Predicting the precipitated calcium carbonate and unconfined compressive strength of bio-mediated sands through robust hybrid optimization algorithms

Abstract

Biological soil stabilization through Microbial-Induced Calcite Precipitation (MICP) demonstrates the potential to be an eco-friendly and sustainable approach to enhance the strength properties of cohesionless granular soils. No systematic study has been performed so far in the literature on predicting the strength of bio-mediated sands prior to testing. In this study, to overcome this deficiency, based on a comprehensive set of experimental data compiled from literature, the amounts of Precipitated Calcium Carbonate (PCC) and Unconfined Compressive Strength (UCS) of MICP-treated sands are estimated through hybridizing Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models with metaheuristic algorithms. During the data extraction procedure, a total of 70 and 115 datasets are used to predict the PCC and UCS, respectively. To this end, five key features of urea concentration (Mu), calcium chloride (Mcc), optical density of bacterial suspension (OD600), pH and total volume of injection per volume of sample (Vt), are first selected as the inputs of the hybrid models to estimate the amount of calcium carbonate precipitation within the porous structure of MICP-treated granular medium. The experimental data on the PCC along with the basic characteristics of the host sand including mean grain size (D50), uniformity coefficient (Cu) and void ratio (e), are then adopted as the inputs of the numerical models in the second phase whilst the UCS of bio-mediated sands is set as the output. The performance and accuracy of implemented models are rigorously assessed through analyzing various statistical indices and performance criteria. According to the numerical analysis, the ANN-Particle Swarm Optimization (PSO) and ANFIS-PSO hybrid models show the best performance in predicting PCC and UCS of bio-mediated sands, respectively. Using the well-established Gene Expression Programming (GEP) algorithm, practical correlations are developed to predict the PCC and UCS values of MICP-mediated soils based on the characteristics of biological binding agents as well as the host material. The Machine Learning (ML)-based models presented in this study provide engineers with a fruitful framework for the rough and preliminary estimation of the amount of calcite precipitation as well as the UCS of bio-mediated sands in the field prior to stabilization and performing complementary tests. Nevertheless, it is important to consider the limitations of extrapolation in the models presented in this research.