Write to us
enquiry@myfinb.com

Combining News Media and AI to Rapidly Identify Flooded Buildings

"Artificial intelligence (AI) has sped up the process of detecting flooded buildings immediately after a large-scale flood, allowing emergency personnel to direct their efforts efficiently. Now, researchers have created a machine learning (ML) model that uses news media photos to identify flooded buildings accurately within 24 hours of the disaster."

Artificial intelligence (AI) has sped up the process of detecting flooded buildings immediately after a large-scale flood, allowing emergency personnel to direct their efforts efficiently. Now, researchers have created a machine learning (ML) model that uses news media photos to identify flooded buildings accurately within 24 hours of the disaster.

Artificial intelligence (AI) has sped up the process of detecting flooded buildings immediately after a large-scale flood, allowing emergency personnel to direct their efforts efficiently. Now, a research group from Tohoku University has created a machine learning (ML) model that uses news media photos to identify flooded buildings accurately within 24 hours of the disaster.

Their research was published in the journal Remote Sensing on 5 April 2021.

Our model demonstrates how the rapid reporting of news media can speed up and increase the accuracy of damage mapping activities, accelerating disaster relief and response decisions, said Shunichi Koshimura of Tohoku University’s International Research Institute of Disaster Science and co-author of the study.

ML and deep learning algorithms are tailored to classify objects through image analysis. For AI and ML to be effective, data is needed to train the model – flood data in the current case.

Although flood data can be collected from previous events, it will inadvertently lead to problems on account of every event being different and subject to the local characteristics of the flooded area. Thus, onsite information has higher reliability.

News crews and media teams are often the first on the scene of a disaster to broadcast images to viewers at home, and the research team recognized that this information too could be used in AI algorithms.

They applied their model to Mabi-cho, Kurashiki city in Okayama Prefecture, which was affected by the heavy rains across western Japan in 2018.

First, researchers identified press photos and geolocated them based on landmarks and other clues appearing in the photo. Next, they used synthetic aperture radar (SARPALSAR-2 images provided by JAXA to discretize flooded and non-flooded conditions of unknown areas.

Here, SAR images can be employed to classify water bodies since microwaves irradiate differently on wet and dry surfaces. A support vector machine (SVM), one of the machine learning techniques, was used to classify buildings surrounded by floodwaters or within non-flooded areas.

The performance of our model resulted in an 80% estimation accuracy,” added Koshimura.

Looking ahead, the research group will explore the applicability of news media databases from past events as training datasets for developing AI Models at present situations to increase the accuracy and speed of classification.

 

Source: Homeland Security Newswire

Share:

Share on facebook
Facebook
Share on twitter
Twitter
Share on linkedin
LinkedIn
Share on telegram
Telegram
Share on whatsapp
WhatsApp
Share on email
Email

AI Blog – Latest news on Artificial Intelligence and its applications on the globe. 

Browse more

Related Posts

Board Directors Can Do More With AI

Corporate governance is an evolving area that changes with policy matters and economic reforms in a country. There is notably an increasing pressure on the board of directors and management to implement policies; while maintaining a healthy culture and good corporate governance responsibility across the organisation.

Read More »

New Way Forward to Formulate Strategic Plans

The Centre for AI Innovation (CEAI), the social innovation arm of MyFinB Group, has launched a series of capacity building programme to help diverse types of organisations with strategic planning, using AI. This was implemented in view of the volatility of the business environment that causes many organisations to adopt reactive strategies rather than proactive ones. However, reactive strategies or “fire-fighting” are typically only viable as a short-term solution, even though they may require spending significant resources and time to execute them.

Read More »

Professional Firms Get AI Boost for their Clients

InfoTrust, a Singapore-based, award-winning ICT company, is embarking on a journey to build internal competencies in AI to disrupt traditional professional services such as corporate reporting solutions. The primary goal is for InfoTrust to build a suite of AI solutions using predictive and prescriptive analytics, to boost its existing suite of solutions for the Singapore market as a start.

Read More »