Artificial intelligence in the fight against forest fires – The innovative programs of the National Observatory

By | May 1, 2023

In the battle for the prevention and treatment of forests fires artificial intelligence enters through innovative programs that have been developed, whose coordinator is the National Observatory of Athens.

These are two innovative programs in “deep cube” and “seafireLaunched in January 2021 and March 2022 respectively and through the use of artificial intelligence technologies, they seek to assess the risk of forest fires in different ways.

As the commissioned researcher at the National Observatory of Athens, at the Institute of Astronomy, Astrophysics, Space Applications and Remote Sensing, newly elected at NTUA, emphasizes to the Athens-Macedonian News Agency, Yannis Papoutsisthe goal of Deep Cube is to exploit a large amount of satellite data that is available at the moment, freely and freely in combination with artificial intelligence technologies to be able to extract new information from satellite data“, and adds that in Deep Cube there are various technologies and applications, one of which is the assessment of the risk of forest fires for the next day. “It is an application that we have developed in collaboration with Bomberos“, he says on the occasion of today’s start of the firefighting season.

Last year’s specific program functioned as a pilot for Greece however, this year its application has been extended throughout the Mediterranean. “As a country and as an organization (National Observatory of Athens) we have innovated, we are among the first. We will also develop it for other countries, within the framework of other programs that have been requested of us, in Spain for example, and we will also do it for the rest of the Mediterranean.“he emphasizes.

Through the innovative program we try to solve the problem of risk prevention, which is complex and multidimensional since it is a series of environmental parameters and others that interact with each other, increasing or decreasing the risk each time. This is because it’s hard to model, so we try to train an AI system to learn all of these complex, non-linear interactions between all of these parameters.. This can happen by leveraging historical data. We let a model take these parameters as input and, based on the history of burned areas, learn these complex interrelationships. And then after we train that model, we put it into production. We collect all these parameters daily and make an estimate for the next day.“, says Mr. Papoutsis to APE-MPE and adds the important contribution of the Fire Department to this project.

Guided by the “Deep Cube”, the IAADET/EAA Orion Lab research group proceeded after one year, in March 2022, to the development of a second groundbreaking “SeasFire” program. which was funded by the European Space Agency. “SeasFire” studies wildfire risk assessment but on a different time scale, 2, 3, 4, 5 months from today. “After DeepCube, we are encouraged to go a step further and analyze how we can use artificial intelligence to predict the frequency and intensity of forest fires in Europe in the long term. A basic assumption that we make is the butterfly effect, that is, something that happened at some point in the past, in another part of the planet, can affect what will happen here and now, and this is because it is a large system interconnected with processes natural. that affect each other, at various spatial and temporal distances. These are the teleconnections. That is what we are trying to model in SeasFire and we are focusing on Europe, but in order to assess the risk of seasonal fires in Europe we need to get information on what is happening in the Atlantic Ocean, what is happening in Africa, what is happening in other areas of the planet in the past to be able to predict what will happen this summer. This is your innovation.“, emphasizes Mr. Papoutsis to APE-MPE.

Artificial intelligence can help prevent natural disasters

According to Mr. Papoutsis, the scientific community is moving rapidly in the direction of using artificial intelligence to prevent these phenomena. “The question is how all these technological tools that take advantage of artificial intelligence and satellite data will win the trust of companies.. Therefore, trust and understanding of these tools must be built before they can be used operationally.“, says Mr. Papoutsis.

In recent years, it seems that artificial intelligence is being used more and more by the scientific community in combination with weather and satellite data. “There is a lot of mobility and it shows that artificial intelligence can offer a lot. In the coming years we will also have very good results in terms of the use of artificial intelligence in the entire phase of the fire management cycle. These types of applications will continue to appear and are already leaving the scientific community, the question is how they will be integrated into an operational or response plan based on the protocols of Civil Protection, Firefighters, OASP or others. organizations in charge of managing natural disasters. This is another matter and refers to the national policy and a phase of systematic evaluation, as well as joint development of some services.“, says Mr. Papoutsis.

Leave a Reply

Your email address will not be published. Required fields are marked *