Machine learning approaches to estimation of the compressibility of soft soils
The modulus of compression and coefficient of compressibility of soft soils are key parameters for assessing deformation of geotechnical infrastructure. However, the consolidation tests used to determine these two indices are time-consuming and the results are easily and heavily influenced by workma...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2023.1147825/full |
| _version_ | 1797861037414809600 |
|---|---|
| author | Huifen Liu Peiyuan Lin Peiyuan Lin Jianqiang Wang |
| author_facet | Huifen Liu Peiyuan Lin Peiyuan Lin Jianqiang Wang |
| author_sort | Huifen Liu |
| collection | DOAJ |
| description | The modulus of compression and coefficient of compressibility of soft soils are key parameters for assessing deformation of geotechnical infrastructure. However, the consolidation tests used to determine these two indices are time-consuming and the results are easily and heavily influenced by workmanship, testing apparatus, and other factors. Therefore, it is of great interest to develop a simple approach to accurately estimate these compressibility indices. This article presents the development of three machine learning (ML) models—at artificial neural network (ANN), a random forest model, and a support vector machine model—for mapping of the two compressibility indices for soft soils. A database containing 743 sets of measured physical and compression parameters of soft soils was adopted to train and validate the models. To quantify model uncertainty, the accuracies of the ML models were statistically evaluated using a bias factor defined as the ratio of the measured to the predicted compression indices. The results showed that all three ML models were accurate on average, with low dispersion in prediction accuracy. The ANN was found to be the best model, as it provides a simple analytical form and has no hidden dependency between the bias and predicted indices. Finally, the probability distribution functions of the bias factors were also determined using the fit-to-tail technique. The results of this study will be helpful in saving cost and time in geotechnical investigation of soft soils. |
| first_indexed | 2024-04-09T21:56:44Z |
| format | Article |
| id | doaj.art-bdb9c47b7f634d488dec7aed7eb145df |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-04-09T21:56:44Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-bdb9c47b7f634d488dec7aed7eb145df2023-03-24T05:13:05ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-03-011110.3389/feart.2023.11478251147825Machine learning approaches to estimation of the compressibility of soft soilsHuifen Liu0Peiyuan Lin1Peiyuan Lin2Jianqiang Wang3School of Transportation, Civil Engineering and Architecture, Foshan University, Foshan, Guangdong Province, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, Guangdong Province, ChinaSchool of Civil Engineering, Sun Yat-Sen University, Zhuhai, Guangdong Province, ChinaGuangdong Wisdom Cloud Engineering Science and Technology Co Ltd, Foshan, ChinaThe modulus of compression and coefficient of compressibility of soft soils are key parameters for assessing deformation of geotechnical infrastructure. However, the consolidation tests used to determine these two indices are time-consuming and the results are easily and heavily influenced by workmanship, testing apparatus, and other factors. Therefore, it is of great interest to develop a simple approach to accurately estimate these compressibility indices. This article presents the development of three machine learning (ML) models—at artificial neural network (ANN), a random forest model, and a support vector machine model—for mapping of the two compressibility indices for soft soils. A database containing 743 sets of measured physical and compression parameters of soft soils was adopted to train and validate the models. To quantify model uncertainty, the accuracies of the ML models were statistically evaluated using a bias factor defined as the ratio of the measured to the predicted compression indices. The results showed that all three ML models were accurate on average, with low dispersion in prediction accuracy. The ANN was found to be the best model, as it provides a simple analytical form and has no hidden dependency between the bias and predicted indices. Finally, the probability distribution functions of the bias factors were also determined using the fit-to-tail technique. The results of this study will be helpful in saving cost and time in geotechnical investigation of soft soils.https://www.frontiersin.org/articles/10.3389/feart.2023.1147825/fullartificial neural networkrandom forestsupport vector machinesoft soilmodel uncertaintycompression indices |
| spellingShingle | Huifen Liu Peiyuan Lin Peiyuan Lin Jianqiang Wang Machine learning approaches to estimation of the compressibility of soft soils Frontiers in Earth Science artificial neural network random forest support vector machine soft soil model uncertainty compression indices |
| title | Machine learning approaches to estimation of the compressibility of soft soils |
| title_full | Machine learning approaches to estimation of the compressibility of soft soils |
| title_fullStr | Machine learning approaches to estimation of the compressibility of soft soils |
| title_full_unstemmed | Machine learning approaches to estimation of the compressibility of soft soils |
| title_short | Machine learning approaches to estimation of the compressibility of soft soils |
| title_sort | machine learning approaches to estimation of the compressibility of soft soils |
| topic | artificial neural network random forest support vector machine soft soil model uncertainty compression indices |
| url | https://www.frontiersin.org/articles/10.3389/feart.2023.1147825/full |
| work_keys_str_mv | AT huifenliu machinelearningapproachestoestimationofthecompressibilityofsoftsoils AT peiyuanlin machinelearningapproachestoestimationofthecompressibilityofsoftsoils AT peiyuanlin machinelearningapproachestoestimationofthecompressibilityofsoftsoils AT jianqiangwang machinelearningapproachestoestimationofthecompressibilityofsoftsoils |