Science & Technology

Davos 2023: Can AI make wildfire mitigation efficient? WEF’s FireAId initiative shows how

Successful pilot in Turkey reduced both response time and risk to firefighters; can be scaled up: WEF report

By Preetha Banerjee
Published: Tuesday 17 January 2023
Photo: iStock_

The FireAId initiative of using artificial intelligence to effectively manage wildfire had a successful pilot run since it was launched in January 2022 by the World Economic Forum (WEF), a new report showed.

The project was made operational in the South Aegean and West Mediterranean region of Turkey, WEF’s The Next Frontier in Fighting Wildfires: FireAId Pilot and Scaling report published January 16, 2023 said. The region was chosen since a quarter of the country’s wildfires occurred there in 2010-2021 and accounted for 75 per cent of the total burned area during the period. From July-August 2021, Turkey experienced some of its worst wildfires that charred a total of 139,503 hectares.

Here, scientists used static and meteorological data to map areas where fires can start, predicted the intensity and planned the logistics required for efficient response. 

The predictions reduced both response time and risk to firefighters, the report on the pilot operation showed. The project can now be scaled up and expanded to other locations, WEF noted in the report.

The report was unveiled at the World Economic Forum Annual Meeting 2023 being held in Davos, Switzerland from January 16-20, 2023.  

The multistakeholder initiative that collaborates resources from governments, civil society and the private sector was formulated by Koç Holding, Turkey’s largest industrial conglomerate, and was joined by Deloitte, an international professional services network, that brought on board its own AI technology to develop a ‘digital twin’ for fire management. 

“The digital twin presents firefighters with the possibility of testing hypotheses of intervention measures and observing their outcomes in time-accelerated simulations of the region under their care,” the WEF report noted. 

Five stages of a wildfire risk-management solution

Source: Deloitte

Wildfires are a natural phenomenon that has always occurred and in a controlled manner, is even helpful for the ecosystems. But climate change has increased the severity and frequency of forest fires over the last few years, causing unprecedented biodiversity loss, carbon dioxide emissions and financial losses worldwide.

“The average annual global cost of wildfires is around $50 billion, while in 2021, global wildfires released an estimated 6,450 megatonnes of CO2 into the atmosphere,” WEF noted in a press release on the report. 

To make matters worse, incidences of extreme fires across the globe is projected to increase 30 per cent by 2050 and double by the end of the century, according to the World Meteorological Organization.

Previous research identified AI and machine learning as useful tools to mitigate wildfire risks but were not fully utilised. The WEF report based on findings from the pilot run of FireAId highlights how their potential can be unlocked and scaled up for immediate use. 

The initiative serves as a space for global climate technology leaders in industry and government to share, learn and accelerate new, sustainable data-driven AI for wildfire efforts, Jeremy Jurgens, managing director, WEF, adding: 

The findings from this initiative can also be applied to further strengthen efforts in using AI applications to mitigate other climate risks, which can eventually safeguard populations, natural environments and economic prosperity. 

Forest lands provide the majority of freshwater supplies, WEF noted in its statement. “But wildfires severely affect water quality in rivers, reservoirs and streams. Ash settles on water surfaces, while burned landscapes may erode more quickly, increasing the accumulation of sediment in water. After a wildfire, the soil may have reduced capacity to absorb and store water, increasing the likelihood of flooding.” 

Managing and preventing wildfires is a vital element of efforts to control climate change and protect habitats, lives and livelihoods, the organisation added. 

There is a need for greater collaboration to improve the quality, scope and accessibility of relevant data and to enable this with minimum data requirement standards, the experts stressed in the report.  "Encouraging states to share their wildfire data and resources in order to promote the faster development and enhancement of AI technology, and greater crossgovernment and cross-entity collaboration, is an important prerequisite to addressing barriers in data access and data compatibility," they wrote.

The WEF report illustrated how AI-based data collection can support firefighting and wildfire risk management. 

Sensors with inbuilt AI, for instance, can collect acoustic information or operate as smoke detectors in forests and alert authorities within the first hour of a wildfire starting, it stated.

“Unmanned aerial vehicles can be flown over fires to provide live images and help firefighters plan their response,” the authors noted. 

Subscribe to Daily Newsletter :

Comments are moderated and will be published only after the site moderator’s approval. Please use a genuine email ID and provide your name. Selected comments may also be used in the ‘Letters’ section of the Down To Earth print edition.