In a groundbreaking study, researchers from Shibaura Institute of Technology have created an AI-based model to predict soil liquefaction risks, revolutionizing urban planning and resilience efforts in earthquake-prone regions.
The journey toward building smart cities has taken a significant leap forward with the development of an innovative AI-driven model designed to predict soil liquefaction risks. This breakthrough, achieved by researchers at the Shibaura Institute of Technology and published in the journal Smart Cities, promises to enhance urban resilience and emergency preparedness in seismic zones.
Soil liquefaction, a natural hazard where saturated soil loses its strength due to earthquake-induced shaking, poses a severe threat to urban infrastructure. Addressing this challenge is crucial for developing smart cities, especially in regions prone to seismic activity.
Led by Shinya Inazumi, the research team, which includes Arisa Katsuumi and Yuxin Cong, has made significant strides in risk prediction.
“We were motivated to pursue this research after we recognized the urgent need to improve urban resilience to earthquakes, especially in rapidly urbanizing areas prone to seismic activity — there are critical weaknesses in existing geotechnical risk assessments and urban planning strategies,” Inazumi said in a news release.
He outlined the limitations of traditional methods and emphasized the need to leverage AI and machine learning for improved data integration and analysis speed.
The model employs advanced machine learning techniques, including artificial neural networks and gradient-boosting decision trees, to predict soil liquefaction risks with high accuracy. By integrating geotechnical and geographical data, the researchers have crafted a tool that improves urban planning in Yokohama, Japan, an area susceptible to seismic activity due to its extensive reclaimed lands.
Remarkably, this AI model generates comprehensive hazard maps, offering critical insights for urban planners and engineers.
“The real-world application of our research is the development of hazard maps which can help urban planners and engineers to visualize and identify areas at high risk for soil liquefaction and make informed decisions regarding the development of infrastructures,” added Prof. Inazumi.
He further emphasized its role in bolstering emergency response planning and fostering community engagement and education.
This innovative approach marks a transformative development in geotechnical engineering, showcasing the profound impact of AI on soil liquefaction risk prediction and urban resilience.