Artificial intelligence can boost disaster management
The World Meteorological Organization is participating in a new interdisciplinary Focus Group to contend with the increasing prevalence and se
The World Meteorological Organization is participating in a new interdisciplinary Focus Group to contend with the increasing prevalence and severity of natural hazards with the help of artificial intelligence (AI).
The International Telecommunications Union Focus Group on 'AI for natural disaster management' will support global efforts to improve our understanding and modelling of natural hazards and disasters. Led by ITU in partnership with WMO and the UN Environment Programme, it will distill emerging best practices to develop a roadmap for international action in AI for natural disaster management.
The group's first meeting is scheduled for 15-17 March 2021.
"With new data and new insight come new powers of prediction able to save countless numbers of lives," says ITU Secretary-General Houlin Zhao. "This new Focus Group is the latest ITU initiative to ensure that AI fulfils its extraordinary potential to accelerate the innovation required to address the greatest challenges facing humanity."
Over the past 50 years, more than 11,000 disasters have been attributed to weather, climate and water-related hazards, involving 2 million deaths and US$ 3.6 trillion in economic losses. While the average number of deaths recorded for each disaster has fallen by a third during this period, the number of recorded disasters has increased five times and the economic losses have increased by a factor of seven, according to WMOs State of Climate Services 2020 report.
Extreme weather and climate events have increased in frequency, intensity and severity as result of climate change and hit vulnerable communities disproportionately hard. Yet one in three people are still not adequately covered by early warning systems.
In 2018, globally, around 108 million people required help from the international humanitarian system as a result of storms, floods, droughts and wildfires. By 2030, it is estimated that this number could increase by almost 50% at a cost of around US$ 20 billion a year, says the WMO report.
Although the global death toll has fallen, the poor remain disproportionately exposed.
"AI has the potential to help all countries to achieve major advances in disaster management that will leave no one behind," according to Jrg Luterbacher, Chief Scientist and Director of Science and Innovation at WMO.
"The WMO Disaster Risk Reduction Programme assists countries in protecting lives, livelihoods and property from natural hazards, and it is strengthening meteorological support to humanitarian operations for disaster preparedness through the development of a WMO Coordination Mechanism and Global Multi-Hazard Alert System. Complementary to the Focus Group, we aim to advance knowledge transfer, communication and education all with a focus on regions where resources are limited."
The Focus Group's work will pay particular attention to the needs of vulnerable and resource-constrained regions. It will make special effort to support the participation of the countries shown to be most acutely impacted by natural disasters, notably Small Island Developing States and Least Developed Countries.
AI is becoming increasingly important to WMOs work. Supercomputers crunch petabytes of data to forecast weather around the world. The WMO also coordinates a global programme of surface-based and satellite observations. Their models merge data from more than 30 satellite sensors, weather stations and ocean-observing platforms all over the planet, explains Anthony Rea, Director of the Infrastructure Department at WMO.
The WMO Information System (WIS) acts as a one-stop shop for all activities related to data management. AI can help interpret resulting data and help with decision support for forecasters who receive an overwhelming amount of data. AI can help recognize where there might be a severe event or a risk of it happening.
AI is not, however, a magic bullet which will replace the models built on physical understanding and decades of research into interactions between the atmosphere and oceans. And in order for AI to thrive, data needs to be open, available and interoperable, says Rea.