Machine learning methods to map stabilizer effectiveness based on common soil properties

被引:17
作者
Gajurel, Amit [1 ]
Chittoori, Bhaskar [2 ]
Mukherjee, Partha Sarathi [3 ]
Sadegh, Mojtaba [2 ]
机构
[1] Texas A&M Univ, Dept Civil & Environm Engn, 400 Bizzell St, College Stn, TX 77843 USA
[2] Boise State Univ, Dept Civil Engn, 1910 Univ Dr, Boise, ID 83725 USA
[3] Indian Stat Inst ISI, Kolkata 700108, W Bengal, India
关键词
Machine learning; Chemical stabilization; Spatial mapping; Strength prediction; Classification; Regression; SUPPORT VECTOR MACHINES; UNCONFINED COMPRESSIVE STRENGTH; CLAY PARAMETERS; CEMENT; PREDICTION; SELECTION; MODEL;
D O I
10.1016/j.trgeo.2020.100506
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Most chemical stabilization guidelines for subgrade/base use unconfined compressive strength (UCS) of treated soils as the primary acceptance criteria for selecting optimum stabilizer in laboratory testing. Establishing optimal additive content to augment UCS involves a resource-intensive trial-and-error procedure. Also, samples collected from discrete locations for laboratory trials may not be representative of the overall site. This study aims to minimize the number of laboratory trials and help strategize sampling locations by developing spatial maps of UCS at different treatment levels for lime and cement. These spatial maps were developed using machine-learning techniques, and using a database compiled from various reported studies on lime and cement stabilization of soils in the United States. Supervised learning methods under regression and classification categories were used to quantify and classify UCS values after treatments, respectively. Commonly available soil properties like Atterberg limits, gradation, and organic contents along with treatment type and amount were used as predictors and UCS values as the response. Median R-2 for the best regression model was 0.75 for lime and 0.82 for cement, while the Correct Prediction Rate (CPR) for the best classification model was 92% for lime and 80% for cement. Results showed that satisfactory predictions could be made regarding stabilizer effectiveness using simple soil information commonly available. Best performing models for cement treatment were selected for generating the spatial maps for two counties in Montana. Soil samples collected from these counties were tested with different cement contents to verify the predictions. The results indicate that the Pearson's correlation coefficient for the regression model was 0.78 and CPR for the classification model was 92%. The authors hope that this study and future studies like these will increase data-driven-decision-making in geotechnical engineering practices.
引用
收藏
页数:10
相关论文
共 50 条
  • [31] Performance of Machine Learning Methods for Ligand-Based Virtual Screening
    Plewczynski, Dariusz
    Spieser, Stephane A. H.
    Koch, Uwe
    COMBINATORIAL CHEMISTRY & HIGH THROUGHPUT SCREENING, 2009, 12 (04) : 358 - 368
  • [32] Forest Fire Occurrence Prediction in China Based on Machine Learning Methods
    Pang, Yongqi
    Li, Yudong
    Feng, Zhongke
    Feng, Zemin
    Zhao, Ziyu
    Chen, Shilin
    Zhang, Hanyue
    REMOTE SENSING, 2022, 14 (21)
  • [33] Machine learning based evaluation of concrete strength from saturated to dry by non-destructive methods
    Guenaydin, Osman
    Akbas, Erguen
    Ozbeyaz, Abdurrahman
    Guclueer, Kadir
    JOURNAL OF BUILDING ENGINEERING, 2023, 76
  • [34] Prediction of shear strength of soft soil using machine learning methods
    Binh Thai Pham
    Le Hoang Son
    Tuan-Anh Hoang
    Duc-Manh Nguyen
    Dieu Tien Bui
    CATENA, 2018, 166 : 181 - 191
  • [35] Monitoring soil mercury content based on hyperspectral data and machine learning methods
    Han, Lei
    Chang, Shanshan
    Chen, Rui
    Liu, Zhao
    Zhao, Yonghua
    Li, Risheng
    Xia, Longfei
    JOURNAL OF APPLIED REMOTE SENSING, 2022, 16 (02)
  • [36] Control Map Generation Strategy for Hybrid Electric Vehicles Based on Machine Learning With Energy Optimization
    Kwon, Hyukjoon
    IEEE ACCESS, 2022, 10 : 15163 - 15174
  • [37] Machine learning-based methods for TTF estimation with application to APU prognostics
    Chunsheng Yang
    Sylvain Letourneau
    Jie Liu
    Qiangqiang Cheng
    Yubin Yang
    Applied Intelligence, 2017, 46 : 227 - 239
  • [38] A State-of-Art-Review on Machine-Learning Based Methods for PV
    Tina, Giuseppe Marco
    Ventura, Cristina
    Ferlito, Sergio
    De Vito, Saverio
    APPLIED SCIENCES-BASEL, 2021, 11 (16):
  • [39] Alzheimer's Ailment Prediction Using Neuroimage Based on Machine Learning Methods
    Enumula, Raveendra Reddy
    Amudhavel, J.
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA ENGINEERING (ICCIDE 2018), 2019, 28 : 89 - 94
  • [40] Machine Learning Methods to Predict and Analyse Unconfined Compressive Strength of Stabilised Soft Soil with Polypropylene Columns
    Hoque, Md. Ikramul
    Hasan, Muzamir
    Islam, Md Shofiqul
    Houda, Moustafa
    Abdallah, Mirvat
    Sobuz, Md. Habibur Rahman
    COGENT ENGINEERING, 2023, 10 (01):