Gaussian Process Regression (GPR) for Auto-Estimation of Resilient Modulus of Stabilized Base Materials

The resilient modulus of different pavement materials is one of the most important parameters for the pavement design using the mechanistic-empirical (M-E) method. The resilient modulus is generally determined by a triaxial test, which is expensive and time-consuming and requires special laboratory facilities. This study aims to develop a model based on the Gaussian Process Regression (GPR) to predict the resilient modulus of stabilized base material with different additives under wetting-drying cycles. For this purpose, a laboratory dataset containing 704 records have been used. The input parameters were considered as the wetting-drying cycles, free lime to silica ratio, Alumina and iron oxide compounds in the additives, maximum dry density to optimum moisture content ratio, deviator stress, and confining stress. The results indicate high accuracy of the GPR method with a regression coefficient of 0.997 and 0.986 respectively for train and test data and 0.995 for all datasets. Comparing the developed model based on the GPR method with the developed models in the literature based on the artificial neural network methods and the support vector machines shows higher accuracy of the GPR method.

[1]  Yingjie Yang,et al.  A hierarchical analysis for rock engineering using artificial neural networks , 1997 .

[2]  Dong-Soo Kim,et al.  CHARACTERIZATION OF RESILIENT MODULUS OF COMPACTED SUBGRADE SOILS USING RESONANT COLUMN AND TORSIONAL SHEAR TESTS (WITH DISCUSSION AND CLOSURE) , 1992 .

[3]  Jie Wang.  An Intuitive Tutorial to Gaussian Processes Regression , 2020, ArXiv.

[4]  Ali Reza Ghanizadeh,et al.  Application of Artificial Neural Network to Predict the Resilient Modulus of Stabilized Base Subjected to Wet-Dry Cycles , 2016 .

[5]  Final Document,et al.  Guide for Mechanistic-Empirical Design OF NEW AND REHABILITATED PAVEMENT STRUCTURES FINAL DOCUMENT APPENDIX QQ : STRUCTURAL RESPONSE MODELS FOR RIGID PAVEMENTS NCHRP , 2004 .

[6]  Ehsan Sadrossadat,et al.  Towards application of linear genetic programming for indirect estimation of the resilient modulus of pavements subgrade soils , 2018 .

[7]  Norbert J. Delatte,et al.  Mechanistic-Empirical Pavement Design Guide , 2014 .

[8]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[9]  Musharraf Zaman,et al.  Durability Effects on Resilient Moduli of Stabilized Aggregate Base , 1999 .

[10]  Felipe Filizzola Camargo,et al.  Strength and Stiffness of Recycled Base Materials Blended with Fly Ash , 2009 .

[11]  Min-Yuan Cheng,et al.  Predicting Project Success in Construction using an Evolutionary Gaussian Process Inference Model , 2014 .

[12]  M. Zaman,et al.  Durability Effects on Flexural Behavior of Fly Ash Stabilized Limestone Aggregate , 2006 .

[13]  Mahesh Pal,et al.  Extreme Learning Machine Based Modeling of Resilient Modulus of Subgrade Soils , 2013, Geotechnical and Geological Engineering.

[14]  Maher Maalouf,et al.  Support vector regression to predict the performance of stabilized aggregate bases subject to wet–dry cycles , 2012 .

[15]  Alireza Rahai,et al.  Developing a hybrid artificial neural network-genetic algorithm model to predict resilient modulus of polypropylene/polyester fiber-reinforced asphalt concrete , 2015 .

[16]  Musharraf Zaman,et al.  Neural Network Modeling of Resilient Modulus Using Routine Subgrade Soil Properties , 2010 .

[17]  Mahesh Pal,et al.  Modelling pile capacity using Gaussian process regression , 2010 .

[18]  Pranshoo Solanki,et al.  Artificial Neural Network Models to Estimate Resilient Modulus of Cementitiously Stabilized Subgrade Soils , 2013 .

[19]  K P George,et al.  PREDICTION OF RESILIENT MODULUS FROM SOIL INDEX PROPERTIES , 2004 .

[20]  Matthew W Witczak,et al.  Use of nonlinear subgrade modulus in AASHTO design procedure , 1995 .

[21]  Amir Tavana Amlashi,et al.  Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine , 2018, Frontiers of Structural and Civil Engineering.

[22]  Gerald A. Miller,et al.  Field and Laboratory Evaluation of Cement Kiln Dust as a Soil Stabilizer , 2000 .

[23]  Sherif M. El-Badawy,et al.  Advanced characterization of unbound granular materials for pavement structural design in Egypt , 2020, International Journal of Pavement Engineering.

[24]  Pijush Samui,et al.  Particle Swarm Optimization Algorithm-Extreme Learning Machine (PSO-ELM) Model for Predicting Resilient Modulus of Stabilized Aggregate Bases , 2019, Applied Sciences.

[25]  K. P. George,et al.  DEVELOPMENT OF A FREEZE-THAW TEST FOR DESIGN OF SOIL-CEMENT , 1963 .

[26]  Naji Khoury,et al.  Effect of Wet-Dry Cycles on Resilient Modulus of Class C Coal Fly Ash-Stabilized Aggregate Base , 2002 .

[27]  Mark Ebden,et al.  Gaussian Processes: A Quick Introduction , 2015, 1505.02965.

[28]  Kole Chandler Berg.  Durability and strength of activated reclaimed Iowa Class C fly ash aggregate in road bases , 1998 .

[29]  Naji Najib. Khoury.  Durability of cementitiously stabilized aggregate bases for pavement application. , 2005 .

[30]  K P George.  RESILIENT TESTING OF SOILS USING GYRATORY TESTING MACHINE (WITH DISCUSSION AND CLOSURE) , 1992 .

[31]  Jidong J. Yang,et al.  Prediction of subgrade resilient modulus using artificial neural network , 2014 .

[32]  Gi-Chul Kweon,et al.  Alternative method of determining resilient modulus of subgrade soils using a static triaxial test , 2001 .

[33]  Emmanuel G Fernando,et al.  Impact of Moisture Variation on Response of Pavements Through Small-Scale Models , 2006 .

[34]  Ali Behnood,et al.  Prediction of the resilient modulus of non-cohesive subgrade soils and unbound subbase materials using a hybrid support vector machine method and colliding bodies optimization algorithm , 2021 .

[35]  Dennis L. Eggett,et al.  Effects of Environmental Factors on Construction of Soil–Cement Pavement Layers , 2009 .

[36]  H F Southgate.  Sensitivity Study of 1986 AASHTO Guide for Design of Pavement Structures , 1991 .

[37]  Qian Chen,et al.  Comparison of Data Mining Techniques for Predicting Compressive Strength of Environmentally Friendly Concrete , 2016, J. Comput. Civ. Eng..