Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach
This research assesses the effectiveness of plastic polyethylene terephthalate (PET) on the strength of clayey soil, examining both untreated and lime-treated specimens. Various lime treatment percentages (3 %, 6 % and 10 % by dry weight of soil), along with distinct shapes and dimensions of PET (in...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025000015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553802790961152 |
|---|---|
| author | Javadreza Vahedi Mehdi Koohmishi |
| author_facet | Javadreza Vahedi Mehdi Koohmishi |
| author_sort | Javadreza Vahedi |
| collection | DOAJ |
| description | This research assesses the effectiveness of plastic polyethylene terephthalate (PET) on the strength of clayey soil, examining both untreated and lime-treated specimens. Various lime treatment percentages (3 %, 6 % and 10 % by dry weight of soil), along with distinct shapes and dimensions of PET (including strip, square and pellet), and varying PET contents (0.5 %, 1 %, 1.5 %, 2 %, 3 %, 4 %, 5 %, 8 % and 10 %) are taken into account in the analysis. In this context, a machine learning (ML) model, i.e. XGBoost, is employed to delineate the most effective properties impacting the strength of clayey soil. To develop a ML-based data-driven approach, the standard Proctor compaction test and the point load test (PLT) are performed on prepared specimens. Although the PLT is performed to determine the strength of lime-treated/PET-reinforced clay specimens, represented by point load strength index (PLSI), the unconfined compressive strength test is conducted to confirm the appropriateness of PLT's results. The ML model trained and tested based on the data acquired reveals that the content of PET within the structure of the clayey soil is the most important parameter influencing the strength of clayey soil represented by PLSI. Moreover, using the optimum content of strip-shaped PET is characterized as the most effective reinforcing method, though coupling effects of lime treatment and PET reinforcement significantly contribute to the improvement of PLSI. |
| format | Article |
| id | doaj-art-2f9ab8afcf0f4a019e0ca3ca0cd3ae86 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-2f9ab8afcf0f4a019e0ca3ca0cd3ae862025-01-09T06:14:31ZengElsevierResults in Engineering2590-12302025-03-0125103913Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approachJavadreza Vahedi0Mehdi Koohmishi1Department of Civil Engineering, Faculty of Engineering, University of Bojnord, Bojnord, IranCorresponding author.; Department of Civil Engineering, Faculty of Engineering, University of Bojnord, Bojnord, IranThis research assesses the effectiveness of plastic polyethylene terephthalate (PET) on the strength of clayey soil, examining both untreated and lime-treated specimens. Various lime treatment percentages (3 %, 6 % and 10 % by dry weight of soil), along with distinct shapes and dimensions of PET (including strip, square and pellet), and varying PET contents (0.5 %, 1 %, 1.5 %, 2 %, 3 %, 4 %, 5 %, 8 % and 10 %) are taken into account in the analysis. In this context, a machine learning (ML) model, i.e. XGBoost, is employed to delineate the most effective properties impacting the strength of clayey soil. To develop a ML-based data-driven approach, the standard Proctor compaction test and the point load test (PLT) are performed on prepared specimens. Although the PLT is performed to determine the strength of lime-treated/PET-reinforced clay specimens, represented by point load strength index (PLSI), the unconfined compressive strength test is conducted to confirm the appropriateness of PLT's results. The ML model trained and tested based on the data acquired reveals that the content of PET within the structure of the clayey soil is the most important parameter influencing the strength of clayey soil represented by PLSI. Moreover, using the optimum content of strip-shaped PET is characterized as the most effective reinforcing method, though coupling effects of lime treatment and PET reinforcement significantly contribute to the improvement of PLSI.http://www.sciencedirect.com/science/article/pii/S2590123025000015Clayey soilPET reinforcementStrengthMachine learningXGBoost |
| spellingShingle | Javadreza Vahedi Mehdi Koohmishi Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach Results in Engineering Clayey soil PET reinforcement Strength Machine learning XGBoost |
| title | Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach |
| title_full | Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach |
| title_fullStr | Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach |
| title_full_unstemmed | Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach |
| title_short | Assessing the strength of lime-treated clayey soil reinforced with PET: A ML-based data-derived approach |
| title_sort | assessing the strength of lime treated clayey soil reinforced with pet a ml based data derived approach |
| topic | Clayey soil PET reinforcement Strength Machine learning XGBoost |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025000015 |
| work_keys_str_mv | AT javadrezavahedi assessingthestrengthoflimetreatedclayeysoilreinforcedwithpetamlbaseddataderivedapproach AT mehdikoohmishi assessingthestrengthoflimetreatedclayeysoilreinforcedwithpetamlbaseddataderivedapproach |