Developing correlations between the soil fines content and CPT results using neural networks

M. S. Kovacevic; K. G. Gavin; C. Reale; L. Libric; D. Juric Kacunic

doi:10.32075/17ECSMGE-2019-0244

Developing correlations between the soil fines content and CPT results using neural networks

Translated title of the contribution: Développer des corrélations entre la teneur en fines de sol et les résultats de CPT en utilisant des réseaux de neurones

M. S. Kovacevic, K. G. Gavin, C. Reale, L. Libric, D. Juric Kacunic

Geo-engineering

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

10 Downloads (Pure)

Abstract

Knowledge of the fines content is necessary for all soil classification systems and an important factor in the evaluation of soil strength in liquefaction and seismic settlement analysis. This paper presents the application of cone penetration test, CPT data for estimating the soil fines content. The correlation can be used either as a first estimate of fines content (for example in the offshore environment) or to provide statistical information on the variation of fines content within a given area of interest (e.g. for a regional liquefaction study). The paper shows how field and laboratory test data were used with a neural network to correlate the CPT results and the fines content. Data from five site investigation locations across Northern Croatia were utilised. Verification of the approach is performed using field and lab test data from the Veliki vrh landslide.

Translated title of the contribution	Développer des corrélations entre la teneur en fines de sol et les résultats de CPT en utilisant des réseaux de neurones
Original language	French
Title of host publication	17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings
Editors	Haraldur Sigursteinsson, Sigurour Erlingsson, Sigurour Erlingsson, Bjarni Bessason
Publisher	International Society for Soil Mechanics and Geotechnical Engineering
Pages	1-8
Number of pages	8
ISBN (Electronic)	978-9935-9436-1-3
DOIs	https://doi.org/10.32075/17ECSMGE-2019-0244
Publication status	Published - 2019
Event	17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Reykjavik, Iceland Duration: 1 Sept 2019 → 6 Sept 2019

Conference

Conference	17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019
Country/Territory	Iceland
City	Reykjavik
Period	1/09/19 → 6/09/19

Keywords

Correlation
CPT
Fines content
Neural network

Access to Document

10.32075/17ECSMGE-2019-0244

0244-ecsmge-2019_KovacevicFinal published version, 426 KB

Cite this

Kovacevic, M. S., Gavin, K. G., Reale, C., Libric, L., & Kacunic, D. J. (2019). Developing correlations between the soil fines content and CPT results using neural networks. In H. Sigursteinsson, S. Erlingsson, S. Erlingsson, & B. Bessason (Eds.), 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings (pp. 1-8). International Society for Soil Mechanics and Geotechnical Engineering. https://doi.org/10.32075/17ECSMGE-2019-0244

Kovacevic, M. S. ; Gavin, K. G. ; Reale, C. et al. / Developing correlations between the soil fines content and CPT results using neural networks. 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings. editor / Haraldur Sigursteinsson ; Sigurour Erlingsson ; Sigurour Erlingsson ; Bjarni Bessason. International Society for Soil Mechanics and Geotechnical Engineering, 2019. pp. 1-8

@inproceedings{2b5c9235c65b48baa7fcbb8d4c449a0e,

title = "Developing correlations between the soil fines content and CPT results using neural networks",

abstract = "Knowledge of the fines content is necessary for all soil classification systems and an important factor in the evaluation of soil strength in liquefaction and seismic settlement analysis. This paper presents the application of cone penetration test, CPT data for estimating the soil fines content. The correlation can be used either as a first estimate of fines content (for example in the offshore environment) or to provide statistical information on the variation of fines content within a given area of interest (e.g. for a regional liquefaction study). The paper shows how field and laboratory test data were used with a neural network to correlate the CPT results and the fines content. Data from five site investigation locations across Northern Croatia were utilised. Verification of the approach is performed using field and lab test data from the Veliki vrh landslide.",

keywords = "Correlation, CPT, Fines content, Neural network",

author = "Kovacevic, {M. S.} and Gavin, {K. G.} and C. Reale and L. Libric and Kacunic, {D. Juric}",

year = "2019",

doi = "10.32075/17ECSMGE-2019-0244",

language = "French",

pages = "1--8",

editor = "Haraldur Sigursteinsson and Sigurour Erlingsson and Sigurour Erlingsson and Bjarni Bessason",

booktitle = "17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings",

publisher = "International Society for Soil Mechanics and Geotechnical Engineering",

note = "17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 ; Conference date: 01-09-2019 Through 06-09-2019",

}

Kovacevic, MS, Gavin, KG, Reale, C, Libric, L & Kacunic, DJ 2019, Developing correlations between the soil fines content and CPT results using neural networks. in H Sigursteinsson, S Erlingsson, S Erlingsson & B Bessason (eds), 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings. International Society for Soil Mechanics and Geotechnical Engineering, pp. 1-8, 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019, Reykjavik, Iceland, 1/09/19. https://doi.org/10.32075/17ECSMGE-2019-0244

Developing correlations between the soil fines content and CPT results using neural networks. / Kovacevic, M. S.; Gavin, K. G.; Reale, C. et al.
17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings. ed. / Haraldur Sigursteinsson; Sigurour Erlingsson; Sigurour Erlingsson; Bjarni Bessason. International Society for Soil Mechanics and Geotechnical Engineering, 2019. p. 1-8.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Developing correlations between the soil fines content and CPT results using neural networks

AU - Kovacevic, M. S.

AU - Gavin, K. G.

AU - Reale, C.

AU - Libric, L.

AU - Kacunic, D. Juric

PY - 2019

Y1 - 2019

N2 - Knowledge of the fines content is necessary for all soil classification systems and an important factor in the evaluation of soil strength in liquefaction and seismic settlement analysis. This paper presents the application of cone penetration test, CPT data for estimating the soil fines content. The correlation can be used either as a first estimate of fines content (for example in the offshore environment) or to provide statistical information on the variation of fines content within a given area of interest (e.g. for a regional liquefaction study). The paper shows how field and laboratory test data were used with a neural network to correlate the CPT results and the fines content. Data from five site investigation locations across Northern Croatia were utilised. Verification of the approach is performed using field and lab test data from the Veliki vrh landslide.

AB - Knowledge of the fines content is necessary for all soil classification systems and an important factor in the evaluation of soil strength in liquefaction and seismic settlement analysis. This paper presents the application of cone penetration test, CPT data for estimating the soil fines content. The correlation can be used either as a first estimate of fines content (for example in the offshore environment) or to provide statistical information on the variation of fines content within a given area of interest (e.g. for a regional liquefaction study). The paper shows how field and laboratory test data were used with a neural network to correlate the CPT results and the fines content. Data from five site investigation locations across Northern Croatia were utilised. Verification of the approach is performed using field and lab test data from the Veliki vrh landslide.

KW - Correlation

KW - CPT

KW - Fines content

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=85111906545&partnerID=8YFLogxK

U2 - 10.32075/17ECSMGE-2019-0244

DO - 10.32075/17ECSMGE-2019-0244

M3 - Conference contribution

AN - SCOPUS:85111906545

SP - 1

EP - 8

BT - 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings

A2 - Sigursteinsson, Haraldur

A2 - Erlingsson, Sigurour

A2 - Bessason, Bjarni

PB - International Society for Soil Mechanics and Geotechnical Engineering

T2 - 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019

Y2 - 1 September 2019 through 6 September 2019

ER -

Kovacevic MS, Gavin KG, Reale C, Libric L, Kacunic DJ. Developing correlations between the soil fines content and CPT results using neural networks. In Sigursteinsson H, Erlingsson S, Erlingsson S, Bessason B, editors, 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 - Proceedings. International Society for Soil Mechanics and Geotechnical Engineering. 2019. p. 1-8 doi: 10.32075/17ECSMGE-2019-0244

Developing correlations between the soil fines content and CPT results using neural networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this