Protecting forests with AI
What do forests need if the climate changes? That’s what the FutureForest project is attempting to find out with the aid of AI.
Kim Berg,
28.09.2023 
Drought, torrential rain, storms and pest infestation destroyed around 501,000 hectares of forest in Germany from 2018 to 2021. That’s nearly five percent of the total area covered by German forests. Rapid global warming and the resulting extreme weather events are having an increasingly detrimental effect on forests. The goal of the FutureForest project is to halt this trend. With the aid of artificial intelligence (AI), it is developing recommendations for action aimed at protecting Germany’s forests long-term and making them climate-resistant. The project, which is scheduled to run for three years, was launched in 2022. It is being funded by Germany’s Federal Ministry for the Environment, Nature Conservation, Nuclear Safety and Consumer Protection.
A monitoring system for the forest
AI is able to analyse large quantities of environmental data and compile precise forecasts. FutureForest is using these capabilities to continuously monitor the state of the forests, to identify potential problems at an early stage and to recommend appropriate measures to preserve the forests. To this end, FutureForest analyses data from satellite images, soil samples, weather observations and other sources, such as sensors that it has developed itself to measure stress factors such as hot and dry conditions. “Based on this data, we have developed a method that focuses on identifying tree mortality and highly stressed forests,” says Thorsten Reitz, the founder of the wetransform software development company in Darmstadt that runs the project.
Proposals for different climate scenarios
In addition, AI can also provide support when it comes to planning reforestation projects and selecting the most suitable tree species. After a forest fire, for example, FutureForest intends in future to propose five to ten different options for climate-resistant reforestation. “The AI approach puts us in a position to provide detailed tree maps for planning the restructuring of the forest,” explains Reitz. For this purpose, the AI develops proposals for up to nine different climate scenarios, from the 1.5 degree target enshrined in the Paris Agreement to the extreme scenario of more than four degrees of warming by 2100.
In the medium term, the FutureForest data are to be made available in an online cloud. This will allow other projects to access the data, meaning they can be used by a wide public.
