Using the past to predict the future: The case of Typhoon Hagibis

July 15, 2020

The past is often the window to our future, especially when it comes to natural disasters. Using data from the 2018 floods that struck southwestern Japan to calibrate a machine learning model, researchers from the International Research Institute of Disaster Science (IRIDeS) at Tohoku University and the Japan-Peru Center for Earthquake Engineering Research and Disaster Mitigation (CISMID, in Spanish), have successfully identified the flooding caused by Typhoon Hagibis.

Typhoon Hagibis devastated Japan in October 2019, killing 91 people, damaging 85,000 homes, and causing approximately $15 billion in damage. Flooding across the affected regions was profound.

In natural disaster rescue and recovery efforts, real-time flood mapping is crucial. It allows governments to direct relief to the areas that need it most. To aid this effort, satellite images using artificial intelligence (AI) are often employed.

Crucial to this is training data. Training data allows the algorithms to learn data and produce outputs when new inputs arise in a process known as machine learning. However, the amount of training data is limited in many cases. Collecting training data immediately following a disaster is costly, time-consuming and many times impossible.

At IRIDeS and CISMID, authors of the study, evaluated the performance of a model to learn from the 2018 floods that struck southwestern Japan, and to identify the floods induced by the 2019 Typhoon Hagibis. The resulting flood maps were consistent with the results of actual flooding maps released by local governments and public institutions.

The authors note that "Our model successfully identifies the inundated areas and verified that AI can learn from past disasters, ultimately allowing us to better predict flooding in future events." They add that "Our next step in this project would be to incorporate data from the unknown event into a second stage of training for a more accurate estimation."
-end-


Tohoku University

Related Flooding Articles from Brightsurf:

Coastal flooding will disproportionately impact 31 million people globally
Indiana University researchers analyzed these geographic regions, which include cities like New Orleans, Bangkok, and Shanghai, using a new global dataset to determine how many people live on river deltas, how many are vulnerable to a 100-year storm surge event, and the ability of the deltas to naturally mitigate impacts of climate change.

New woodlands can help reduce flooding risk within 15 years
New research by the University of Plymouth suggests the planting of more trees could have a significant and positive effect in preventing flash flooding.

Land use change leads to increased flooding in Indonesia
While high greenhouse gas emissions and biodiversity loss are often associated with rapid land-use change in Indonesia, impacts on local water cycles have been largely overlooked.

Climate change: Coastal flooding could threaten up to 20% of global GDP
Coastal flooding events could threaten assets worth up to 20% of the global GDP by 2100, a study in Scientific Reports suggests.

River plants counter both flooding and drought to protect biodiversity
'Water plants are a nuisance in streams, blocking the flow.

Scientists predict dramatic increase in flooding, drought in California
California may see a 54 percent increase in rainfall variability by the end of this century, according to research from a UC Davis atmospheric scientist.

Multiple flooding sources threaten Honolulu's infrastructure
In a study published in Scientific Reports, researchers at the University of Hawai'i at Mānoa, found in the next few decades, sea level rise will likely cause large and increasing percentages of land area to be impacted simultaneously by the three flood mechanisms.

Climate change: Extreme coastal flooding events in the US expected to rise
Extreme flooding events in some US coastal areas could double every five years if sea levels continue to rise as expected, a study published in Scientific Reports suggests.

Study find delta helps to decrease the impact of river flooding
Most coastal cities and ports face a double threat from storm surge and river flooding.

Texas A&M researchers develop flooding prediction tool
By incorporating the architecture of city drainage systems and readings from flood gauges into a comprehensive statistical framework, researchers at Texas A&M University can now accurately predict the evolution of floods in extreme situations like hurricanes.

Read More: Flooding News and Flooding Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.