PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Towards better earthquake risk assessment with machine learning

Researchers utilize geological survey data and machine learning algorithms for accurately predicting liquefaction risk in earthquake-prone areas.

2025-08-08
(Press-News.org)

“A building is only as strong as its foundation” is a common adage to signify the importance of having a stable and solid base to build upon. The type and design of foundation are important for ensuring the structural safety of a building. Among several factors that can affect the design and laying of a foundation, bearing stratum depth, namely the depth at which the underlying layer of soil or rock has adequate strength to support a foundation, is one of the most crucial. This is because in regions that are prone to earthquakes or landslides, the bearing stratum depth, also known as bearing layer depth, serves as an indirect indicator of soil liquefaction risk, or the risk of soil collapsing and losing its stiffness, and behaving like a liquid. Understandably, an accurate estimation of the bearing layer depth is key to designing robust foundations, limiting soil liquefaction risks, and mitigating soil-related disasters.

Traditional methods to assess the bearing layer depth, notably the standard penetration test (SPT), are generally reliable but involve both time- and labor-intensive processes for obtaining subsurface soil samples and are expensive. A cost-effective alternative is, therefore, imperative.

To address this issue, scientists from Shibaura Institute of Technology (SIT), Japan recently turned their attention to machine learning (ML). A team of researchers led by Professor Shinya Inazumi from the College of Engineering at SIT utilized 942 geological survey records and SPT data from the Tokyo metropolitan area and employed three ML algorithms, random forest (RF), artificial neural network (ANN), and support vector machine (SVM), to predict the bearing layer depth. Their research findings were published in volume 7, Issue 69 of the journal Machine Learning and Knowledge Extraction on July 21, 2025.

“The inspiration for this research stemmed from the pressing challenges in geotechnical engineering within earthquake-vulnerable urban landscapes like Tokyo. As a region with a history of devastating seismic events, such as the 1923 Great Kanto Earthquake, accurate prediction of bearing layer depth is vital.  Through our research study, we hope to empower urban planners and engineers with efficient tools for sustainable development, reducing costs and enhancing safety”, shares Inazumi, explaining the motivation behind the present study.

In their study, the researchers initially trained and optimized the chosen ML models using the SPT dataset. Thereafter, they developed two experimental case scenarios depending on the set of explanatory variables utilized for the assessment. While the first case scenario (Case-1) employed latitude, longitude, and elevation as explanatory variables, the second scenario (Case-2) included stratigraphic classification data, namely information about the underground soil layer, in addition to the other three geographical parameters.

During the comparative evaluation, the researchers found that the RF model consistently outperformed ANN and SVM, particularly in terms of depth prediction accuracy (a mean absolute error of 0.86 m for Case-2 vs. 1.26 m for Case-1) and robustness to noisy data. Moreover, the prediction accuracy of all three models in the Case-2 scenario, which includes stratigraphic classification data as an additional explanatory variable, was markedly improved.

Inspired by their research findings, the researchers went a step further and investigated the impact of spatial data density on prediction performance. To this end, they generated six different data subsets with varying spatial densities: 0.5, 1.0, 1.5, 2.0, 2.5, and 3.0 points/km2. They found that the prediction accuracy of RF model in case-2 improved with increasing data density, indicating that spatially denser datasets are valuable for accurate predictions of bearing layer depth.

Overall, the team’s study demonstrates that ML, especially RF, can offer a much-needed alternative to traditional methods for regional disaster risk assessment. Moreover, unlike SPT, ML models are cost-effective and, with further improvements to the computing architecture and integration with advanced real-time platforms, could revolutionize infrastructure planning in seismically active areas, reducing reliance on expensive, localized tests while improving safety and efficiency.

Emphasizing the potential applications of the study, Inazumi concludes, ”Our findings highlight the transformative real-world potential of ML models in geotechnical engineering and urban planning, especially in earthquake-prone regions like Tokyo. By combining ML with existing geological data, stakeholders can optimize site selection for resilient smart cities and other infrastructure projects, such as bridges or subways, with rapid, scalable simulations”.

 

***

 

Reference
DOI: 10.3390/make7030069

 

About Shibaura Institute of Technology (SIT), Japan
Shibaura Institute of Technology (SIT) is a private university with campuses in Tokyo and Saitama. Since the establishment of its predecessor, Tokyo Higher School of Industry and Commerce, in 1927, it has maintained “learning through practice” as its philosophy in the education of engineers. SIT was the only private science and engineering university selected for the Top Global University Project sponsored by the Ministry of Education, Culture, Sports, Science and Technology and had received support from the ministry for 10 years starting from the 2014 academic year. Its motto, “Nurturing engineers who learn from society and contribute to society,” reflects its mission of fostering scientists and engineers who can contribute to the sustainable growth of the world by exposing their over 9,500 students to culturally diverse environments, where they learn to cope, collaborate, and relate with fellow students from around the world.

Website: https://www.shibaura-it.ac.jp/en/

 

About Professor Shinya Inazumi from SIT, Japan
Dr. Shinya Inazumi serves as a professor in the College of Engineering, Shibaura Institute of Technology (SIT), Japan. He received his Ph.D. from Kyoto University. His main research interests include social infrastructure engineering, civil engineering, geo-disaster engineering, geotechnical analysis studies, and artificial intelligence. In addition to leading the Geotechnical Engineering Laboratory at SIT, he has published 320 papers in high-impact factor journals and has also received several prestigious awards for his research excellence.

 

Funding Information
This research received no external funding.

END



ELSE PRESS RELEASES FROM THIS DATE:

Reducing the global burden of liver cancer: Recommendations from The Lancet commission

2025-08-08
Liver cancer is the sixth most common cancer as well as the third highest cause of cancer-related mortality worldwide. In particular, a subtype of liver cancer known as hepatocellular carcinoma accounts for around 80% of all liver cancer cases. Given the increasing disease burden of hepatocellular carcinoma globally, a Commission consisting of experts in a wide range of fields – from clinical medicine to public health – has now been established to tackle this issue. Recently, in a comprehensive ...

Researchers succeed in building a low temperature hydrogen fuel cell, thanks to a scandium superhighway

2025-08-08
Fukuoka, Japan—As global energy demand increases, researchers, industries, governments, and stakeholders are working together to develop new ways of meeting that demand. This is especially important as we address the ongoing climate crisis and transition away from fossil fuels. One very promising type of energy generation is solid-oxide fuel cells, or SOFCs. Unlike batteries, which release stored chemical energy as electricity, fuel cells convert chemical fuel directly into electricity and continue to do so as long as fuel is provided. A common ...

New UC Irvine survey reveals shifting work landscape

2025-08-08
The University of California, Irvine School of Social Ecology today released the results of its latest UCI-OC Poll, shedding light on the changing nature of work in Orange County two years after the official end of the COVID-19 pandemic.   Conducted from June 20 to July 1, 2025, the survey of 800 Orange County adults offers insights into remote work preferences, attitudes toward artificial intelligence and overall job satisfaction – providing valuable insights for business leaders and policymakers navigating ...

Quantum ‘Starry Night’: Physicists capture elusive instability and exotic vortices

2025-08-08
Van Gogh’s “The Starry Night” has stirred the souls of art lovers for over a century. Now, its swirling skies may also speak to physicists, as it echoes the patterns of quantum turbulence. Physicists at Osaka Metropolitan University and the Korea Advanced Institute of Science and Technology have for the first time successfully observed the quantum Kelvin–Helmholtz instability (KHI) — a phenomenon predicted decades ago but never before seen in quantum fluids. The instability produces exotic vortex patterns known as eccentric fractional skyrmions, whose crescent-shaped structures ...

Excessive ultraprocessed foods (UPFs) and poor nutrition tied to poor health

2025-08-08
Science Advisory Highlights: Most ultraprocessed foods (UPFs) are characterized by poor nutritional quality, contributing to excessive calories, and are typically high in saturated fats, added sugars and sodium (salt), the combination of which is often abbreviated as HFSS, which contribute to adverse cardiometabolic health outcomes, including heart attack, stroke, obesity, inflammation, Type 2 diabetes and vascular complications. Observational studies have found links between eating higher amounts of UPFs and an increased risk of cardiovascular disease, chronic illness and mortality. Emerging evidence also suggests certain additives and industrial processing techniques ...

'One child called the robot "my little brother"': Can assistance tech become part of the family?

2025-08-08
What happens to a social robot after it retires?  Four years ago, we placed a small owl-shaped reading robot named Luka into 20 families’ homes. At the time, the children were preschoolers, just learning to read. Luka’s job was clear: scan the pages of physical picture books and read them aloud, helping children build early literacy skills.  That was in 2021. In 2025, we went back — not expecting to find much. The children had grown. The reading level was no longer age-appropriate. Surely, Luka’s work was done.  Instead, ...

Small but mighty: A biomimetic idea takes flight

2025-08-08
When Singapore celebrated its 50th  year of independence in 2015, a team of student researchers led by Associate Professor Foong Shaohui from Singapore University Technology and Design (SUTD) embarked on an ambitious challenge: to design and build a drone capable of 50 minutes of sustained flight. At the time, most hobbyist quadcopters could barely manage half of that. The SG50 Multi-Rotor Drone project succeeded, but to fly that long, the craft had to be large, complex, and heavy.   A decade on, Assoc Prof Foong has reached new heights in his drone research—this time by going small and pursuing a completely different ...

New hydrogel-based treatment accelerates infected wound healing and balances skin microbiota

2025-08-08
A novel ε-poly-L-lysine-loaded sodium-alginate/gelatin hydrogel (PSG15) has shown exceptional promise in accelerating the healing of infected wounds. This multifunctional injectable hydrogel delivers robust antibacterial properties while regulating macrophage polarization and stabilizing the skin microbiota. It significantly inhibited bacterial growth, including that of E. coli and S. aureus, and promoted tissue regeneration in infected wounds. In animal models, PSG15 enhanced angiogenesis, collagen deposition, and wound closure. These findings demonstrate the ...

New bioactive dressing promises faster diabetic wound healing

2025-08-08
Chronic diabetic wounds, including diabetic foot ulcers, are a significant burden for patients, as impaired blood vessel growth hinders the healing process. A recent breakthrough offers hope by combining small extracellular vesicles (sEVs) loaded with miR-221-3p and a GelMA hydrogel to target thrombospondin-1 (TSP-1), a protein that suppresses angiogenesis. This new bioactive wound dressing not only accelerates healing but also promotes blood vessel formation, offering a promising new approach to treating one of the most challenging complications of diabetes. Diabetic wounds, particularly foot ulcers, are notorious for their slow and often incomplete healing due to reduced blood flow and endothelial ...

Japan launches fully domestically produced quantum computer

2025-08-08
Osaka, Japan – A Japanese superconducting quantum computer, fully designed and built with homegrown components and software, went live on July 28th at The University of Osaka’s Center for Quantum Information and Quantum Biology (QIQB). This achievement signifies Japan's technological prowess in quantum computing, demonstrating the nation's capacity to design, manufacture, and integrate a complete quantum system. Visitors to Expo 2025, Osaka, Kansai, Japan will have the opportunity to interact with this cutting-edge technology through a dedicated exhibit. The project, spearheaded ...

LAST 30 PRESS RELEASES:

How a rare cycad's wax crystals conjure blue without pigment

Dana-Farber Cancer Institute unveils groundbreaking blood test for multiple myeloma

Public data reveal extent of air quality impacts during 2025 Los Angeles wildfires

Towards better earthquake risk assessment with machine learning

Reducing the global burden of liver cancer: Recommendations from The Lancet commission

Researchers succeed in building a low temperature hydrogen fuel cell, thanks to a scandium superhighway

New UC Irvine survey reveals shifting work landscape

Quantum ‘Starry Night’: Physicists capture elusive instability and exotic vortices

Excessive ultraprocessed foods (UPFs) and poor nutrition tied to poor health

'One child called the robot "my little brother"': Can assistance tech become part of the family?

Small but mighty: A biomimetic idea takes flight

New hydrogel-based treatment accelerates infected wound healing and balances skin microbiota

New bioactive dressing promises faster diabetic wound healing

Japan launches fully domestically produced quantum computer

Home is where the airfields are: What happens when hawks are moved from Los Angeles airports

Study: Sylvester researchers uncover molecular drivers of cellular differentiation

Withdrawal of kidney treatment significantly benefits patients and NHS

Illinois Tech hosts EV Readiness Community Awards, showcasing nation-leading energy innovation

Rice bioscientist wins NSF CAREER Award to investigate bacterial toxins, expand inclusion in STEM

Study links exercise with decreased mortality and cardiovascular events in people recently diagnosed with type 2 diabetes but no previous cardiovascular disease

Genetic testing reduces risks from chemotherapy for gastrointestinal cancer patients

UVic research predicts worldwide glacier erosion

A new boost for CryoZoo, Barcelona’s animal cell biobank

Asthma drug Zileuton blocks food allergy reactions in mice

Molecules in the spotlight: Snapshots reveal the eternal dance of particles

What drives anaphylactic response in food allergies

A thoughtful approach to governing emerging quantum technologies

What makes the teeth of chitons iron hard?

New antibody targeting approach, tested in mice, improves distribution and safety of Alzheimer’s immunotherapies

UC Irvine scientist takes a lesson from ultrahard, wear-resistant mollusk teeth

[Press-News.org] Towards better earthquake risk assessment with machine learning
Researchers utilize geological survey data and machine learning algorithms for accurately predicting liquefaction risk in earthquake-prone areas.