LAB LOGA page on LabLog, a review site (not the lab's official page)
Miyamoto Lab
Machine-translated · View original
A disaster prevention engineering lab that uses machine learning to assess earthquake damage and forecast heavy rainfall.
AboutAbout the lab
Using artificial intelligence to quickly grasp disaster damage
Miyamoto Lab studies technologies that use machine learning to detect disaster damage and hazards.
The lab is building a system that analyzes satellite images taken immediately after a major earthquake with deep learning to assess damage to each individual house.
To prepare for heavy rain, it is also developing methods that predict rainfall several tens of minutes ahead from observation data.
The lab also works on how to determine the ground motions used in structural design, and on large-scale numerical analyses that examine how strongly the ground shakes.
Key terms
- Deep learning
- A machine learning method that uses neural networks with many stacked layers to learn features from large amounts of data.
- Design ground motion
- A hypothetical ground motion set to represent the shaking expected at a site, used to verify the safety of a structure.
- Finite element method
- A method that divides ground or structures into small elements and computes deformation and shaking on a computer.
ResearchResearch themes
Specializing in data-driven science and disaster prevention engineering, the lab applies machine learning to civil engineering problems. Its main themes are earthquake damage detection, rainfall prediction, and the analysis of ground motion and ground response.
*Illustrative imageEarthquake Damage Detection from Satellite Images
After a major earthquake, collecting the damage information needed for tasks such as rescue still takes a great deal of effort and time. The lab aims to build a system that analyzes satellite images with deep learning and quickly grasps conditions across an area, starting from damage to individual houses.
*Illustrative imageShort-Term Rainfall Prediction from Data
In Japan, which keeps suffering heavy-rain disasters, predicting rainfall locally is a challenge for disaster prevention. The lab predicts rainfall 5 to 30 minutes ahead with a deep learning model that combines convolution, which captures spatial features, and a recurrent structure, which learns temporal relationships.
*Illustrative imageSetting Representative Design Ground Motions
In the design of infrastructure structures, hypothetical ground motions that represent the expected shaking are used. This research determines design ground motions that condense key information from many records observed under very similar conditions, or from groups of ground motions generated by numerical simulation.
*Illustrative imageGround Motion Analysis of the Kofu Basin
Estimating which areas will shake and how much is important information for planning disaster countermeasures. Using a parallelized nonlinear finite element method, the lab analyzes ground motion in the Kofu Basin under the anticipated Tokai earthquake, examining how susceptible each area is to shaking and how much the ground deforms.
MembersFaculty
Miyamoto Lab consists of faculty members and master's and undergraduate students.
- Associate ProfessorTakashi MiyamotoPublications ↗
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 Miyamoto Lab
Takahashi LabSchool of Environment and Society, Department of Civil and Environmental EngineeringGeotechnical engineering, disaster prevention engineering
Matsuzaki LabSchool of Environment and Society, Department of Civil and Environmental EngineeringStructural engineering, earthquake engineering, concrete eng…
Oguchi LabSchool of Environment and Society, Department of Civil and Environmental EngineeringRock weathering degree assessment, earth science, geoheritag…
Morikawa LabSchool of Environment and Society, Department of Civil and Environmental EngineeringEarthquake engineering, engineering seismology, stochastic p…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: “Tokyo L7 lrg” Image courtesy Ron Beck, USGS Eros Data Center Satellite Systems Branch / Public domain (cropped)
- Earthquake Damage Detection from Satellite Images: “US Navy 110322-N-SB672-673 An aerial view of Baba Utatsu Minamisanriku, Motoyoshi, Japan, 11 days after a 9.0 magnitude earthquake and subsequent tsunami” U.S. Navy photo by Mass Communication Specialist 3rd Class Dylan McCord / Public domain (cropped)
- Short-Term Rainfall Prediction from Data: “Typhoon Ampil Brushes Japan (CIRA )” Himawari imagery: CSU/CIRA & JMA/JAXA / Public domain (cropped)
- Setting Representative Design Ground Motions: “A seismogram of 2011 Tōhoku earthquake and tsunami” Z22 / CC BY-SA 3.0 (cropped)
- Ground Motion Analysis of the Kofu Basin: “Kofu-Basin from Mt.Daibosatsurei 02” Σ64 / CC BY-SA 3.0 (cropped)
- Related lab (高橋研究室): “Full breach at levee L-575 near Hamburg” US Army Corps of Engineers from USA / CC BY 2.0 (cropped)
- Related lab (松﨑研究室): “022srUSGSCyprusVia” H.G. Wilshire, U.S. Geological Survey / Public domain (cropped)
- Related lab (小口研究室): “Ffionphort cracked granite boulder” 作者不詳 / Public domain (cropped)
- Related lab (盛川研究室): “Đorđićeva Street damaged building in 2021” Milan Kušnjačić / CC0 (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.