Developing free swell index of soil test as smart experiment in virtual geotechnical engineering laboratory

This research combines predictive analytics with interactive graphics to create a smart virtual lab for geotechnical engineering students. Traditional virtual labs usually run fixed simulations that don’t capture the variability of real tests. To fix that, we use past experimental data to train machine learning regression models that can predict test results in real time from soil properties. We use the Free Swell Index (FSI) of soils as a test case. The study compares several machine learning methods: Linear Regression, Support Vector Regression, Decision Tree Regression, and Random Forest Regression. The Random Forest model gives the best accuracy, so we use it in the final system. The model’s predictions feed

directly into web‑based graphics and animations, giving students a realistic, data‑driven experiment experience. This approach shows how to turn ordinary simulation‑based virtual labs into intelligent, predictive learning tools, improving remote geotechnical engineering education.

Message: Hi FE, I need help with “Developing free swell index of soil test as smart experiment in virtual geotechnical engineering laboratory” in “Civil Engineering”