In the fight for the prevention and treatment of forestry fires included in Artificial intelligence thanks to the innovative programs developed, coordinated by the National Observatory of Athens.

These are two innovative programs “Deep Cube” and “SeasFire”, which launched in January 2021 and March 2022, respectively, and with the help of artificial intelligence technologies, seek to assess the risk of forest fires in different ways.

As emphasized by Yannis Papoutsis, authorized researcher at the National Observatory of Athens, Institute of Astronomy, Astrophysics, Space Applications and Remote Sensing, recently elected to the National Technical University of Athens, “The goal of Deep Cube is to use the very large amount of satellite data currently available, free of charge and free in combination with artificial intelligence technologies to be able to extract new information from satellite data,” and adds that Deep Cube has various technologies and applications, one of which is the risk assessment of forest fires the next day. “This is an app that we developed in collaboration with the fire department,” he says, referring to today’s start of the fire season.

Expansion throughout the Mediterranean

Last year the specific program worked as a pilot project for Greece, but this year its application has been extended to the entire Mediterranean. “As a country and as an institution (National Observatory of Athens) we have been innovating, we are one of the first. We will develop it for other countries, as part of other programs that have been requested from us, for example in Spain, and we will also do this for the wider Mediterranean,” he emphasizes.

“Through an innovative program, we are trying to solve the problem of risk prevention, which is complex and multifaceted, as it is a series of environmental and other parameters that interact with each other, each time increasing or decreasing the risk. This is because it is difficult to model, so we are trying to train an AI system to learn all these complex and non-linear interactions between all these parameters. This can happen using historical data. We allow the model to take these parameters as input and, based on the history of the burnt areas, we study these complex relationships. And then, after we train this model, we put it into production. Every day we collect all these parameters and make an assessment the next day,” notes Mr. Papucis at APE-MBE and adds a significant contribution from the fire department to this project.

Based on the Deep Cube, the research group of the Orion Lab IAADET/EAA laboratory a year later, in March 2022, began to develop the second innovative SeasFire program, funded by the European Space Agency. SeasFire is studying forest fire risk assessment, but on a different time scale, 2, 3, 4, 5 months from today. “After DeepCube, we plucked up the courage to take it a step further and see how we can use artificial intelligence to predict the frequency and intensity of wildfires in Europe over the long term. The main assumption that we make is the butterfly effect, that is, what happened sometime in the past, in another part of the planet, can affect what happens here and now, and this is because it is a large interconnected system with natural processes. which influence each other at different spatial and temporal distances. These are teleconnects. This is what we are trying to model in SeasFire, and we are focusing on Europe, but to be able to assess the seasonal fire risk in Europe, we need information about what is happening in the Atlantic Ocean, what is happening in Africa, what is happening in other parts of the planet. in the past to be able to predict what will happen this summer. This is his innovation,” emphasizes Mr. Papucis in an interview with APE-MPE.

Disaster Prevention

According to Mr. Papoucis, the scientific community is rapidly moving towards the use of artificial intelligence to prevent these phenomena. “The question is how all these technological tools, using artificial intelligence and satellite data, will win the trust of business people. Therefore, these tools need to be trusted and understood in order to be able to use them online,” says Mr. Papoutsis.

In recent years, it seems that artificial intelligence is being used more and more by the scientific community in combination with climatological and satellite data. “There is a lot of mobility and it shows that artificial intelligence has a lot to offer. 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. Such applications will continue to come out and are already coming out of the scientific community, the question is how they will be integrated into the operational plan or response based on the protocols that the GO, the fire department, the DSA or other bodies in charge of disaster management. This is a different issue, and it concerns the national policy and the systematic evaluation phase, as well as the joint development of some services,” notes Mr. Papoutsis.]

^{Source: APE-MEB}