nach oben

Bulletin of Engineering Geology and the Environment

Erschienen in:

01.07.2024 | Original Paper

Intelligent regional subsurface prediction based on limited borehole data and interpretability stacking technique of ensemble learning

verfasst von: Jun Bai, Sheng Wang, Qiang Xu, Junsheng Zhu, Zhaoqi Li, Kun Lai, Xingyi Liu, Zongjie Chen

Erschienen in: Bulletin of Engineering Geology and the Environment | Ausgabe 7/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This study introduces an intelligent method for regional subsurface prediction using a Stacking ensemble learning approach, which incorporates K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosted Decision Trees (GBDT), and Xgboost as base classifiers, with Logistic Regression (LR) serving as the meta-classifier. Leveraging data from 1119 boreholes in Zigong City, China, this method achieves a prediction accuracy of 93%, and notably improves the prediction of weak layers, with accuracy rates ranging from 71.4% to 81.5%. This enhancement is particularly significant in areas with a random distribution of excavation and backfill. Furthermore, this study employs the SHAP method (SHapley Additive explanations) to interpret the Stacking ensemble learning model, revealing that the outputs of the base classifiers enhance the feature set for the meta-classifier, effectively addressing the insensitivity of the spatial coordinates x, y, and z as input features for lithology prediction. The findings demonstrate that the expansion of effective feature dimensions is key to the superior performance of the Stacking ensemble learning method in regional subsurface lithology prediction.

Vorheriger Artikel Evaluating instability & failure pattern of landslides, Giri valley, Northwest Himalaya, India

Nächster Artikel Fractal discrete fracture network modeling of radon gas concentration in underground tunnels under Książ Castle in Poland

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Anemangely M, Ramezanzadeh A, Amiri H, Hoseinpour S-A (2019b) Machine learning technique for the prediction of shear wave velocity using petrophysical logs. J Pet Sci Eng 174:306–327. https://doi.org/10.1016/j.petrol.2018.11.032CrossRef

Anemangely M, Ramezanzadeh A, Behboud MM (2019a) Geomechanical parameter estimation from mechanical specific energy using artificial intelligence. J Pet Sci Eng 175:407–429. https://doi.org/10.1016/j.petrol.2018.12.054CrossRef

Anemangely M, Ramezanzadeh A, Tokhmechi B, Molaghab A, Mohammadian A (2018) Development of a new rock drillability index for oil and gas reservoir rocks using punch penetration test. J Pet Sci Eng 166:131–145. https://doi.org/10.1016/j.petrol.2018.03.024CrossRef

Bai J, Wang S, Xu Q et al (2023) Intelligent real-time predicting method for rock characterization based on multi-source information integration while drilling. Bull Eng Geol Environ 82(4):150. https://doi.org/10.1007/s10064-023-03182-8CrossRef

Chen Z, Lin T, Xia X, Xu H, Ding S (2018) A synthetic neighborhood generation-based ensemble learning for the imbalanced data classification. Appl Intell 48(8):2441–2457. https://doi.org/10.1007/s10489-017-1088-8CrossRef

Gao Z, Wang L, Soroushmehr R, Wood A, Gryak J, Nallamothu B et al (2022) Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features. BMC Med Imaging 22(1):10. https://doi.org/10.1186/s12880-022-00734-4CrossRef

Gladchenko ES, Gubanova AE, Orlov DM, Koroteev DA (2023) Kriging-boosted CR modeling for prompt infill drilling optimization. Petroleum. https://doi.org/10.1016/j.petrol.2023.02.014

Gonçalves ÍG, Guadagnin F, Cordova DP (2022) Learning spatial patterns with variational Gaussian processes: Regression. Comput Geosci 161:105056. https://doi.org/10.1016/j.cageo.2022.105056CrossRef

Guo J, Wang X, Wang J, Dai X, Wu L, Li C et al (2021) Three-dimensional geological modeling and spatial analysis from geotechnical borehole data using an implicit surface and marching tetrahedra algorithm. Eng Geol 284. https://doi.org/10.1016/j.enggeo.2021.106047

He Y, Zhang H, Dong Y, Wang C, Ma P (2024) Residential net load interval prediction based on stacking ensemble learning. Energy 296:131134. https://doi.org/10.1016/j.energy.2024.131134CrossRef

Hou H, Liu C, Wei R, He H, Wang L, Li W (2023) Outage duration prediction under typhoon disaster with stacking ensemble learning. Reliab Eng Syst Saf 237:109398. https://doi.org/10.1016/j.ress.2023.109398CrossRef

Huang S, Wang Y, Wong EYC, Yu L (2024) Ensemble learning with soft-prompted pretrained language models for fact checking. Nat Lang Process 7:100067. https://doi.org/10.1016/j.nlp.2024.100067CrossRef

Jesell M, Guo J, Li Y, Lindsay M, Scalzo R, Giraud J et al (2022) Into the Noddyverse: a massive data store of 3D geological models for machine learning and inversion applications. Earth Syst Sci Data 14(1):381–392. https://doi.org/10.5194/essd-14-381-2022CrossRef

Jesu Godwin D, Varuvel EG, Leenus Jesu Martin M (2023) Prediction of combustion, performance, and emission parameters of ethanol-powered spark ignition engine using ensemble Least Squares boosting machine learning algorithms. J Clean Prod 421:138401. https://doi.org/10.1016/j.jclepro.2023.138401CrossRef

Kadkhodaei HR, Moghadam AME, Dehghan M (2020) HBoost: A heterogeneous ensemble classifier based on the Boosting method and entropy measurement. Expert Syst Appl 157:113482. https://doi.org/10.1016/j.eswa.2020.113482CrossRef

Krishna TB, Kokil P (2024) Standard fetal ultrasound plane classification based on stacked ensemble of deep learning models. Expert Syst Appl 238:122153. https://doi.org/10.1016/j.eswa.2023.122153CrossRef

Lawal AI, Kwon S (2021) Application of artificial intelligence to rock mechanics: An overview. J Rock Mech Geotech Eng 13(1):248–266. https://doi.org/10.1016/j.jrmge.2020.05.010CrossRef

Li S, Liu B, Xu X, Nie L, Liu Z, Song J, Sun H, Chen L, Fan K (2017) An overview of ahead geological prospecting in tunneling. Tunn Undergr Space Technol 63:69–94. https://doi.org/10.1016/j.tust.2016.12.011CrossRef

Li X, Huang F, Yang Z (2024) Multisource monitoring data-driven slope stability prediction using ensemble learning techniques. Comput Geotech 169:106255. https://doi.org/10.1016/j.compgeo.2024.106255CrossRef

Luo Z, Qi X, Sun C, Dong Q, Gu J, Gao X (2024) Investigation of influential variations among variables in daylighting glare metrics using machine learning and SHAP. Build Environ 254:111394. https://doi.org/10.1016/j.buildenv.2024.111394CrossRef

Maciąg PS, Bembenik R, Piekarzewicz A, Del Ser J, Lobo JL, Kasabov NK (2023) Effective air pollution prediction by combining time series decomposition with Stacking and bagging ensembles of evolving spiking neural networks. Environ Model Softw 170:105851. https://doi.org/10.1016/j.envsoft.2023.105851CrossRef

Madsen RB, Høyer A-S, Andersen LT, Møller I, Hansen TM (2022) Geology-driven modeling: a new probabilistic approach for incorporating uncertain geological interpretations in 3D geological modeling. Eng Geol 309. https://doi.org/10.1016/j.enggeo.2022.106833

Miao C, Wang Y (2024) Interpolation of non-stationary geo-data using Kriging with sparse representation of covariance function. Comput Geotech 169:106183CrossRef

Mo R, Chen L, Chen Y, Xiong C, Zhang C, Chen Z, Lin E (2024) Prediction and correlations estimation of seismic capacities of pier columns: extended Gaussian process regression models. Struct Saf 109:102457. https://doi.org/10.1016/j.strusafe.2024.102457CrossRef

Özbayrak F, Foster JT, Pyrcz MJ (2024) Spatial bagging to integrate spatial correlation into ensemble machine learning. Comput Geosci 186:105558. https://doi.org/10.1016/j.cageo.2024.105558CrossRef

Pavlyshenko, B. (2018). Using stacking approaches for machine learning models. In Proceedings of the 2018 IEEE 2nd International Conference on Data Stream Mining and Processing, DSMP 2018 (pp. 255-258). https://doi.org/10.1109/DSMP.2018.8478522.

Pelegrina GD, Duarte LT, Grabisch M (2023) A k-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning. Artif Intell 325:104014. https://doi.org/10.1016/j.artint.2023.104014CrossRef

Qi X, Wang H, Pan X, Chu J, Chiam K (2021) Prediction of interfaces of geological formations using the multivariate adaptive regression spline method. Undergr Space 6(3):252–266. https://doi.org/10.1016/j.undsp.2020.02.006CrossRef

Sesmero MP, Iglesias JA, Magán E, Ledezma A, Sanchis A (2021) Impact of the learners diversity and combination method on the generation of heterogeneous classifier ensembles. Appl Soft Comput 111:107689. https://doi.org/10.1016/j.asoc.2021.107689CrossRef

Shi C, Wang Y (2022) Data-driven construction of Three-dimensional subsurface geological models from limited Site-specific boreholes and prior geological knowledge for underground digital twin. Tunn Undergr Space Technol 126:104493. https://doi.org/10.1016/j.tust.2022.104493CrossRef

Wang N, Zhang H, Dahal A, Cheng W, Zhao M, Lombardo L (2024) On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values. Geosci Front 15(4):101800. https://doi.org/10.1016/j.gsf.2024.101800CrossRef

Wu R-j, Xia J, Chen K-y, Chen J-j, Liu Q-f, Jin W-l (2023) Spatiotemporal interpolation of surface chloride content for marine RC structures based on non-uniform spatiotemporal Kriging interpolation method. Struct Saf 103:102329. https://doi.org/10.1016/j.strusafe.2023.102329CrossRef

Ye M, Li L, Yoo D-Y, Li H, Zhou C, Shao X (2023) Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation. Constr Build Mater 408:133752. https://doi.org/10.1016/j.conbuildmat.2023.133752CrossRef

Zhang L, Cheng Y, Zhang J, Chen H, Cheng H, Gou W (2023) Refrigerant charge fault diagnosis strategy for VRF systems based on stacking ensemble learning. Build Environ 234:110209. https://doi.org/10.1016/j.buildenv.2023.110209CrossRef

Zhang W, Han L, Gu X, Wang L, Chen F, Liu H (2022) Tunneling and deep excavations in spatially variable soil and rock masses: a short review. Undergr Space (China) 7(3):380–407. https://doi.org/10.1016/j.undsp.2020.03.003CrossRef

Zhang Y, Wang Y, Zhang C, Qiao X, Ge Y, Li X, Peng T, Nazir MS (2024) State-of-health estimation for lithium-ion battery via an evolutionary Stacking ensemble learning paradigm of random vector functional link and active-state-tracking long–short-term memory neural network. Appl Energy 356:122417. https://doi.org/10.1016/j.apenergy.2023.122417CrossRef

Titel: Intelligent regional subsurface prediction based on limited borehole data and interpretability stacking technique of ensemble learning
verfasst von: Jun Bai
Sheng Wang
Qiang Xu
Junsheng Zhu
Zhaoqi Li
Kun Lai
Xingyi Liu
Zongjie Chen
Publikationsdatum: 01.07.2024
Verlag: Springer Berlin Heidelberg
Erschienen in: Bulletin of Engineering Geology and the Environment / Ausgabe 7/2024
Print ISSN: 1435-9529
Elektronische ISSN: 1435-9537
DOI: https://doi.org/10.1007/s10064-024-03758-y

Refined implicit characterization of engineering geology with uncertainties: a divide-and-conquer tactic-based approach

Open Access
Original Paper

Rockfall susceptibility analysis of the “San Michele Arcangelo” historic trail (Central Italy) based on virtual outcrops and multiple propagation models

Open Access
Original Paper

An approach for the design of dewatering systems: the case of an excavation for the construction of the assembly shaft of a tunnel boring machine

Open Access
Original Paper

Rate-dependent shear behaviors of rock discontinuities with different joint wall strengths

Original Paper

Study on rock stability and structural response of shield-driven twin tunnels crossing fault fracture zone based on 3d numerical simulation

Original Paper

Evaluation method of rock brittleness based on post-peak energy conversion under monotonic and cyclic triaxial compression

Original Paper