LAB LOGA page on LabLog, a review site (not the lab's official page)
Disaster Mathematics Lab
Machine-translated · View original
The lab predicts disaster damage in advance using numerical analysis and machine learning.
AboutAbout the lab
Confronting disasters with the edge of mathematical science.
The Disaster Mathematics Lab studies how to predict the damage caused by natural disasters such as tsunamis and landslides before they happen.
Using mathematical science, the lab seeks to understand the principles of nature (water, soil, and wind) and to quantify the uncertainty inherent in disasters.
The lab works on disaster simulation using the particle method, a numerical analysis technique, together with machine learning and high-performance computing on supercomputers and GPUs.
The lab also studies VR, which lets people experience damage in a virtual space beforehand, and photogrammetry, which creates 3D models from photographs.
Key terms
- Particle method
- A numerical analysis technique that treats water, ground, and solids as collections of particles to represent large deformation and flow
- PINN
- Machine learning that incorporates knowledge of physics. Short for Physics-Informed Neural Network
- High-performance computing
- Computing technology that makes it possible to run large-scale, complex simulations in a short time. Also called HPC
- Photogrammetry
- A machine learning technique that reconstructs 3D models from photographs alone
NewsLab news
A doctoral student received the Outstanding Presentation Award in the Student-Led Session, among other awards, at the JSCES Summer Student Lecture Meeting
A doctoral student received the Graphics Award (Video category), among other awards, at the 31st Computational Engineering Conference
A master's student received a Student Presentation Award at APCOM-ACCM 2025
A student received the Outstanding Presentation Award at the Japan Society of Civil Engineers Western Branch Research Presentation Meeting (FY2025)
A paper by a researcher and a graduate of the lab was published in Computer Methods in Applied Mechanics and Engineering
ResearchResearch themes
The lab's greatest goal is to predict the scale of a disaster before it occurs and to support efforts to eliminate man-made disasters. The lab considers that achieving this requires multiphysics computation spanning several fields, such as structures, geotechnics, and hydraulics, as well as acceleration techniques that use machine learning.
*Illustrative imageDisaster Simulation with the Particle Method
To predict damage from tsunamis, landslides, and other disasters in advance, the lab develops its own SPH (smoothed particle hydrodynamics), a particle method. Water, ground, and solids are treated as collections of particles, representing everything from large deformation to flow.
*Illustrative imagePhysics-Informed Machine Learning
The lab also researches using machine learning to speed up disaster prediction simulations. For disasters, where data are scarce and predictions are also needed beyond the range of available data, PINN, a machine learning approach that incorporates knowledge of physics, is attracting attention.
*Illustrative imageHigh-Performance Computing with Supercomputers and GPUs
The lab researches high-performance computing that makes it possible to run large-scale, complex simulations in a short time. Equipped with supercomputers including the NVIDIA DGX Station, the lab supports simulations based on the particle method and machine learning.
*Illustrative imageExperiencing Disasters in Advance with VR
Using VR and a walking controller, the lab makes it possible to experience tsunami damage across an entire city or wide-area landslides in advance in a virtual space. Together with government agencies, the lab is building disaster prevention systems that minimize damage.
MembersFaculty
The members of the Disaster Mathematics Lab consist of faculty, a secretary, researchers, and doctoral, master's, and undergraduate students.As of 2026
- ProfessorMitsuteru Asai
- Project Assistant ProfessorGuoming Ling
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Disaster Mathematics Lab
Disaster Prevention Geotechnical Engineering LabFaculty of Engineering, Department of Civil EngineeringDisaster prevention geotechnical engineering: theory for und…
Structural Analysis LabFaculty of Engineering, Department of Civil EngineeringResearch on numerical analysis based on structural engineeri…
Earthquake Engineering LabFaculty of Engineering, Department of Civil EngineeringSeismic safety of infrastructure: analysis and experiments o…
Coastal and Ocean Engineering LabFaculty of Engineering, Department of Civil EngineeringCoastal ocean engineering: principles of wave and other natu…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Tsunami simulations Ofunato City” Ōfunato City, Prefecture Iwate, Japan / CC BY 3.0 igo (cropped)
- Disaster Simulation with the Particle Method: “August 2007, disaster simulation in central Kyoto 2” Syced / CC0 (cropped)
- Physics-Informed Machine Learning: “Multilayer Neural Network” John Salatas / CC BY-SA 3.0 (cropped)
- High-Performance Computing with Supercomputers and GPUs: “Columbia Supercomputer - NASA Advanced Supercomputing Facility” Trower, NASA / Public domain (cropped)
- Experiencing Disasters in Advance with VR: “Virtual reality headset” FloppaIngénieur / CC BY 4.0 (cropped)
- Related lab (防災地盤工学研究室): “Road failure from slope instability in Shasta-Trinity National Forest” Shopstone / CC0 (cropped)
- Related lab (構造解析学研究室): “Static Structural Analysis of a Gripper Arm” SimScale GmbH / CC BY-SA 4.0 (cropped)
- Related lab (地震工学研究室): “View of the Five-storied Pagoda from the Lotus Pond, Tō-ji Temple, Kyoto” Jakub Hałun / CC BY 4.0 (cropped)
- Related lab (沿岸海洋工学研究室): “Seawall-large(USGS)” USGS / Public domain (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.