Data from Surface and Subsurface Samples outside of and within Liquefaction-Related Ground Failures Caused by the October 17, 1989, Loma Prieta earthquake, Santa Cruz and Monterey Counties, California. U.S. Geological Survey. Open-File Report 95-663. 1995
31
PEER. Documentation of soil conditions at liquefaction sites from 1999 Chi-Chi, Taiwan Earthquake. Extracted from the website of PEER. 2000
32
R E S Moss, R B Seed, R E Kayen, J P Stewart, T L Youd, K Tokimatsu. Field Case Histories for CPT-based in situ Liquefaction Potential Evaluation. Geoengineering Research Report. UCB/GE-2003/04. 2003
33
PEER. Documenting Incidents of Ground Failure Resulting from the August 17, 1999, Kocaeli, Turkey Earthquake. Extracted from the website of PEER. 2000
34
B Sancio. Ground failure and building performance Adapazarı Turkey. Dissertation for the Doctoral Degree. Berkeley, CA: University of California, Berkeley, 2003
35
J D Bray, R B Sancio, T Durgunoglu, A Onalp, T L Youd, J P Stewart, R B Seed, O K Cetin, E Bol, M B Baturay, C Christensen, T Karadayilar. Subsurface characterization of ground failure sites in Adapazari, Turkey. Journal of Geotechnical and Geoenvironmental Engineering, 2004, 130(7): 673–685 https://doi.org/10.1061/(ASCE)1090-0241(2004)130:7(673)
36
M J Bennett, D J Ponti, J C Tinsley, T L Holzer, C H Conaway. Subsurface Geotechnical Investigations Near Sites of Ground Deformations Caused by the January 17, 1994, Northridge, California, Earthquake. U.S. Geological Survey. Open-File Report 98-373. 1998
37
T L Holzer, M J Bennett, D J Ponti, J C, III Tinsley. Liquefaction and soil failure during 1994 Northridge earthquake. Journal of Geotechnical and Geoenvironmental Engineering, 1999, 125(6): 438–452
38
K Cetin. Reliability-based assessment of soil liquefaction initiation hazard. Dissertation for the Doctoral Degree. Berkeley, CA: University of California, Berkeley, 2000
39
J R Quinlan. Improved use of continuous attributes in C4. 5. Journal of Artificial Intelligence Research, 1996, 4: 77–90 https://doi.org/10.1613/jair.279
40
H G John, P Langley. Estimating continuous distributions in Bayesian classifiers. In: The Eleventh Conference on Uncertainty in Artificial Intelligence. San Mateo: Morgan Kaufmann, 1995, 338–345
41
I H Witten, E Frank. Data Mining: Practical Machine Learning Tools and Techniques. San Francisco: Morgan Kaufmann, 2005
42
J Landis, G Koch. The measurement of observer agreement for categorical data. Biometrics, 1977, 33(1): 159–174 https://doi.org/10.2307/2529310
43
Y Sakiyama, H Yuki, T Moriya, K Hattori, M Suzuki, K Shimada, T Honma. Predicting human liver microsomal stability with machine learning techniques. Journal of Molecular Graphics & Modelling, 2008, 26(6): 907–915 https://doi.org/10.1016/j.jmgm.2007.06.005
44
K M Hamdia, M Marino, X Zhuang, P Wriggers, T Rabczuk. Sensitivity analysis for the mechanics of tendons and ligaments: Investigation on the effects of collagen structural properties via a multiscale modelling approach. International Journal for Numerical Methods in Biomedical Engineering, 2019, 35(8): e3209 https://doi.org/10.1002/cnm.3209
45
K M Hamdia, H Ghasemi, X Zhuang, N Alajlan, T Rabczuk. Sensitivity and uncertainty analysis for flexoelectric nanostructures. Computer Methods in Applied Mechanics and Engineering, 2018, 337: 95–109 https://doi.org/10.1016/j.cma.2018.03.016
46
N Vu-Bac, T Lahmer, X Zhuang, T Nguyen-Thoi, T Rabczuk. A software framework for probabilistic sensitivity analysis for computationally expensive models. Advances in Engineering Software, 2016, 100: 19–31 https://doi.org/10.1016/j.advengsoft.2016.06.005
47
J Cheng, R Greiner, J Kelly, D Bell, W Liu. Learning Bayesian networks from data: An information-theory based approach. Artificial Intelligence, 2002, 137(1–2): 43–90 https://doi.org/10.1016/S0004-3702(02)00191-1