AI enhances Chemical Grouting Predictions for Soil Liquefaction in Earthquake-Prone Areas
Table of Contents
Soil liquefaction, a phenomenon where soil loses its strength and behaves like a liquid, poses a important threat too infrastructure, notably in earthquake-prone regions. A new study demonstrates how artificial intelligence (AI) can improve predictions of chemical grouting, a technique used to stabilize soil and prevent liquefaction.
Schematic representation of the chemical grouting process. Credit: Results in Engineering (2025). Doi: 10.1016/j.rineng.2025.105071
The research, published in results in Engineering, integrates AI-based predictive modeling with the Finite Element Method (FEM) to assess grout permeation behavior in soils with low-permeability zones. This approach offers a more efficient and accurate way to predict the effectiveness of chemical grouting in complex soil conditions.
The Challenge of Soil Liquefaction
Soil liquefaction occurs when saturated soil loses its structure and behaves like a fluid, often triggered by earthquakes. the Great East Japan Earthquake in 2011 demonstrated the devastating consequences of this phenomenon, causing widespread damage to homes and infrastructure in the Tokyo Bay area.
Chemical grouting is a technique used to prevent soil liquefaction by injecting grout into the soil, replacing pore water with a solidifying chemical. Though, achieving uniform grout permeation in heterogeneous soil with low-permeability areas can be challenging.
Previous studies have shown that grout tends to bypass areas of low permeability,negatively affecting soil remediation. Thus, predicting and optimizing permeation performance is crucial for accomplished chemical grouting in complex soil types.
AI-Powered Solution for Improved Grouting
To address this challenge, Professor Shinya Inazumi from the College of Engineering, Shibaura Institute of Technology (SIT), Japan, and a team of researchers developed a framework that integrates AI-based predictive modeling into FEM-based permeation analysis.
“Unlike previous studies that relied solely on traditional permeation analysis methods to highlight the effects of soil heterogeneity on chemical grout permeation efficiency, this study is unique by combining traditional permeation analysis with advanced AI techniques such as neural networks and gradient boosting decision trees,” explains Prof. Inazumi.
The researchers created a soil model with low-permeability regions and performed a 2D FEM-based permeation analysis to calculate permeation velocity.Parameters contributing to a permeation risk of greater than 10% were identified and used as inputs for multiple regression analysis to predict permeation risk.
The FEM-derived permeation datasets were then used to train two AI-based predictive models: a neural network and a gradient boosting decision tree.
Methodological framework for FEM-based permeation analysis and AI-based predictive modeling. Credit: Professor Shinya Inazumi from SIT, japan Source Link: https://doi.org/10.1016/j.rineng.2025.105071
Promising Results and Future Directions
The results of the study showed that FEM-based permeation analysis demonstrated an average permeation rate of 94.5% and a worst-case value of 81% when 5.5% of the soil was of low permeability. The AI-based predictive models showed an average permeation rate of 96% and a worst-case drop of 83%.
A comparative validation of AI-based predictive models with FEM simulations and previous studies suggested a high predictive accuracy of R2= 0.849. This demonstrates that AI-based models can be integrated with numerical modeling when trained on well-structured datasets.
Moreover, AI-based models delivered predictions in less than two seconds, compared to FEM simulations which took almost 30-40 minutes to process predictions. Simple regression models developed in this study using inputs like soil geometry and proximity to low-permeability zones accurately estimated permeation risks without the need for exhaustive computational steps.
The FEM-based analysis also revealed that the low-permeability zones block flow patterns and reduce permeation velocities in the soil.
The researchers emphasize the need for experimental validation with field data to achieve further reliable prediction models. With more diverse training data, the AI-based predictive models can become more accurate, reducing the risk of overestimation.
“These findings contribute to the field by proposing a practical framework that helps engineers to predict grout permeation behavior more efficiently, even in complex and heterogeneous soils,” concludes Prof. Inazumi.
Future research will focus on incorporating more physical properties of the grouting process, such as grout pressure, grout rheology, injection conditions, and grain size distributions into FEM simulations. This will further improve the practical field applicability of this novel integrative framework.
this study offers a promising approach to address the critical challenges associated with soil liquefaction in earthquake-prone regions worldwide.
